Information transmission method and device, equipment, storage medium and computer program product

Abstract

The invention discloses an information transmission method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: a first network device obtains first information sent by at least one second network device; the first information is related to available computing power of the second network equipment; wherein the first network device and the at least one second network device are in a master-slave relationship.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to an information transmission method, device, equipment, storage medium and computer program product. Background Art

[0002] At present, with the development of artificial intelligence (AI), the demand for computing power in the entire network is increasing exponentially. If users want to use AI in a high-quality manner, the computing power on the terminal side alone cannot meet the computing resources required for AI services. The computing power on the base station side, as the computing power resource closest to the service in the communication network, can better meet the computing task requirements of latency-sensitive AI services compared to the computing power resources of the core network. Therefore, how to schedule the computing power on the base station side has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application is intended to provide an information transmission method, apparatus, device, storage medium and computer program product.

[0004] The technical solution of this application is implemented as follows:

[0005] The present application provides an information transmission method, which is applied to a first network device, and the method includes:

[0006] Acquire first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device;

[0007] The first network device and the at least one second network device are in a master-slave relationship.

[0008] In addition, according to at least one embodiment of the present application, the obtaining of first information respectively sent by at least one second network device includes:

[0009] Sending a first request to each of the at least one second network devices; the first request is used to request the second network device to send the first information to the first network device;

[0010] Receive responses to the first request respectively sent by the at least one second network device; the responses carry the first information.

[0011] In addition, according to at least one embodiment of the present application, the obtaining of first information respectively sent by at least one second network device includes:

[0012] According to a first period, first information respectively sent by the at least one second network device is received.

[0013] In addition, according to at least one embodiment of the present application, the method further includes:

[0014] Determine, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device;

[0015] Alternatively, determining a third network device that provides computing power services for the terminal according to the second information and the third information;

[0016] in,

[0017] The first information includes available computing power information of the second network device; the computing power information includes computing power resource type and computing power resource size;

[0018] The third information includes available computing power information of the first network device; the computing power information includes computing power resource type and computing power resource size;

[0019] The second information includes:

[0020] Latency of AI services;

[0021] and / or,

[0022] The types and amounts of computing resources required for AI services.

[0023] In addition, according to at least one embodiment of the present application, the method further includes:

[0024] receiving a second request sent by the terminal; the terminal has established a connection with the first network device;

[0025] The second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal.

[0026] In addition, according to at least one embodiment of the present application, the method further includes:

[0027] receiving a second request sent by a fourth network device among the at least one second network device; the terminal has established a connection with the fourth network device;

[0028] Among them, the second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal; the second request is sent by the terminal to the fourth network device, and forwarded by the fourth network device to the first network device.

[0029] In addition, according to at least one embodiment of the present application, determining, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device includes:

[0030] Determine, from the at least one second network device, a third network device that provides computing services for the terminal according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device;

[0031] or,

[0032] Based on the latency of the AI ​​service, determine the type and size of computing resources required for the AI ​​service; according to the type and size of computing resources required for the AI ​​service, and the type and size of computing resources available for use by the second network device, determine a third network device from the at least one second network device to provide computing services for the terminal.

[0033] In addition, according to at least one embodiment of the present application, the method further includes:

[0034] Receiving first data sent by the terminal in a preset first data format; the first data is related to AI; the preset first data format meets the transmission requirements between the first network device and the third network device;

[0035] sending the first data to the third network device so that the third network device calculates the first data;

[0036] Receiving a calculation result sent by the third network device;

[0037] The calculation result is sent to the terminal.

[0038] At least one embodiment of the present application provides an information transmission method, which is applied to a second network device, and the method includes:

[0039] Sending first information to a first network device; the first information is related to the available computing power of the second network device;

[0040] The first network device and at least one of the second network devices are in a master-slave relationship.

[0041] In addition, according to at least one embodiment of the present application, sending the first information to the first network device includes:

[0042] receiving a first request sent by the first network device; the first request is used to request the second network device to send the first information to the first network device;

[0043] A response to the first request is sent to the first network device; the response carries the first information.

[0044] In addition, according to at least one embodiment of the present application, sending the first information to the first network device includes:

[0045] The first information is sent to the first network device according to a first cycle.

[0046] In addition, according to at least one embodiment of the present application, the second network device is a fourth network device in at least one of the second network devices, and the terminal has established a connection with the fourth network device; the method further includes:

[0047] receiving a second request sent by a terminal; the second request carries second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal;

[0048] forwarding the second request to the first network device;

[0049] in,

[0050] The second information includes:

[0051] Latency of AI services;

[0052] and / or,

[0053] The types and amounts of computing resources required for AI services.

[0054] In addition, according to at least one embodiment of the present application, the method further includes:

[0055] A response to the second request sent by the first network device is received; the response carries information of the third network device.

[0056] In addition, according to at least one embodiment of the present application, the method further includes:

[0057] receiving first data sent by the terminal in a preset second data format; the first data is related to AI; the preset second data format meets the transmission requirements between the fourth network device and the third network device;

[0058] Sending the first data to the third network device;

[0059] Receiving a calculation result sent by the third network device;

[0060] The calculation result is sent to the terminal.

[0061] At least one embodiment of the present application provides an information transmission device, including:

[0062] An acquisition module is used to acquire first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

[0063] At least one embodiment of the present application provides an information transmission device, including:

[0064] A sending module is used to send first information to a first network device; the first information is related to the available computing power of a second network device; wherein the first network device and at least one of the second network devices are in a master-slave relationship.

[0065] At least one embodiment of the present application provides a first network device, including a processor and a memory for storing a computer program that can be run on the processor.

[0066] Wherein, when the processor is used to run the computer program, it executes the steps of any one of the methods described above on the first network device side.

[0067] At least one embodiment of the present application provides a second network device, including a processor and a memory for storing a computer program that can be run on the processor.

[0068] Wherein, when the processor is used to run the computer program, it executes the steps of any one of the methods described above on the second network device side.

[0069] At least one embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program implements the steps of any one of the methods described in the first network device side, or implements the steps of any one of the methods described in the second network device side.

[0070] At least one embodiment of the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements any of the methods described above on the first network device side, or implements any of the methods described above on the second network device side.

