An AI model information acquisition method, apparatus, device, and storage medium
By specifying an AI model to neighboring nodes in a 5G network to obtain information, the problem of signaling overhead and resource waste between radio access network nodes is solved, achieving efficient information acquisition and accurate data transmission.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA MOBILE COMM LTD RES INST
- Filing Date
- 2023-09-04
- Publication Date
- 2026-07-10
AI Technical Summary
In 5G networks, there are issues of signaling overhead and resource waste when information is acquired between radio access network nodes that have deployed AI models. In particular, when only some AI models are active, the acquired information may not provide significant gains.
By sending instruction messages to neighboring nodes, specific AI models can be designated to acquire information, reducing the transmission of data for unspecified models. The information acquisition process can be optimized using identifiers and status information, thereby improving data quality and reducing resource consumption.
It effectively reduces signaling overhead and resource waste, improves the quality and accuracy of information acquisition, ensures that only necessary information is acquired, and avoids incompatible data feedback.
Smart Images
Figure CN119561855B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, device and storage medium for acquiring information from an artificial intelligence (AI) model. Background Technology
[0002] In existing 5G networks, AI models can be deployed on gNBs. However, for a 5G radio access network node 1 (NG-RAN node1) with an AI model deployed, to perform predictions based on the AI model, it needs to request some information from a neighboring NG-RAN node (such as node2) as input data for the AI model. But in practical applications, there's a scenario where gNB2 has three models (AI model 1, model 2, and model 3), but only AI model 1 is active. In this case, gNB1 requests prediction / measurement information from gNB2, and gNB2 might directly provide the prediction information from AI model 1. In this situation, the information obtained by gNB1 from gNB2 may not provide a significant gain for the AI model prediction on gNB1, and the information acquisition signaling overhead is high. The storage and processing of the acquired information also consume resources, meaning this results in a waste of signaling overhead, storage, and computing resources. Summary of the Invention
[0003] In view of this, embodiments of this application aim to provide an AI model information acquisition method, apparatus, device, and storage medium.
[0004] The technical solution of this application embodiment is implemented as follows:
[0005] This application provides an AI model information acquisition method, applied to a first network node, including:
[0006] Send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0007] In one embodiment, before sending the first message to the second network node, the method further includes:
[0008] Send a second message to the second network node, the second message being used to request information related to the AI model deployed by the second network node;
[0009] Receive AI model-related information sent by the second network node; wherein the AI model-related information includes at least one of the following:
[0010] Identification information of the AI model deployed on the second network node;
[0011] The state information of the AI model deployed on the second network node.
[0012] The first message includes: first information and a first indicator; wherein,
[0013] The first information includes: the information requested by the first network node;
[0014] The first indicator is used to indicate the AI model that provides information to the first network node.
[0015] The first message further includes: second information and a second indicator; wherein,
[0016] The second information includes: necessary information from the information requested by the first network node;
[0017] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0018] In one embodiment, the method further includes:
[0019] Receive a third or fourth message sent by the second network node; wherein,
[0020] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0021] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0022] This application also provides an artificial intelligence (AI) model information acquisition method, applied to a second network node, including:
[0023] The first message sent by the first network node is received, which instructs the second network node to obtain the information requested by the first network node from the specified AI model.
[0024] In one embodiment, before receiving the first message sent by the first network node, the method further includes:
[0025] Receive a second message sent by the first network node, the second message being used to request information related to the AI model deployed by the second network node;
[0026] Send AI model-related information to the first network node; wherein the AI model-related information includes at least one of the following:
[0027] Identification information of the AI model deployed on the second network node;
[0028] The state information of the AI model deployed on the second network node.
[0029] The first message includes: first information and a first indicator; wherein,
[0030] The first information includes: the information requested by the first network node;
[0031] The first indicator is used to indicate the AI model that provides information to the first network node.
[0032] The first message further includes: second information and a second indicator; wherein,
[0033] The second information includes: necessary information from the information requested by the first network node;
[0034] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0035] In one embodiment, after receiving the first message sent by the first network node, the method further includes:
[0036] The decision to send a third or fourth message to the first network node is based on at least one of the following information:
[0037] The state of the AI model that provides information to the first network node;
[0038] The AI model may provide first information or provide both first and second information.
