Transfer method of service processing data, related equipment and medium

Abstract

The invention discloses a business processing data transfer method, related equipment and a medium. The business processing data transfer method applied to the PINE equipment comprises the following steps: acquiring a first state of the PINE equipment; if the first state meets a preset condition, generating a data transfer request; wherein the data transfer request is used for requesting to transfer at least part of data in the service processing data to other equipment; the service processing data is used for realizing a service processing process in the PINE equipment; sending the data transfer request to a PEMC device in the PIN, and sending the data transfer request to a server device through the PEMC device, so that the server device determines a target device bearing the at least part of data; and receiving a device identifier of the target device, and transferring the at least part of data to the target device based on the device identifier.

Description

Technical Field

[0001] This application relates to the technical field of Personal IoT Network (PIN), and particularly to a method for transferring service processing data, related devices and media. Background Art

[0002] In the technical field of PIN, a PIN Element (PINE) can perform service processing operations through the service processing data deployed therein. However, when the PINE device is running, its device state will also fluctuate, which will affect the stability of service processing operations. Therefore, when the device state of the PINE device fluctuates, how to process the service processing data deployed in the PINE device has become a technical problem to be solved urgently. Summary of the Invention

[0003] Based on the above technical problems, embodiments of this application provide a method for transferring service processing data, related devices and media.

[0004] The technical solutions provided by the embodiments of this application are as follows:

[0005] Embodiments of this application provide a method for transferring service processing data. The method is applied to a PINE device in a PIN. The method includes:

[0006] Obtain a first state of the PINE device;

[0007] If the first state meets a preset condition, generate a data transfer request. Wherein, the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process of the PINE device;

[0008] Send the data transfer request to a PIN Element with Management Capability (PEMC) device in the PIN, and send the data transfer request to a server device through the PEMC device, so that the server device determines a target device for carrying the at least part of the data;

[0009] Receive the device identifier of the target device, and transfer the at least part of the data to the target device based on the device identifier.

[0010] In some embodiments, the service processing data includes an Artificial Intelligence (AI) model; the AI model includes at least two layers of AI units; at least part of the data includes the AI units to be transferred in the AI model; the AI units are used to implement at least one service processing operation in the service processing process; and if the first state meets a preset condition, generating a data transfer request includes:

[0011] If the first state meets the preset condition, obtain the model identifier of the AI model;

[0012] Determine the transfer level parameter corresponding to the AI unit to be transferred;

[0013] Generate the data transfer request based on the model identifier and the transfer level parameter.

[0014] In some embodiments, the generating the data transfer request based on the model identifier and the transfer level parameter includes:

[0015] Obtain the first identifier of the PINE device;

[0016] Generate the data transfer request based on the first identifier, the model identifier, and the transfer level parameter.

[0017] In some embodiments, the determining the transfer level parameter corresponding to the AI unit to be transferred includes:

[0018] Obtain the association relationship between the level parameter and the device state of the PINE device;

[0019] Based on the matching degree between the first state and the device state in the association relationship, determine the transfer level parameter corresponding to the first state from the association relationship.

[0020] In some embodiments, the determining the transfer level parameter corresponding to the AI unit to be transferred includes:

[0021] Obtain the change parameter of the device state of the PINE device;

[0022] Based on the change parameter and the first state, determine the second state of the PINE device after a specified period;

[0023] Based on the difference state between the first state and the second state, determine the transfer level parameter.

[0024] In some embodiments, the target device includes the server device and / or the PEGC (PIN Element with Gateway Capability) device in the PIN that has gateway function; receiving the device identifier of the target device and transferring at least part of the data to the target device based on the device identifier includes:

[0025] Receiving a reply message sent by the PEMC device; wherein, the reply message is determined by the server device and sent to the PEMC device, or sent by the server device to the PEMC device via a Network Exposure Function (NEF) network element and an Access and Mobility Management Function (AMF) network element; the reply message at least includes the device identifier of the target device;

[0026] Transferring at least part of the data to the target device based on the device identifier in the reply message.

[0027] This application also provides a method for transferring service processing data, which is applied to the PEMC device in the PIN; the method includes:

[0028] Receiving a data transfer request sent by the PINE device in the PIN; wherein, the data transfer request is generated when the first state of the PINE device meets a preset condition; the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process in the PINE device;

[0029] Sending the data transfer request to the server device for the server device to determine the target device for carrying at least part of the data;

[0030] Sending the device identifier of the target device to the PINE device for the PINE device to transfer at least part of the data to the target device based on the device identifier.

[0031] In some embodiments, sending the data transfer request to the server device includes:

[0032] Obtaining the second identifier of the PIN;

[0033] Sending the data transfer request and the second identifier to the AMF network element for the AMF network element to forward the data transfer request to the server device through the NEF network element associated with the second identifier.

[0034] In some embodiments, sending the device identifier of the target device to the PINE device includes:

[0035] Receiving a reply message sent by the server device; wherein, the reply message at least includes the device identifier of the target device; the target device includes the PEGC device in the PIN and / or the server device;

[0036] Sending the reply message to the PINE device.

[0037] This application also provides a method for transferring service processing data, which is applied to a server device, and the method includes:

[0038] Receiving a data transfer request sent by the PEMC device in the PIN; wherein, the data transfer request is sent by the PINE device in the PIN to the PEMC device when the first state of the PINE device meets a preset condition; the service processing data is used to implement the service processing process in the PINE device; the data transfer request is used to request to transfer at least part of the data in the service processing data to other devices;

[0039] Determining a target device for carrying the at least part of the data;

[0040] Sending the device identifier of the target device to the PEMC device for the PEMC device to send the device identifier to the PINE device; wherein, the device identifier is used for the PINE device to transfer the at least part of the data to the target device.

[0041] In some embodiments, the target device includes the server device and / or the PEGC device in the PIN; sending the device identifier of the target device to the PEMC device includes:

[0042] Determining the device identifier of the target device;

[0043] Generating a reply message corresponding to the data forwarding request based on the device identifier;

[0044] Sending the reply message to the PEMC device.

[0045] In some embodiments, determining the target device for carrying the at least part of the data includes:

[0046] Determining candidate devices; wherein, the candidate devices include candidate PEGC devices in the PIN and / or candidate server devices;

[0047] Determine the target device from the candidate devices based on the distance parameter between the candidate device and the PINE device and / or the operating state parameter of the candidate device.

[0048] In some embodiments, if the candidate device is the candidate PEGC device, determining the candidate device includes:

[0049] Obtain the third state of the PEGC device in the PIN; wherein, the third state includes at least one of the resource utilization rate of the PEGC device, the data processing performance parameter, and the type of AI model carried by the PEGC device;

[0050] If at least one of the resource utilization rate, the data processing performance parameter, and the type of the carried AI model in the third state meets the specified conditions, determine the PEGC device corresponding to the third state as the candidate PEGC device.

[0051] In some embodiments, obtaining the third state of the PEGC device in the PIN includes:

[0052] Send a status subscription request to the NEF network element for the NEF network element to determine the target AMF network element based on the identification list of the PEGC device in the status subscription request; wherein, the target AMF network element is used to instruct the PEGC device to report the third state based on the status report indication message and the identification list; the PEGC device is used to determine whether to report the third state based on the PIN identification included in the status report indication message; the status report indication message is generated by the target AMF network element; the target AMF network element is associated with the PIN;

[0053] Receive the third state sent by the NEF network element; wherein, the third state is obtained by the target AMF network element from the PEGC device and sent to the NEF network element.

[0054] In some embodiments, the service processing data includes an AI model; the AI model includes at least two layers of AI units; the AI unit is used to implement at least one service processing operation included in the service processing process; the third state is obtained and sent by the PEGC device according to a preset policy; the prediction policy includes a preset period policy and an event trigger policy.

[0055] This application also provides a PINE device, which includes a first processor and a first memory; wherein, a first computer program is stored in the first memory; when the first computer program is executed by the first processor, it can implement the method for transferring service processing data applied to the PINE device as described in any one of the previous paragraphs.

[0056] The present application also provides a PEMC device, which includes a second processor and a second memory; wherein, a second computer program is stored in the second memory; when the second computer program is executed by the second processor, it can implement the method for transferring service processing data applied to the PMEC device as described in any one of the previous paragraphs.

[0057] The present application also provides a server device, which includes a third processor and a third memory; wherein, a third computer program is stored in the third memory; when the third computer program is executed by the third processor, it can implement the method for transferring service processing data applied to the server device as described in any one of the previous paragraphs.

[0058] The present application also provides a computer-readable storage medium, in which a fourth computer program is stored; when the fourth computer program is executed by a processor of an electronic device, it can implement the method for transferring service processing data as described in any one of the previous paragraphs.

[0059] In the method for transferring service processing data applied to a PINE device provided by an embodiment of the present application, when a first state of the PINE device meets a preset condition, a data transfer request for requesting to transfer at least part of the service processing data to other devices is generated, and the service processing data is used to implement a service processing process in the PINE device. In this way, not only is it possible to determine whether to generate and request to transfer at least part of the service processing data based on the state of the PINE device itself, but also, by adjusting the preset condition, flexible control of the operation of generating a data transfer request can be achieved; and after the PINE device sends a data transfer request to the PEMC device in the PIN, the PEMC device sends the data transfer request to the server device, and the server device is used to determine a target device for carrying at least part of the data. In this way, not only is the decoupling of the data forwarding request process and the target device determination process achieved, but also, by having the server device determine the target device, the matching degree between the target device and the resources required for the operation of at least part of the data can be improved, thereby improving the success rate of transferring at least part of the data, and also improving the operation efficiency after transferring at least part of the data; on this basis, the PINE device receives the device identifier of the target device and transfers at least part of the data to the target device based on the device identifier, thereby improving the accuracy of transferring at least part of the data. In this way, when the first state meets the preset condition indicating that the state of the PINE device fluctuates, through the above operations, the service processing data in the PINE device can be transferred to the target device in real time, thereby improving the stability and robustness of the service processing process corresponding to the service processing data, and also meeting the actual service processing requirements of the PINE device. Description of the Drawings

[0060] Figure 1A It is a schematic structural diagram of the PIN network architecture in the 3rd Generation Partnership Project (3GPP).