[0071] The information transmission method, apparatus, device, storage medium and computer program product provided in the embodiments of the present application include: a first network device obtains first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

[0072] By adopting the technical solution provided in the embodiment of the present application, the first network device can obtain the computing power information on the second network device side. In this way, the first network device can subsequently schedule the computing power resources on the second network device side to meet the user's business needs, such as AI business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a schematic diagram of the system architecture of the information transmission method of the embodiment of the present application;

[0074] Figure 2 This is a schematic diagram of the implementation process of the information transmission method of the embodiment of the present application Figure 1 ;

[0075] Figure 3 This is a schematic diagram of the implementation process of the information transmission method of the embodiment of the present application Figure 2 ;

[0076] Figure 4 This is a schematic diagram of the specific implementation process of the information transmission method of the embodiment of the present application. Figure 1 ;

[0077] Figure 5 This is a schematic diagram of the specific implementation process of the information transmission method of the embodiment of the present application. Figure 2 ;

[0078] Figure 6 This is a schematic diagram of the structure of the information transmission device according to the embodiment of the present application. Figure 1 ;

[0079] Figure 7 This is a schematic diagram of the structure of the information transmission device according to the embodiment of the present application. Figure 2 ;

[0080] Figure 8 This is a schematic diagram of the composition structure of the first network device in the embodiment of the present application.

[0081] Fig. 9 It is a schematic diagram of the composition structure of the second network device in an embodiment of the present application. DETAILED DESCRIPTION

[0082] Before introducing the technical solutions of the embodiments of the present application, the related technologies are first introduced.

[0083] In related technologies, with the development of artificial intelligence (AI), the demand for computing power in the entire network has increased exponentially. Users want to use AI with high quality, but the computing power on the terminal side alone cannot meet the computing resources required for AI services. The computing power on the base station side, as the computing power resource closest to the service in the communication network, can better meet the computing task requirements of latency-sensitive AI services compared to the computing power resources of the core network. At the same time, since the computing power on the base station side is limited compared to the computing power of the core network, it needs to be reasonably scheduled.

[0084] Based on this, in an embodiment of the present application, a first network device obtains first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

[0085] See also Figure 1 , Figure 1 Schematic diagram of the system architecture of the information transmission method of the present application embodiment. Figure 1 As shown, including:

[0086] The first network device obtains first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device.

[0087] At least one second network device sends the first information to the first network device respectively.

[0088] The first network device and the at least one second network device are in a master-slave relationship.

[0089] Here, the system architecture may be a 6G network architecture.

[0090] Here, the at least one second network device may refer to a 5G base station and may be a slave base station, which may be represented by a gNB slave station. The gNB slave station is an ordinary base station with communication capabilities and the ability to provide computing power services at this station.

[0091] Here, the first network device may refer to a 5G base station and is a master base station, which may be represented by a gNB master station. The gNB master station is an enhanced base station with communication capabilities and the ability to provide computing services for the local / cross-slave stations.

[0092] Here, the gNB slave is deployed locally at the closest physical distance to the customer and is responsible for the provision of converged services and communication services.

[0093] Here, the gNB master station is deployed at the district and county level and has the capabilities of a slave station. In addition, the gNB master station is also the control unit of the converged service (except for communication services), responsible for the policy formulation of the converged services (such as computing power services) within the scope, and the scheduling of computing power resources across slave stations.

[0094] Here, the terminal (UE) can establish a connection with the gNB master station or with the gNB slave station.

[0095] See also Figure 2 , Figure 2 Schematic diagram of the implementation flow of the information transmission method of the embodiment of the present application, which is applied to the first network device, such as Figure 2 As shown, the method comprises step 201:

[0096] Step 201: Obtain first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

[0097] Here, the first network device may refer to a 5G base station and is a master base station, which may be represented by a gNB master station. The at least one second network device may refer to a 5G base station and is a slave base station, which may be represented by a gNB slave station.

[0098] Here, the first information includes the available computing power information of the second network device; the computing power information includes the computing power resource type and the computing power resource size.

[0099] Here, the computing power resource types include central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, etc., and the computing power resource size includes the number of CPU cores, the floating-point computing power of the CPU, the number of GPU cores, the memory size, etc.

[0100] Here, the process in which the first network device obtains the first information respectively sent by at least one second network device may include the following two methods:

[0101] The first method is as follows:

[0102] The first network device (gNB master) sends a first request, i.e., a computing resource reporting request, to at least one second network device (gNB slave) of the first network device (gNB slave). The first request is used to request the second network device (gNB slave) to send the first information to the first network device (gNB master).

[0103] At least one second network device (gNB slave station) sends a response to the first request to the first network device (gNB master station), i.e., a computing resource reporting response, and the response carries the available computing power information of the second network device (gNB slave station), i.e., the first information.

[0104] The second method is as follows:

[0105] At least one second network device (gNB slave station) periodically reports its own computing power information, i.e., the first information, to the first network device (gNB master station) according to the first period.

[0106] Based on this, in some embodiments, obtaining the first information respectively sent by at least one second network device includes:

[0107] Sending a first request to each of the at least one second network devices; the first request is used to request the second network device to send the first information to the first network device;

[0108] Receive responses to the first request respectively sent by the at least one second network device; the responses carry the first information.

[0109] Based on this, in some embodiments, obtaining the first information respectively sent by at least one second network device includes:

[0110] According to a first period, first information respectively sent by the at least one second network device is received.

[0111] In some embodiments, the method further comprises:

[0112] Determine, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device;

[0113] Alternatively, determining a third network device that provides computing power services for the terminal according to the second information and the third information;

[0114] in,

[0115] The first information includes available computing power information of the second network device; the computing power information includes computing power resource type and computing power resource size;

[0116] The third information includes available computing power information of the first network device; the computing power information includes computing power resource type and computing power resource size;

[0117] The second information includes:

[0118] Latency of AI services;

[0119] and / or,

[0120] The types and amounts of computing resources required for AI services.

[0121] Here, the computing power resource types include central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, etc., and the computing power resource size includes the number of CPU cores, the floating-point computing power of the CPU, the number of GPU cores, the memory size, etc.

[0122] In actual application, the terminal can establish an RRC connection with the first network device and establish a dedicated computing bearer (SRB, DRB). In this way, the terminal can send a second request to the first network device through the established dedicated computing bearer (SRB), and the second request carries the second information for the first network device to execute the computing power scheduling strategy.

[0123] Based on this, in some embodiments, the method further includes:

[0124] receiving a second request sent by the terminal; the terminal has established a connection with the first network device;

[0125] The second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal.

[0126] In actual application, the terminal can establish an RRC connection with a fourth network device among the at least one second network device and establish a dedicated computing bearer (SRB, DRB). In this way, the terminal can send a second request to the fourth network device through the established dedicated computing bearer (SRB), and the second request carries the second information. The fourth network device forwards the second request to the first network device so that the first network device can execute the computing power scheduling strategy.

