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

Abstract

The invention discloses an information transmission method and device, equipment, a storage medium and a program product. A first network node sends first information to a second network node; wherein the second network node is a network node for generating original movement track prediction information, and the first information comprises indication information for indicating updated movement track prediction information and / or related information of new movement track prediction information; and / or the first network node sends second information to a third network node; wherein the third network node is a network node located behind the first network node on the actual movement track or a network node located behind the first network node in the new movement track prediction information, and the second information comprises the movement track prediction information. By adopting the method and the device, the information is sent to the network node generating the original moving track prediction information through the intermediate node after the moving track prediction information is updated, the related condition of the new prediction information is indicated, and the process of terminal moving track prediction is optimized.

Description

Technical Field

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

[0002] AI technology can extract features of massive data in complex scenarios and train and derive models to achieve prediction and decision-making. Therefore, it is increasingly valued and applied by various industries. Mobility Optimization is one of the typical scenarios of the combination of 5G and AI technology. It uses data collection and AI technology to predict the mobile trajectory (UE Trajectory) of user terminals UE in the future, so as to assist network switching decisions and reserve resources in advance. UE mobile trajectory prediction refers to the mobile trajectory prediction information generated by the source node for a certain UE in the cell within the next hop or multi-hop target network node after leaving the source node. The subsequent target network node feeds back the real mobile trajectory information of the UE in each cell within the target network node to the source node so that the source node can realize the performance detection and training of the AI ​​model.

[0003] With the deep integration of AI technology and wireless networks, there will be a large number of nodes in the network that deploy AI models to have prediction capabilities. In the UE mobile trajectory prediction scenario, after the source node generates multi-hop mobile trajectory prediction information for a certain UE and forwards it to the target network node 1, if the target network node 1 also has multi-hop UE mobile trajectory prediction capabilities, the target network node 1 may generate new trajectory prediction information to replace the original prediction information and send it to the target network node 2.

[0004] However, the inventors have discovered that the prior art has at least the following problems: in the above scenario, the source node cannot know that its own trajectory prediction information has been replaced by the prediction information of other nodes, which may cause the source node to wait for a long time for subsequent nodes to feedback the true movement trajectory information. It will also be impossible to iterate and update the AI ​​model due to the lack of feedback information, affecting the prediction performance. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an information transmission method, device, equipment, medium and product, which sends information to the network node that generates the original mobile trajectory prediction information after updating the mobile trajectory prediction information through the intermediate node, indicates the relevant situation of the new prediction information, and optimizes the process of terminal mobile trajectory prediction.

[0006] To achieve the above objective, an embodiment of the present invention provides an information transmission method, which is applied to a first network node. The method includes:

[0007] Sending first information to a second network node; wherein the second network node is a network node that generates original movement trajectory prediction information, and the first information includes indication information for indicating updated movement trajectory prediction information and / or relevant information of new movement trajectory prediction information;

[0008] And / or, sending second information to a third network node; wherein the third network node is a network node located after the first network node on the actual mobile trajectory or a network node located after the first network node in the new mobile trajectory prediction information, and the second information includes relevant information of the original mobile trajectory prediction information or relevant information of the new mobile trajectory prediction information.

[0009] As a preferred embodiment, the method further comprises:

[0010] When it is determined that the movement trajectory prediction update condition is met, generating relevant information of new movement trajectory prediction information; the movement trajectory prediction update condition is at least one of the following conditions:

[0011] The first update condition is that the original movement trajectory prediction information exceeds the validity period;

[0012] The second update condition is that the original movement trajectory prediction information does not match the actual movement trajectory of the terminal;

[0013] The third updating condition is that the remaining predicted trajectories in the original movement trajectory prediction information are insufficient.

[0014] As a preferred implementation, the relevant information of the new mobile trajectory prediction information includes a predicted target network node sequence and / or a target cell sequence within each target network node range and / or a residence time of the terminal in each cell.

