Task notification method and apparatus

Abstract

A task notification method. A base station obtains a first task request from a first network device, and the base station executes a first task associated with the first task request and sends an execution result of the first task to the first network device; or a base station obtains a first task request from a first network device, and the base station executes a first task associated with the first task request, and sends a second task request to a second network device, wherein the second task request is associated with a second task, and the second network device may continue to execute the second task. By means of the method, computing power resources of the base station and a core network device are fully utilized, effectively mitigating the shortage of AI service computing power of servers, and achieving the beneficial effect of improving the AI service satisfaction of terminals.

Description

Method and device for task notification TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, and in particular to a method and device for task notification. BACKGROUND

[0002] With the rise of large models and artificial intelligence generated content (AIGC) applications, the massive growth of user business brings severe computing power challenges to central servers. Wireless networks are naturally close to terminals, and distributed learning based on wireless transmission has outstanding value in terms of sensing data acquisition, auxiliary training, and auxiliary reasoning. According to relevant estimates, the total computing power of current base stations exceeds 2.2 trillion extra operations per second (ETOPS), and considering the growing trend of future wireless network computing power resources, the computing power capabilities and real-time computing power resource states of wireless networks can fully support the computing power of massive terminal users and tight central servers.

[0003] Using application servers to perform deep neural network (DNN) model computing task segmentation can optimize the computing power of terminals and servers in collaboration, without considering the collaborative optimization between base stations, core networks, terminals, and servers. Considering the growing trend of future base station and core network computing power resources, the computing power capabilities and real-time computing power resource states of base stations and core networks can fully support the computing power of massive terminal users and tight central servers. Therefore, how base stations and core networks provide artificial intelligence (AI) services or AI computing power support to terminals and servers to alleviate the computing power shortage of existing end-to-cloud AI service systems and improve AI service quality is a problem that needs to be solved. SUMMARY

[0004] In a first aspect, an embodiment of the present application provides a communication method, which can be executed by a base station, or by a module (such as a chip, a chip system, or a processor) applied to the base station, or by a logic node, a logic module, or software realizing all or part of the base station function. The method comprises: receiving a first task request, the first task request being associated with a first task; executing the first task to obtain an execution result of the first task; and sending the execution result, or sending a second task request, the second task request being associated with a second task. The first task request can be carried by uplink control information (UCI), downlink control information (DCI), a media access control layer control element (MAC CE), radio resource control (RRC) signaling, access stratum (AS) signaling, or non-access stratum (NAS) signaling. The specific carrying manner of the first task request is not limited in the present application. The first task can be an AI-associated task, such as an AI model training task or an AI model calculation task. The first task can also be another task in the communication of the communication system of the present application. The first task can also be a combination of an AI-associated task and another task in the communication of the communication system of the present application. The first task request and the first task are associated, which means that the first task request is used to request the base station to execute the first task. After receiving the first task request sent by the first network device, the base station can execute part of the first task, or execute the whole first task, or not execute the first task. The condition for sending the execution result of the first task to the first network device can be that the whole first task is executed, or that the whole first task is not executed, but the base station receives an indication to send the execution result of the first task. In the case of executing part of the first task, the second task can be a task containing part of the first task executed by the base station, or a task not containing part of the first task executed by the base station. In the case of not executing the first task, the second task can be a task containing the first task. The specific carrying manner of the second task request is consistent with the foregoing description of the first task request, which will not be repeated here. The specific form of the second task is consistent with the foregoing description of the first task, which will not be repeated here.

[0005] By the above method, the base station obtains a first task request from the first network device, and the base station executes a first task associated with the first task request and sends an execution result of the first task to the first network device; or the base station obtains a first task request from the first network device, and the base station executes a first task associated with the first task request and sends a second task request to the second network device, the second task request and the second task are associated, and the second network device can continue to execute the second task. By the above method, the base station, or the base station and the core network device computing resource are fully utilized, which can effectively alleviate the problem of AI service computing power shortage of the server, and achieve the beneficial effect of improving the terminal AI service satisfaction.

[0006] In combination with the first aspect, in some embodiments of the first aspect, the first task request includes at least one of the following: a model category used by the first task, an execution proportion of a model used by the first task, an execution accuracy of the model used by the first task, or a time delay requirement for executing the first task; and the second task request includes at least one of the following: a model category used by the second task, an execution proportion of a model used by the second task, an execution accuracy of the model used by the second task, or a time delay requirement for executing the second task.

[0007] In combination with the first aspect, in some embodiments of the first aspect, the sending of the execution result includes: executing all the first tasks to obtain execution results of all the first tasks, and sending the execution results to the terminal device.

[0008] In combination with the first aspect, in some embodiments of the first aspect, the sending of the second task request includes: executing part of the first tasks, and sending the second task request to the core network device.

[0009] In combination with the first aspect, in some embodiments of the first aspect, the sending of the execution result includes: executing the first task to obtain an execution result of the first task, and sending the execution result to the core network device.

[0010] In a second aspect, an embodiment of the present application provides a communication method, which can be executed by a core network device, or by a module (for example, a chip, a chip system, or a processor) applied to the core network device, or by a logic node, a logic module, or software realizing all or part of the core network device function. The method comprises: receiving a third task request, the third task request being associated with a third task; executing the third task to obtain an execution result of the third task; and sending the execution result, or sending a fourth task request, the fourth task request being associated with a fourth task. The third task request can be carried by uplink control information (UCI), downlink control information (DCI), a media access control layer control element (MAC CE), radio resource control (RRC) signaling, access stratum (AS) signaling, or non-access stratum (NAS) signaling. The specific carrying manner of the third task request is not limited in the present application. The third task can be an AI-associated task, such as an AI model training task or an AI model calculation task. The third task can also be another task in the communication of the communication system of the embodiment of the present application. The third task can also be a combination of an AI-associated task and another task in the communication of the communication system of the embodiment of the present application. The third task request and the third task can be associated, that is, the third task request is used to request the core network device to execute the third task. After receiving the third task request sent by the first network device, the core network device can execute part of the third task, or execute the entire third task, or not execute the third task. The condition for sending the execution result of the third task to the first network device can be that the entire third task is executed, or that the core network device receives an instruction to send the execution result of the third task without executing the entire third task. In the case of executing part of the third task, the fourth task can be a task containing part of the third task executed by the core network device, or a task not containing part of the third task executed by the core network device. In the case of not executing the third task, the fourth task can be a task containing the third task. The specific carrying manner of the fourth task request is consistent with the foregoing description of the third task request, and will not be repeated here. The specific form of the fourth task is consistent with the foregoing description of the third task, and will not be repeated here.

[0011] Through the above method, the core network device obtains the third task request from the first network device, and the core network device performs the third task associated with the third task request and sends the execution result of the third task to the first network device; or the core network device obtains the third task request from the first network device, and the core network device performs the third task associated with the third task request and sends a fourth task request to the second network device, the fourth task request and the fourth task are associated, and the second network device can continue to perform the fourth task. Through the above method, the core network device, or the base station and the core network device computing resource are fully utilized, which can effectively alleviate the problem of AI service computing power shortage of the server, and achieve the beneficial effect of improving the terminal AI service satisfaction.

[0012] In combination with the second aspect, in some embodiments of the second aspect, the third task request includes at least one of the following: a model category used by the third task, an execution proportion of a model used by the third task, an execution accuracy of the model used by the third task, or a time delay requirement for executing the third task; and the fourth task request includes at least one of the following: a model category used by the fourth task, an execution proportion of a model used by the fourth task, an execution accuracy of the model used by the fourth task, or a time delay requirement for executing the fourth task.

[0013] In combination with the second aspect, in some embodiments of the second aspect, the sending of the execution result includes: performing all the third tasks to obtain the execution result of all the third tasks, and sending the execution result to the base station or the server.