[0061] Figure 1B It is a schematic structural diagram of the application layer network architecture of PIN.

[0062] Figure 1C It is a schematic structural diagram of the PIN network based on network capability open.

[0063] Figure 1D It is a schematic structural diagram of the hierarchical deployment of the AI model in the image recognition process.

[0064] Figure 2 It is a schematic flow diagram of the method for transferring service processing data applied to the PINE device provided by the embodiment of the present application.

[0065] Figure 3 It is a schematic flow diagram of the method for transferring service processing data applied to the PEMC device provided by the embodiment of the present application.

[0066] Figure 4A It is a schematic flow diagram of the method for forwarding a data transfer request to an Application Function (AF) device provided by the embodiment of the present application.

[0067] Figure 4B It is another schematic flow diagram of the method for forwarding a data transfer request to an AF device provided by the embodiment of the present application.

[0068] Figure 5 It is a schematic flow diagram of the method for transferring service processing data applied to the server device provided by the embodiment of the present application.

[0069] Figure 6A It is a schematic flow diagram of the process for the server device to obtain the third state provided by the embodiment of the present application.

[0070] Figure 6B It is another schematic flow diagram of the process for the server device to obtain the third state provided by the embodiment of the present application.

[0071] Figure 7 It is a schematic structural diagram of the PINE device provided by the embodiment of the present application.

[0072] Figure 8 It is a schematic structural diagram of the PEMC device provided by the embodiment of the present application.

[0073] Figure 9 It is a schematic structural diagram of the server device provided by the embodiment of the present application. Detailed implementation manners

[0074] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

[0075] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0076] In practical applications, in various scenarios corresponding to vertical industry technical fields with small space capacities such as medical care, education, home, and industrial control production, there are various types of devices that need to share data and information through a network. Moreover, the types of operating systems of various devices are complex and diverse, and their network access methods are also different. Therefore, compared with traditional Internet of Things (IoT) devices, the stability of the operating states of the devices applied in the above scenarios is relatively weak. For example, the battery capacity, communication distance, signal transmission power, etc. of the devices applied in the above scenarios are all weaker than the corresponding parameters of IoT devices; and in the above scenarios, the user platform traffic is usually transmitted in an environment with a small space capacity. Therefore, it is difficult to connect the devices in the above scenarios through IoT.

[0077] In this case, PIN came into being. PIN can realize functions such as intelligent identification, positioning, tracking, supervision, and management of devices in the above scenarios, and can uniformly integrate the digital information between devices and items in the above scenarios, thereby enhancing the management of various devices.

[0078] In PIN, the terminal devices connected to PIN are called PINE devices. PINE devices have the following characteristics: the ways they connect to PIN include multiple non-3GPP connection methods such as WLAN, Z-Wave, Zigbee, and Bluetooth, and the degree of fragmentation of daily operations is relatively high. These characteristics have a negative impact on both the user experience and the data connection stability. Therefore, 3GPP defines that PIN should include at least one PEGC device and at least one PEMC device.

[0079] Figure 1A FIG. is a schematic structural diagram of the PIN network architecture in 3GPP. As Figure 1A shown, PIN 101 establishes a data transmission connection with the PIN application server 103 through the 5th Generation Mobile Communication Technology Core (5GC) 102; where: th Generation Mobile Communication Technology Core, 5GC) 102 to establish a data transmission connection with the PIN application server 103; where:

[0080] The PEGC device can provide a data connection between other PINE devices and the 5G network for them, or act as a relay for data transmission between different PINE devices. In practical applications, the PEGC device realizes data transmission with the PIN application server 103 through the AMF network element, NEF network element, Authentication Server Function (AUSF), Network Repository Function (NRF), Session Management Function (SMF) network element, Policy Control Function (PCF) network element, Unified Data Management (UDM) network element, Unified Data Repository (UDR) network element, User Plane Function (UPF) network element, and Radio Access Network (RAN) in the 5GC102.

[0081] The PEMC device has the function of managing PINE devices. Based on the PINE device identification list, it manages the behavior of each PINE device and masters the access rights of PINE devices. The following information of the PINE devices it manages is stored in the PEMC device:

[0082] a) The unique identifier of the PINE device within the PIN;

[0083] b) The connection types supported by the PIN device;

[0084] c) The application program identifier running in the PINE device;

[0085] d) The relevant metadata including event occurrence, event type, and timestamp, etc.;

[0086] e) The security credentials of the PINE device.

[0087] 3GPP also provides the application layer architecture, processes, and signaling required to maintain the normal operation of the PIN application. Figure 1B It is a schematic diagram of the structure of the application layer network architecture of the PIN. As Figure 1B shown, a communication connection is established between the PIN 101 and the data network server 104 through the 5GC 102, where:

[0088] Application clients including a first application client, a second application client, and a third application client are respectively deployed on a first PINE device, a second PINE device, and a third PINE device in the PIN, and they are respectively used to provide client programs for the first to third PINE devices to provide application service functions.

[0089] The PIN server is deployed on the data network server 104 and is used to provide server-side functions required for managing the PIN, configuration files of each PIN, and configuration files of PINE devices set in each PIN.

[0090] The PIN management client is deployed on the PEMC device and is used for network operators or authorized users to configure PIN policies, support authorized PEGC devices and PINE devices, and configure parameters therein for communication.

[0091] The PIN gateway client is deployed on the PEGC device, which has a gateway function to exchange data and signaling with the PEMC device, PINE device, or data network server 104. It supports forwarding traffic data of the PINE device to the data network server 104 and also supports relaying PIN management messages associated with the PINE device.

[0092] The PIN-3 interface is deployed between the PIN client and the PEMC device. Through this interface, the PEMC device can send various signaling and configuration information to the PINE device and authorize the PIN client to access the PIN.

[0093] The PIN-4 interface is deployed between the PEGC device and the PEMC device. Through this interface, the PEMC device can send the PIN configuration information to the PEGC device when the PIN configuration information changes dynamically, and can also notify the PEGC device of the PINE devices added or removed in the PIN.

[0094] The PIN-6 interface is deployed between the PEMC device and the data network server 104. Through this interface, the authorization of the PIN server for the PEMC device can be completed. The PEMC device can report changes in devices within the PIN through this interface, such as the addition and deletion of PINE devices and changes in PEGC devices; the PEMC device can also implement the interaction of dynamic configuration file information with the data network server 104 through this interface.

[0095] In terms of capability open, the 3GPP standard introduces the NEF network element to provide the aggregation and external opening of 5G network capabilities. Figure 1C It is a schematic diagram of the structure of the PIN network based on network capability open, as Figure 1CAs shown in the figure, the NEF1 network element and the NEF2 network element in the NEF set 105 are docked southward with the NF set 106 including network functions (NFs) 1 to NFn and other 5GC network elements, and provide northward the capability application programming interfaces (APIs) 1 to APIn to implement the invocation of AF1 to AF3 in the AF set 107.

[0096] Through the above network architecture, PIN can provide network connection and data transmission services for devices of diverse types and access methods; at the same time, with the development of emerging technologies such as edge computing and artificial intelligence (AI), higher requirements are put forward for more and more terminal devices in various industry application scenarios to have computing capabilities. Therefore, deploying an AI model in the PINE device of PIN to implement the service processing process has also become a popular trend in the service data processing of PIN.

[0097] Among them, the AI model can use mathematical algorithms to create a prediction model, enabling computing nodes including terminal devices to perform inference and prediction on service data through the AI model. On the other hand, with the continuous upgrade of the computing power of the AI model, its computing intensity, memory occupancy, and power consumption are getting larger and larger. However, terminal devices usually have strict restrictions on energy consumption, computing resources, and memory application, resulting in difficulty in implementing the full offline operation and calculation of the AI model on terminal devices. And currently, most AI models are built based on the hierarchical structure of convolutional neural networks (CNNs). For the hierarchical architecture based on CNNs, to separate the AI computing model by layer and deploy resources such as memory, power consumption, and computing power required for each layer to other devices, the terminal device is connected to other devices through the network and jointly completes the AI model calculation and processing of data with the layers separately deployed in other devices. The above solution can effectively reduce the computing resource pressure generated by the terminal device loading the AI model calculation, and can also reduce the end-to-end delay, thereby improving the accuracy, efficiency, and privacy of the AI model data processing.

[0098] Figure 1D It is a schematic structural diagram of the hierarchical deployment of the AI model in the image recognition process. As Figure 1DAs shown, the structure may include the input image data 108, the terminal device 109, the network-side device 110, and the output layer 111. Among them, after the AI model for image recognition is divided into a first layer set and a second layer set, the first layer set is deployed on the terminal device 109, and the second layer set is deployed on the network-side device 110. The image data 108 is input into the terminal device 109, and after the image processing operation of the first layer set, the intermediate data is output to the network-side device 110 for the second layer set deployed in the network-side device to perform the remaining operations of the AI model on the intermediate data and obtain the recognition result, and then the recognition result is output through the output layer 111. Among them, when the AI model includes CNN, the first layer set and the second layer set may respectively include at least some feature extraction layers of CNN.

[0099] At the same time, PIN can provide network data transmission functions for PINE devices in diverse scenarios. For example, in the smart ward scenario, patients can discover each other through the PINE devices they carry and wear. Among them, by using a 5G smartphone as a PEMC device, the 5G smart hospital bed in the ward can be configured as a PEGC device. These devices, together with the patient-worn devices and other network-type PINE devices in the ward, jointly form a PIN network. The data collected by these PINE devices can be accessed through PEGC to the 5G network and then transmitted to the hospital data center. At the same time, combined with AI technology, the medical devices in PIN can also realize functions such as automatically analyzing the patient's condition, outputting analysis reports, warning prompts, and assisting medical staff.