[0015] As a preferred implementation, the first information includes at least one of the following information: time information, reason information, real movement track information and identification information of the second network node; wherein,

[0016] The time information is the generation time of the original movement trajectory prediction information and / or the generation time of the new movement trajectory prediction information;

[0017] The reason information is the triggered moving trajectory prediction update condition;

[0018] The real mobile trajectory information includes at least one of the following information: a real cell sequence within the range of the first network node, the previous real network node, the previous real cell, the next real network node, and the next real cell; the real network node is the node actually entered by the terminal, and the real cell is the cell actually entered by the terminal.

[0019] As a preferred implementation, before generating new movement trajectory prediction information and / or sending the first information to the second network node when determining that the movement trajectory prediction update condition is met, the method further includes:

[0020] Receive original movement trajectory prediction information of the terminal generated by the second network node; wherein the movement trajectory prediction information includes a predicted target network node sequence and / or a target cell sequence within the range of each target network node.

[0021] As a preferred implementation, determining whether the first update condition is met includes:

[0022] When the residence time is greater than the preset effective time of the original mobile trajectory prediction information, it is determined that the original mobile trajectory prediction information exceeds the validity period; wherein the residence time is the time during which the terminal has resided in the target cell within the target network node range in the original mobile trajectory prediction information.

[0023] Determining whether the second update condition is met includes:

[0024] When the next target network node or target cell predicted in the original moving trajectory prediction information is inconsistent with the next real network node or real cell actually switched by the terminal, it is determined that the original moving trajectory prediction information is inconsistent with the real moving trajectory of the terminal.

[0025] Determining whether the third update condition is met includes:

[0026] When the number of remaining nodes is less than a preset node number threshold, or the number of remaining cells is less than a preset cell number threshold, it is determined that the remaining predicted trajectories in the original mobile trajectory prediction information are insufficient; wherein the number of remaining nodes or the number of remaining cells is the number of target network nodes or target cells after the first network node in the original mobile trajectory prediction information.

[0027] As a preferred implementation manner, the sending the first information to the second network node includes:

[0028] When there is a communication interface between the first network node and the second network node, sending first information to the second network node through the communication interface;

[0029] When there is no communication interface between the first network node and the second network node, the first information is forwarded to the second network node via an intermediate network node having a communication interface.

[0030] As a preferred implementation, after receiving the first information, the second network node can update the movement trajectory prediction model deployed by itself according to the first information.

[0031] The embodiment of the present invention further provides an information transmission device, which is applied to a first network node, and the device includes:

[0032] A first information sending module, configured to send first information to a second network node; wherein the second network node is a network node that generates original movement trajectory prediction information, and the first information includes indication information for indicating updated movement trajectory prediction information and / or relevant information of new movement trajectory prediction information;

[0033] and / or,

[0034] The second information sending module is used to send second information to a third network node; wherein the third network node is a network node located after the first network node on the actual movement trajectory or a network node located after the first network node in the new movement trajectory prediction information, and the second information includes relevant information of the original movement trajectory prediction information or relevant information of the new movement trajectory prediction information.

[0035] An embodiment of the present invention further provides an information transmission device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-described information transmission methods when executing the computer program.

[0036] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the information transmission methods described above.

[0037] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, the information transmission method as described in any one of the above is implemented.

[0038] Compared with the prior art, the information transmission method, device, equipment, storage medium and program product disclosed in the present invention optimize the information interaction process between nodes after the new prediction information is generated in the multi-node terminal mobile trajectory prediction scenario. After receiving the mobile trajectory prediction information predicted by the previous network node, the intermediate network node determines the mobile trajectory prediction update condition, generates new mobile trajectory prediction information when the update condition is met, and sends the first information to the network node that generates the original mobile trajectory prediction information, informing the network node that the mobile trajectory prediction information has been updated and the relevant information of the new mobile trajectory prediction information. The network node can be informed in time that its own trajectory prediction information is replaced by the prediction information of other nodes, and obtain the effective first information for iterative optimization of the prediction model deployed by itself when it is replaced. It can also avoid the network node from being in a state of waiting for other nodes to feedback the real mobile trajectory information for a long time, causing unnecessary waste of resources, and effectively improving the cell switching performance and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of mobile trajectory prediction information in the prior art;

[0040] Figure 2 It is a schematic diagram of the signaling process of mobile trajectory prediction information and real mobile trajectory information in the prior art;