[0014] In combination with the second aspect, in some embodiments of the second aspect, the sending of the fourth task request includes: performing part of the third tasks, and sending the fourth task request to the server or the base station.

[0015] In the third aspect, an embodiment of the present application provides a device, which can implement the method in the first aspect or any possible implementation manner of the first aspect. The device includes corresponding units or modules for performing the above method. The units or modules included in the device can be implemented by software and / or hardware. The device may, for example, be a base station, a chip, a chip system, or a processor supporting the base station to implement the above method, and can also be a logic node, a logic module, or software capable of implementing all or part of the functions of the base station.

[0016] In a fourth aspect, an embodiment of the present application provides an apparatus, which can implement the method in the second aspect or any possible implementation of the second aspect. The apparatus includes corresponding units or modules for performing the method. The units or modules included in the apparatus can be implemented by software and / or hardware. The apparatus can be, for example, a core network device, a chip, a chip system, or a processor supporting the core network device to implement the method, and can also be a logic node, a logic module, or software capable of implementing all or part of the functions of the core network device.

[0017] In a fifth aspect, an embodiment of the present application provides an apparatus, which includes a processor coupled with a memory, the memory being configured to store instructions, when the instructions are executed by the processor, causing the apparatus to implement the method in the first aspect or any possible implementation of the first aspect.

[0018] In a sixth aspect, an embodiment of the present application provides an apparatus, which includes a processor coupled with a memory, the memory being configured to store instructions, when the instructions are executed by the processor, causing the apparatus to implement the method in the second aspect or any possible implementation of the second aspect.

[0019] In a seventh aspect, an embodiment of the present application provides a computer readable storage medium, which stores instructions, when the instructions are executed, causing a computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0020] In an eighth aspect, an embodiment of the present application provides a computer readable storage medium, which stores instructions, when the instructions are executed, causing a computer to execute the method in the second aspect or any possible implementation of the second aspect.

[0021] In a ninth aspect, an embodiment of the present application provides a computer program product, which includes computer program codes, when the computer program codes are run on a computer, causing the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0022] In a tenth aspect, an embodiment of the present application provides a computer program product, which includes computer program codes, when the computer program codes are run on a computer, causing the computer to execute the method in the second aspect or any possible implementation of the second aspect.

[0023] In an eleventh aspect, an embodiment of the present application provides a chip, which includes a processor coupled with a memory, the memory being configured to store instructions, when the instructions are executed by the processor, causing the chip to implement the method in the first aspect, the second aspect, any possible implementation of the first aspect, or any possible implementation of the second aspect.

[0024] In a twelfth aspect, the embodiments of the present application provide a communication system, comprising the apparatus of the third aspect and the apparatus of the fourth aspect.

[0025] In a thirteenth aspect, the embodiments of the present application provide a communication system, comprising the apparatus of the fifth aspect and the apparatus of the sixth aspect.

[0026] It can be understood that the beneficial effects of the features corresponding to the first aspect and the second aspect in the third aspect to the thirteenth aspect are described in the first aspect and the second aspect, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0027] FIG. 1 is a schematic diagram of a communication system to which the embodiments of the present application are applied;

[0028] FIGS. 2-5 show several system framework schematic diagrams to which the embodiments of the present application are applied;

[0029] FIG. 6 is an information flow diagram required for a DNN model calculation task division of an application server;

[0030] FIG. 7 is a schematic diagram of a communication method provided by the embodiments of the present application;

[0031] FIG. 8 is a schematic diagram of a terminal device initiating a task request provided by the embodiments of the present application;

[0032] FIG. 9 is a schematic diagram of a server initiating a task request provided by the embodiments of the present application;

[0033] FIG. 10 is a schematic diagram of a communication method provided by the embodiments of the present application;

[0034] FIG. 11 is a schematic diagram of a terminal device initiating a task request provided by the embodiments of the present application;

[0035] FIG. 12 is a schematic diagram of a server initiating a task request provided by the embodiments of the present application;

[0036] FIG. 13 is a schematic diagram of a terminal provided by the embodiments of the present application;

[0037] FIGS. 14-15 are schematic diagrams of apparatuses provided by the embodiments of the present application. DETAILED DESCRIPTION

[0038] FIG. 1 is a schematic diagram of an architecture of a communication system to which embodiments of the present application are applied. As shown in FIG. 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 130. Optionally, the communication system 10 can also include an Internet 140. The RAN 100 can include at least one RAN node (e.g., 110a and 110b in FIG. 1, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in FIG. 1, collectively referred to as 120). The RAN 100 can also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in FIG. 1), etc. The terminals 120 are connected to the RAN nodes 110 in a wireless manner. The RAN nodes 110 are connected to the core network 130 in a wireless or wired manner. The core network devices in the core network 130 and the RAN nodes 110 in the RAN 100 can be independent and different physical devices, respectively, or can be the same physical device integrated with the core network logic function and the radio access network logic function, or can be a device integrated with part of the core network logic function and part of the radio access network logic function. Terminals and terminals, and RAN nodes and RAN nodes can be connected to each other in a wired or wireless manner. FIG. 1 is only a schematic diagram, and the communication system can also include other network devices, such as relay devices and backhaul devices, which are not shown in FIG. 1.

[0039] The method and device provided by the embodiments of the present application can be used in various communication systems, such as a 4th generation (4G) communication system, a 4.5G communication system, a 5G communication system, a 5.5G communication system, a 6G communication system, a system integrating multiple communication systems, or a future evolved communication system. For example, the communication system can be a long term evolution (LTE) system, a new radio (NR) system, an open RAN (O-RAN or ORAN) system, a cloud radio access network (CRAN) system, a wireless-fidelity (WiFi) system, a 3rd generation partnership project (3GPP) related communication system, and other such communication systems, and can also be a communication system integrating two or more of the above systems.

[0040] The RAN node can also be variously expressed, such as radio access network device. In this application, the radio access network device is used for expression without special instructions. The radio access network device (sometimes referred to as network device in this application) can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5G mobile communication system, a next generation NodeB in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc.; it can also be a module or unit that completes part of the function of the base station, such as a central unit (CU) or a distributed unit (DU). The radio access network device can be a macro base station (such as 110a in FIG. 1), a micro base station or an indoor station (such as 110b in FIG. 1), a relay node or a donor node, etc., or a wireless controller in a CRAN scenario. Optionally, the radio access network device can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). It can be understood that all or part of the functions of the radio access network device in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform). The radio access network device in this application can also be a logical node, a logical module or software that can realize all or part of the functions of the radio access network device.

[0041] In another possible scenario, a terminal is assisted by multiple wireless access network devices to implement wireless access, and different wireless access network devices respectively implement part of functions of a base station. For example, a wireless access network device can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0042] In different systems, the CU (or CU-CP and CU-UP), the DU, or the RU can also have different names, but a person skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, the CU-CP, the CU-UP, the DU, and the RU are taken as examples for description in this application. Any one of the CU (or the CU-CP, the CU-UP), the DU, and the RU in this application can be implemented by means of a software module, a hardware module, or a combination of a software module and a hardware module. The embodiments of this application do not limit the specific technology and the specific device form of the wireless access network device. For the convenience of description, a base station is taken as an example of the wireless access network device for description hereinafter.

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

[0044] The terminal in the present application can also be a VR terminal, an AR terminal, or an MR terminal. The VR terminal, the AR terminal, and the MR terminal can all be referred to as an XR terminal. The XR terminal can be a head-mounted device (such as a helmet or glasses), an all-in-one machine, a television, a display, a car, a vehicle-mounted device, a tablet, a smart screen, etc. The XR terminal can present XR data to a user, and the user can experience diversified XR services by wearing or using the XR terminal. The XR terminal can access a network in a wireless or wired manner, such as through WiFi, 5G, or other systems.

[0045] The base station and the terminal can be fixed in position or mobile. The base station and the terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can be deployed on the water surface; and can be deployed on an airplane, a balloon, and a man-made satellite in the air. Embodiments of the present application do not limit the application scenarios of the base station and the terminal.