[0100] In the medical scenario, the PINE devices in PIN, in addition to medical devices that require continuous power supply such as electrocardiogram monitors and ventilators, also include movable medical devices such as 5G smart medical carts. By configuring an AI model for medical consultations on these medical devices, it is possible to record the medical consultations for a preliminary diagnosis of the patient and perform data interaction and sharing with the Hospital Information System (HIS) and the electronic medical record system, thus providing the possibility for remote guidance and consultation communication between experts and doctors.

[0101] However, in practical applications, in PIN including the medical scenario, when the operating state of the PINE device fluctuates, such as when its power drops to a certain threshold, to extend its operating time, the PINE device will gradually turn off the local computing power and reduce the overall power consumption to maintain the normal operation of the main functions. And in practical applications, there is no mechanism for transferring or unloading the AI model of PIN, so that the PINE device cannot determine the target and process of transferring and unloading the AI model, resulting in an impact on the business processing process of the PINE device.

[0102] Based on the above problems, the embodiments of the present application provide a method for transferring service processing data, related devices, and storage media. The service data transfer method provided by the embodiments of the present application can be implemented by a processor of a PINE device in a PIN; wherein, the above-mentioned processor can be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a Micro Controller Unit (MCU), and a microprocessor.

[0103] Exemplarily, the PINE device can be a physical machine device or a virtual machine device.

[0104] Exemplarily, the PINE device can be a computer device or a mobile terminal device; Exemplarily, the mobile terminal device can include a smart phone.

[0105] Figure 2 The flowchart of the method for transferring service processing data applied to the PINE device provided by the embodiments of the present application is shown in Figure 2 As shown, the process can include the following steps:

[0106] Step 201, obtain the first state of the PINE device.

[0107] In one implementation, the PINE device can be any PINE device in the PIN.

[0108] In one implementation, the first state can include the running state of the PINE device; Exemplarily, the above-mentioned running state can be related to the hardware and / or software of the PINE device; Exemplarily, the running state related to the hardware can include the heating state of the hardware components during the operation of the PINE device, the remaining power of the energy storage device of the PINE device, and the power supply mode of the PINE device, etc.; Exemplarily, the running state related to the software can include at least one of the memory occupancy rate of the PINE device, the number of threads and / or processes in the parallel running state, and the type and / or number of running application programs.

[0109] In one embodiment, the first state can be obtained by monitoring the operation process of the PINE device.

[0110] Step 202: If the first state meets the preset conditions, generate a data transfer request.

[0111] Wherein, the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process of the PINE device.

[0112] Exemplarily, if the first state does not meet the preset conditions, the data transfer request may not be generated.

[0113] In one embodiment, the service processing process can implement the processing of at least one type of service by the PINE device; exemplarily, the service processing process may include at least one service processing operation or link.

[0114] In one embodiment, the service processing data may include a set of modules or executable codes for executing the service processing process; exemplarily, the service processing data may include application programs set in the PINE device.

[0115] In one embodiment, at least part of the data may include data in the service processing data with a data operation amount greater than a first threshold, a resource occupancy rate greater than a second threshold, and a running power consumption greater than a third threshold.

[0116] In one embodiment, other devices may include other devices with data processing functions except the current PINE device in the PIN, or may also include devices with data processing functions deployed in other networks outside the PIN.

[0117] In one embodiment, the preset conditions may include conditions related to the software and / or hardware state of the PINE device; exemplarily, the conditions related to the software may include the quantity and / or power consumption of data processing resources occupied by the service data processing process, etc.; exemplarily, the conditions related to the hardware state may include the matching degree between the duration of the service data processing process and the standby time of the PINE device.

[0118] In one embodiment, the data transfer request may include at least part of the data and data such as the reason for generating the data transfer request.

[0119] Step 203: Send the data transfer request to the PEMC device in the PIN, and send the data transfer request to the server device through the PEMC device, so that the server device determines the target device for carrying at least part of the data.

[0120] In one implementation, the server device may include a physical machine device or a virtual machine device of the server for managing PINs.

[0121] In one implementation, the server device may include a service server for providing service processing data; illustratively, the server device may be the data network server or PIN application server mentioned above.

[0122] In one implementation, the target device may be at least one device that can be managed by the server device; illustratively, the target device may be at least one device in the PIN excluding the PINE device.

[0123] In one implementation, the PEMC device may transmit a data transfer request to the PEMC device via PIN-6, and may also transmit a data transfer request to the PEMC device via other network elements in the 5GC.

[0124] In one implementation, the target device may be determined by:

[0125] The server device obtains the operating status of each device in the device set of the devices it manages, and determines the device in the device set whose operating status can meet the resources required for the operation of at least part of the data as the target device.

[0126] Step 204: Receive a device identification of the target device, and transfer at least part of the data to the target device based on the device identification.

[0127] In one implementation, the device identification may include at least one of a name, a number, and a network address of the target device.

[0128] In one embodiment, the PINE device can receive the device identification of the target device from the PEMC device; exemplarily, the PEMC device can receive the device identification sent by the server device through PIN-6, and can also receive the above-mentioned device identification through relevant network elements in the 5GC network.

[0129] In one embodiment, transferring at least part of the data to the target device may be achieved by:

[0130] At least part of the data is sent to the target device based on the device identification, and after the target device successfully loads at least part of the data, the at least part of the data is removed from the PINE device.

[0131] In one embodiment, after transferring at least part of the data to the target device, the PINE device may perform part of the service processing process based on the data in the service processing data excluding the above-mentioned at least part of the data, and perform the service processing steps or links in the service processing process excluding the above-mentioned part of the service processing process by means of at least part of the data deployed in the target device.

[0132] As can be seen from the above, in the service processing data transfer method applied to the PINE device provided by the embodiment of the present application, when the first state of the PINE device meets the preset conditions, a data transfer request for requesting to transfer at least part of the service processing data to other devices is generated, and the service processing data is used to implement the service processing process in the PINE device. In this way, not only is it possible to determine whether to generate and request to transfer at least part of the service processing data based on the state of the PINE device itself, but also, by adjusting the preset conditions, flexible control of the operation of generating the data transfer request can be achieved; and after the PINE device sends the data transfer request to the PEMC device in the PIN, the PEMC device sends the data transfer request to the server device, and the server device is used to determine the target device carrying at least part of the data. In this way, not only is the decoupling of the data forwarding request process and the target device determination process achieved, but also, by having the server device determine the target device, the matching degree between the target device and the resources required for the operation of at least part of the data can be improved, thereby improving the success rate of transferring at least part of the data, and also improving the operation efficiency after transferring at least part of the data; on this basis, the PINE device receives the device identifier of the target device and transfers at least part of the data to the target device based on the device identifier, thereby improving the accuracy of transferring at least part of the data. In this way, when the first state meets the preset conditions indicating that the state of the PINE device fluctuates, through the above operations, the service processing data in the PINE device can be transferred to the target device in real time, thereby improving the stability and robustness of the service processing process corresponding to the service processing data, and also meeting the actual service processing needs of the PINE device.

[0133] Based on the foregoing embodiments, in the service processing data transfer method applied to the PINE device provided by the embodiment of the present application, the service processing data includes an AI model; the AI model includes at least two layers of AI units; at least part of the data includes the AI units to be transferred in the AI model; and the AI units are used to implement at least one service processing operation in the service processing process.

[0134] In one embodiment, the coupling degree between at least two layers of AI units included in the AI model may be less than the coupling degree threshold, thereby laying a foundation for dividing the AI model to obtain the AI units to be transferred corresponding to at least part of the data.

[0135] In one embodiment, the AI unit is used to implement at least one step or link in the business processing process.

[0136] Correspondingly, if the first state meets the preset conditions, a data transfer request can be generated, which can be achieved through the following steps:

[0137] Step A1: If the first state meets the preset conditions, obtain the model identifier of the AI model.

[0138] Exemplarily, if the first state does not meet the preset conditions, the model identifier may not be obtained.

[0139] In one embodiment, the model identifier may include at least one of the type, name, number, and address of the AI model.

[0140] Step A2: Determine the transfer level parameter corresponding to the AI unit to be transferred.

[0141] In one embodiment, the transfer level parameter may include a set of levels to which the AI unit to be transferred belongs in the AI model.

[0142] In one embodiment, the transfer level parameter can be determined in the following manner:

[0143] Analyze at least one of the data processing resources, power consumption, and data processing time required when the AI units included in the AI model are in the running state to obtain a first analysis result, then perform a reverse order sorting on the data processing resource occupancy, power consumption level, and data processing time length in the first analysis result to obtain a sorting result, and determine the AI units that meet at least one of the conditions that the data processing resource occupancy is greater than a first threshold, the power consumption is greater than a second threshold, and the data processing time length is greater than a third threshold in the sorting result as the AI units to be transferred, and then determine the level corresponding to the AI units to be transferred as the transfer level parameter.

[0144] Analyze the privacy level of the data processed by the AI units included in the AI model to obtain a second analysis result, and determine the AI units used to process non-private data in the second analysis result as the AI units to be transferred, and then determine the level corresponding to the AI units to be transferred as the transfer level parameter.

[0145] Step A3: Generate a data transfer request based on the model identifier and the transfer level parameter.

[0146] In one embodiment, the data transfer request can be generated in the following manner:

[0147] Determine the fields in the request data packet for setting the model identifier and the transfer level parameters to be transferred, and then add the model identifier and the transfer level parameters to the above fields of the request data packet, so as to generate a data transfer request.

[0148] As can be seen from the above, in the method for transferring business processing data applying the PINE device provided by the embodiments of the present application, the business processing data includes an AI model including at least two AI units for implementing at least one business processing operation in the business processing process, and at least part of the data includes the AI units to be transferred in the AI model. Thus, in combination with the steps provided in the foregoing embodiments, when the first state of the PINE device meets the preset conditions, accurate stratification of the AI units to be transferred in the AI model set in the PINE device can be achieved; and, if the first state meets the preset conditions, the model identifier of the AI model is obtained, and the transfer level parameters corresponding to the AI units to be transferred are determined. Thus, when the first state meets the preset conditions indicating fluctuations in the state of the PINE device, the AI model to which the AI units to be transferred belong and their level parameters in the AI model can be accurately represented by the model identifier and the transfer level parameters; on this basis, a data transfer request is generated based on the model identifier and the transfer level parameters, so that the data transfer request can accurately indicate the relevant parameters of the AI units to be transferred in the PINE model.