[0127] Based on this, in some embodiments, the method further includes:

[0128] receiving a second request sent by a fourth network device among the at least one second network device; the terminal has established a connection with the fourth network device;

[0129] Among them, the second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal; the second request is sent by the terminal to the fourth network device, and forwarded by the fourth network device to the first network device.

[0130] In some embodiments, determining, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device includes:

[0131] Determine, from the at least one second network device, a third network device that provides computing services for the terminal according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device;

[0132] or,

[0133] Based on the latency of the AI ​​service, determine the type and size of computing resources required for the AI ​​service; according to the type and size of computing resources required for the AI ​​service, and the type and size of computing resources available for use by the second network device, determine a third network device from the at least one second network device to provide computing services for the terminal.

[0134] Here, considering that the computing power resources on the second network device side are the computing power resources closest to the business in the communication network, the first network device can schedule the computing power resources on the second network device side to meet the user's business needs, such as AI business needs.

[0135] Specifically, the first network device may execute the computing power scheduling strategy in the following cases:

[0136] In the first case, a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station) based on the type and size of computing resources available from the second network device (gNB slave station) and the type and size of computing resources required for the AI ​​service.

[0137] In this case, if the type and size of computing resources available provided by the second network device (gNB slave station) can meet the type and size of computing resources required by the AI ​​service, the corresponding second network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0138] For example, assuming that the computing power resource type required for the AI ​​service is CPU resources and the computing power resource size is 30% of the computing power of each core of a 2-core CPU, if the computing power resource type provided by a second network device (gNB slave station) is CPU resources and the computing power resource size is 50% of the computing power of each core of a 2-core CPU, then the second network device (gNB slave station) will be used as a third network device that can provide computing power services for the terminal (UE).

[0139] In the second case, based on the latency of the AI ​​service, the type and size of computing resources required for the AI ​​service are determined; according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device (gNB slave station), a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0140] In this case, the type and size of computing resources required for the AI ​​service can be determined based on the preset correspondence between the AI ​​service latency, the type of computing resources, and the size of computing resources.

[0141] For example, assuming that the latency of the AI ​​service is 30 milliseconds, according to the preset correspondence, it is determined that the type of computing power resources required for the AI ​​service is CPU resources and the size of the computing power resources is 50% of the computing power of each core of the 2-core CPU.

[0142] In this way, after determining the type and size of computing power resources required for the AI ​​service, a third network device that provides computing power services to the terminal (UE) is determined from at least one second network device (gNB slave station) based on the type and size of computing power resources required for the AI ​​service and the type and size of computing power resources available for use by the second network device (gNB slave station).

[0143] In the third case, a third network device that provides computing power services to the terminal is determined based on the second information and the third information.

[0144] In this case, if the type and size of computing resources available by the first network device (gNB master station) can meet the type and size of computing resources required by the AI ​​service, the first network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0145] It should be noted that, when the terminal establishes an RRC connection with the first network device, a third network device providing computing power services for the terminal can be determined from the at least one second network device based on the first information and the second information; or, the third network device providing computing power services for the terminal can be determined based on the second information and the third information. When the terminal establishes an RRC connection with a fourth network device among the at least one second network device, the third network device providing computing power services for the terminal can be determined from the at least one second network device based on the first information and the second information.

[0146] In actual application, after the first network device determines a third network device that provides computing power services for the terminal from the at least one second network device, if the terminal establishes an RRC connection with the first network device and establishes a dedicated computing bearer (SRB, DRB), the terminal can send first data to the first network device through the established dedicated computing bearer (DRB), so that the first network device forwards the first data to the third network device for calculation, thereby realizing the calculation of the first data related to AI using the computing power on the side of the third network device.

[0147] Based on this, in some embodiments, the method further includes:

[0148] Receiving first data sent by the terminal in a preset first data format; the first data is related to AI; the preset first data format meets the transmission requirements between the first network device and the third network device;

[0149] sending the first data to the third network device so that the third network device calculates the first data;

[0150] Receiving a calculation result sent by the third network device;

[0151] The calculation result is sent to the terminal.

[0152] Here, the first data is related to AI, and specifically may include AI data in the form of images, texts, audios, videos, etc.

[0153] Here, the preset first data format meets the transmission requirements between the first network device (gNB master station) and the third network device. For example, assuming that the data format of the first data that can be transmitted between the first network device (gNB master station) and the third network device is JSON format, the terminal (UE) uses this format to send the first data to the first network device (gNB master station), so that the first network device (gNB master station) forwards the first data to the third network device.

[0154] Here, the third network device may use an AI model to calculate the first data to obtain a calculation result.

[0155] It should be noted that if the first network device determines that it is a third network device that provides computing services to the terminal, after receiving the first data sent by the terminal, it calculates the first data to obtain a calculation result, and sends the calculation result to the terminal.

[0156] Here, after the first network device sends the calculation result to the terminal, it can release the dedicated calculation bearer established between the first network device and the terminal, such as (SRB, DRB).

[0157] The embodiment of the present application has the following advantages:

[0158] (1) A first network device obtains first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device.

[0159] It can be seen that the first network device can obtain the computing power information on the second network device side. In this way, the first network device can subsequently schedule the computing power resources on the second network device side to meet the user's business needs, such as AI business needs.

[0160] Alternatively, the first network device may also dispatch its own computing resources to meet the user's business needs, such as AI business needs.

[0161] (2) Propose a wireless computing resource scheduling scheme.

[0162] Specifically, the first network device allocates computing power services according to the requirements of the AI ​​services on the terminal side (such as latency, FLOPS, etc.) and the computing power information provided by the second network device side; and utilizes network signaling and data transmission mechanisms to enable wireless endogenous provision of computing power services, fully utilize network computing power resources, and enhance user computing power service experience.

[0163] See also Figure 3 , Figure 3 Schematic diagram of the implementation flow of the information transmission method of the embodiment of the present application, which is applied to the second network device, such as Figure 3 As shown, the method comprises step 301:

[0164] Step 301: Send first information to a first network device; the first information is related to the available computing power of the second network device; wherein the first network device and at least one of the second network devices are in a master-slave relationship.

[0165] Here, the first network device may refer to a 5G base station and is a master base station, which may be represented by a gNB master station. The at least one second network device may refer to a 5G base station and is a slave base station, which may be represented by a gNB slave station.

[0166] Here, the first information includes the available computing power information of the second network device; the computing power information includes the computing power resource type and the computing power resource size.