[0039] Second indicator;
[0040] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0041] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0042] This application embodiment also provides a network node, including: a first communication interface and a first processor; wherein,
[0043] The first communication interface is used to send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0044] This application embodiment also provides a network node, including: a second communication interface and a second processor; wherein,
[0045] The second communication interface is used to receive a first message sent by the first network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0046] This application also provides a network node, including: a first processor and a first memory for storing a computer program capable of running on the processor.
[0047] Wherein, when the first processor is used to run the computer program, it executes the steps of the above method.
[0048] This application also provides a network node, including: a second processor and a second memory for storing computer programs capable of running on the processor.
[0049] The second processor is used to execute the steps of the above method when running the computer program.
[0050] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.
[0051] The AI model information acquisition method, apparatus, device, and storage medium provided in this application embodiment involve a first network node sending a first message to a second network node. The first message instructs the second network node to acquire the information requested by the first network node from a specified AI model. In this application embodiment, the first network node acquires the required information (data) from the AI model specified by the second network node (neighboring node), eliminating the need for unspecified AI models to send data. This reduces the likelihood of low-value or incompatible feedback data and also saves signaling overhead caused by processing unnecessary information. Attached Figure Description
[0052] Figure 1 This is a schematic diagram of the AI model information acquisition method described in the embodiments of this application. Figure 1 ;
[0053] Figure 2 This is a schematic diagram of the AI model information acquisition method described in the embodiments of this application. Figure 2 ;
[0054] Figure 3 This is a schematic diagram of the AI model information acquisition device described in the embodiments of this application. Figure 1 ;
[0055] Figure 4 This is a schematic diagram of the AI model information acquisition device described in the embodiments of this application. Figure 2 ;
[0056] Figure 5 This is a schematic diagram of the network node structure described in the embodiments of this application. Figure 1 ;
[0057] Figure 6 This is a schematic diagram of the network node structure described in the embodiments of this application. Figure 2 . Detailed Implementation
[0058] The present application will now be described in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other. The present application will now be described in detail with reference to the accompanying drawings and embodiments.
[0059] This application provides a method for obtaining AI model information, such as... Figure 1 As shown, it is applied to the first network node and includes:
[0060] Step 101: Send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0061] In practical applications, the first network node and / or the second network node may include a 5G Radio Access Network (NG-RAN) node, and the first network node and the second network node are adjacent nodes to each other.
[0062] In this embodiment of the application, before sending the first message to the second network node, the method further includes:
[0063] Send a second message to the second network node, the second message being used to request information related to the AI model deployed by the second network node;
[0064] Receive AI model-related information sent by the second network node; wherein the AI model-related information includes at least one of the following:
[0065] Identification information of the AI model deployed on the second network node;
[0066] The state information of the AI model deployed on the second network node.
[0067] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0068] The first information includes: the information requested by the first network node;
[0069] The first indicator is used to indicate the AI model that provides information to the first network node.
[0070] In this embodiment, the first information may include at least one of the following for prediction: the number of active terminals connected to the second network node, the resource status information of the second network node, the number of Infinite Resource Control (RRC) connections of the second network node, and the terminal performance of the second network node; the terminal performance may include: average uplink and downlink throughput, average packet delay, and average packet loss. In practical applications, the first indicator may include: the model ID of the AI model, used to indicate which AI model in the second network node provides information to the first network node.
[0071] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0072] The second information includes: necessary information from the information requested by the first network node;
[0073] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0074] In this embodiment, the necessary information is the information that must be included in the information requested by the first network node, that is, a subset of the first information. In practical applications, the necessary information may include one or more of the first information: the number of active terminals connected to the second network node, the resource status information of the second network node, the number of RRC connections of the second network node, the terminal performance of the second network node, etc., used to indicate the information necessary for the first network node to make predictions, that is, the information that the second network node must provide.