[0041] Figure 3 It is a flowchart of an information transmission method provided by an embodiment of the present invention;

[0042] Figure 4 is a flow chart of a preferred information transmission method in an embodiment of the present invention;

[0043] Figure 5 is a structural schematic diagram of an information transmission device provided by an embodiment of the present invention;

[0044] Figure 6 It is a structural schematic diagram of an information transmission device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0047] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0048] It should be noted that the embodiments of the present invention are applicable to scenarios involving prediction of the mobile trajectory of a terminal UE. Currently, 5GNR (New Radio) introduces single-hop (first-hop) UE mobile trajectory prediction (Predicted UE Trajectory) and real / measured UE mobile trajectory collection / acquisition (measured UE trajectory collection) functions, and will introduce UE mobile trajectory prediction for multi-hop scenarios in the future. UE mobile trajectory prediction refers to the mobile trajectory prediction information generated by a source node (source node) for a certain UE in the next hop or multi-hop target network node (target node) after leaving the source node. Taking a multi-hop scenario as an example, Figure 1 As shown, Figure 1 It is a schematic diagram of mobile trajectory prediction information in the prior art. The mobile trajectory prediction (Predicted UE Trajectory) information generated by the source node source node for a certain UE includes the order and related information of the UE successively entering the target network node 1 (Target node-1), target network node 2 (Target node-2) and target network node 3 (Target node-3) in each target cell (cell). The real / measured UE mobile trajectory collection / acquisition is that one or more target network nodes feed back the real mobile trajectory information (measured UE trajectory) of the UE in each cell within the target network node to the source node for performance testing and training of AI / ML models.

[0049] See also Figure 2, is a schematic diagram of the signaling process of mobile trajectory prediction information and real mobile trajectory information in the prior art. Taking the single-hop UE mobile trajectory related signaling process as an example, the UE mobile trajectory prediction information and the real / measured UE mobile trajectory collection / acquisition process is as follows Figure 2 As shown, node 1 sends a data collection request (DATA COLLECTION REQUEST) to node 2, expecting to carry configuration information for collecting real mobile trajectory information. Node 2 returns a data collection response (DATA COLLECTION RESPONSE) to node 1. Node 1 sends a handover request (HANDOVER REQUEST) to node 2, which carries the predicted mobile trajectory prediction information, and node 2 returns a handover response (HANDOVER REQUEST ACK). Node 2 starts / stops collecting real mobile trajectory information and UE performance information, and returns a data collection update instruction (DATA COLLECTION UPDATE) to node 1, which carries relevant measurement information such as real mobile trajectory information and UE performance information.

[0050] However, in the UE mobile trajectory prediction scenario, the following situation may exist: assuming that both the source node and the target network node 1 have multi-hop UE mobile trajectory prediction capabilities, the source node generates multi-hop mobile trajectory prediction information for a certain UE and sends it to the target network node 1. The target network node 1 can choose to continue to send the prediction information generated by the source node to the next hop target network node 2, or it can choose to generate new trajectory prediction information and send it to the target network node 2, that is, the new prediction information replaces the original prediction information. The source node and Target node-1 both generate UE mobile trajectory prediction information, and both require the subsequent target network node to feedback the UE's true mobile trajectory information for performance testing of the AI / ML model. The above scenario mainly has the following problems that cannot be solved: how does the source node know that its trajectory prediction information is replaced by the prediction information of other nodes, and how to obtain the UE's true mobile trajectory information when the prediction information is replaced. There is no corresponding process support in the prior art. This problem may cause the source node to wait for a long time for the feedback of the true mobile trajectory information, and it will also be impossible to iteratively update the AI / ML model due to the lack of feedback information, affecting the prediction performance.

[0051] To solve the above problems, see Figure 3 , is a flow chart of an information transmission method provided by an embodiment of the present invention. The embodiment of the present invention provides an information transmission method, which is applied to a first network node. The method includes the following steps:

[0052] S11. Sending first information to a second network node; wherein the second network node is a network node that generates original movement trajectory prediction information, and the first information includes indication information for indicating updated movement trajectory prediction information and / or relevant information of new movement trajectory prediction information;

[0053] and / or;

[0054] S12. Send second information to a third network node; wherein the third network node is a network node located after the first network node on the actual movement trajectory or a network node located after the first network node in the new movement trajectory prediction information, and the second information includes relevant information of the original movement trajectory prediction information or relevant information of the new movement trajectory prediction information.