[0167] Here, the computing power resource types include central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, etc., and the computing power resource size includes the number of CPU cores, the floating-point computing power of the CPU, the number of GPU cores, the memory size, etc.

[0168] Here, the process in which the first network device obtains the first information respectively sent by at least one second network device may include the following two methods:

[0169] The first method is as follows:

[0170] The first network device (gNB master) sends a first request, i.e., a computing resource reporting request, to at least one second network device (gNB slave) of the first network device (gNB slave). The first request is used to request the second network device (gNB slave) to send the first information to the first network device (gNB master).

[0171] At least one second network device (gNB slave station) sends a response to the first request to the first network device (gNB master station), i.e., a computing resource reporting response, and the response carries the available computing power information of the second network device (gNB slave station), i.e., the first information.

[0172] The second method is as follows:

[0173] At least one second network device (gNB slave station) periodically reports its own computing power information, i.e., the first information, to the first network device (gNB master station) according to the first period.

[0174] Based on this, in some embodiments, sending the first information to the first network device includes:

[0175] receiving a first request sent by the first network device; the first request is used to request the second network device to send the first information to the first network device;

[0176] A response to the first request is sent to the first network device; the response carries the first information.

[0177] Based on this, in some embodiments, sending the first information to the first network device includes:

[0178] The first information is sent to the first network device according to a first cycle.

[0179] In actual application, the terminal can establish an RRC connection with a fourth network device among the at least one second network device and establish a dedicated computing bearer (SRB, DRB). In this way, the terminal can send a second request to the fourth network device through the established dedicated computing bearer (SRB), and the second request carries the second information. The fourth network device forwards the second request to the first network device so that the first network device can execute the computing power scheduling strategy in combination with the first information.

[0180] Based on this, in some embodiments, the second network device is a fourth network device in at least one of the second network devices, and the terminal has established a connection with the fourth network device; the method further includes:

[0181] receiving a second request sent by a terminal; the second request carries second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal;

[0182] forwarding the second request to the first network device;

[0183] in,

[0184] The second information includes:

[0185] Latency of AI services;

[0186] and / or,

[0187] The types and amounts of computing resources required for AI services.

[0188] In some embodiments, the method further comprises:

[0189] A response to the second request sent by the first network device is received; the response carries information of the third network device.

[0190] Here, considering that the computing power resources on the second network device side are the computing power resources closest to the business in the communication network, the first network device can schedule the computing power resources on the second network device side to meet the user's business needs, such as AI business needs.

[0191] Specifically, the first network device may execute the computing power scheduling strategy in the following cases:

[0192] In the first case, a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station) based on the type and size of computing resources available from the second network device (gNB slave station) and the type and size of computing resources required for the AI ​​service.

[0193] In this case, if the type and size of computing resources available provided by the second network device (gNB slave station) can meet the type and size of computing resources required by the AI ​​service, the corresponding second network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0194] For example, assuming that the computing resource type required for the AI ​​service is CPU resource and the computing resource size is 30% of the computing power of each core in a 2-core CPU, if the computing resource type provided by a second network device (gNB slave station) is CPU resource and the computing resource size is 50% of the computing power of each core in a 2-core CPU, then the second network device (gNB slave station) is used as a third network device that can provide computing services for the terminal (UE).

[0195] In the second case, based on the latency of the AI ​​service, the type and size of computing resources required for the AI ​​service are determined; according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device (gNB slave station), a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0196] In this case, the type and size of computing resources required for the AI ​​service can be determined based on the preset correspondence between the AI ​​service latency, the type of computing resources, and the size of computing resources.

[0197] For example, assuming that the latency of the AI ​​service is 30 milliseconds, according to the preset correspondence, it is determined that the type of computing power resources required for the AI ​​service is CPU resources and the size of the computing power resources is 50% of the computing power of each core of the 2-core CPU.

[0198] In this way, the type and size of computing power resources required for the AI ​​service are determined; based on the type and size of computing power resources required for the AI ​​service, and the type and size of computing power resources available for use by the second network device (gNB slave station), a third network device that provides computing power services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0199] It should be noted that, when the terminal establishes an RRC connection with the first network device, or when the terminal establishes an RRC connection with a fourth network device among the at least one second network device, the first network device determines a third network device that provides computing power services to the terminal from among the at least one second network device based on the first information and the second information.

[0200] In actual application, after the first network device determines a third network device that provides computing power services for the terminal from the at least one second network device, if the terminal establishes an RRC connection with the fourth network device and establishes a dedicated computing bearer (SRB, DRB), the terminal can send the first data to the fourth network device through the established dedicated computing bearer (DRB), so that the fourth network device forwards the first data to the third network device for calculation, thereby realizing the calculation of the first data related to AI using the computing power on the side of the third network device.

[0201] Based on this, in some embodiments, the method further includes:

[0202] receiving first data sent by the terminal in a preset second data format; the first data is related to AI; the preset second data format meets the transmission requirements between the fourth network device and the third network device;

[0203] Sending the first data to the third network device;

[0204] Receiving a calculation result sent by the third network device;

[0205] The calculation result is sent to the terminal.

[0206] Here, the first data is related to AI, and specifically may include AI data in the form of images, texts, audio, video, etc.

[0207] Here, the preset second data format meets the transmission requirements between the fourth network device (gNB slave station) and the third network device. For example, assuming that the data format of the first data that can be transmitted between the fourth network device (gNB slave station) and the third network device is in JSON format, the terminal (UE) uses this format to send the first data to the fourth network device (gNB slave station), so that the fourth network device (gNB slave station) forwards the first data to the third network device.

[0208] Here, after the fourth network device sends the calculation result to the terminal, it can release the dedicated calculation bearer established between the fourth network device and the terminal, such as (SRB, DRB).

[0209] The embodiment of the present application has the following advantages:

[0210] (1) At least one second network device sends first information to each first network device; the first information is related to the available computing power of the second network device.

[0211] It can be seen that the first network device can obtain the computing power information on the second network device side. In this way, the first network device can subsequently schedule the computing power resources on the second network device side to meet the user's business needs, such as AI business needs.

[0212] See also Figure 4 , Figure 4 is a schematic diagram of a specific implementation flow of the information transmission method of the embodiment of the present application, such as Figure 4 As shown, it includes steps 401 to 409:

[0213] Step 401: A radio resource control (RRC) connection is established between the terminal (UE) and the first network device (gNB master station), and a dedicated computing bearer is established.

[0214] Here, establishing a computing-dedicated bearer may refer to establishing a signaling radio bearer (SRBx), a data radio bearer (DRBx), and the like.