[0046] The roles of the base station and the terminal can be relative, for example, the airplane or the unmanned aerial vehicle 120i in FIG. 1 can be configured as a mobile base station, and for the terminal 120j that accesses the wireless access network 100 through 120i, the terminal 120i is a base station; but for the base station 110a, 120i is a terminal, that is, 110a and 120i communicate through a wireless air interface protocol. Of course, 110a and 120i can also communicate through a base station-to-base station interface protocol, and in this case, 120i is also a base station relative to 110a. Therefore, the base station and the terminal can be collectively referred to as a communication apparatus, 110a and 110b in FIG. 1 can be referred to as a communication apparatus with a base station function, and 120a-120j in FIG. 1 can be referred to as a communication apparatus with a terminal function.

[0047] The base station and the terminal, the base station and the base station, the terminal and the terminal can communicate through a licensed spectrum, can communicate through an unlicensed spectrum, and can communicate through both the licensed spectrum and the unlicensed spectrum; can communicate through a spectrum below 6 gigahertz (GHz), can communicate through a spectrum above 6 GHz, and can communicate through both the spectrum below 6 GHz and the spectrum above 6 GHz. Embodiments of the present application do not limit the spectrum resources used for wireless communication.

[0048] In embodiments of the present application, the functions of the base station can also be performed by a module (such as a chip) in the base station, or by a control subsystem containing base station functions. The control subsystem containing base station functions herein can be a control center in the application scenarios of the above terminals such as smart grids, industrial control, intelligent transportation, and smart cities. The functions of the terminal can also be performed by a module (such as a chip or modem) in the terminal, or by a device containing terminal functions.

[0049] In the present application, the base station sends a downlink signal or downlink information to the terminal, the downlink information is carried on a downlink channel; the terminal sends an uplink signal or uplink information to the base station, the uplink information is carried on an uplink channel; the terminal sends a sidelink signal or sidelink information to the terminal, the sidelink information is carried on a sidelink channel. The information can be control information or data information.

[0050] Embodiments provided by the present application are applicable to a variety of different scenarios. Figures 2-5 show several system framework schematic diagrams to which embodiments of the present application are applicable.

[0051] Figure 2 shows a schematic diagram of a scenario to which embodiments of the present application are applicable. Figure 2 shows a system 200 containing a server 210, a core network and an access network 220 (which can be referred to as a transmission network 220, for example, an LTE, 5G or 6G network), and a terminal 230. The server 210 can be used for encoding and rendering of source data of XR, the transmission network 220 can be used for transmission of XR data, and the terminal 230 provides diversified XR experience for users by processing XR data. It can be understood that the transmission network 220 and the terminal 230 can also contain other devices, for example, other terminals (such as mobile phones, laptops, or vehicle-mounted terminals, etc.) and / or network equipment (such as relay equipment, integrated access backhaul (IAB) equipment, WiFi routers, or WiFi access points, etc.), and the terminal 230 obtains XR data from the transmission network 220 with the aid of other terminals and / or network equipment.

[0052] Fig. 3 shows another scenario to which embodiments of the present application are applicable. Fig. 3 shows a system 300 comprising a terminal 320 and other terminals 310. The other terminals 310 are terminals other than the terminal 320. The other terminals 310 can transmit XR data to the terminal 320. For example, the other terminals 310 can cast XR data to the terminal 320. For another example, the other terminals 310 and the terminal 320 are vehicle-mounted terminals, and the vehicle-mounted terminals can interact with each other in XR data. It can be understood that the other terminals 310 can also be connected to a transmission network (e.g., an LTE, 5G or 6G network) to obtain XR data from the transmission network or send data to the transmission network.

[0053] Fig. 4 shows another scenario to which embodiments of the present application are applicable. Fig. 4 shows a system 400 comprising a terminal 430, a WiFi router or WiFi access point 420 (which can be referred to as a WiFi device 420), and other terminals 410. The other terminals 410 are terminals other than the terminal 430. The other terminals 410 can transmit XR data to the terminal 430 via the WiFi device 420. For example, the other terminals 410 are mobile phone devices, the WiFi device 420 is a WiFi router, WiFi access point or set-top box, and the terminal 430 is a television device, smart screen device or electronic tablet device. The mobile phone devices can cast XR data to the television device, smart screen device or electronic tablet device via the WiFi router, WiFi access point or set-top box for presentation to a user.

[0054] Fig. 5 shows another scenario to which embodiments of the present application are applicable. Fig. 5 shows a system 500 comprising a server 510, a fixed network 520, a WiFi router or WiFi access point 530 (which can be referred to as a WiFi device 530), and a terminal 540. The server 510 can be used to encode and render source data of XR and transmit XR data to the terminal 540 via the fixed network 520 and the WiFi device 530. For example, the fixed network 520 is an operator network, the WiFi device 530 is a WiFi router, WiFi access point or set-top box, and the server 510 transmits or casts XR data to the terminal 540 via the operator network 520 and the WiFi device 530.

[0055] It can be understood that Figs. 2-5 only show several scenarios to which embodiments of the present application can be applicable, and do not limit the applicable scenarios of embodiments of the present application.

[0056] The technical solutions of the present application will be described below with reference to the accompanying drawings.

[0057] With the rise of large models, artificial intelligence generated content (AIGC) applications, the massive user business growth brings severe computing power challenges to central servers. Wireless networks are naturally close to terminals, and distributed learning based on wireless transmission has outstanding value in terms of sensing data acquisition, auxiliary training, and auxiliary reasoning. According to relevant estimates, the total computing power of current base stations exceeds 2.2 trillion extra operations per second (ETOPS), and considering the growing trend of future wireless network computing resources, the computing power and real-time computing resource status of wireless networks can fully support the computing power of massive terminal users and the central server.

[0058] With the continuous development of terminal devices, the terminal itself also has a certain computing power and can bear a certain neural network calculation. The application server can segment the deep neural network (DNN) model calculation task, for example, the application server can allocate the front-end preprocessing calculation part to the terminal for execution, and upload the complex calculation part to the cloud application server for execution. Compared with the traditional network directly uploading the original image quantity, after the DNN model calculation task is segmented, the terminal extracts the image information, and the network only needs to upload the extracted intermediate feature information, and the data quantity is also reduced.

[0059] The application server needs to consider the computing power of the terminal (for example, terminals with strong computing power can allocate more computing tasks, and terminals with weak computing power can allocate less computing tasks), network transmission rate, and selection of segmentation point when performing DNN model calculation task segmentation. FIG. 6 is an information flow diagram required for the application server to perform DNN model calculation task segmentation. Among them, the computing power information measures the ability of the terminal to execute neural network calculation, which can be sent by the terminal to the server. The computing power information can include the floating point calculation capability of the terminal per unit time, etc. The network transmission rate is the average rate of network transmission business, which can be sent by the core network to the server. The network transmission rate can include the average rate guarantee provided by the core network when configuring quality of service (QoS) information for business. After receiving the above computing power information and network transmission rate, the server determines the decision information of the DNN model calculation task segmentation point (which can also be understood as the selection of the segmentation point).

[0060] The above calculation task segmentation of the DNN model by using the application server only optimizes the calculation power of the terminal and the server, and does not comprehensively consider the collaborative optimization among the base station, the core network, the terminal and the server. Considering that the calculation power resources of the base station and the core network have a growing trend in the future, the calculation power capacity and real-time calculation power resource status of the base station and the core network can fully provide calculation power support for a large number of terminal users and the tight central server. Therefore, how the base station and the core network provide artificial intelligence (AI) services or AI calculation power support to the terminal and the server to alleviate the calculation power shortage problem of the existing end-to-cloud AI service system and improve the AI service quality is a problem to be solved.