[0075] In practical applications, if the AI model of the first network node wants to predict whether the second network node is suitable for terminal (UE) handover (e.g., whether the second network node has sufficient resources to support handover), it must input the resource status information of the second network node. If the resource status information is not available and only other information is input, the prediction accuracy will be very poor. Therefore, the first network node can set the resource status information as necessary information and the other information as auxiliary information to further improve the prediction accuracy.
[0076] In this embodiment of the application, the method further includes:
[0077] Receive a third or fourth message sent by the second network node; wherein,
[0078] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0079] The fourth message indicates that the designated AI model cannot provide the information requested by the first network node.
[0080] In practical applications, after receiving the first message, the second network node determines whether the AI model specified in the second network node can provide the first information. If it can provide all the first information, it sends a third message to the first network node. If it cannot provide all the first information, but can only provide some information, and the first network node supports partial reporting, it sends a third message, including which information cannot be provided. If it cannot provide all the first information, but can only provide some information, and the first network node does not support partial reporting, it sends a fourth message. If it cannot provide any information requested by the first network node for the time being, it sends a fourth message to the first network node.
[0081] As can be seen, the embodiments of this application can obtain the state of at least one AI model of a neighboring network node through interaction between network nodes, and evaluate which neighboring network node to obtain the data that the model wants based on the AI model state; when a network node has multiple AI models deployed, it can specify which model to provide the requested data to improve the quality of the obtained data and reduce the situation of incompatible feedback data; in the embodiments of this application, the requested node can only provide data from the specified model. When the specified model is in an inactive state, it will not provide the data that the currently active model can provide. It is necessary to determine whether the current network node supports reactivation. If it does not support it, it will not provide data.
[0082] This application also provides a method for obtaining AI model information, such as... Figure 2 As shown, it is applied to the second network node and includes:
[0083] Step 201: Receive a first message sent by the first network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0084] In practical applications, the first network node and / or the second network node may include a 5G Radio Access Network (NG-RAN) node, and the first network node and the second network node are adjacent nodes to each other.
[0085] In this embodiment of the application, before receiving the first message sent by the first network node, the method further includes:
[0086] Receive a second message sent by the first network node, the second message being used to request information related to the AI model deployed by the second network node;
[0087] Send AI model-related information to the first network node; wherein the AI model-related information includes at least one of the following:
[0088] Identification information of the AI model deployed on the second network node;
[0089] The state information of the AI model deployed on the second network node.
[0090] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0091] The first information includes: the information requested by the first network node;
[0092] The first indicator is used to indicate the AI model that provides information to the first network node.
[0093] In this embodiment, the first information may include at least one of the following for prediction: the number of active terminals connected to the second network node, the resource status information of the second network node, the number of RRC connections of the second network node, and the terminal performance of the second network node; the terminal performance may include: average uplink and downlink throughput, average packet delay, and average packet loss. In practical applications, the first indicator may include: the model ID of the AI model, used to indicate which AI model in the second network node provides information to the first network node.
[0094] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0095] The second information includes: necessary information from the information requested by the first network node;
[0096] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0097] In this embodiment, the necessary information is the information that must be included in the information requested by the first network node, that is, a subset of the first information. In practical applications, the necessary information may include one or more of the first information: the number of active terminals connected to the second network node, the resource status information of the second network node, the number of RRC connections of the second network node, the terminal performance of the second network node, etc., used to indicate the information necessary for the first network node to make predictions, that is, the information that the second network node must provide.
[0098] In practical applications, if the AI model of the first network node wants to predict whether the second network node is suitable for terminal (UE) handover (e.g., whether the second network node has sufficient resources to support handover), it must input the resource status information of the second network node. If the resource status information is not available and only other information is input, the prediction accuracy will be very poor. Therefore, the first network node can set the resource status information as necessary information and the other information as auxiliary information to further improve the prediction accuracy.
[0099] In this embodiment of the application, after receiving the first message sent by the first network node, the method further includes:
[0100] The decision to send a third or fourth message to the first network node is based on at least one of the following information:
[0101] The state of the AI model that provides information to the first network node;
[0102] The AI model may provide first information or provide both first and second information.