[0055] It should be noted that the network nodes such as the first network node, the second network node and the third network node may include NG-RAN (5G wireless access network) nodes, specifically base stations, which does not affect the beneficial effects achieved by the present invention.

[0056] In the embodiment of the present invention, the first network node is a network node with a mobile trajectory prediction capability. In the mobile trajectory prediction process of the terminal, the first network node has the function of forwarding mobile trajectory prediction information, and also has the ability to update the mobile trajectory prediction information and feedback the first information to the previous network node that generated the original mobile trajectory prediction information.

[0057] Preferably, the method further comprises:

[0058] When it is determined that the movement trajectory prediction update condition is satisfied, new movement trajectory prediction information is generated.

[0059] The relevant information of the new mobile trajectory prediction information includes a predicted target network node sequence, a target cell sequence within the range of each target network node and / or a residence time of the terminal in each cell.

[0060] Preferably, before generating new movement trajectory prediction information and / or sending the first information to the second network node when determining that the movement trajectory prediction update condition is met, the method further includes:

[0061] Receive original movement trajectory prediction information of the terminal generated by the second network node; wherein the movement trajectory prediction information includes a predicted target network node sequence and / or a target cell sequence within the range of each target network node.

[0062] In an embodiment of the present invention, the second network node generates multi-hop mobile trajectory prediction information for a terminal UE. It can be understood that the mobile trajectory of the terminal refers to the trajectory of the terminal moving in each cell, and one or more cells are within the range of a certain node and monitored by the node. The mobile trajectory prediction information includes the target network node sequence predicted by the second network node, that is, the order of the multi-hop target network node range that the terminal UE may enter, and also includes the target cell sequence within each target network node range, that is, the mobile trajectory of the terminal UE in each target cell after entering the target network node range.

[0063] As an example, the second network node generates mobile trajectory prediction information for the terminal UE as a cell sequence of target cell cell-11, target cell cell-12, target cell cell-13, target cell cell-21, target cell cell-22, target cell cell-31 and target cell cell-32, among which cell-11, cell-12 and cell-13 are within the range of target network node 1, cell-21 and cell-22 are within the range of target network node 2, and cell-31 and cell-32 are within the range of target network node 3.

[0064] After generating the movement trajectory prediction information, the second network node sends the movement trajectory prediction information to the first-hop target network node 1 in the prediction information. The target network node 1 may choose to continue to send the movement trajectory prediction information to the next-hop target network node 2.

[0065] The embodiment of the present invention is applied to an intermediate network node in a certain mobile trajectory, denoted as the first network node A. The first network node A is deployed with a terminal mobile trajectory prediction model and has the terminal mobile trajectory prediction capability. When the first network node A receives the mobile trajectory prediction information (denoted as predictedUE trajectory-1) from other nodes (the previous hop target network node), it determines whether the preset mobile trajectory prediction update condition is currently met. If it is determined that the mobile trajectory prediction update condition is not met, the first network node A does not update the mobile trajectory prediction information, but sends the original mobile trajectory prediction information and related information to the next hop target network node, that is, the third network node. If it is determined that the mobile trajectory prediction update condition is met, the first network node A generates new mobile trajectory prediction information (denoted as predicted UE trajectory-2) based on its own AI prediction capability.

[0066] After determining that the mobile trajectory prediction update condition is met and generating new mobile trajectory prediction information, the first network node A generates first information, wherein the first information includes indication information for indicating that the mobile trajectory prediction information has been updated, and the indication information is used to indicate that the first network node A generates new UE mobile trajectory prediction information (predicted UEtrajectory-2) to replace the UE mobile trajectory prediction (predicted UE trajectory-1) generated by the second network node, that is, the first network node A no longer sends the prediction information predicted UEtrajectory-1 to the subsequent target network node. The first information also includes relevant information of the new mobile trajectory prediction information. The first network node A sends the first information to the second network node. As a result, the second network node can know that its own mobile trajectory prediction information has been replaced after receiving the first information, and can perform iterative optimization of its own prediction model based on the effective first information, so as to avoid wasting resources by waiting for a long time for the subsequent nodes to feedback the real mobile trajectory information.