[0215] Step 402: The first network device (gNB master station) obtains the available computing power information of at least one second network device (gNB slave station) of its own, that is, the first information.

[0216] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type and the computing power resource size.

[0217] Here, the computing power resource types include central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, etc., and the computing power resource size includes the number of CPU cores, the floating-point computing power of the CPU, the number of GPU cores, the memory size, etc.

[0218] Specifically, the following two methods can be included:

[0219] The first method is as follows:

[0220] The first network device (gNB master) sends a first request, i.e., a computing resource reporting request, to at least one second network device (gNB slave) of the first network device (gNB slave). The first request is used to request the second network device (gNB slave) to send the first information to the first network device (gNB master).

[0221] At least one second network device (gNB slave station) sends a response to the first request to the first network device (gNB master station), i.e., a computing resource reporting response, and the response carries the available computing power information of the second network device (gNB slave station), i.e., the first information.

[0222] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type (GPU / CPU, etc.) and the computing power resource size (such as the number of floating-point operations per second FLOPS, etc.).

[0223] The second method is as follows:

[0224] At least one second network device (gNB slave station) periodically reports its own computing power information, i.e., the first information, to the first network device (gNB master station) according to the first period.

[0225] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type (GPU / CPU, etc.) and the computing power resource size (such as FLOPS, etc.), etc.

[0226] Step 403: When the terminal (UE) needs to call the computing power on the network side, a second request, namely, a computing power call request, is sent to the first network device (gNB master station) through an established dedicated computing bearer such as a signaling radio bearer (SRBx); the second request is used to request the first network device (gNB master station) to determine a third network device that provides computing power services for the terminal (UE).

[0227] Here, the second request carries second information.

[0228] Here, the second information includes at least one of the following:

[0229] Latency of AI services;

[0230] and / or,

[0231] The types and amounts of computing resources required for AI services.

[0232] Step 404: The first network device (gNB master station) executes the computing power scheduling strategy.

[0233] Here, the first network device (gNB master station) executes the computing power scheduling strategy, which may refer to:

[0234] The first network device (gNB master station) determines a third network device that provides computing power services to the terminal (UE) from at least one second network device (gNB slave station) based on the computing power information reported by each second network device (gNB slave station), i.e., the first information, and the second request reported by the terminal (UE), i.e., the second information carried in the computing power call request.

[0235] Alternatively, the first network device (gNB master station) determines a third network device that provides computing power services to the terminal based on the third information and the second information.

[0236] Specifically, the following situations may be included:

[0237] In the first case, a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station) based on the type and size of computing resources available from the second network device (gNB slave station) and the type and size of computing resources required for the AI ​​service.

[0238] In this case, if the type and size of computing resources available provided by the second network device (gNB slave station) can meet the type and size of computing resources required by the AI ​​service, the corresponding second network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0239] For example, assuming that the computing resource type required for the AI ​​service is CPU resource and the computing resource size is 30% of the computing power of each core in a 2-core CPU, if the computing resource type provided by a second network device (gNB slave station) is CPU resource and the computing resource size is 50% of the computing power of each core in a 2-core CPU, then the second network device (gNB slave station) is used as a third network device that can provide computing services for the terminal (UE).

[0240] In the second case, based on the latency of the AI ​​service, the type and size of computing resources required for the AI ​​service are determined; according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device (gNB slave station), a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0241] In this case, the type and size of computing resources required for the AI ​​service can be determined based on the preset correspondence between the AI ​​service latency, the type of computing resources, and the size of computing resources.

[0242] For example, assuming that the latency of the AI ​​service is 30 milliseconds, according to the preset correspondence, it is determined that the type of computing power resources required for the AI ​​service is CPU resources and the size of the computing power resources is 50% of the computing power of each core of the 2-core CPU.

[0243] In this way, the type and size of computing power resources required for the AI ​​service are determined; based on the type and size of computing power resources required for the AI ​​service, and the type and size of computing power resources available for use by the second network device (gNB slave station), a third network device that provides computing power services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0244] In the third case, the first network device (gNB master station) determines the third network device that provides computing power services to the terminal based on the third information and the second information.

[0245] In this case, if the type and size of computing resources available by the first network device (gNB master station) can meet the type and size of computing resources required by the AI ​​service, the first network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0246] Here, if the computing power resources of the current serving base station (gNB master station) of the terminal (UE) can meet the needs of the terminal (UE), the current serving base station (gNB master station) of the terminal (UE) is preferably used to provide computing power services.

[0247] Step 405: The first network device (gNB master station) sends a response to the second request to the terminal (UE), namely, a computing power scheduling request response, and the response carries information of a third network device (base station) that provides computing power services to the terminal (UE).

[0248] Step 406: The terminal (UE) sends the first data that needs to call the base station computing power to the first network device (gNB master station) in a defined first data format through an established dedicated computing bearer such as a data radio bearer (DRBx).

[0249] Here, the first data is related to AI, and specifically may include AI data in the form of images, texts, audios, videos, etc.

[0250] Here, the preset first data format meets the transmission requirements between the first network device (gNB master station) and the third network device. For example, assuming that the data format of the first data that can be transmitted between the first network device (gNB master station) and the third network device is JSON format, the terminal (UE) uses this format to send the first data to the first network device (gNB master station), so that the first network device (gNB master station) forwards the first data to the third network device.

[0251] Step 407: If the first network device (gNB master station) determines that it is the third network device, the serving base station (gNB master station) of the terminal (UE) performs calculations on the first data.

[0252] Here, if the first network device (gNB master station) determines a third network device from at least one second network device (gNB slave station), the first data is sent to the third network device so that the third network device calculates the first data.

[0253] Here, the AI ​​model can be used to calculate the first data to obtain a calculation result.

[0254] Step 408: If the first network device (gNB master station) determines that it is the third network device, it performs calculation on the first data and sends the calculation result to the terminal (UE).

[0255] Here, if the first network device (gNB master station) determines a third network device from at least one second network device (gNB slave station), the first network device (gNB master station) receives the calculation result sent by the third network device, and sends the calculation result to the terminal (UE) through an established dedicated calculation bearer such as a data radio bearer (DRBx).

[0256] Step 409: The first network device (gNB master station) releases the dedicated computing bearer (SRBx, DRBx) between the first network device (gNB master station) and the terminal (UE).

[0257] In this example, the following advantages are achieved:

[0258] (1) The terminal (UE) establishes a connection with the first network device (gNB master station).

[0259] (2) The base station that provides communication services to the terminal (UE) is the gNB master station. The base station of the third network device that provides computing power services for the terminal (UE) is also the gNB master station. The base station that provides computing power services to the terminal (UE) is the gNB master station or the gNB slave station.