[0103] Second indicator;
[0104] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0105] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0106] In one embodiment of this application, determining to send a third message or a fourth message to the first network node based on at least one of the above information may include:
[0107] The state of the AI model that provides information to the first network node is determined. If the AI model is inactive and cannot be activated, a fourth message is sent to the first network node. If the AI model is inactive but can be activated, it is determined whether the AI model can provide the first information. If it cannot provide any information requested by the first network node, a fourth message is sent to the first network node.
[0108] If the AI model is active, or inactive but can be activated, and if the AI model can provide all the first information, then a third message is sent to the first network node; if the AI model cannot provide all the first information, then it is determined whether the first message includes the second information and the second indicator. If not, and the AI model can only provide partial information, and the first network node supports partial reporting, then a third message is sent, including which information cannot be provided; if the first network node does not support partial reporting, then a fourth message is sent.
[0109] If the first message includes the second information and the second indicator, the first network node's ability to support partial reporting is determined based on the second indicator. If the first network node does not support partial reporting, a fourth message is sent. If it does support partial reporting, it is determined whether the AI model can provide the second information. If it can provide the second information, a third message is sent to the first network node, including which information cannot be fed back. If it cannot provide the second information, a fourth message is sent to the first network node.
[0110] The following two application examples will be used to illustrate this application in detail.
[0111] Application Example 1
[0112] In this example, it is assumed that NG-RAN node2 has three AI models, AI model1, 2 and 3, with model2 being in an activated state.
[0113] Step 1: NG-RAN node1 sends a second message to NG-RAN node2 to obtain the model ID of the AI model deployed in node2;
[0114] Step 2: NG-RAN node2 reports the model IDs of its deployed models 1, 2, and 3, and indicates that model 2 is in the activated state;
[0115] Step 3: NG-RAN node1 sends the first message to NG-RAN node2 to obtain input data for AI model prediction;
[0116] The first message includes first information, indicating that it requests information 1, and / or information 2, and / or information 3, and indicating that NG-RAN node1 is requesting data from model2 in node2;
[0117] Step 4: After receiving the second message, NG-RAN node2 determines whether model2 is still in the activated state and whether it can provide all the first information; among which,
[0118] If model2 is still in the activated state and can provide all the first information (information 1 / information 2 / information 3), then send the third message to node1;
[0119] If model2 is still in the activated state but cannot provide all the first information and can only report some information, and node1 supports partial reporting, then NG-RAN node2 sends a third message, including which information cannot be reported.
[0120] If model2 is still in the activated state but cannot provide all the first information, only some information, and node1 does not support partial reporting, then NG-RAN node2 sends the fourth message;
[0121] If model2 is still in the activate state but cannot provide any requested information at the moment, then send the fourth message to node1;
[0122] If model2 is already in a non-activate state, then node2 evaluates whether it can currently support the activation of model2 (considering power consumption, computing power, etc.); if it cannot support the activation of model2, then it sends a fourth message to node1.
[0123] If the activated model2 can be supported without affecting the use of other currently activated models, then activate model2 and determine whether the information requested by node1 can be provided; where,
[0124] If all the first information (information 1 / information 2 / information 3) can be provided, then send the third message to node1;
[0125] If not all first information can be provided, and only partial information can be reported, and node1 supports partial reporting, then NG-RAN node2 sends a third message, including which information cannot be reported.
[0126] If not all the first information can be provided, and only some information can be reported, and node1 does not support partial reporting, then NG-RAN node2 sends a fourth message;
[0127] If no requested information can be provided at this time, a fourth message is sent to node1.
[0128] Application Example 2
[0129] In this example, it is assumed that NG-RAN node2 has three AI models, AI model1, 2 and 3, with model2 in the activated state. NG-RAN node1 sends the first message to NG-RAN node2 to obtain the input data for AI model prediction.
[0130] The first message includes first information, indicating that it requests information 1, and / or information 2, and / or information 3; and indicates that NG-RAN node1 is requesting data from model 2 in node 2;
[0131] The first message also includes indicator 2 and second information, whereby indicator 2 indicates that its supporting part should report; the second information includes information 1, indicating that the requested information 1 must be provided.