[0149] Based on the foregoing embodiments, in the method for transferring business processing data applying to the PINE device provided by the embodiments of the present application, generating a data transfer request based on the model identifier and the transfer level parameters can be achieved in the following manner:

[0150] Obtain the first identifier of the PINE device, and generate a data transfer request based on the first identifier, the model identifier, and the transfer level parameters.

[0151] In one implementation, the first identifier may include at least one of the name, number, and network address of the PINE device.

[0152] In one implementation, the data transfer request can be generated in the following manner:

[0153] Determine the fields in the request data packet for setting the first identifier, the model identifier, and the transfer level parameters, and then add the first identifier, the model identifier, and the transfer level parameters to the above fields of the request data packet, so as to generate a data transfer request.

[0154] As can be seen from the above, in the method for transferring service processing data applied to a PINE device provided by the embodiments of the present application, after obtaining the first identifier of the PINE device, a data transfer request is generated based on the first identifier, the model identifier, and the hierarchical parameter to be transferred. In this way, after the server device receives the data transfer request, it can obtain the first identifier, the model identifier, and the hierarchical parameter to be transferred from the data transfer request, so as to accurately determine the PINE device that generates the data transfer request, the AI model to which the AI unit to be transferred belongs, and the level corresponding to the AI unit to be transferred, thereby improving the pertinence of determining the target device and also improving the transfer accuracy and transfer efficiency of the subsequent AI unit to be transferred.

[0155] Based on the foregoing embodiments, in the method for transferring service processing data applied to a PINE device provided by the embodiments of the present application, determining the hierarchical parameter to be transferred corresponding to the AI unit to be transferred can be implemented through the following steps:

[0156] Step B1: Obtain the association relationship between the hierarchical parameter and the device state of the PINE device.

[0157] In one implementation, the association relationship may include a one-to-one correspondence between the i-th level in the hierarchical parameter and the i-th device state in the device state; where i may be an integer greater than or equal to 1.

[0158] In one implementation, the i-th data processing resource required for running the i-th level may be pre-evaluated, and the i-th data processing resource may be analyzed to determine the i-th device state corresponding to the i-th data processing resource, and then the above association relationship is established.

[0159] In one implementation, the association relationship may be automatically set by the PINE device or manually set by the user of the PINE device.

[0160] Step B2: Determine the hierarchical parameter to be transferred corresponding to the first state from the association relationship based on the matching degree between the first state and the device state in the association relationship.

[0161] In one implementation, the hierarchical parameter to be transferred may be determined in the following manner:

[0162] Based on the matching degree between the first state and the device state in the association relationship, determine the i-th device state that matches the first state, and determine at least one level corresponding to the i-th device state as the hierarchical parameter to be transferred.

[0163] In one embodiment, the level parameter to be transferred can be determined in segments according to different first states. For example, if the first state indicates that the remaining power of the PINE device is less than 40%, the level parameter to be transferred can include m layers of AI units at this time, and when the first state indicates that the power of the PINE device is less than 20%, the level parameter to be transferred can include n layers of AI units; where m is a positive integer, and n is a positive integer greater than m.

[0164] As can be seen from the above, in the method for transferring service processing data applied to the PINE device provided by the embodiments of the present application, after obtaining the association relationship between the level parameter and the device state of the PINE device, based on the matching degree between the first state and the device state in the association relationship, the level parameter to be transferred corresponding to the first state is determined from the association relationship. In this way, through the above operations, the association degree between the level parameter to be transferred and the first state of the PINE device can be improved, thereby improving the accuracy of the level parameter to be transferred; and by adjusting or changing the association relationship, it is possible to flexibly and accurately determine the level parameter to be transferred in various situations.

[0165] Based on the foregoing embodiments, in the method for transferring service processing data applied to the PINE device provided by the embodiments of the present application, determining the level parameter to be transferred corresponding to the AI unit to be transferred can also be achieved through the following steps:

[0166] Step C1: Obtain the change parameter of the device state of the PINE device.

[0167] In one embodiment, the change parameter can represent the change state of parameters such as the remaining power, computing speed, and power consumption of the PINE device over time during the execution of service processing by the PINE device.

[0168] In one embodiment, the change parameter can be determined according to at least one of the hardware and / or software configuration state, operating mode, and continuous operating time of the PINE device.

[0169] Step C2: Based on the change parameter and the first state, determine the second state of the PINE device after a specified period.

[0170] In one embodiment, the specified period can be determined by the PINE device itself or input by the user of the PINE device; for example, the specified period can be one hour.

[0171] In one embodiment, the second state can represent the predicted state of the PINE device after a specified period obtained by predicting the device state of the PINE device based on the change parameter on the basis of the first state.

[0172] Step C3: Determine the to-be-transferred level parameter based on the difference state between the first state and the second state.

[0173] In one implementation, the to-be-transferred level parameter can be determined in the following manner:

[0174] Determine the first level parameter corresponding to the first state, and determine the second level parameter corresponding to the second state. If the second level parameter is greater than the first level parameter, the difference between the second level parameter and the first level parameter can be determined as the to-be-transferred level parameter. Exemplarily, if the first level parameter is m, the second level parameter is n, and n is greater than m, the to-be-transferred level parameter can be determined as n - m.

[0175] Exemplarily, the determination processes of the first level parameter and the second level parameter can be determined based on the first state, the second state, and the association relationship in the foregoing embodiments, which will not be elaborated here.

[0176] As can be seen from the above, in the method for transferring service processing data applied to a PINE device provided by the embodiments of the present application, after obtaining the change parameter of the device state of the PINE device, based on the change parameter and the first state, the state of the PINE device after a specified period is determined. In this way, through the above operations, accurate prediction of the device state of the PINE device after a specified period is achieved based on the first state and the change parameter; moreover, by determining the to-be-transferred level parameter based on the difference state between the first state and the second state, the to-be-transferred level parameter is not only related to the current state of the PINE device but also related to the future state of the PINE device after a specified period; on this basis, in combination with the foregoing embodiments, by transferring the to-be-transferred AI unit corresponding to the to-be-transferred level parameter, the data transmission energy consumption generated by frequent transfer of AI units can be reduced, the AI unit transfer process can be simplified, and the transfer efficiency can be improved.

[0177] Based on the foregoing embodiments, in the method for transferring service processing data applied to a PINE device provided by the embodiments of the present application, the target device includes a server device and / or a PEGC device in the PIN.

[0178] In one implementation, the server device may include an AF device or a PIN server.

[0179] In one implementation, when the number of available resources of the PEGC device is greater than the number of resources required for at least part of the data to run, the target device may only include the PEGC device.

[0180] In one embodiment, when the number of available resources of the PEGC device is less than the number of resources required for at least part of the data to run, the target device may only include the server device, or may include the server device and the PEGC device. At this time, the PINE device may transfer the first part of at least part of the data to the PEGC device, and transfer the second part of at least part of the data to the server device.

[0181] Correspondingly, receiving the device identifier of the target device and transferring at least part of the data to the target device based on the device identifier can be achieved in the following manner:

[0182] Receive the reply message sent by the PEMC device; transfer at least part of the data to the target device based on the device identifier in the reply message.

[0183] Wherein, the reply message is determined by the server device and sent to the PEMC device, or is sent by the server device to the PEMC device via the NEF network element and the AMF network element; the reply message at least includes the device identifier of the target device.

[0184] In one embodiment, after determining the target device, the server device may obtain the device identifier of the target device and generate a reply message based on the device identifier.

[0185] In one embodiment, under the application layer network architecture of PIN, the server device may send a reply message to the PEMC device through the PIN-6 interface, while under the PIN network architecture with network capability open, the server device may send a reply message to the PEMC device via the NEF network element and the AMF network element.

[0186] It should be noted that under the application layer network architecture of PIN, if it is necessary to implement the sending of data transfer requests and the normal sending and receiving of reply messages, it is necessary to pre-configure the addresses of the PIN server, that is, the server device, for the PEMC device and the PEGC device in PIN; while under the PIN network architecture with network capability open, it is not necessary to set the above addresses for the PEMC device and the PEGC device.

[0187] In one embodiment, the server device may determine that the target device is a PEGC device in the following manner:

[0188] Obtain the third identifier of the PEGC device in the PIN, then obtain the third status of the PEGC device based on the third identifier, and determine the PEGC device in the PIN as a candidate PEGC device when at least one of the resource utilization rate, data processing performance included in the third status, and the type of AI model carried by the PEGC device meets the specified conditions; then, determine the device with a distance parameter less than the distance threshold between the candidate PEGC device and the PINE device as the target device; wherein, the above-mentioned specified conditions may include that the resource utilization rate indicates that the remaining available resources of the PEGC are greater than the resources required for at least part of the data operation, the data processing performance meets the data operation requirements of at least part of the data, and at least one of the types of AI models carried by the PEGC device is the same as the type of AI model in the PINE device.

[0189] In one implementation, the server device can determine the target device as the server device in the following way:

[0190] The server device obtains the third status, and determines the server device as a candidate device when at least one parameter in the third status does not meet the above-mentioned specified conditions, and then determines the server device as the target device when the data processing resources that the server device can provide are greater than the data processing resources required for at least part of the data operation.

[0191] In one implementation, when the parameters in the third status partially meet the specified conditions and the data processing resources in the PEGC device combined with the data processing resources that the server device can provide can meet the data operation requirements of at least part of the data, the server device and the PEGC device are determined as the target devices.