[0061] The application provides a task notification method. A terminal sends a task request to a base station, or a server sends a task request to a core network device. The base station and the core network device can determine how to complete an AI task in collaboration with the terminal and the server system according to their own calculation power capacity. Through the above method, the calculation power resources of the base station and the core network device are fully utilized, which can effectively alleviate the AI service calculation power shortage problem of the server and achieve the beneficial effect of improving the terminal AI service satisfaction.

[0062] FIG. 7 is an interaction schematic diagram of a communication method 700 provided by an embodiment of the application. In FIG. 7, a first network device, a base station and a second network device are taken as an example to illustrate the execution subject of the interaction schematic. However, the application is not limited to the execution subject of the interaction schematic. For example, the method executed by the first network device in FIG. 7 can also be executed by a module (such as a chip, a chip system or a processor) applied to the first network device, or a logic node, a logic module or software realizing all or part of the function of the first network device; the method executed by the base station in FIG. 7 can also be executed by a module (such as a chip, a chip system or a processor) applied to the base station, or a logic node, a logic module or software realizing all or part of the function of the base station; the method executed by the second network device in FIG. 7 can also be executed by a module (such as a chip, a chip system or a processor) applied to the second network device, or a logic node, a logic module or software realizing all or part of the function of the second network device. The first network device can be a terminal device, and the second network device can be a core network device; or the first network device can be a core network device, and the second network device can be a terminal device. As shown in FIG. 7, the method 700 of the embodiment can include a 710 part and a 720 part. Optionally, the method 700 of the embodiment can also include a 730 part or a 740 part.

[0063] 710 part: the first network device sends a first task request to the base station, and the first task request is associated with the first task. The first task request can be carried by uplink control information (UCI), downlink control information (DCI), a media access control layer control element (MAC CE), radio resource control (RRC) signaling, access stratum (AS) signaling, or non-access stratum (NAS) signaling. The specific carrying manner of the first task request is not limited in the present application. The first task can be an AI-related task, such as an AI model training task or an AI model calculation task. The first task can also be another task in the communication system in the embodiments of the present application. The first task can also be a combination of an AI-related task and another task in the communication system in the embodiments of the present application, and the present application is not limited in this regard. The first task request and the first task can also be understood as the first task request being used to request the base station to perform the first task.

[0064] 720 part: the base station performs the first task and obtains the execution result of the first task. After receiving the first task request sent by the first network device, the base station can perform part of the first task, can perform the entire first task, or can not perform the first task.

[0065] Optionally, 730 part: the base station sends the execution result of the first task to the first network device. The execution condition of the method 700 in the embodiments of the present application in the 730 part can be that the base station performs the entire first task in the 720 part, or the condition can also be that the base station does not perform the entire first task, but the base station receives an indication to send the execution result of the first task, and the present application is not limited in this regard.

[0066] Alternatively, 740: the base station sends a second task request to the second network device, the second task request is associated with a second task. In the case that the base station performs the first task, the second task can be a task containing the part of the first task that has been performed by the base station, or a task not containing the part of the first task that has been performed by the base station, which is not limited in the present application; in the case that the base station does not perform the first task, the second task can be a task containing the first task. The specific bearing mode of the second task request is consistent with the description of the first task request in the 710 part, which will not be repeated here. The specific form of the second task is consistent with the description of the first task in the 710 part, which will not be repeated here. After the second network device receives the second task request, it can continue to perform the second task, which is developed in the subsequent embodiment part, which will not be repeated here.

[0067] In the method 700, the base station obtains a first task request from the first network device, and the base station performs a first task associated with the first task request, and sends the execution result of the first task to the first network device; or, the base station obtains a first task request from the first network device, and the base station performs a first task associated with the first task request, and sends a second task request to the second network device, the second task request is associated with a second task, and the second network device can continue to perform the second task. Through the above method, the base station, or the base station and the core network device computing resource are fully utilized, which can effectively alleviate the problem of AI service computing power shortage of the server, and achieve the beneficial effect of improving the terminal AI service satisfaction.

[0068] In the present application, "sending information to (the second network device)" can be understood as that the destination of the information is the second network device. It can include directly or indirectly sending information to the second network device. "Receiving information from (the first network device)" can be understood as that the source of the information is the first network device, which can include directly or indirectly receiving information from the first network device. The information between the source and the destination of the information transmission may be processed as necessary, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, which will not be repeated here.

[0069] In a possible implementation of the first task request and the second task request, the first task request includes at least one of a model type used by the first task, an execution proportion of a model used by the first task, an execution accuracy of the model used by the first task, or a latency requirement of executing the first task; and the second task request includes at least one of a model type used by the second task, an execution proportion of a model used by the second task, an execution accuracy of the model used by the second task, or a latency requirement of executing the second task.

[0070] For example, the first task request includes at least one of a model type used by the first task, an execution proportion of a model used by the first task, an execution accuracy of the model used by the first task, or a latency requirement of executing the first task. The content included in the first task request is further described as follows.

[0071] 1. Model type used by the first task: The model type used by the first task can be used to indicate a model structure applicable to the first task and / or a task type of the first task. The model type used by the first task can be represented as a first task model type field. For example, the first task is an AI-related task, and the first task model type field can be represented as an AI Type of 2 bits. The AI Type can be "00", "01", "10" or "11". Different values of the AI Type can correspond to different model types used by the first task, or different model structures applicable to the first task and / or different task types of the first task. For example, the following table shows the correspondence between the values of the AI Type and the model type used by the first task (and the model structure applicable to the first task and the task type of the first task):

[0072] For example, when the value of the AI Type is "00", it indicates that the model structure applicable to the first task is "ResNet-34", and the task type of the first task is "Detection". When the value of the AI Type is "01", "10" or "11", the model structure applicable to the first task and the task type of the first task can refer to the above table, which will not be described here. It can be understood that the above table is only an example. For example, the model structure applicable to the first task can also be other model structures, such as "ResNet-101" or "Transform", and the present application is not limited to this. The model structure applicable to the first task can also have other forms of expression other than the above table, and the present application is not limited to this. The task type of the first task can also be other task types, and the present application is not limited to this. The task type of the first task can also have other forms of expression other than the above table, such as "detection", "classification", "generation" or "prediction", and the present application is not limited to this. The task type of the first task can be further refined, such as "Generation" can be a refined task in the text-to-image generation task or a refined task in the painting style change task, and the task type of the first task can be further refined according to actual needs, and the present application is not limited to this.

[0073] 2, the execution ratio of the model used by the first task: the execution ratio of the model used by the first task can be used to indicate the number of to-be-executed layers, the number of to-be-executed blocks, the proportion of the number of to-be-executed layers to the total number of layers, or the proportion of the number of to-be-executed blocks to the total number of blocks of the model that needs to be executed in the first task. Further, the to-be-executed layers and the to-be-executed blocks can be the subsequent to-be-executed layers and the subsequent to-be-executed blocks of the model that needs to be executed in the first task, and can also be understood as the remaining to-be-executed layers and the remaining to-be-executed blocks of the model that needs to be executed in the first task. The execution ratio of the model used by the first task can be represented as a model execution ratio field. Taking the first task associated with AI as an example, for example, the model execution ratio field is a 2-bit field, the value of the model execution ratio field can be "00", "01", "10" or "11", and different values of the model execution ratio field can correspond to different to-be-executed layers, to-be-executed blocks, to-be-executed layers Proportion of the total number of layers or the proportion of the number of to-be-executed blocks to the total number of blocks, as shown in the following table is the correspondence between the value of the model execution ratio field and the to-be-executed layer / the proportion of the to-be-executed layer to the total number of layers:

[0074] In the above table, the total number of layers of the model used by the first task is 20, and the model execution ratio field is "10", which means that the number of layers to be executed by the model used by the first task is 15 or the proportion of the number of layers to be executed to the total number of layers is 75%. It can also be understood that the first network device has executed 5 layers or 25% of the model used by the first task, and the base station needs to execute the remaining 15 layers or 75% of the model used by the first task. As to the 5 layers or 25% of the model used by the first task that have been executed by the first network device, they are located in the front 25% (the first 5 layers), the middle 25% (the middle 5 layers), or the rear 25% (the last 5 layers) of the model used by the first task, which is not limited in the present application. For example, when the model execution ratio field is "11", it means that the number of layers to be executed by the model used by the first task is 20 or the proportion of the number of layers to be executed to the total number of layers is 100%. It can also be understood that the first network device does not execute any model used by the first task, and the base station needs to execute all the model used by the first task. For other values of the model execution ratio field, please refer to the foregoing examples, which will not be repeated here.