[0132] After receiving the first message, NG-RAN node2 determines whether model2 can provide all the first information. If it can provide all the first information, it sends a third message to node1.
[0133] If not all the first information can be provided, determine whether the first message includes indicator 2 and instruct it to support the reporting of the relevant part;
[0134] If partial reporting is supported, NG-RAN node2 determines whether it can provide information 1; if it can, it sends a third message to node1; if it cannot, it sends a fourth message to node1.
[0135] To implement the method on the first network node side of this application embodiment, this application embodiment also provides an AI model information acquisition device, such as... Figure 3 As shown, the device includes:
[0136] The first communication unit 301 is used to send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0137] In this embodiment of the application, before the first communication unit 301 sends the first message to the second network node, it is also used to send a second message to the second network node. The second message is used to request information related to the AI model deployed by the second network node.
[0138] Receive AI model-related information sent by the second network node; wherein the AI model-related information includes at least one of the following:
[0139] Identification information of the AI model deployed on the second network node;
[0140] The state information of the AI model deployed on the second network node.
[0141] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0142] The first information includes: the information requested by the first network node;
[0143] The first indicator is used to indicate the AI model that provides information to the first network node.
[0144] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0145] The second information includes: necessary information from the information requested by the first network node;
[0146] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0147] In this embodiment of the application, the first communication unit 301 is further configured to receive a third message or a fourth message sent by the second network node; wherein,
[0148] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0149] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0150] In practical applications, the first communication unit 301 can be implemented by the communication interface in the AI model information acquisition device.
[0151] It should be noted that the AI model information acquisition device provided in the above embodiments is only illustrated by the division of the above program modules during communication. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.
[0152] To implement the method on the second network node side of this application embodiment, this application embodiment also provides an AI model information acquisition device, such as... Figure 4 As shown, the device includes:
[0153] The second communication unit 401 is used to receive a first message sent by the first network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0154] In this embodiment of the application, before the second communication unit 401 receives the first message sent by the first network node, it is further used for
[0155] Receive a second message sent by the first network node, the second message being used to request information related to the AI model deployed by the second network node;
[0156] Send AI model-related information to the first network node; wherein the AI model-related information includes at least one of the following:
[0157] Identification information of the AI model deployed on the second network node;
[0158] The state information of the AI model deployed on the second network node.
[0159] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0160] The first information includes: the information requested by the first network node;
[0161] The first indicator is used to indicate the AI model that provides information to the first network node.
[0162] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0163] The second information includes: necessary information from the information requested by the first network node;
[0164] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0165] In this embodiment of the application, after receiving the first message sent by the first network node, the second communication unit 401 is further configured to determine whether to send a third message or a fourth message to the first network node based on at least one of the following information:
[0166] The state of the AI model that provides information to the first network node;
[0167] The AI model may provide first information or provide both first and second information.
[0168] Second indicator;
[0169] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0170] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0171] In practical applications, the second communication unit 401 can be implemented by the communication interface in the AI model information acquisition device.
[0172] It should be noted that the AI model information acquisition device provided in the above embodiments is only illustrated by the division of the above program modules during communication. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.
[0173] Based on the hardware implementation of the above program modules, and in order to implement the method on the first network node side of the embodiments of this application, the embodiments of this application also provide a (first) network node, such as... Figure 5 As shown, the network node 500 includes:
[0174] The first communication interface 501 is capable of exchanging information with the second network node and / or other nodes on the network side;
[0175] The first processor 502 is connected to the first communication interface 501 to enable information interaction with the second network node and / or other nodes on the network side, and to execute the methods provided by one or more technical solutions on the network node side when running a computer program;
[0176] The computer program is stored in the first memory 503.
[0177] Specifically, the first communication interface 501 is used to send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0178] In this embodiment of the application, before the first communication interface 501 sends the first message to the second network node, it is also used to send a second message to the second network node. The second message is used to request information related to the AI model deployed by the second network node.
[0179] Receive AI model-related information sent by the second network node; wherein the AI model-related information includes at least one of the following:
[0180] Identification information of the AI model deployed on the second network node;
[0181] The state information of the AI model deployed on the second network node.