[0260] See also Figure 5 , Figure 5 is a schematic diagram of a specific implementation flow of the information transmission method of the embodiment of the present application, such as Figure 5 As shown, it includes steps 501 to 511:

[0261] Step 501: The first network device (gNB master station) obtains the available computing power information of at least one second network device (gNB slave station) of its own, that is, the first information.

[0262] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type and the computing power resource size.

[0263] Here, the computing power resource types include central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, etc., and the computing power resource size includes the number of CPU cores, the floating-point computing power of the CPU, the number of GPU cores, the memory size, etc.

[0264] Specifically, the following two methods can be included:

[0265] The first method is as follows:

[0266] The first network device (gNB master) sends a first request, i.e., a computing resource reporting request, to at least one second network device (gNB slave) of the first network device (gNB slave). The first request is used to request the second network device (gNB slave) to send the first information to the first network device (gNB master).

[0267] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type (GPU / CPU, etc.) and the computing power resource size (such as the number of floating-point operations per second FLOPS, etc.).

[0268] The second method is as follows:

[0269] At least one second network device (gNB slave station) periodically reports its own computing power information, i.e., the first information, to the first network device (gNB master station) according to the first period.

[0270] Here, the first information includes the available computing power information of the second network device (gNB slave station); the computing power information includes the computing power resource type (GPU / CPU, etc.) and the computing power resource size (such as FLOPS, etc.), etc.

[0271] Step 502: The terminal (UE) and a fourth network device (gNB slave station) in at least one second network device (gNB slave station) establish an RRC connection and establish a dedicated computing bearer.

[0272] Here, establishing a dedicated computing bearer may refer to establishing SRBx, DRBx, etc.

[0273] Step 503: When the terminal (UE) needs to call the computing power on the network side, a second request, namely a computing power call request, is sent to the fourth network device (gNB slave station) through a dedicated computing bearer such as a signaling radio bearer (SRBx); the second request is used to request the first network device (gNB master station) to determine a third network device that provides computing power services for the terminal (UE).

[0274] Here, the second request carries second information.

[0275] Here, the second information includes at least one of the following:

[0276] Latency of AI services;

[0277] and / or,

[0278] The types and amounts of computing resources required for AI services.

[0279] Step 504: The fourth network device (gNB slave station) forwards the second request carrying the second information, namely the computing power scheduling request, to the first network device (gNB master station).

[0280] Step 505: The first network device (gNB master station) executes the computing power scheduling strategy.

[0281] Here, the first network device (gNB master station) executes the computing power scheduling strategy, which may refer to:

[0282] The first network device (gNB master station) determines a third network device that provides computing power services to the terminal (UE) from at least one second network device (gNB slave station) based on the computing power information reported by each second network device (gNB slave station), i.e., the first information, and the second request reported by the terminal (UE), i.e., the second information carried in the computing power call request.

[0283] Specifically, the following situations may be included:

[0284] In the first case, a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station) based on the type and size of computing resources available from the second network device (gNB slave station) and the type and size of computing resources required for the AI ​​service.

[0285] In this case, if the type and size of computing resources available provided by the second network device (gNB slave station) can meet the type and size of computing resources required by the AI ​​service, the corresponding second network device (gNB slave station) will be used as the third network device that can provide computing services for the terminal (UE).

[0286] For example, assuming that the computing resource type required for the AI ​​service is CPU resource and the computing resource size is 30% of the computing power of each core in a 2-core CPU, if the computing resource type provided by a second network device (gNB slave station) is CPU resource and the computing resource size is 50% of the computing power of each core in a 2-core CPU, then the second network device (gNB slave station) is used as a third network device that can provide computing services for the terminal (UE).

[0287] In the second case, based on the latency of the AI ​​service, the type and size of computing resources required for the AI ​​service are determined; according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device (gNB slave station), a third network device that provides computing services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0288] In this case, the type and size of computing resources required for the AI ​​service can be determined based on the preset correspondence between the AI ​​service latency, the type of computing resources, and the size of computing resources.

[0289] For example, assuming that the latency of the AI ​​service is 30 milliseconds, according to the preset correspondence, it is determined that the type of computing power resources required for the AI ​​service is CPU resources and the size of the computing power resources is 50% of the computing power of each core of the 2-core CPU.

[0290] In this way, the type and size of computing power resources required for the AI ​​service are determined; based on the type and size of computing power resources required for the AI ​​service, and the type and size of computing power resources available for use by the second network device (gNB slave station), a third network device that provides computing power services to the terminal (UE) is determined from at least one second network device (gNB slave station).

[0291] It should be noted that when the computing power resources of the terminal UE's current serving base station (gNB slave station) can meet the terminal (UE) needs, the terminal (UE)'s current serving base station (gNB slave station) is preferred to provide computing power services.

[0292] Step 506: The first network device (gNB master station) sends a response to the second request to the fourth network device (gNB slave station), namely, a computing power scheduling request response, and the response carries information of a third network device (base station) that provides computing power services to the terminal (UE).

[0293] Step 507: The fourth network device (gNB slave station) sends a response to the second request to the terminal (UE), namely, a computing power scheduling request response, and the response carries information of the third network device (base station) that provides computing power services to the terminal (UE).

[0294] Step 508: The terminal (UE) sends the first data that needs to call the base station computing power to the fourth network device (gNB slave station) in a defined second data format through an established dedicated computing bearer such as a data radio bearer (DRBx).

[0295] Here, the first data is related to AI, and specifically may include AI data in the form of images, texts, audio, video, etc.

[0296] Here, the preset second data format meets the transmission requirements between the fourth network device (gNB slave station) and the third network device. For example, assuming that the data format of the first data that can be transmitted between the fourth network device (gNB slave station) and the third network device is in JSON format, the terminal (UE) uses this format to send the first data to the fourth network device (gNB slave station), so that the fourth network device (gNB slave station) forwards the first data to the third network device.

[0297] Step 509: The fourth network device (gNB slave station) receives the first data and provides the first data to the third network device so that the third network device performs calculation.

[0298] Here, the third network device may use an AI model to calculate the first data to obtain a calculation result.

[0299] Step 510: The fourth network device (gNB slave station) receives the calculation result sent by the third network device, and sends the calculation result to the terminal (UE) through an established dedicated calculation bearer such as a data radio bearer (DRBx).

[0300] Step 510: The fourth network device (gNB slave station) releases the computing dedicated bearers (SRBx, DRBx) between the fourth network device (gNB slave station) and the terminal (UE).