[0067] In addition, after determining that the mobile trajectory prediction update condition is met and generating new mobile trajectory prediction information, the first network node A replaces the original mobile trajectory prediction information, and sends the new mobile trajectory prediction information predicted UE trajectory-2 and related information to the predicted next hop target network node, that is, the third network node, during handover preparation (for example, in a HANDOVER REQUEST message).

[0068] By adopting the technical means of the embodiments of the present invention, in a multi-node terminal mobile trajectory prediction scenario, the information interaction process between nodes after the new prediction information is generated is optimized, and the intermediate network node judges the mobile trajectory prediction update condition after receiving the mobile trajectory prediction information predicted by the previous network node, generates new mobile trajectory prediction information when the update condition is met, and sends the first information to the network node that generates the original mobile trajectory prediction information, informing the network node that the mobile trajectory prediction information has been updated and the relevant information of the new mobile trajectory prediction information, so that the network node can promptly know that its own trajectory prediction information is replaced by the prediction information of other nodes, and obtain the effective first information for iterative optimization of the prediction model deployed by itself when it is replaced, and can also avoid the network node from being in a state of waiting for other nodes to feedback the real mobile trajectory information for a long time, causing unnecessary waste of resources, and effectively improving the cell switching performance and user experience.

[0069] It should be noted that in the above UE mobile trajectory prediction scenario, there are still the following problems that cannot be solved by existing technologies: how the intermediate network node chooses to continue forwarding the prediction information of the previous network node or generate new prediction information, and there is no corresponding mechanism support in the existing technology. This problem may cause the intermediate network node to be unable to adapt to changes in the situation and provide accurate and reliable prediction information to the subsequent target network node. The subsequent target network node may perform operations such as resource reservation based on inaccurate prediction information, resulting in unnecessary waste of resources.

[0070] In order to solve the above problem, the embodiment of the present invention improves the moving trajectory prediction update condition. As a preferred implementation, the moving trajectory prediction update condition includes at least one of the first update condition, the second update condition and the third update condition; wherein,

[0071] The first update condition is that the original movement trajectory prediction information exceeds the validity period;

[0072] The second update condition is that the original movement trajectory prediction information does not match the actual movement trajectory of the terminal;

[0073] The third updating condition is that the remaining predicted trajectory in the original movement trajectory prediction information is insufficient.

[0074] Preferably, determining whether the first update condition is met comprises the following steps:

[0075] When the residence time is greater than the preset effective time of the original mobile trajectory prediction information, it is determined that the original mobile trajectory prediction information exceeds the validity period; wherein the residence time is the time during which the terminal has resided in the target cell within the target network node range in the original mobile trajectory prediction information.

[0076] In an embodiment of the present invention, whether the UE mobile trajectory prediction information (predicted UE trajectory-1) exceeds the validity period may be determined by obtaining a preset valid time of the original mobile trajectory prediction information, obtaining the time for which the terminal has resided in the target cell within the target network node range predicted by the original mobile trajectory prediction information, and then comparing the size relationship between the valid time of the UE mobile trajectory prediction information and the time for which the UE has resided in the node involved in the prediction information. If the valid time is less than or equal to the resided time, it is determined that the UE mobile trajectory prediction information exceeds the validity period, that is, the prediction information no longer has a relatively accurate reference significance for the target network node after the first network node A. At this time, the first network node A determines that new UE mobile trajectory prediction information (predicted UEtrajectory-2) needs to be generated.

[0077] It should be noted that the validity period of the UE mobile trajectory prediction information and the length of time the UE has resided at the node can be transmitted in the prediction information and / or the configuration of the first information collection, and is not specifically limited here.

[0078] Preferably, determining whether the second update condition is met comprises the following steps:

[0079] When the next target network node or target cell predicted in the original moving trajectory prediction information is inconsistent with the next real network node or real cell actually switched by the terminal, it is determined that the original moving trajectory prediction information is inconsistent with the real moving trajectory of the terminal.