[0182] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0183] The first information includes: the information requested by the first network node;
[0184] The first indicator is used to indicate the AI model that provides information to the first network node.
[0185] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0186] The second information includes: necessary information from the information requested by the first network node;
[0187] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0188] In this embodiment of the application, the first communication interface 501 is further configured to receive a third message or a fourth message sent by the second network node; wherein,
[0189] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0190] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0191] It should be noted that the specific processing procedures of the first communication interface 501 and the first processor 502 can be understood by referring to the above method, and will not be repeated here.
[0192] Of course, in practical applications, the various components in network node 500 are coupled together through bus system 504. It can be understood that bus system 504 is used to implement communication between these components. In addition to a data bus, bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 5 The general designated all buses as Bus System 504.
[0193] The first memory 503 in this embodiment is used to store various types of data to support the operation of the network node 500. Examples of such data include any computer program used to operate on the network node 500.
[0194] The methods disclosed in the embodiments of this application can be applied to the first processor 502, or implemented by the first processor 502. The first processor 502 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 integrated logic circuit of the hardware or by instructions in the form of software in the first processor 502. The first processor 502 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The first processor 502 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the first memory 503. The first processor 502 reads the information in the first memory 503 and completes the steps of the aforementioned method in combination with its hardware.
[0195] In an exemplary embodiment, network node 500 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.
[0196] Based on the hardware implementation of the above program modules, and in order to implement the method on the second network node side of the embodiments of this application, the embodiments of this application also provide a (second) network node, such as... Figure 6 As shown, the network node 600 includes:
[0197] The second communication interface 601 is capable of exchanging information with the first network node and / or other nodes on the network side;
[0198] The second processor 602 is connected to the second communication interface 601 to enable information interaction with the first network node and / or other nodes on the network side, and to execute the methods provided by one or more technical solutions on the network node side when running a computer program;
[0199] The computer program is stored in the first memory 603, which is a second memory 603.
[0200] Specifically, the second communication interface 601 is used to receive a first message sent by the first network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model.
[0201] In this embodiment of the application, before the second communication interface 601 receives the first message sent by the first network node, it is also used for
[0202] Receive a second message sent by the first network node, the second message being used to request information related to the AI model deployed by the second network node;
[0203] Send AI model-related information to the first network node; wherein the AI model-related information includes at least one of the following:
[0204] Identification information of the AI model deployed on the second network node;
[0205] The state information of the AI model deployed on the second network node.
[0206] In this embodiment of the application, the first message includes: first information and a first indicator; wherein...
[0207] The first information includes: the information requested by the first network node;
[0208] The first indicator is used to indicate the AI model that provides information to the first network node.
[0209] In this embodiment of the application, the first message further includes: second information and a second indicator; wherein...
[0210] The second information includes: necessary information from the information requested by the first network node;
[0211] The second indicator is used to indicate the first network node's ability to support partial reporting.
[0212] In this embodiment of the application, after receiving the first message sent by the first network node, the second communication interface 601 is further configured to determine, based on at least one of the following information, to send a third message or a fourth message to the first network node:
[0213] The state of the AI model that provides information to the first network node;
[0214] The AI model may provide first information or provide both first and second information.
[0215] Second indicator;
[0216] The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node;
[0217] The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
[0218] It should be noted that the specific processing procedures of the second communication interface 601 and the second processor 602 can be understood by referring to the above method, and will not be repeated here.
[0219] Of course, in practical applications, the various components in network node 600 are coupled together through bus system 604. It can be understood that bus system 604 is used to implement communication between these components. In addition to a data bus, bus system 604 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 6 The general designated all buses as Bus System 604.
[0220] The second memory 603 in this embodiment is used to store various types of data to support the operation of the network node 600. Examples of such data include any computer program used to operate on the network node 600.
[0221] The methods disclosed in the embodiments of this application can be applied to, or implemented by, the second processor 602. The second processor 602 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware or by instructions in the form of software within the second processor 602. The second processor 602 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 602 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, specifically a second memory 603. The second processor 602 reads information from the second memory 603 and, in conjunction with its hardware, completes the steps of the aforementioned method.