[0075] 3. Execution accuracy of the model used by the first task: The execution accuracy of the model used by the first task can be used to indicate the execution accuracy of the model used by the first task when it is executed. It can also be understood that the execution accuracy of the model used by the first task can be used to indicate the accuracy of the model used by the first task when it is inferred or trained. The execution accuracy of the model used by the first task can be represented by the Precision field. Taking the first task associated with AI as an example, the Precision field is a 2-bit field, and the values of the Precision field can be "00", "01", "10" or "11". Different values of the Precision field can correspond to different model execution accuracies, as shown in the following table for the correspondence between the values of the Precision field and the model execution accuracy:

[0076] In the above table, the model execution precision of "INT4" indicates that all model parameters are half-integer precision, the model execution precision of "INT8" indicates that all model parameters are integer precision, the model execution precision of "FP16" indicates that all model parameters are half-float precision, and the model execution precision of "FP32" indicates that all model parameters are float precision. It can be understood that the model execution precision in the above table is only an example. For example, the model execution precision in the above table can also be "INT2", "Double64" or "Double128". The model execution precision of "INT2" indicates that all model parameters are 0 or 1, the model execution precision of "Double64" indicates that all model parameters are double precision, that is, each float number is represented by 64 bits, and the model execution precision of "Double128" indicates that each float number in the model parameter is represented by 128 bits. The specific form of the model execution precision is not limited in the present application. As shown in the above table, when the value of the Precision field is "00", the model execution precision is "INT4", which can also be understood as the precision of "INT4" of the model trained for the first task. For other value conditions of the Precision field, please refer to the foregoing examples, which will not be repeated here.

[0077] 4. Latency requirement of the first task: The latency requirement of the first task can be used to indicate the latency requirement when the first task is executed, and the base station needs to meet the latency requirement as much as possible when executing the first task. The latency requirement of the first task can be represented by a latency requirement field. Taking the first task as an AI-related task as an example, the latency requirement field is a 2-bit field, and the value of the latency requirement field can be "00", "01", "10" or "11". Different values of the latency requirement field can correspond to different latency requirements, as shown in the following table for the correspondence between the value of the latency requirement field and the latency requirement:

[0078] For example, when the value of the latency requirement field is "01", the latency requirement when the first task is executed is 100 ms, and the base station needs to meet the latency requirement of 100 ms as much as possible when executing the first task. For other value conditions of the latency requirement field, please refer to the foregoing examples, which will not be repeated here.

[0079] Further elaboration of the content contained in the second task request is similar to the further elaboration of the content contained in the first task request, which will not be repeated here.

[0080] In a possible implementation of the method 700, the first network device is a terminal device, and the second network device is a core network device. It can be understood that the terminal device initiates the task request. The base station receives the first task request from the terminal device, the first task request is associated with the first task; the base station executes the first task to obtain the execution result of the first task; the base station sends the execution result of the first task to the terminal device, or the base station sends the second task request to the core network device, the second task request is associated with the second task.

[0081] In a possible implementation of the terminal device initiating the task request, the base station executes all the first tasks to obtain the execution result of all the first tasks, and sends the execution result to the terminal device.

[0082] In another possible implementation of the terminal device initiating the task request, the base station executes part of the first tasks and sends the second task request to the core network device.

[0083] For example, as shown in FIG. 8, a schematic diagram of the terminal device initiating the task request is provided in the embodiment of the present application. In FIG. 8, the terminal device sends the first task request to the base station, and correspondingly, the base station receives the first task request from the terminal device, the first task request is associated with the first task. After receiving the first task request, the base station executes the first task in combination with the computing power of the base station to obtain the execution result of the first task. When the computing power of the base station is sufficient and sufficient to complete all the first tasks, the base station executes all the first tasks to obtain the execution result of all the first tasks, and sends the execution result to the terminal device; when the computing power of the base station is insufficient and insufficient to complete all the first tasks, the base station executes part of the first tasks and sends the second task request to the core network device, the second task request is associated with the second task. After receiving the second task request from the base station, the core network device executes the second task in combination with the computing power of the core network device to obtain the execution result of the second task. If the computing power of the core network device is sufficient and sufficient to complete all the second tasks, the core network device executes all the second tasks to obtain the execution result of all the second tasks, and sends the execution result to the base station; if the computing power of the core network device is insufficient and insufficient to complete all the second tasks, the core network device executes part of the second tasks and sends the fifth task request to the server, the fifth task request is associated with the fifth task, and the specific description of the fifth task request and the fifth task can refer to the description of the first task request and the first task, which will not be described here. After receiving the fifth task request sent by the core network device, the server executes all the fifth tasks to obtain the execution result of all the fifth tasks, and sends the execution result to the core network device.

[0084] In another possible implementation of the method 700, the first network device is a core network device, and the second network device is a terminal device. It can be understood that the embodiment is initiated by the server to request a task. The base station receives the first task request from the core network device, the first task request is associated with the first task; the base station executes the first task to obtain the execution result of the first task; and the base station sends the execution result of the first task to the core network device.

[0085] In a possible implementation of the server initiating a task request, the base station executes the first task to obtain the execution result of the first task, and sends the execution result to the core network device.

[0086] For example, FIG. 9 shows a schematic diagram of a server initiating a task request according to an embodiment of the present application. In FIG. 9, the server sends a sixth task request to the core network device. Accordingly, the core network device receives the sixth task request from the server, the sixth task request is associated with the sixth task, and the specific description of the sixth task request and the sixth task can refer to the description of the first task request and the first task, which will not be repeated here. After receiving the sixth task request, the core network device executes the sixth task in combination with its own computing power to obtain the execution result of the sixth task. When the computing power of the core network device is sufficient and sufficient to complete all the sixth tasks, the core network device executes all the sixth tasks to obtain the execution result of all the sixth tasks, and sends the execution result to the server. When the computing power of the core network device is insufficient and insufficient to complete all the sixth tasks, the core network device executes part of the sixth tasks, and sends a first task request to the base station, the first task request is associated with the first task. After receiving the first task request sent by the core network device, the base station executes part or all of the first task to obtain the execution result of part or all of the first task, and sends the execution result to the core network device.

[0087] FIG. 10 is an interaction diagram of a communication method 1000 provided by an embodiment of the present application. The method is exemplified in FIG. 10 by taking a first network device, a core network device and a second network device as the execution subject of the interaction diagram, but the present application does not limit the execution subject of the interaction diagram. For example, the method performed by the first network device in FIG. 10 can also be performed by a module (such as a chip, a chip system or a processor) applied to the first network device, or a logic node, a logic module or software realizing all or part of the function of the first network device; the method performed by the core network device in FIG. 10 can also be performed by a module (such as a chip, a chip system or a processor) applied to the core network device, or a logic node, a logic module or software realizing all or part of the function of the core network device; the method performed by the second network device in FIG. 10 can also be performed by a module (such as a chip, a chip system or a processor) applied to the second network device, or a logic node, a logic module or software realizing all or part of the function of the second network device. The first network device can be a base station, and the second network device can be a server; or the first network device can be a server, and the second network device can be a base station. As shown in FIG. 10, the method 1000 of the embodiment can include a 1010 part and a 1020 part. Optionally, the method 1000 of the embodiment can also include a 1030 part or a 1040 part.