[0080] In an embodiment of the present invention, it is determined that the UE mobile trajectory prediction information (predicted UE trajectory-1) is inconsistent with the UE's actual mobile trajectory. The specific method may be to obtain the next target network node or target cell predicted in the mobile trajectory prediction information; determine the next real network node or real cell to which the terminal actually switches according to the actual mobile information of the terminal; when the target network node is inconsistent with the real network node, or the target cell is inconsistent with the real cell, it is determined that the mobile trajectory prediction information is inconsistent with the terminal's actual mobile trajectory. That is, when the first network node A finds that the real network node it determines to switch for the UE is different from the target network node located at the next hop of node A in the prediction information predicted UEtrajectory-1, or node A finds that the real cell it determines to switch for the UE is different from the next target cell in the prediction information predicted UE trajectory-1, that is, the UE mobile trajectory prediction information is inaccurate, at this time node A determines that new UE mobile trajectory prediction information predicted UEtrajectory-2 needs to be generated.

[0081] Preferably, determining whether the third update condition is met comprises the following steps:

[0082] When the number of remaining nodes is less than a preset node number threshold, or the number of remaining cells is less than a preset cell number threshold, it is determined that the remaining predicted trajectories in the original mobile trajectory prediction information are insufficient; wherein the number of remaining nodes or the number of remaining cells is the number of target network nodes or target cells after the first network node in the original mobile trajectory prediction information.

[0083] In an embodiment of the present invention, it is determined that the number of remaining nodes included in the UE mobile trajectory prediction information is insufficient. The specific method may be that the first network node A pre-sets a node number threshold. If the number of remaining nodes included in the UE mobile trajectory prediction information, that is, the number of target network nodes that the UE is expected to enter after the first network node A is less than or equal to the node number threshold, the first network node A determines that new UE mobile trajectory prediction information needs to be generated; or, the first network node A pre-sets a cell number threshold. If the number of remaining cells included in the UE mobile trajectory prediction information, that is, the number of target cells that the UE is expected to enter after the first network node A is less than or equal to the cell number threshold, the first network node A determines that new UE mobile trajectory prediction information predicted UE trajectory-2 needs to be generated.

[0084] By adopting the technical means of the embodiment of the present invention, in the scenario of multi-node terminal mobile trajectory prediction, the conditions for the intermediate network node to judge whether the prediction information needs to be updated, and the information interaction process between network nodes after the new prediction information is generated are optimized. After receiving the mobile trajectory prediction information predicted by the network node, the intermediate network node judges whether the original prediction information has expired according to the actual situation, and promptly provides prediction information with higher prediction accuracy and more reliability when it is invalid or about to expire, effectively avoiding the subsequent target network node from performing operations such as resource reservation or switching decision based on erroneous prediction information. At the same time, after the new mobile trajectory prediction information is generated, the first information is sent to the network node that generates the original mobile trajectory prediction information to inform the network node that the mobile trajectory prediction information has been updated and the relevant information of the new mobile trajectory prediction information, so that the network node can promptly know that its own trajectory prediction information is replaced by the prediction information of other nodes, and obtain the effective first information for iterative optimization of the prediction model deployed by itself when it is replaced, and can also avoid the network node from being in a state of waiting for other nodes to feedback the real mobile trajectory information for a long time, causing unnecessary waste of resources, and effectively improving the cell switching performance and user experience.

[0085] As a preferred implementation, step S11, that is, sending the first information to the second network node, includes:

[0086] When there is a communication interface between the first network node and the second network node, sending first information to the second network node through the communication interface;

[0087] When there is no communication interface between the first network node and the second network node, the first information is forwarded to the second network node via an intermediate network node having a communication interface.

[0088] In an embodiment of the present invention, in the process of sending the first information to the second network node, if there is an interface (for example, an Xn interface) between the first network node A and the second network node, the first network node A can directly send the first information to the second network node; if there is no interface between the first network node A and the second network node, the first network node A can send the first information to other intermediate nodes for forwarding, and the intermediate node has an interface with the first network node A and the second network node respectively. The first network node can determine the forwarding target of the first information based on the identification information of the second network node in the first information.