[0301] In this example, the following advantages are achieved:

[0302] (1) The terminal (UE) establishes a connection with a fourth network device (gNB slave station) in at least one second network device (gNB slave station).

[0303] (2) The base station that provides communication services to the terminal (UE) is the fourth network device (gNB slave station), the base station that provides computing power services to the terminal (UE) is also a gNB slave station, and the base station of the third network device that provides computing power services for the terminal (UE) is the first network device (gNB master station).

[0304] In order to implement the information transmission method of the embodiment of the present application, the embodiment of the present application also provides an information transmission device, which is arranged in the first network device. Figure 6 Schematic diagram of the structure of the information transmission device according to the embodiment of the present application. Figure 6 As shown, the device comprises:

[0305] The acquisition module 61 is used to acquire first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

[0306] In some embodiments, the acquisition module 61 is specifically used to:

[0307] Sending a first request to each of the at least one second network devices; the first request is used to request the second network device to send the first information to the first network device;

[0308] Receive responses to the first request respectively sent by the at least one second network device; the responses carry the first information.

[0309] In some embodiments, the acquisition module 61 is specifically used to:

[0310] According to a first period, first information respectively sent by the at least one second network device is received.

[0311] In some embodiments, the device is further used to:

[0312] Determine, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device;

[0313] Alternatively, determining a third network device that provides computing power services for the terminal according to the third information and the second information;

[0314] in,

[0315] The first information includes available computing power information of the second network device; the computing power information includes computing power resource type and computing power resource size;

[0316] The third information includes available computing power information of the first network device; the computing power information includes computing power resource type and computing power resource size;

[0317] The second information includes:

[0318] Latency of AI services;

[0319] and / or,

[0320] The types and amounts of computing resources required for AI services.

[0321] In some embodiments, the acquisition module 61 is further used to:

[0322] receiving a second request sent by the terminal; the terminal has established a connection with the first network device;

[0323] The second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal.

[0324] In some embodiments, the acquisition module 61 is further used to:

[0325] receiving a second request sent by a fourth network device among the at least one second network device; the terminal has established a connection with the fourth network device;

[0326] Among them, the second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal; the second request is sent by the terminal to the fourth network device, and forwarded by the fourth network device to the first network device.

[0327] In some embodiments, the device is further used to:

[0328] Determine, from the at least one second network device, a third network device that provides computing services for the terminal according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device;

[0329] or,

[0330] Based on the latency of the AI ​​service, determine the type and size of computing resources required for the AI ​​service; according to the type and size of computing resources required for the AI ​​service, and the type and size of computing resources available for use by the second network device, determine a third network device from the at least one second network device to provide computing services for the terminal.

[0331] In some embodiments, the device is further used to:

[0332] Receiving first data sent by the terminal in a preset first data format; the first data is related to AI; the preset first data format meets the transmission requirements between the first network device and the third network device;

[0333] sending the first data to the third network device so that the third network device calculates the first data;

[0334] Receiving a calculation result sent by the third network device;

[0335] The calculation result is sent to the terminal.

[0336] In actual application, the acquisition module 61 can be implemented by a communication interface in an information transmission device.

[0337] It should be noted that: the information transmission device provided in the above embodiment only uses the division of the above program modules as an example when performing information transmission. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the information transmission device provided in the above embodiment and the information transmission method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0338] In order to implement the information transmission method of the embodiment of the present application, the embodiment of the present application also provides an information transmission device, which is arranged in the second network device. Figure 7 Schematic diagram of the structure of the information transmission device according to the embodiment of the present application. Figure 7 As shown, the device comprises:

[0339] A sending module 71, configured to send first information to a first network device; the first information is related to the available computing power of the second network device;

[0340] The first network device and at least one of the second network devices are in a master-slave relationship.

[0341] In some embodiments, the sending module 71 is specifically used to:

[0342] receiving a first request sent by the first network device; the first request is used to request the second network device to send the first information to the first network device;

[0343] A response to the first request is sent to the first network device; the response carries the first information.

[0344] In some embodiments, the sending module 71 is specifically used to:

[0345] The first information is sent to the first network device according to a first cycle.

[0346] In some embodiments, the second network device is a fourth network device among at least one of the second network devices, and the terminal has established a connection with the fourth network device; and the apparatus is further configured to:

[0347] receiving a second request sent by a terminal; the second request carries second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal;

[0348] forwarding the second request to the first network device;

[0349] in,

[0350] The second information includes:

[0351] Latency of AI services;

[0352] and / or,

[0353] The types and amounts of computing resources required for AI services.

[0354] In some embodiments, the device is further used to:

[0355] A response to the second request sent by the first network device is received; the response carries information of the third network device.

[0356] In some embodiments, the device is further used to:

[0357] receiving first data sent by the terminal in a preset second data format; the first data is related to AI; the preset second data format meets the transmission requirements between the fourth network device and the third network device;

[0358] Sending the first data to the third network device;

[0359] Receiving a calculation result sent by the third network device;

[0360] The calculation result is sent to the terminal.

[0361] In actual application, the sending module 71 can be implemented by a communication interface in an information transmission device.

[0362] It should be noted that: the information transmission device provided in the above embodiment only uses the division of the above program modules as an example when performing information transmission. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the information transmission device provided in the above embodiment and the information transmission method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0363] The embodiment of the present application also provides a first network device, such as Figure 8 As shown, including:

[0364] A first communication interface 81, capable of exchanging information with other devices;

[0365] The first processor 82 is connected to the first communication interface 81 and is used to execute the method provided by one or more technical solutions of the first network device side when running a computer program. The computer program is stored in the first memory 83.

[0366] It should be noted that the specific processing process of the first processor 82 and the first communication interface 81 is detailed in the method embodiment and will not be repeated here.

[0367] Of course, in actual application, the various components in the first network device 80 are coupled together through the bus system 84. It can be understood that the bus system 84 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 84 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 8 Various buses are labeled as bus system 84 .

[0368] The first memory 83 in the embodiment of the present application is used to store various types of data to support the operation of the first network device 80. Examples of such data include: any computer program used to operate on the first network device 80.

[0369] The method disclosed in the above embodiment of the present application can be applied to the first processor 82, or implemented by the first processor 82. The first processor 82 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 82. The above-mentioned first processor 82 may be a general-purpose processor, a digital data processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The first processor 82 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the first memory 83, and the first processor 82 reads the information in the first memory 83 and completes the steps of the above method in combination with its hardware.