[0088] 1010 part: the first network device sends a third task request to the core network device, and the third task request is associated with the third task. The third task request can be carried by uplink control information (UCI), downlink control information (DCI), media access control control element (MAC CE), radio resource control (RRC) signaling, access stratum (AS) signaling, or non-access stratum (NAS) signaling. The specific carrying mode of the third task request is not limited in the application. The third task can be an AI-related task, such as an AI model training task or an AI model calculation task. The third task can also be other tasks in the communication system of the embodiments of the application. The third task can also be a combination of an AI-related task and other tasks in the communication system of the embodiments of the application, and the application is not limited. The third task request and the third task can also be understood as the third task request being used to request the core network device to perform the third task.

[0089] 1020 part: the core network device performs the third task and obtains the execution result of the third task. After receiving the third task request sent by the first network device, the core network device can perform part of the third task, can perform all of the third task, or can not perform the third task.

[0090] Optionally, 1030 part: the core network device sends the execution result of the third task to the first network device. The execution condition of the method 1000 of the embodiments of the application in the 1030 part can be that the core network device performs all of the third task in the 1020 part, or the condition can also be that the core network device does not perform all of the third task, but the core network device receives an indication to send the execution result of the third task, and the application is not limited.

[0091] Alternatively, 1040 part: the core network device sends a fourth task request to the second network device, and the fourth task request is associated with the fourth task. In the case where the core network device performs part of the third task, the fourth task can be a task containing the part of the third task that has been executed by the core network device, or a task not containing the part of the third task that has been executed by the core network device, which is not limited in the present application; in the case where the core network device does not perform the third task, the fourth task can be a task containing the third task. For the specific bearing mode of the fourth task request, the above-mentioned 1010 part about the third task request is consistent, which will not be repeated here. For the specific form of the fourth task, the above-mentioned 1010 part about the third task is consistent, which will not be repeated here. After the second network device receives the fourth task request, it can continue to execute the fourth task, which is developed in the subsequent embodiment part, which will not be repeated here.

[0092] In the method 1000, the core network device obtains a third task request from the first network device, and the core network device executes a third task associated with the third task request, and sends the execution result of the third task to the first network device; or, the core network device obtains a third task request from the first network device, and the core network device executes a third task associated with the third task request, and sends a fourth task request to the second network device, the fourth task request is associated with the fourth task, and the second network device can continue to execute the fourth task. Through the above method, the core network device, or the base station and the core network device computing resource are fully utilized, which can effectively alleviate the problem of AI service computing power shortage of the server, and realize the beneficial effect of improving the terminal AI service satisfaction.

[0093] In the present application, "sending information to (the second network device)" can be understood as that the destination of the information is the second network device. It can include directly or indirectly sending information to the second network device. "Receiving information from (the first network device)" can be understood as that the source of the information is the first network device, which can include directly or indirectly receiving information from the first network device. The information between the source and the destination of the information transmission may be processed as necessary, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be similarly understood, which will not be repeated here.

[0094] In a possible implementation of the third task request and the fourth task request, the third task request comprises at least one of the following: a model category used by the third task, an execution proportion of a model used by the third task, an execution accuracy of the model used by the third task, or a time delay requirement for executing the third task; and the fourth task request comprises at least one of the following: a model category used by the fourth task, an execution proportion of a model used by the fourth task, an execution accuracy of the model used by the fourth task, or a time delay requirement for executing the fourth task. Further details about the content included in the third task request and the fourth task request are similar to those included in the first task request, and are not repeated here.

[0095] In a possible implementation of the method 1000, the first network device is a base station, and the second network device is a server. It can be understood that the present embodiment is initiated by a terminal device. The core network device receives the third task request from the base station, the third task request being associated with the third task; the core network device executes the third task to obtain an execution result of the third task; and the core network device sends the execution result of the third task to the base station, or the core network device sends the fourth task request to the server, the fourth task request being associated with the fourth task.

[0096] In a possible implementation of the terminal device initiating the task request, the core network device executes all the third tasks to obtain execution results of all the third tasks, and sends the execution results to the base station.

[0097] In another possible implementation of the terminal device initiating the task request, the core network device executes part of the third tasks, and sends the fourth task request to the server.

[0098] For example, FIG. 11 shows a schematic diagram of a terminal device initiating a task request according to an embodiment of the present application. In FIG. 11, the terminal device sends a seventh task request to the base station. Correspondingly, the base station receives the seventh task request from the terminal device, and the seventh task request is associated with a seventh task. The seventh task request and the seventh task can be described with reference to the first task request and the first task, which will not be described here. After receiving the seventh task request, the base station executes the seventh task by combining its own computing power, and obtains the execution result of the seventh task. When the computing power of the base station is sufficient to complete all the seventh tasks, the base station executes all the seventh tasks, obtains the execution result of all the seventh tasks, and sends the execution result to the terminal device. When the computing power of the base station is insufficient to complete all the seventh tasks, the base station executes part of the seventh tasks, and sends a third task request to the core network device, where the third task request is associated with a third task. After receiving the third task request from the base station, the core network device executes the third task by combining its own computing power, and obtains the execution result of the third task. If the computing power of the core network device is sufficient to complete all the third tasks, the core network device executes all the third tasks, obtains the execution result of all the third tasks, and sends the execution result to the base station. If the computing power of the core network device is insufficient to complete all the third tasks, the core network device executes part of the third tasks, and sends a fourth task request to the server, where the fourth task request is associated with a fourth task. After receiving the fourth task request from the core network device, the server executes all the fourth tasks, obtains the execution result of all the fourth tasks, and sends the execution result to the core network device.

[0099] In another possible implementation of the method 1000, the first network device is a server, and the second network device is a base station. It can be understood that the server initiates the task request. The core network device receives the third task request from the server, where the third task request is associated with the third task. The core network device executes the third task, obtains the execution result of the third task, and sends the execution result of the third task to the server, or the core network device sends the fourth task request to the base station, where the fourth task request is associated with the fourth task.

[0100] In one possible implementation of the server initiating the task request, the core network device executes all the third tasks, obtains the execution result of all the third tasks, and sends the execution result to the server.

[0101] In another possible implementation of the server initiating the task request, the core network device executes part of the third tasks, and sends the fourth task request to the base station.

[0102] For example, FIG. 12 shows a schematic diagram of a server initiating a task request according to an embodiment of the present application. In FIG. 12, the server sends a third task request to the core network device. Accordingly, the core network device receives the third task request from the server, and the third task request is associated with the third task. After receiving the third task request, the core network device executes the third task by combining its own computing power, and obtains the execution result of the third task. When the computing power of the core network device is sufficient and sufficient to complete all the third tasks, the core network device executes all the third tasks, obtains the execution result of all the third tasks, and sends the execution result to the server. When the computing power of the core network device is insufficient and insufficient to complete all the third tasks, the core network device executes part of the third tasks, and sends a fourth task request to the base station, wherein the fourth task request is associated with the fourth task. After receiving the fourth task request sent by the core network device, the base station executes part or all of the fourth task, obtains the execution result of part or all of the fourth task, and sends the execution result to the core network device.

[0103] Corresponding to the method provided by the method embodiment, the embodiment of the present application also provides a corresponding device, which includes a module for executing the corresponding modules of the above embodiments. The module can be software, hardware, or a combination of software and hardware.