[0089] As a preferred implementation, the relevant information of the new mobile trajectory prediction information includes at least one of the following information: time information, cause information, real mobile trajectory information and identification information of the second network node; wherein the time information is the generation time of the original mobile trajectory prediction information, and / or the generation time of the new mobile trajectory prediction information; the cause information is the triggered mobile trajectory prediction update condition; the real mobile trajectory information includes at least one of the following information: a real cell sequence within the range of the first network node, the previous real network node, the previous real cell, the next real network node, and the next real cell; the real network node is the node actually entered by the terminal, and the real cell is the cell actually entered by the terminal.

[0090] Specifically, the first information sent by the first network node A to the second network node includes relevant information of the new movement trajectory prediction information generated by the first network node A in addition to the indication information used to indicate that the first network node A has generated new movement trajectory prediction information predicted UE trajectory-2.

[0091] The time information is the generation time of the original movement trajectory prediction information predicted UE trajectory-1, and / or the generation time of the new movement trajectory prediction information predicted UE trajectory-2, which can be used to assist the second network node to iteratively optimize the performance of its AI model or the effective duration of the prediction information.

[0092] The reason information is used to indicate why the original prediction information is invalid or cannot continue to be sent to the subsequent target network node. The specific reasons may include but are not limited to: the UE mobile trajectory prediction information has expired, does not match the UE's actual mobile trajectory, and there are insufficient remaining prediction trajectories, etc., which helps the second network node to iterate its AI model performance according to the reason information.

[0093] The measured UE trajectory information is used to indicate the UE trajectory within the range of the first network node A and / or related to the first network node A (for example, the previous hop and next hop network nodes of the first network node A), that is, the information may include: the previous hop network node and / or cell identifier of the first network node A, one or more cell identifiers within the range of the first network node A and the UE's residence time in each cell, the next hop node and / or cell identifier of the first network node A (that is, the real network node and / or real cell determined by the first network node A for the UE).

[0094] It should be noted that the previous-hop network node and / or cell identification information of the first network node A can enable the second network node to learn about the network nodes before the network node and the network node, and the original prediction information is valid. The second network node can wait to obtain the real mobile trajectory information measured UE trajectory fed back by the relevant nodes, which is used to optimize the prediction performance of the AI ​​model. The next-hop network node and / or cell identification information of the first network node A can enable the second network node to learn whether the original prediction information is wrong and the real network node or real cell to which the UE actually switches, which is used to optimize the prediction performance of the AI ​​model, and also enables the second network node to learn that it no longer needs to wait for the real mobile trajectory information measured UE trajectory fed back by the target network node located after the first network node A in the original prediction information.

[0095] The identification information of the second network node is used to indicate the second network node that receives the first information, and at the same time, when the first network node A forwards the first information to the second network node through other intermediate nodes, indicates that the intermediate node forwarding the first information knows the identity information of the second network node that needs to receive the first information.

[0096] By adopting the technical means of the embodiments of the present invention, the content of the first information sent by the intermediate network node to the network node that generates the original mobile trajectory prediction information after generating new mobile trajectory prediction information is optimized, which is beneficial for the original network node to obtain useful first information and perform related operations for performance optimization of the AI ​​model, thereby improving the prediction accuracy of the mobile trajectory prediction information of the terminal, and improving the cell switching performance and user experience.

[0097] As a preferred embodiment, see Figure 4 , is a flow chart of a preferred information transmission method in an embodiment of the present invention. After receiving the first information, the second network node can update the mobile trajectory prediction model deployed by itself according to the first information.

[0098] In the embodiment of the present invention, after receiving the first information, the second network node may perform AI model prediction performance optimization iteration according to the first information and other relevant information, and the specific operations may be but are not limited to:

[0099] According to the indication information in the first information indicating that a new UE mobile trajectory prediction has been generated, the second network node can learn that its own prediction information may have prediction errors or validity period timeouts, and some target network nodes included in the original prediction information may not be able to feedback the real mobile trajectory information. Further, it can be determined that the AI ​​model prediction performance optimization iteration can be performed based on the real mobile trajectory information fed back by the target network node before the first network node A and the information of the next hop real network node fed back by the first network node A in combination with the real mobile trajectory information in the first information.