[0192] As can be seen from the above, in the method for transferring service processing data applied to the PINE device provided by the embodiments of the present application, the target device includes the server device and / or the PEGC device in the PIN, thus providing diversified target devices for the transfer of at least part of the data, and further improving the flexibility of the transfer of at least part of the data; and, the PINE device receives the reply message sent by the PEMC device, which is sent to the PEMC device by the server device, or sent to the PEMC device by the server device via the NEF network element and the AMF network element, thus providing flexible transmission of the reply message between the PINE device and the server device, and further being able to make full use of various network architectures of the PIN provided in the related technologies, and being able to improve the flexibility of data transmission between the PINE device and the network server; at the same time, since the reply message contains the device identifier, the accuracy of the PINE device for transferring at least part of the data based on the device identifier can be improved.

[0193] Based on the foregoing embodiments, an embodiment of the present application further provides a method for transferring service processing data of a PEMC device applied to a PIN. It should be noted that this method can be implemented by a processor of the PEMC device, and the above-mentioned processor can be at least one of an ASIC, a DSP, a DSPD, a PLD, an FPGA, a CPU, a controller, a microcontroller, and a microprocessor.

[0194] Figure 3 It is a schematic flowchart of a method for transferring service processing data of a PEMC device provided by an embodiment of the present application. As Figure 3 shown, this process may include the following steps:

[0195] Step 301, receive a data transfer request sent by a PINE device in the PIN.

[0196] Among them, the data transfer request is generated when the first state of the PINE device meets a preset condition; the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process of the PINE device.

[0197] Step 302, send the data transfer request to the server device for the server device to determine the target device for carrying at least part of the data.

[0198] Step 303, send the device identifier of the target device to the PINE device for the PINE device to transfer at least part of the data to the target device based on the device identifier.

[0199] As can be seen from the above, in the method for transferring service processing data of a PMEC device provided by an embodiment of the present application, after receiving the data transfer request sent by the PIEN device, by sending the data transfer request to the server device and having the server device determine the target device for carrying at least part of the data requested by the data transfer request, relying on the device hierarchy of the server device in the network topology, the scope and breadth of the target device can be improved through the above operations, and the probability of successful transfer of at least part of the data can be increased; moreover, the PEMC device sending the device identifier of the target device to the PINE device can improve the accuracy of the PINE device in transferring at least part of the data to the target device based on the device identifier.

[0200] Based on the foregoing embodiments, in the method for transferring service processing data of a PEMC device provided by an embodiment of the present application, sending the data transfer request to the server device can be implemented in the following manner:

[0201] Obtain the second identifier of the PIN; send the data transfer request and the second identifier to the AMF network element for the AMF network element to forward the data transfer request to the server device through the NEF network element associated with the second identifier.

[0202] In one embodiment, the second identifier may include the name and / or number of the PIN.

[0203] In one embodiment, the NEF network element associated with the second identifier may include the NEF network element that subscribes to the third state of the PEGC device in the PIN.

[0204] In one embodiment, when the PIN is in the PIN network architecture with network capability open, the PEMC device may forward the data transfer request to the server device in the above manner.

[0205] Figure 4A The following is a schematic diagram of the process for forwarding a data transfer request to the AF device provided by the embodiments of the present application, as Figure 4A shown. This process may be jointly implemented by the PINE device 401, the PEMC device 402, the AMF network element 403, the NEF network element 404, and the AF device 405; this process may include the following steps:

[0206] Step D1: Send a resource offloading request.

[0207] Exemplarily, the resource offloading request may be the data transfer request in the foregoing embodiment.

[0208] Exemplarily, when the service processing data is an AI model, the resource offloading request may be used to request to transfer or offload the AI unit to be transferred in the AI model to other devices.

[0209] Exemplarily, when the PINE device 401 detects a situation such as insufficient computing performance or insufficient power of itself, it may determine that its first state meets the preset conditions. At this time, based on the first identifier of the PINE device, the model identifier of the AI model, and the parameter of the level to be transferred corresponding to the AI unit to be transferred, a resource offloading request may be generated and sent to the PEMC device 402.

[0210] Exemplarily, the resource offloading request may further include the demand parameter of the AI unit to be offloaded for computing performance.

[0211] Exemplarily, after receiving the resource offloading request, the PEMC device may obtain the second identifier of the PIN and forward the second identifier and the resource offloading request to the AMF network element 403.

[0212] Step D2: Forward the resource offloading request.

[0213] Exemplarily, the AMF network element 403 selects the NEF network element 404 that has subscribed to the computing resource status information of the PEGC device in the PIN corresponding to the second identifier according to the second identifier, forwards the resource offloading request to the aforementioned NEF network element 404, and then the NEF network element 404 forwards the request to the AF device 405.

[0214] Exemplarily, the AF device 405 may be the server device in the foregoing embodiment.

[0215] Step D3: Determine the target device.

[0216] Exemplarily, the AF device 405 may determine that the target device is the PEGC device or the AF device 405 in the PIN through the method provided in the foregoing embodiment, and obtain the device identifier of the target device.

[0217] Exemplarily, if the target device is a PEGC device, the device identifier may include the third identifier of the PEGC device; if the target device is the AF device 405, the device identifier may include the address of the AF device, and the above address may include a Uniform Resource Locator (URL) or a Fully Qualified Domain Name (FQDN).

[0218] Exemplarily, the AF device 405 may also re-check the layer parameters to be offloaded.

[0219] Step D4: Return the device identifier.

[0220] Exemplarily, the AF device 405 may first send the device identifier to the NEF network element 404.

[0221] Step D5: Forward the device identifier.

[0222] Exemplarily, the NEF network element 404 may send the device identifier to the AMF network element 403, and then the AMF network element 403 sends it to the PEMC device 402, and finally the PEMC device forwards the device identifier to the PINE device.

[0223] Step D6: Perform the offloading operation.

[0224] Exemplarily, the PINE device may unload the AI unit to be transferred corresponding to the layer parameter to be transferred to the PEGC device or the AF device indicated by the device identifier according to the device identifier.

[0225] It should be noted that Figure 4A the shown process may be executed based on the PIN network architecture with network open capabilities.

[0226] Figure 4B Another schematic diagram of the process for forwarding a data transfer request to an AF device provided by an embodiment of this application. As Figure 4B shown, this process may include the following steps:

[0227] Step E1: Send a resource offloading request.

[0228] Exemplarily, the PINE device 401 may send a resource offloading request to the PEMC device 402 through the PIN-3 interface, and the PEMC device 402 forwards the resource offloading request to the AF device 405 through the PIN-6 interface.

[0229] Step E2: Determine the target device.

[0230] Step E3: Return the device identifier.

[0231] Exemplarily, the AF device 405 may return the device identifier to the PEMC device 402 through the PIN-6 interface, and then the PEMC device 402 sends it to the PINE device 401.

[0232] Step E4: Perform the offloading operation.

[0233] It should be noted that Figure 4B the process shown may be executed by the PIN application layer network architecture.

[0234] As can be seen from the above, in the method for transferring service processing data applied to a PEMC device provided by an embodiment of this application, the PEMC device obtains the second identifier of the PIN, and sends a data transfer request and the second identifier to the AMF network element, so that the AFM network element forwards the data transfer request to the server device through the target NEF network element associated with the second identifier. In this way, in the above operations, the PIN network architecture based on network open capabilities in related technologies is fully utilized to achieve efficient and stable transparent transmission of the data transfer request and the second identifier.

[0235] Based on the foregoing embodiments, in the method for transferring service processing data applied to a PEMC device provided by an embodiment of this application, sending the device identifier of the target device to the PINE device may be implemented in the following manner:

[0236] Receive a reply message sent by the server device; send the reply message to the PINE device.

[0237] Among them, the reply message includes at least the device identifier of the target device; the target device includes the PEGC device and / or the server device in the PIN.

[0238] Exemplarily, the transmission process of the reply message may be as Figures 4A to 4B shown in the transmission process of the device identifier in, which will not be elaborated here.

[0239] As can be seen from the above, in the transfer method for business data processing applied to a PEMC device provided in the embodiments of the present application, after the PEMC device receives the reply message sent by the server device, it can send the reply message to the PINE device, and the reply message includes the device identifier of the target device. In this way, through the above operations, the stable transparent transmission between the PINE device and the server device through the device identifier carried in the reply message is achieved; and since the target device includes the PEGC device and / or the server device in the PIN, the range of device types of the target device can be expanded, thereby improving the flexibility of business processing data transfer.

[0240] Based on the foregoing embodiments, the embodiments of the present application further provide a method for transferring business processing data applied to a server device. Figure 5 It is a schematic flowchart of the method for transferring business processing data applied to a server device provided in the embodiments of the present application, as Figure 5 shown, the method may include the following steps:

[0241] Step 501, receive a data transfer request sent by a PEMC device in the PIN.

[0242] Wherein, the data transfer request is sent by the PINE device in the PIN to the PEMC device when the first state of the PINE device meets a preset condition; the business processing data is used to implement the business processing process of the PINE device; the data transfer request is used to request to transfer at least part of the data in the business processing data to other devices.

[0243] Step 502, determine a target device for carrying at least part of the data.

[0244] Step 503, send the device identifier of the target device to the PEMC device for the PEMC device to send the device identifier to the PINE device.

[0245] Wherein, the device identifier is used for the PINE device to transfer at least part of the data to the target device.

[0246] As can be seen from the above, in the method for transferring service processing data applied to a server device provided in the embodiments of the present application, after the server device receives a data transfer request, it can determine a target device for carrying at least part of the service processing data requested to be transferred in the data transfer request, and the service processing data is used to implement the service processing process in the PINE device. Thus, through the above operations, conditions are provided for transferring at least part of the service processing data in the PINE device to the target device; and since the data transfer request is sent by the PINE device when its first state meets a preset condition, thus, in the case where the first state meeting the preset condition includes fluctuations in the operating state of the PINE device, through the above operations, it is realized that when the operating state of the PINE device fluctuates, a target device for transferring at least part of the data in the PINE is determined in real time and flexibly; on this basis, the device identifier of the target device is sent to the PEMC device for the PEMC device to send the device identifier to the PINE device. Thus, when the PINE device transfers at least part of the data to the target device based on the device identifier, the negative impact on its service processing process caused by fluctuations in the operating state of the PINE device can be weakened.