[0104] FIG. 13 provides a schematic diagram of the structure of a terminal. The terminal can be applicable to the scenarios shown in FIG. 1, FIG. 2, FIG. 3, FIG. 4 or FIG. 5. The terminal or the modules in the terminal can execute the foregoing methods 700 and 1000 and various possible implementations. For ease of illustration, FIG. 13 only shows the main modules of the terminal. As shown in FIG. 13, the terminal 1300 includes a processor, a memory, a control circuit, an antenna and an input / output device. The processor is mainly used for processing communication protocols and communication data, controlling the entire terminal, executing software programs and processing data of the software programs. The memory is mainly used for storing software programs and data. The radio frequency circuit is mainly used for conversion between baseband signals and radio frequency signals and processing of radio frequency signals. The antenna is mainly used for transmitting and receiving radio frequency signals in the form of electromagnetic waves. The input / output device, such as a touch screen, a display screen, a keyboard, etc., is mainly used for receiving user input data and outputting data to the user.

[0105] When the terminal is powered on, the processor can read the software program in the storage unit, parse and execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor performs baseband processing on the data to be transmitted, and outputs the baseband signal to the radio frequency circuit. The radio frequency circuit processes the baseband signal to obtain a radio frequency signal and transmits the radio frequency signal in the form of an electromagnetic wave through the antenna. When data is transmitted to the terminal, the radio frequency circuit receives a radio frequency signal through the antenna. The radio frequency signal is further converted into a baseband signal, and the baseband signal is output to the processor. The processor converts the baseband signal into data and processes the data.

[0106] For ease of illustration, FIG. 13 only shows one memory and one processor. In an actual terminal, there can be multiple processors and memories. The memory can also be referred to as a storage medium or a storage device, and the like, and the embodiments of the present application do not limit this.

[0107] As an optional implementation, the processor can include a baseband processor and a central processor. The baseband processor is mainly used for processing communication protocols and communication data. The central processor is mainly used for controlling the entire terminal device, executing software programs, and processing data of the software programs. The processor in FIG. 13 integrates the functions of the baseband processor and the central processor. Those skilled in the art can understand that the baseband processor and the central processor can also be independent processors interconnected through a bus or the like. Those skilled in the art can understand that the terminal can include multiple baseband processors to adapt to different network standards, and the terminal can include multiple central processors to enhance its processing capability. Various modules of the terminal can be connected through various buses. The baseband processor can also be referred to as a baseband processing circuit or a baseband processing chip. The central processor can also be referred to as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built into the processor, or can be stored in the storage unit in the form of a software program, and the processor executes the software program to realize the baseband processing function.

[0108] In an example, the antenna and control circuit with transceiving function can be regarded as a transceiving unit 1311 of the terminal 1300, and the processor with processing function can be regarded as a processing unit 1312 of the terminal 1300. As shown in FIG. 13, the terminal 1300 includes the transceiving unit 1311 and the processing unit 1312. The transceiving unit can also be referred to as a transceiver, a transceiver unit, etc. Optionally, the device for realizing the receiving function in the transceiving unit 1311 can be regarded as a receiving unit, and the device for realizing the sending function in the transceiving unit 1311 can be regarded as a sending unit, that is, the transceiving unit 1311 includes the receiving unit and the sending unit. Exemplarily, the receiving unit can also be referred to as a receiver, a receiving circuit, etc., and the sending unit can be referred to as a transmitter, a transmitting circuit, etc. Optionally, the above-mentioned receiving unit and sending unit can be integrated into one unit, or can be multiple independent units. The above-mentioned receiving unit and sending unit can be in one geographical location, or can be dispersed in multiple geographical locations.

[0109] As shown in FIG. 14, another embodiment of the present application provides a device 1400. The device can be a base station, or a module (for example, an integrated circuit, a chip, etc.) applied to the base station, and can also be a logic node, a logic module or software capable of realizing all or part of the function of the base station. Alternatively, the device can be a core network device, or a module (for example, an integrated circuit, a chip, etc.) applied to the core network device, and can also be a logic node, a logic module or software capable of realizing all or part of the function of the core network device. The device can also be other communication modules. For example, the device 1400 can realize the function of the base station in the method 700 and various possible embodiments, or the device 1400 can realize the function of the core network device in the method 1000 and various possible embodiments. The device 1400 can include an interface module 1401 (or an interface unit) and a processing module 1402 (or a processing unit), and can also include a storage module 1403 (or a storage unit).

[0110] In a possible design, one or more modules in FIG. 14 can be implemented by one or more processors, or by one or more processors and memories; or by one or more processors and transceivers; or by one or more processors, memories and transceivers, and the embodiments of the present application are not limited here. The processor, the memory and the transceiver can be separately arranged, or integrated.

[0111] The apparatus has the functions of the terminal described in the embodiments of the present application, for example, the apparatus includes modules or units or means corresponding to the steps performed by the terminal described in the embodiments of the present application. The functions or units or means can be implemented by software or by hardware, or by a combination of hardware and software. Further details can be referred to the corresponding description in the foregoing method embodiments. Alternatively, the apparatus has the functions of the wireless access network device described in the embodiments of the present application, for example, the apparatus includes modules or units or means corresponding to the steps performed by the wireless access network device described in the embodiments of the present application. The functions or units or means can be implemented by software or by hardware, or by a combination of hardware and software. Further details can be referred to the corresponding description in the foregoing method embodiments.

[0112] In a possible design, the apparatus 1400 includes an interface module 1401 and a processing module 1402. The apparatus 1400 can be a base station, or a module (for example, a processor, a chip, or a chip system) applied to a base station, or a logic node, a logic module, or software capable of implementing all or part of functions of a base station. The interface module 1401 is configured to receive a first task request, where the first task request is associated with a first task. The processing module 1402 is configured to perform the first task to obtain an execution result of the first task. The interface module 1401 is configured to send the execution result. Alternatively, the interface module 1401 is configured to send a second task request, where the second task request is associated with a second task.

[0113] In a possible implementation of the apparatus 1400, the first task request includes at least one of the following: a model type used by the first task, an execution proportion of a model used by the first task, an execution accuracy of the model used by the first task, or a time delay requirement for performing the first task. The second task request includes at least one of the following: a model type used by the second task, an execution proportion of a model used by the second task, an execution accuracy of the model used by the second task, or a time delay requirement for performing the second task.

[0114] In a possible implementation of the apparatus 1400, the processing module 1402 is configured to perform all the first tasks to obtain execution results of all the first tasks. The interface module 1401 is configured to send the execution results to a terminal device.

[0115] In a possible implementation of the apparatus 1400, the processing module 1402 is configured to perform the first task described above; and the interface module 1401 is configured to send the second task request described above to the core network device.

[0116] In a possible implementation of the apparatus 1400, the processing module 1402 is configured to perform the first task described above, and obtain an execution result of the first task; and the interface module 1401 is configured to send the execution result to the core network device.

[0117] In a possible design, the apparatus 1400 includes an interface module 1401 and a processing module 1402. The apparatus 1400 can be, for example, a core network device, or a module (for example, a processor, a chip, or a chip system) applied to the core network device, or a logic node, a logic module, or software capable of implementing all or part of the functions of the core network device. The interface module 1401 is configured to receive a third task request, and the third task request is associated with a third task; the processing module 1402 is configured to perform the third task, and obtain an execution result of the third task; and the interface module 1401 is configured to send the execution result, or the interface module 1401 is configured to send a fourth task request, and the fourth task request is associated with a fourth task.

[0118] In a possible implementation of the apparatus 1400, the third task request includes at least one of the following: a model category used by the third task, an execution proportion of a model used by the third task, an execution accuracy of the model used by the third task, or a time delay requirement for performing the third task; and the fourth task request includes at least one of the following: a model category used by the fourth task, an execution proportion of a model used by the fourth task, an execution accuracy of the model used by the fourth task, or a time delay requirement for performing the fourth task.

[0119] In a possible implementation of the apparatus 1400, the processing module 1402 is configured to perform all the third tasks described above, and obtain execution results of all the third tasks; and the interface module 1401 is configured to send the execution results to the base station or the server.

[0120] In a possible implementation of the apparatus 1400, the processing module 1402 is configured to perform part of the third tasks described above; and the interface module 1401 is configured to send the fourth task request to the server or the base station.