[0222] In an exemplary embodiment, network node 600 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.
[0223] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a first memory 503 storing a computer program, which can be executed by a first processor 502 of a network node 500 to complete the steps described in the aforementioned first network node-side method. Another example is a second memory 603 storing a computer program, which can be executed by a second processor 602 of a network node 600 to complete the steps described in the aforementioned second network node-side method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.
[0224] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0225] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.
[0226] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.
Claims
1. A method for acquiring information from an artificial intelligence (AI) model, characterized in that, Applied to the first network node, including: A first message is sent to a second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model; wherein, the first network node and the second network node are adjacent nodes to each other; The first message includes: second information and a second indicator; wherein the second information includes: necessary information in the information requested by the first network node; and the second indicator is used to indicate the first network node's ability to support partial reporting.
2. The method according to claim 1, characterized in that, Before sending the first message to the second network node, the method further includes: Send a second message to the second network node, the second message being used to request information related to the AI model deployed by the second network node; Receive AI model-related information sent by the second network node; wherein the AI model-related information includes at least one of the following: Identification information of the AI model deployed on the second network node; The state information of the AI model deployed on the second network node.
3. The method according to claim 1, characterized in that, The first message further includes: first information and a first indicator; wherein, The first information includes: the information requested by the first network node; The first indicator is used to indicate the AI model that provides information to the first network node.
4. The method according to claim 1, characterized in that, The method further includes: Receive a third or fourth message sent by the second network node; wherein, The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node; The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
5. A method for acquiring information from an artificial intelligence (AI) model, characterized in that, Applied to the second network node, including: The system receives a first message from a first network node, which instructs the second network node to obtain the information requested by the first network node from a specified AI model; wherein the first network node and the second network node are adjacent nodes to each other. The first message includes: second information and a second indicator; wherein the second information includes: necessary information in the information requested by the first network node; and the second indicator is used to indicate the first network node's ability to support partial reporting.
6. The method according to claim 5, characterized in that, Before receiving the first message sent by the first network node, the method further includes: Receive a second message sent by the first network node, the second message being used to request information related to the AI model deployed by the second network node; Send AI model-related information to the first network node; wherein the AI model-related information includes at least one of the following: Identification information of the AI model deployed on the second network node; The state information of the AI model deployed on the second network node.
7. The method according to claim 5, characterized in that, The first message further includes: first information and a first indicator; wherein, The first information includes: the information requested by the first network node; The first indicator is used to indicate the AI model that provides information to the first network node.
8. The method according to claim 7, characterized in that, After receiving the first message sent by the first network node, the method further includes: The decision to send a third or fourth message to the first network node is based on at least one of the following information: The state of the AI model that provides information to the first network node; The AI model may provide first information or provide both first and second information. Second indicator; The third message is used to indicate that the designated AI model can provide all or part of the information requested by the first network node; The fourth message is used to indicate that the specified AI model cannot provide the information requested by the first network node.
9. A network node, characterized in that, include: A first communication interface and a first processor; wherein... The first communication interface is used to send a first message to the second network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model; wherein the first network node and the second network node are adjacent nodes to each other; The first message includes: second information and a second indicator; wherein the second information includes: necessary information in the information requested by the first network node; and the second indicator is used to indicate the first network node's ability to support partial reporting.
10. A network node, characterized in that, include: The second communication interface and the second processor; wherein... The second communication interface is used to receive a first message sent by the first network node, the first message being used to instruct the second network node to obtain the information requested by the first network node from the specified AI model; wherein the first network node and the second network node are adjacent nodes to each other; The first message includes: second information and a second indicator; wherein the second information includes: necessary information in the information requested by the first network node; and the second indicator is used to indicate the first network node's ability to support partial reporting.
11. A network node, characterized in that, include: A first processor and a first memory for storing computer programs capable of running on the processor. Wherein, when the first processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 4.
12. A network node, characterized in that, include: A second processor and a second memory for storing computer programs that can run on the processor. Wherein, when the second processor is used to run the computer program, it performs the steps of the method according to any one of claims 5 to 8.
13. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4, or the steps of the method according to any one of claims 5 to 8.