[0247] Based on the foregoing embodiments, in the method for transferring service processing data applied to a server device provided in the embodiments of the present application, the target device includes the server device and / or the PEGC device in the PIN.

[0248] Correspondingly, sending the device identifier of the target device to the PEMC device can be implemented in the following manner:

[0249] Determine the device identifier of the target device; generate a reply message corresponding to the data forwarding request based on the device identifier, and send the reply message to the PEMC device.

[0250] As can be seen from the above, in the method for transferring service processing data applied to a server device provided in the embodiments of the present application, after the server device determines and generates a reply message based on the device identifier, it sends the reply message to the PEMC device. Thus, through the above method, the transparent transmission of the device identifier carried in the reply message between the server device and the PEMC device and between the server device and the PINE device is realized.

[0251] Based on the foregoing embodiments, in the method for transferring service processing data applied to a server device provided in the embodiments of the present application, determining a target device for carrying at least part of the data can be implemented through the following steps:

[0252] Step F1, determine candidate devices.

[0253] Among them, the candidate devices include the candidate PEGC devices and / or candidate server devices in the PIN.

[0254] In one embodiment, the candidate devices may include at least one type of device with data processing capabilities managed by the server device.

[0255] In one embodiment, the candidate PEGC devices may include at least some of the PEGC devices in the PIN.

[0256] In one embodiment, the candidate server devices may include the server device and may also include other server devices that have established a communication connection with the server device.

[0257] In one embodiment, the candidate devices may be determined in the following manner:

[0258] Obtain the device list of the devices managed by the server device, and determine as candidate devices those devices in the device list that are in a running state and whose remaining available data processing resources are greater than the data processing resources required for at least part of the data operation.

[0259] Step F2: Determine the target device from the candidate devices based on the distance parameter between the candidate device and the PINE device and / or the operating state parameter of the candidate device.

[0260] In one embodiment, the distance parameter may characterize the spatial distance between the candidate device and the PINE device and may also include the number of node devices provided between the candidate device and the PINE device.

[0261] In one embodiment, the operating state parameter may include at least one of whether the candidate device is currently in a running state, the change trend of its remaining available data processing resources within a specified period when the candidate device is in a running state, and the power supply state of the candidate device.

[0262] In one embodiment, the target device may be determined in any of the following manners:

[0263] Based on the distance parameter, determine the device with the shortest distance between the candidate devices and the PIN device as the target device.

[0264] Based on the operating state parameter, determine as the target device those devices among the candidate devices whose remaining available data processing resources are still greater than the data processing resources required for at least part of the data operation after a specified period.

[0265] Determine a selection strategy for selecting the distance parameter and the operating state parameter, then integratively select the distance parameter and the operating state parameter based on the selection strategy, and determine the target device from the candidate devices based on the result of the integrative selection.

[0266] Based on a random selection strategy, determine any device among the candidate devices as the target device.

[0267] As can be seen from the above, in the method for transferring service processing data applied to a server device provided by the embodiments of the present application, after the server device determines candidate devices including candidate PEGC devices and / or candidate server devices in the PIN, the target device is determined from the candidate devices based on the distance parameter between the candidate device and the PINE device and / or the operating state parameter of the candidate device. In this way, through the above operations, the target device is determined by secondary screening of the candidate devices, thereby increasing the probability that the target device meets the data processing resources required for at least part of the data operation; and, by determining the target device from the candidate devices based on the distance parameter between the candidate device and the PINE device and / or the operating state parameter of the candidate device, a diversified and flexible screening of the candidate devices is achieved, thereby improving the accuracy of the operation of determining the target device.

[0268] Based on the foregoing embodiments, in the method for transferring service processing data applied to a server device provided by the embodiments of the present application, if the candidate device is a candidate PEGC device, determining the candidate device can be achieved through the following methods:

[0269] Obtain the third state of the PEGC device in the PIN; if at least one of the resource utilization rate, data processing performance parameter, and type of the AI model carried in the third state meets the specified condition, determine the PEGC device corresponding to the third state as the candidate PEGC device.

[0270] Among them, the third state includes at least one of the resource utilization rate of the PEGC device, the data processing performance parameter, and the type of the AI model carried by the PEGC device.

[0271] Exemplarily, if any parameter in the third state does not meet the specified condition, the operation of determining the PEGC device corresponding to the third state as the candidate PEGC device may not be performed.

[0272] In one implementation, the resource utilization rate may include the hardware resource utilization rate or the software resource utilization rate; among them, the hardware resource utilization rate may include the proportion of the storage space that has been occupied, and the software resource utilization rate may include the memory space utilization rate and / or the CPU utilization rate, etc.

[0273] In one implementation, the data processing performance parameter may include at least one of the number of cores of the CPU configured in the PEGC device, the main frequency, and the performance of the operating system carried by it.

[0274] In one implementation, the specified condition may include at least one of: the resource utilization rate is less than the first threshold, the data processing performance parameter is greater than the second threshold, and the type of the AI model carried is consistent with the type of the service processing data.

[0275] In one embodiment, the PEGC device may actively or passively send a third state to the server device; for example, the PEGC device may send the third state to the server device after receiving an indication command sent by the server device for instructing it to send the third state.

[0276] As can be seen from the above, in the method for transferring service processing data applied to the server device provided by the embodiments of the present application, after the server device obtains the third state of the PEGC device in the PIN, when at least one of the resource utilization rate, data processing performance parameter, and the type of AI model carried by the PEGC device in the third state meets the specified conditions, the PEGC device corresponding to the third state is determined as the candidate PEGC device. In this way, through the above operations, accurate screening of the PEGC device based on the third state is achieved, thereby being able to increase the probability that the candidate PEGC device matches the operation requirements of at least part of the data; moreover, by judging at least one of the resource utilization rate, data processing performance parameter, and the type of carried AI model in the third state, flexible and accurate judgment of the parameters included in the third state is realized.

[0277] Based on the foregoing embodiments, for the method for transferring service processing data applied to the server device provided by the embodiments of the present application, obtaining the third state of the PEGC device in the PIN can be achieved through the following steps:

[0278] Step G1: Send a status subscription request to the NEF network element for the NEF network element to determine the target AMF network element based on the identification list of the PEGC device in the status subscription request.

[0279] Wherein, the target AMF network element is used to instruct the PEGC device to report the third state based on the status reporting indication message and the identification list; the PEGC device is used to determine whether to report the third state based on the PIN identification included in the status reporting indication message; the status reporting indication message is generated by the target AMF network element;

[0280] In one embodiment, the NEF network element may be the NEF network element associated with the second identification in the foregoing embodiments.

[0281] In one embodiment, the status subscription request may be used to instruct the PEGC device to send the third state.

[0282] In one embodiment, the identification list of the PEGC device may include a list of the names and / or numbers of the PEGCs; for example, the server device may pre-obtain the identification list of the PEGC devices included in the PIN based on the second identification of the PIN.

[0283] In one embodiment, the target AMF network element may include the AMF network element to which the PEGC device in the PIN belongs.

[0284] In one embodiment, after receiving the identification list sent by the NEF network element, the target AMF network element may generate a status report indication message, and traverse the PEGC devices in the PIN based on the identification list to send the status report indication message to the above-mentioned PEGC devices, so as to instruct the PEGC devices to report the third status to the target AMF device.

[0285] In one embodiment, the status report indication message may include the PIN identifier, that is, the second identifier in the foregoing embodiment.

[0286] In one embodiment, the determination of whether the PIN device reports the third status can be achieved through the following method:

[0287] After receiving the status indication message, the PEGC device parses the status indication message to determine the second identifier of the PIN sent by the target AMF, and determines whether it belongs to the PIN indicated by the second identifier. If it belongs to the PIN indicated by the second identifier, it collects parameters such as CPU utilization rate, Graphic Processing Unit (GPU) utilization rate, memory utilization rate, storage space occupancy rate, and the number of million-level machine language instructions processed per second (Million Instructions Per Second, MIPS), and integrates the above parameters into the third status; if it does not belong to the PIN indicated by the second identifier, it returns a failure message indicating that the third status cannot be reported to the target AMF.

[0288] Step G2: Receive the third status sent by the NEF network element.

[0289] Among them, the third status is obtained by the target AMF network element from the PEGC device and sent to the NEF network element.

[0290] It should be noted that the process of obtaining the third status shown in steps G1 to G2 may be implemented based on the PIN network architecture with network capability open.

[0291] As can be seen from the above, in the method for transferring service processing data applied to a network server provided in the embodiments of the present application, after the network server sends a status subscription request to the NEF network element, the NEF network element determines the target AMF based on the identification list of PEGC devices in the status subscription request, and via the target AMF, instructs the PEGC device to report the third status based on the status reporting indication message and the identification list. The PEGC device is used to determine whether to report the third status based on the PIN identification included in the status reporting indication message. In this way, through the NEF network element and the target AMF network element included in the 5GC, the transparent transmission of the third status between the server device and the PEGC device is realized, thereby improving the stability of the third status transmission. Moreover, by sending a status subscription request to obtain the third status, the on-demand acquisition of the third status is realized, and thus the flexibility of obtaining the third sub-status can be improved.

[0292] Based on the foregoing embodiments, in the method for transferring service processing data applied to a server device provided in the embodiments of the present application, the service processing data includes an AI model; the AI model includes at least two layers of AI units; the AI units are used to implement at least one service processing operation included in the service processing process; the third status is obtained and sent by the PEGC device according to a preset policy, and the prediction policy includes a preset cycle policy and an event trigger policy.

[0293] In one implementation, the preset policy can be determined by the target AMF network element, the server device, or the PEGC device; for example, when the target AMF network element issues a status reporting indication message, it can indicate the above preset policy in the status reporting indication message.

[0294] In one implementation, the preset cycle policy can include instructing the PEGC device to obtain and send the third status to the target AMF network element at a preset cycle.

[0295] In one implementation, the event trigger policy can include triggering the reporting of the third status based on a specified event detected by the PEGC device; for example, the specified event can include that the occupancy rate of any computing resource in the PEGC device is greater than the occupancy rate threshold. For example, the PEGC device can dynamically detect the change status of any of its computing resources and report the third status to the target AMF network element when the occupancy rate of any computing resource is greater than the occupancy rate threshold.