[0121] It can be understood that the apparatus 1400 and the various possible implementations correspond to the beneficial effects described in the foregoing method embodiments or the summary, which will not be described here again.

[0122] Optionally, the apparatus 1400 can further include a storage module 1403 for storing data or instructions (also referred to as code or program), and the above-mentioned modules can interact with or be coupled to the storage module to implement corresponding methods or functions. For example, the processing module 1402 can read the data or instructions in the storage module 1403, so that the apparatus 1400 implements the methods in the above embodiments.

[0123] In one example, the modules in the apparatus can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms. In another example, when the modules in the apparatus can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. In another example, these units can be integrated together to implement a system-on-a-chip (SOC).

[0124] Referring to FIG. 15, an apparatus provided by the embodiments of the present application is shown, which can be used to implement the above methods 700 and 1000 and various possible implementations. As shown in FIG. 15, the apparatus includes a processor 1510 and an interface 1530, the processor 1510 being coupled to the interface 1530. The interface 1530 is configured to implement communication with other modules or devices. The interface 1530 can be a transceiver or an input / output interface. The interface 1530 may, for example, be an interface circuit. Optionally, the apparatus further includes a memory 1520 for storing instructions executed by the processor 1510 or storing input data required by the processor 1510 to run instructions or storing data generated after the processor 1510 runs instructions.

[0125] The above methods 700 and 1000 and various possible implementations can be implemented by the processor 1510 invoking programs or instructions stored in the memory 1520. The memory 1520 can be internal to the apparatus or external to the apparatus, which is not limited in the present application.

[0126] Optionally, the functions / implementation procedures of the interface module 1401 and the processing module 1402 in FIG. 14 can be implemented by the processor 1510 in the apparatus shown in FIG. 15. Alternatively, the functions / implementation procedures of the processing module 1402 in FIG. 14 can be implemented by the processor 1510 in the apparatus shown in FIG. 15, and the functions / implementation procedures of the interface module 1401 in FIG. 14 can be implemented by the interface 1530 in the apparatus shown in FIG. 15. For example, the functions / implementation procedures of the interface module 1401 can be implemented by the processor calling program instructions in the memory to drive the interface 1530.

[0127] When the apparatus is a chip applied to a base station, the chip implements the functions of the base station in the method embodiments. The chip receives information from other modules (such as a radio frequency module or an antenna) in the base station, and the information is from other base stations or core network devices or terminals; or the chip sends information to other modules (such as a radio frequency module or an antenna) in the base station, and the information is sent by the base station to other base stations or core network devices or terminals.

[0128] When the apparatus is a chip applied to a core network device, the chip of the core network device implements the functions of the core network device in the method embodiments. The chip receives information from other modules (such as a radio frequency module or an antenna) in the core network device, and the information is from other core network devices or base stations; or the chip sends information to other modules (such as a radio frequency module or an antenna) in the core network device, and the information is sent by the core network device to other core network devices or base stations.

[0129] Those skilled in the art can understand that the first, second, and various other numbers involved in the present application are only for the convenience of differentiation, and do not limit the scope of the embodiments of the present application, nor indicate the order. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after it are in an "or" relationship. "At least one" means one or more. At least two means two or more. "At least one", "any one" or similar expressions mean any combination of these items, including any combination of single item (s) or multiple items. For example, at least one of a, b, or c (one, kind) can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. "Multiple" means two or more, and other quantifiers are similar.

[0130] It should be understood that the size of the serial number of the above processes does not mean the order of execution in various embodiments of the present application, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0131] In the above embodiments, all or part of the processes can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the processes can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0132] The steps of the method described in the embodiments of the present application can be directly embedded in hardware, software unit executed by a processor, or a combination of the two. The software unit can be stored in a random access memory (RAM), a flash memory, a read-only memory (ROM), a register, a hard disk, a removable magnetic disk or any other form of storage medium in the art. The storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC.

[0133] The present application also provides a computer readable medium having a computer program stored thereon, which, when executed by a computer, implements the functions of any of the above method embodiments.

[0134] The application further provides a computer program product, which, when executed by a computer, realizes the functions of any of the method embodiments. Identical or similar parts among the various embodiments can be mutually referred to. In the various embodiments of the application, and in the various implementation manners / implementation methods / realization methods of the various embodiments, the terms and / or descriptions of different embodiments, and the various implementation manners / implementation methods / realization methods of the various embodiments are consistent and can be mutually referred to, unless otherwise specified and in conflict with logic. The technical features of different embodiments, and the various implementation manners / implementation methods / realization methods of the various embodiments can be combined to form new embodiments, implementation manners, implementation methods, or realization methods according to their inherent logical relationship. The above-described implementation manners of the application do not constitute a limitation on the protection scope of the application.

[0135] The above describes only specific implementation manners of the application, but the protection scope of the application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the application, which should be encompassed within the protection scope of the application.

Claims

1. A communication method characterized by comprising: The method comprises: receiving a first task request, the first task request being associated with a first task; executing the first task to obtain an execution result of the first task; sending the execution result, or sending a second task request, the second task request being associated with a second task.

2. The method of claim 1, wherein, The first task request comprises at least one of the following: a model type used by the first task, an execution proportion of a model used by the first task, an execution accuracy of the model used by the first task, or a time delay requirement for executing the first task. The second task request comprises at least one of the following: a model type used by the second task, an execution proportion of a model used by the second task, an execution accuracy of the model used by the second task, or a time delay requirement for executing the second task.

3. The method according to claim 1 or 2, characterized in that, The sending of the execution result comprises: executing all the first tasks to obtain execution results of all the first tasks, and sending the execution results to a terminal device.

4. The method according to claim 1 or 2, characterized in that, The sending of the second task request comprises: executing part of the first tasks, and sending the second task request to a core network device.

5. The method according to claim 1 or 2, characterized in that, The sending of the execution result comprises: executing the first task to obtain an execution result of the first task, and sending the execution result to a core network device.

6. A communication method characterized by comprising: The method comprises: receiving a third task request, the third task request being associated with a third task; executing the third task to obtain an execution result of the third task; sending the execution result, or sending a fourth task request, the fourth task request being associated with a fourth task.

7. The method of claim 6, wherein, The third task request comprises at least one of the following: a model type used by the third task, an execution proportion of a model used by the third task, an execution accuracy of the model used by the third task, or a time delay requirement for executing the third task. The fourth task request comprises at least one of the following: a model type used by the fourth task, an execution proportion of a model used by the fourth task, an execution accuracy of the model used by the fourth task, or a time delay requirement for executing the fourth task.

8. The method according to claim 6 or 7, characterized in that, The sending of the execution result comprises: executing all the third tasks to obtain execution results of all the third tasks, and sending the execution results to a base station or a server.

9. The method according to claim 6 or 7, characterized in that, The sending of the fourth task request comprises: executing part of the third tasks, and sending the fourth task request to a server or a base station.

10. A communication device, characterized by The apparatus comprises: a processor coupled to a memory, the memory being configured to store programs or instructions, when the programs or instructions are executed by the processor, the apparatus is caused to execute the method according to any one of claims 1 to 5.

11. A communications device, characterized by The apparatus comprises: a processor coupled to a memory, the memory being configured to store programs or instructions, when the programs or instructions are executed by the processor, the apparatus is caused to execute the method according to any one of claims 6 to 9.

12. A communication system, characterized by The communication system comprises a base station and a core network device, the base station is configured to execute the method according to any one of claims 1 to 5, and the core network device is configured to execute the method according to any one of claims 6 to 9.

13. A computer-readable storage medium having stored thereon instructions, The instructions, when executed, result in the method of any of claims 1 to 5 being performed, or result in the method of any of claims 6 to 9 being performed.

14. A computer program product, characterised in that, A computer program product comprising computer program code to, when run on a computer, implement the method of any of claims 1 to 5, or implement the method of any of claims 6 to 9.

Images