[0370] The present application embodiment also provides a second network device, such as Fig. 9 As shown, including:

[0371] The second communication interface 91 is capable of exchanging information with other devices;

[0372] The second processor 92 is connected to the second communication interface 91 and is used to execute the method provided by one or more technical solutions of the second network device side when running a computer program. The computer program is stored in the second memory 93.

[0373] It should be noted that: the specific processing process of the second processor 92 and the second communication interface 91 is detailed in the method embodiment, which will not be repeated here.

[0374] Of course, in actual application, the various components in the second network device 90 are coupled together through the bus system 94. It can be understood that the bus system 94 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 94 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Fig. 9 Various buses are labeled as bus system 94 .

[0375] The second memory 93 in the embodiment of the present application is used to store various types of data to support the operation of the second network device 90. Examples of such data include: any computer program used to operate on the second network device 90.

[0376] The method disclosed in the above embodiment of the present application can be applied to the second processor 92, or implemented by the second processor 92. The second processor 92 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the second processor 92. The above second processor 92 may be a general processor, a digital data processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The second processor 92 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the second memory 93, and the second processor 92 reads the information in the second memory 93 and completes the steps of the above method in combination with its hardware.

[0377] In an exemplary embodiment, the first network device 80 and the second network device 90 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned method.

[0378] It can be understood that the memory (first memory 83, second memory 93) of the embodiment of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0379] In an exemplary embodiment, the present application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, a memory storing a computer program, and the computer program can be executed by the first processor 82 of the first network device 80 to complete the steps of the first network device side method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.

[0380] Exemplarily, an embodiment of the present application also provides a computer program product, including a computer program, which can be executed by a first processor 82 of a first network device 80 to complete the steps of any method described in the aforementioned first network device side, and the computer program can be executed by a second processor 92 of a second network device 90 to complete the steps of any method described in the aforementioned second network device side.

[0381] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0382] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0383] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. An information transmission method, characterized in that: Applied to a first network device, the method comprises: Acquire first information respectively sent by at least one second network device; the first information is related to the available computing power of the second network device; The first network device and the at least one second network device are in a master-slave relationship.

2. The method according to claim 1, characterized in that The obtaining of first information respectively sent by at least one second network device includes: Sending a first request to each of the at least one second network devices; the first request is used to request the second network device to send the first information to the first network device; Receive responses to the first request respectively sent by the at least one second network device; the responses carry the first information.

3. The method according to claim 1, characterized in that The obtaining of first information respectively sent by at least one second network device includes: According to a first period, first information respectively sent by the at least one second network device is received.

4. The method according to claim 1, characterized in that: The method further comprises: Determine, according to the first information and the second information, a third network device that provides computing power services for the terminal from the at least one second network device; Alternatively, determining a third network device that provides computing power services for the terminal according to the second information and the third information; in, The first information includes available computing power information of the second network device; the computing power information includes computing power resource type and computing power resource size; The third information includes available computing power information of the first network device; the computing power information includes computing power resource type and computing power resource size; The second information includes: The latency of artificial intelligence (AI) services; and / or, The types and amounts of computing resources required for AI services.

5. The method according to claim 4, characterized in that The method further comprises: receiving a second request sent by the terminal; the terminal has established a connection with the first network device; The second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal.

6. The method according to claim 4, characterized in that The method further comprises: receiving a second request sent by a fourth network device among the at least one second network device; the terminal has established a connection with the fourth network device; Among them, the second request carries the second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal; the second request is sent by the terminal to the fourth network device, and forwarded by the fourth network device to the first network device.

7. The method according to any one of claims 4 to 6, characterized in that: The determining, according to the first information and the second information, from the at least one second network device, a third network device that provides computing power services for the terminal includes: Determine, from the at least one second network device, a third network device that provides computing services for the terminal according to the type and size of computing resources required for the AI ​​service and the type and size of computing resources available for use by the second network device; or, Based on the latency of the AI ​​service, determine the type and size of computing resources required for the AI ​​service; according to the type and size of computing resources required for the AI ​​service, and the type and size of computing resources available for use by the second network device, determine a third network device from the at least one second network device to provide computing services for the terminal.

8. The method according to claim 7, characterized in that The method further comprises: Receiving first data sent by the terminal in a preset first data format; the first data is related to AI; the preset first data format meets the transmission requirements between the first network device and the third network device; sending the first data to the third network device so that the third network device calculates the first data; Receiving a calculation result sent by the third network device; The calculation result is sent to the terminal.

9. An information transmission method, characterized in that: Applied to the second network device, the method comprises: Sending first information to a first network device; the first information is related to the available computing power of the second network device; The first network device and at least one of the second network devices are in a master-slave relationship.

10. The method according to claim 9, characterized in that The sending the first information to the first network device includes: receiving a first request sent by the first network device; the first request is used to request the second network device to send the first information to the first network device; A response to the first request is sent to the first network device; the response carries the first information.

11. The method according to claim 9, characterized in that The sending the first information to the first network device includes: The first information is sent to the first network device according to a first cycle.

12. The method according to claim 9, characterized in that The second network device is a fourth network device in at least one of the second network devices, and the terminal has established a connection with the fourth network device; the method further includes: receiving a second request sent by a terminal; the second request carries second information; the second request is used to request the first network device to determine a third network device that provides computing power services for the terminal; forwarding the second request to the first network device; in, The second information includes: Latency of AI services; and / or, The types and amounts of computing resources required for AI services.

13. The method according to claim 12, characterized in that The method further comprises: A response to the second request sent by the first network device is received; the response carries information of the third network device.

14. The method according to claim 13, characterized in that The method further comprises: receiving first data sent by the terminal in a preset second data format; the first data is related to AI; the preset second data format meets the transmission requirements between the fourth network device and the third network device; Sending the first data to the third network device; Receiving a calculation result sent by the third network device; The calculation result is sent to the terminal.

15. An information transmission device, characterized in that: include: An acquisition module, used to acquire first information respectively sent by at least one second network device; The first information is related to the available computing power of the second network device; wherein the first network device and the at least one second network device are in a master-slave relationship.

16. An information transmission device, characterized in that: include: A sending module is used to send first information to a first network device; the first information is related to the available computing power of a second network device; wherein the first network device and at least one of the second network devices are in a master-slave relationship.

17. A first network device, characterized in that: comprising a processor and a memory for storing a computer program capable of being executed on the processor, Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 1 to 8.

18. A second network device, characterized in that: comprising a processor and a memory for storing a computer program capable of being executed on the processor, Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 9 to 14.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8, or implements the steps of the method according to any one of claims 9 to 14.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented, or the method according to any one of claims 9 to 14 is implemented.

Images