[0296] Figure 6A It is a schematic flow diagram of the server device obtaining the third status provided by the embodiments of the present application. As Figure 6A shown, the process may include the following steps:

[0297] Step H1: Send an operation resource status subscription request.

[0298] Exemplarily, the AF device may send a computing resource status subscription request to the NEF network element 404.

[0299] Exemplarily, the computing resource status subscription request may include the status subscription request in the foregoing embodiments.

[0300] Step H2, forward the computing resource status subscription request to the AMF network element to which the PEGC belongs.

[0301] Exemplarily, the AMF network element to which the PEGC belongs may be the target AMF network element in the foregoing embodiments.

[0302] Exemplarily, the NEF network element may traverse the identifier list corresponding to the PEGC device and send a computing resource status information subscription request to the AMF network element to which each PEGC device indicated by the identifier list belongs. The data included in the request may include, but is not limited to, the following: PIN identifier, identifier list of the PEGC device, and preset policies, etc.

[0303] Step H3, instruct the PEGC device to send the computing resource status.

[0304] Exemplarily, the computing resource status may include the third status in the foregoing embodiments.

[0305] Exemplarily, the target AMF network element traverses the received identifier list, generates a status reporting indication message, and then instructs each PEGC device to report the computing resource status information based on the identifier list; the data carried in the status reporting indication message may include: PIN identifier and preset policies, etc.

[0306] Step H4, send the computing resource status.

[0307] Exemplarily, the PEGC device first determines whether it belongs to the PIN indicated by the PIN identifier in the status reporting indication message. If it does not belong to the above PIN, it returns a message indicating that the status acquisition fails, and the AMF network element forwards it to the AF device through the NEF network element; if it belongs to the above PIN, it sends the computing resource status information to the AMF network element.

[0308] Step H5, forward the computing resource status.

[0309] It should be noted that the processes shown in steps H1 to H5 may be implemented based on the PIN network architecture with network capability open.

[0310] Figure 6B Another schematic diagram of the process for the server device provided by the embodiment of the present application to obtain the third status is shown in Figure 6B As

[0311] Step J1: Send the operation resource status.

[0312] Exemplarily, the PEGC device 406 can send the operation resource status to the AF device through the PIN-7 interface.

[0313] It should be noted that the process shown in Step J1 can be implemented through the application layer PIN network architecture. In this case, the address of the AF device needs to be set for the PEGC device 406 in advance, and the PEGC device and the AF device can determine the preset policy in advance and send the operation resource status to the AF device based on the preset policy.

[0314] As can be seen from the above, in the method for transferring business processing data applied to the server device provided by the embodiments of the present application, the business processing data includes an AI model, and the AI model includes at least two layers of AI units; the AI units are used to implement at least one business processing operation included in the business processing process. Thus, combined with the method for transferring business processing data provided in the foregoing embodiments, it is possible to realize the real-time and flexible hierarchical transfer of the AI model set in the PINE device, thereby improving the stability of the business processing process of the PINE device; and, since the third state is obtained and sent by the PEGC device according to a preset policy, and the prediction policy includes a preset cycle policy and an event trigger policy, thus, combined with the method provided in the foregoing embodiments, the flexibility of obtaining the third state can be improved.

[0315] In summary, for the method for transferring business processing data as described in any of the foregoing embodiments provided by the embodiments of the present application, when the business processing data is an AI model, the embodiments of the present application provide a flexible offloading method for partial levels of the AI model based on the PIN architecture, and this method can realize the offloading of partial levels of the AI model set in the PINE device to the PEGC device or the server device in both the PIN application layer architecture and the network capability open architecture network modes, thereby ensuring the continuity of the business processing process carried by the PINE device; and, through the above method, the blank of the lack of an AI model offloading mechanism in the scenario of PIN + AI model is filled; at the same time, heterogeneous network convergence and AI are two important directions for the development of mobile communication, so the combination of PIN + AI model is inevitable. Therefore, through the method provided by the embodiments of the present application, it is also possible to solve the problem of AI model offloading when the computing power of intelligent terminals is insufficient in diverse scenarios including smart home, smart healthcare, smart factory, and smart education, thereby ensuring the continuity of intelligent services and having broad application prospects.

[0316] Based on the foregoing embodiments, the embodiments of the present application further provide a first transfer device for business processing data. This device can be applied to the PINE device and can include:

[0317] The first acquisition module is used to acquire the first state of the PINE device;

[0318] The first processing module is used to generate a data transfer request if the first state meets a preset condition; wherein, the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process in the PINE device;

[0319] The first transceiver module is used to send the data transfer request to the PEMC device in the PIN, and send the data transfer request to the server device through the PEMC device, so that the server device determines the target device carrying at least part of the data;

[0320] The first transceiver module is used to receive the device identifier of the target device, and transfer at least part of the data to the target device based on the device identifier.

[0321] In some embodiments, the service processing data includes an AI model; the AI model includes at least two layers of AI units; at least part of the data includes the AI units to be transferred in the AI model; the AI units are used to implement at least one service processing operation in the service processing process;

[0322] The first acquisition module is used to acquire the model identifier of the AI model if the first state meets a preset condition;

[0323] The first processing module is used to determine the to-be-transferred layer parameters corresponding to the to-be-transferred AI units; and generate a data transfer request based on the model identifier and the to-be-transferred layer parameters.

[0324] In some embodiments, the first acquisition module is used to acquire the first identifier of the PINE device;

[0325] The first processing module is used to generate a data transfer request based on the first identifier, the model identifier, and the to-be-transferred layer parameters.

[0326] In some embodiments, the first acquisition module is used to acquire the association relationship between the layer parameters and the device state of the PINE device;

[0327] The first processing module is used to determine the to-be-transferred layer parameters corresponding to the first state from the association relationship based on the matching degree between the first state and the device state in the association relationship.

[0328] In some embodiments, the first acquisition module is used to acquire the change parameter of the device state of the PINE device;

[0329] The first processing module is used to determine the second state of the PINE device after a specified period based on the change parameter and the first state; and determine the to-be-transferred layer parameters based on the difference state between the first state and the second state.

[0330] In some embodiments, the target device includes a server device and / or a PEGC device in the PIN;

[0331] A first transceiver module, configured to receive a reply message sent by the PEMC device; wherein, the reply message is determined by the server device and sent to the PEMC device, or sent by the server device to the PEMC device via the NEF network element and the AMF network element; the reply message includes at least the device identifier of the target device;

[0332] The first transceiver module is further configured to transfer at least part of the data to the target device based on the device identifier in the reply message.

[0333] Based on the foregoing embodiments, an embodiment of the present application further provides a PINE device. Figure 7 The structure diagram of the PINE device provided by the embodiment of the present application is shown in Figure 7 As shown, the PINE device 401 may include a first processor 701 and a first memory 702. Among them, a first computer program is stored in the first memory 702. When the first computer program is executed by the first processor 701, it can implement the method for transferring service processing data applied to the PINE device provided in any previous embodiment.

[0334] Based on the foregoing embodiments, an embodiment of the present application further provides a second transfer device for service processing data. The device can be applied to the PEMC device. The device may include:

[0335] A second transceiver module, configured to receive a data transfer request sent by the PINE device in the PIN; wherein, the data transfer request is generated when the first state of the PINE device meets a preset condition; the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process in the PINE device;

[0336] The second transceiver module is further configured to send the data transfer request to the server device for the server device to determine the target device for carrying at least part of the data; send the device identifier of the target device to the PINE device for the PINE device to transfer at least part of the data to the target device based on the device identifier.

[0337] In some embodiments, the above device further includes a second acquisition module, configured to acquire a second identifier of the PIN;

[0338] The second transceiver module is configured to send the data transfer request and the second identifier to the AMF network element for the AMF network element to forward the data transfer request to the server device through the NEF network element associated with the second identifier.

[0339] In some embodiments, a second transceiver module is configured to receive a reply message sent by a server device; wherein, the reply message includes at least a device identifier of a target device; the target device includes a PEGC device and / or a server device in the PIN;

[0340] The second transceiver module is further configured to send the reply message to the PINE device.

[0341] Based on the foregoing embodiments, an embodiment of the present application further provides a PEMC device, Figure 8 which is a schematic structural diagram of the PEMC device provided by the embodiment of the present application. As Figure 8 shown, the PEMC device 402 may include a second processor 801 and a second memory 802. Among them, a second computer program is stored in the second memory 802. When the second computer program is executed by the second processor 801, it can implement the method for transferring service processing data applied to the PEMC device provided in any previous embodiment.

[0342] Based on the foregoing embodiments, an embodiment of the present application further provides a third transfer device for service processing data. The device can be applied to a server device and may include:

[0343] A third transceiver module is configured to receive a data transfer request sent by a PEMC device in the PIN; wherein, the data transfer request is sent by a PINE device in the PIN to the PEMC device when a first state of the PINE device meets a preset condition; the service processing data is used to implement a service processing process in the PINE device; the data transfer request is used to request to transfer at least part of the data in the service processing data to other devices;

[0344] A second processing module is configured to determine a target device for carrying at least part of the data;

[0345] The third transceiver module is further configured to send the device identifier of the target device to the PEMC device for the PEMC device to send the device identifier to the PINE device; wherein, the device identifier is used for the PINE device to transfer at least part of the data to the target device.

[0346] In some embodiments, the target device includes a server device and / or a PEGC device in the PIN;

[0347] The second processing module is configured to determine the device identifier of the target device; generate a reply message corresponding to the data forwarding request based on the device identifier;

[0348] The third transceiver module is configured to send the reply message to the PEMC device.

[0349] In some embodiments, a second processing module is configured to determine candidate devices, where the candidate devices include candidate PEGC devices and / or candidate server devices in the PIN;

[0350] The second processing module is configured to determine a target device from the candidate devices based on the distance parameter between the candidate device and the PINE device and / or the operating state parameter of the candidate device.

[0351] In some embodiments, if the candidate device is a candidate PEGC device,

[0352] The second processing module is configured to obtain a third state of the PEGC device in the PIN, where the third state includes at least one of the resource utilization rate of the PEGC device, the data processing performance parameter, and the type of the AI model carried by the PEGC device;

[0353] The second processing module is further configured to, if at least one of the resource utilization rate, the data processing performance parameter, and the type of the carried AI model in the third state meets a specified condition, determine the PEGC device corresponding to the third state as a candidate PEGC device.

[0354] In some embodiments, a third transceiver module is configured to send a status subscription request to the NEF network element for the NEF network element to determine a target AMF network element based on the identification list of the PEGC device in the status subscription request, where the target AMF network element is configured to instruct the PEGC device to report the third state based on the status reporting indication message and the identification list, the PEGC device is configured to determine whether to report the third state based on the PIN identification included in the status reporting indication message, the status reporting indication message is generated by the target AMF network element, and the target AMF network element is associated with the PIN;

[0355] The third transceiver module is further configured to receive the third state sent by the NEF network element, where the third state is obtained by the target AMF network element from the PEGC device and sent to the NEF network element.

[0356] In some embodiments, the service processing data includes an AI model, the AI model includes at least two layers of AI units, the AI units are configured to implement at least one service processing operation included in the service processing process, the third state is obtained and sent by the PEGC device according to a preset policy, and the prediction policy includes a preset cycle policy and an event trigger policy.

[0357] Based on the foregoing embodiments, an embodiment of the present application further provides a server device. Figure 9 The structural schematic diagram of the server device provided by the embodiment of the present application is as Figure 9As shown in the figure, the server device 9 may include a third processor 901 and a third memory 902. Among them, a third computer program is stored in the third memory 902. When the third computer program is executed by the third processor 901, it can implement the method for transferring business processing data applied to the server provided in any previous embodiment.

[0358] Based on the foregoing embodiments, an embodiment of the present application further provides a computer-readable storage medium, in which a fourth computer program is stored; when the fourth computer program is executed by a processor of an electronic device, it can implement the method for transferring business processing data provided in any previous embodiment.

[0359] The descriptions of the foregoing embodiments tend to emphasize the differences between the embodiments. The same or similar parts can be referred to each other. For the sake of brevity, they will not be repeated herein.

[0360] The methods disclosed in the method embodiments provided in the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0361] The features disclosed in the product embodiments provided in the present application can be arbitrarily combined without conflict to obtain new product embodiments.

[0362] The features disclosed in the method or device embodiments provided in the present application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0363] It should be noted that the above computer-readable storage medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it may also be various electronic devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0364] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element.

[0365] The serial numbers of the embodiments of the present application above are for description only and do not represent the superiority or inferiority of the embodiments.

[0366] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general hardware nodes. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0367] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0368] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0369] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or a plurality of processes in the flowchart and / or one block or a plurality of blocks in the block diagram.

[0370] The above are only the preferred embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall similarly be included in the patent protection scope of the present application.

Claims

1. A method for transferring service processing data, characterized in that, The method is applied to the PINE device in the PIN; the method includes: Obtain the first state of the PINE device; If the first state meets a preset condition, generate a data transfer request; wherein, the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process of the PINE device; Send the data transfer request to the PEMC device in the PIN, and send the data transfer request to the server device through the PEMC device, so that the server device determines the target device for carrying the at least part of the data; Receive the device identifier of the target device, and transfer the at least part of the data to the target device based on the device identifier.

2. The method according to claim 1, wherein The service processing data includes an AI model; the AI model includes at least two layers of AI units; the at least part of the data includes the AI units to be transferred in the AI model; the AI unit is used to implement at least one service processing operation in the service processing process; the step of if the first state meets the preset condition, generating a data transfer request, includes: If the first state meets the preset condition, obtain the model identifier of the AI model; Determine the transfer level parameter corresponding to the AI unit to be transferred; Generate the data transfer request based on the model identifier and the transfer level parameter.

3. The method according to claim 2, wherein The step of generating the data transfer request based on the model identifier and the transfer level parameter includes: Obtain the first identifier of the PINE device; Generate the data transfer request based on the first identifier, the model identifier and the transfer level parameter.

4. The method according to claim 2, characterized in that, The step of determining the transfer level parameter corresponding to the AI unit to be transferred includes: Obtain the association relationship between the level parameter and the device state of the PINE device; Based on the matching degree between the first state and the device state in the association relationship, determine the transfer level parameter corresponding to the first state from the association relationship.

5. The method according to claim 2, wherein The step of determining the transfer level parameter corresponding to the AI unit to be transferred includes: Obtain the change parameter of the device state of the PINE device; Based on the change parameter and the first state, determine the second state of the PINE device after a specified period; Based on the difference state between the first state and the second state, determine the transfer level parameter.

6. The method according to any one of claims 1 to 5, characterized in that, The target device includes the server device and / or the PEGC device in the PIN; The step of receiving the device identifier of the target device and transferring the at least part of the data to the target device based on the device identifier includes: Receive the reply message sent by the PEMC device; wherein, the reply message is determined and sent to the PEMC device by the server device, or sent to the PEMC device by the server device via the NEF network element and the AMF network element; the reply message at least includes the device identifier of the target device; Transfer the at least part of the data to the target device based on the device identifier in the reply message.

7. A method for transferring service processing data, characterized in that, The method is applied to the PEMC device in the PIN; the method includes: Receiving a data transfer request sent by the PINE device in the PIN; wherein, the data transfer request is generated when the first state of the PINE device meets a preset condition; the data transfer request is used to request to transfer at least part of the service processing data to other devices; the service processing data is used to implement the service processing process of the PINE device; Sending the data transfer request to the server device for the server device to determine a target device for carrying the at least part of the data; Sending the device identifier of the target device to the PINE device for the PINE device to transfer the at least part of the data to the target device based on the device identifier.

8. The method according to claim 7, wherein The sending the data transfer request to the server device includes: Obtaining a second identifier of the PIN; Sending the data transfer request and the second identifier to the AMF network element for the AMF network element to forward the data transfer request to the server device through the NEF network element associated with the second identifier.

9. The method according to claim 7 or 8, characterized in that The sending the device identifier of the target device to the PINE device includes: Receiving a reply message sent by the server device; wherein, the reply message at least includes the device identifier of the target device; the target device includes the PEGC device in the PIN and / or the server device; Sending the reply message to the PINE device.

10. A method for transferring service processing data, characterized in that, The method is applied to the server device, the method includes: Receiving a data transfer request sent by the PEMC device in the PIN; wherein, the data transfer request is sent by the PINE device in the PIN to the PEMC device when the first state of the PINE device meets a preset condition; the service processing data is used to implement the service processing process in the PINE device; the data transfer request is used to request to transfer at least part of the service processing data to other devices; Determining a target device for carrying the at least part of the data; Sending the device identifier of the target device to the PEMC device for the PEMC device to send the device identifier to the PINE device; wherein, the device identifier is used for the PINE device to transfer the at least part of the data to the target device.

11. The method according to claim 10, wherein The target device includes the server device and / or the PEGC device in the PIN; the sending the device identifier of the target device to the PEMC device includes: Determining the device identifier of the target device; Generating a reply message corresponding to the data forwarding request based on the device identifier; Sending the reply message to the PEMC device.

12. The method according to claim 10 or 11, characterized in that, The determining a target device for carrying the at least part of the data includes: Determining candidate devices; wherein, the candidate devices include candidate PEGC devices in the PIN and / or candidate server devices; Determining the target device from the candidate devices based on the distance parameter between the candidate devices and the PINE device and / or the operating state parameter of the candidate devices.

13. The method according to claim 12, characterized in that, If the candidate device is the candidate PEGC device, the determining of the candidate device includes: Obtaining a third state of the PEGC device in the PIN; wherein, the third state includes at least one of a resource utilization rate of the PEGC device, a data processing performance parameter, and a type of the AI model carried by the PEGC device; If at least one of the resource utilization rate, the data processing performance parameter, and the type of the carried AI model in the third state meets a specified condition, determining the PEGC device corresponding to the third state as the candidate PEGC device.

14. The method according to claim 13, wherein The obtaining of the third state of the PEGC device in the PIN includes: Sending a status subscription request to the NEF network element for the NEF network element to determine a target AMF network element based on an identification list of the PEGC device in the status subscription request; wherein, the target AMF network element is used to instruct the PEGC device to report the third state based on a status reporting indication message and the identification list; the PEGC device is used to determine whether to report the third state based on a PIN identification included in the status reporting indication message; the status reporting indication message is generated by the target AMF network element; the target AMF network element is associated with the PIN; Receiving the third state sent by the NEF network element; wherein, the third state is obtained by the target AMF network element from the PEGC device and sent to the NEF network element.

15. The method according to claim 13, wherein The service processing data includes an AI model; the AI model includes at least two layers of AI units; the AI units are used to implement at least one service processing operation included in the service processing process; the third state is obtained and sent by the PEGC device according to a preset policy; the prediction policy includes a preset period policy and an event trigger policy.

16. A PINE device, characterized in that, The PINE device includes a first processor and a first memory; wherein, a first computer program is stored in the first memory; when the first computer program is executed by the first processor, it can implement the transfer method of the service processing data as described in any one of claims 1 to 6.

17. A PEMC device, characterized in that, The PEMC device includes a second processor and a second memory; wherein, a second computer program is stored in the second memory; when the second computer program is executed by the second processor, it can implement the transfer method of the service processing data as described in any one of claims 7 to 9.

18. A server device, characterized in that, The server device includes a third processor and a third memory; wherein, a third computer program is stored in the third memory; when the third computer program is executed by the third processor, it can implement the transfer method of the service processing data as described in any one of claims 10 to 15.

19. A computer-readable storage medium, characterized in that, A fourth computer program is stored in the storage medium; when the fourth computer program is executed by a processor of an electronic device, it can implement the transfer method of the service processing data as described in any one of claims 1 to 6, 7 to 9, or 10 to 15.

Images