[0100] According to the reason value information in the first information, the second network node can learn the specific reason for the failure of the prediction information. For example, if the validity period of the prediction information has expired, there may be inaccurate validity period, or the validity period does not match the number of nodes included in the prediction information, or the prediction information predicts that the UE's expected residence time in each node or cell is inaccurate. The second network node can optimize the prediction performance of the AI ​​model in combination with the generation time / moment of the UE's mobile trajectory prediction in the first information or the time / moment and / or other information determined by the first network node A to generate new prediction information, and improve the prediction accuracy of the validity period, the number of predicted nodes, or the residence time of each node or cell. If the prediction information does not match the actual mobile trajectory of the UE, the second network node can optimize the prediction performance of the AI ​​model in combination with the actual mobile trajectory information and / or other information in the first information to improve the accuracy of the UE mobile trajectory prediction.

[0101] It should be noted that when the first network node A generates new mobile trajectory prediction information, the first network node A is a source node relative to its predicted subsequent target network node, and the above embodiment is also applicable to iterative optimization of the prediction model deployed by itself, which will not be elaborated here.

[0102] By adopting the technical means of the embodiments of the present invention, the relevant operations of the second network node for optimizing the performance of the AI ​​model after receiving the first information are optimized, which is beneficial to improving the prediction accuracy of the terminal's mobile trajectory prediction information and effectively improving the cell switching performance and user experience.

[0103] See also Figure 5 , is a schematic diagram of the structure of an information transmission device provided by an embodiment of the present invention. The embodiment of the present invention further provides an information transmission device 20, which is applied to a node with a mobile trajectory prediction capability. The device 20 includes:

[0104] The first information sending module 21 is used to send first information to the second network node; wherein the second network node is a network node that generates the original movement trajectory prediction information, and the first information includes indication information for indicating the updated movement trajectory prediction information and / or related information of the new movement trajectory prediction information.

[0105] The second information sending module 22 is used to send second information to a third network node; wherein the third network node is a network node located after the first network node on the actual movement trajectory or a network node located after the first network node in the new movement trajectory prediction information, and the second information includes relevant information of the original movement trajectory prediction information or relevant information of the new movement trajectory prediction information.

[0106] Preferably, the device 20 further comprises:

[0107] A prediction information receiving module, configured to receive original movement trajectory prediction information of the terminal generated by the second network node; wherein the movement trajectory prediction information includes a predicted target network node sequence and / or a target cell sequence within the range of each target network node;

[0108] The prediction information updating module is used to generate new movement trajectory prediction information when it is determined that the movement trajectory prediction update condition is met.

[0109] As a preferred implementation, the movement trajectory prediction update condition includes at least one of a first update condition, a second update condition and a third update condition; wherein,

[0110] The first update condition is that the movement trajectory prediction information exceeds the validity period;

[0111] The second update condition is that the movement trajectory prediction information does not match the actual movement trajectory of the terminal;

[0112] The third updating condition is that the remaining predicted trajectories in the movement trajectory prediction information are insufficient.

[0113] As a preferred implementation, determining whether the first update condition is met includes:

[0114] When the residence time is greater than the preset effective time of the original mobile trajectory prediction information, it is determined that the original mobile trajectory prediction information exceeds the validity period; wherein the residence time is the time during which the terminal has resided in the target cell within the target network node range in the original mobile trajectory prediction information.

[0115] Determining whether the second update condition is met includes:

[0116] When the next target network node or target cell predicted in the original moving trajectory prediction information is inconsistent with the next real network node or real cell actually switched by the terminal, it is determined that the original moving trajectory prediction information is inconsistent with the real moving trajectory of the terminal.

[0117] Determining whether the third update condition is met includes:

[0118] When the number of remaining nodes is less than a preset node number threshold, or the number of remaining cells is less than a preset cell number threshold, it is determined that the remaining predicted trajectories in the original mobile trajectory prediction information are insufficient; wherein the number of remaining nodes or the number of remaining cells is the number of target network nodes or target cells after the first network node in the original mobile trajectory prediction information.

[0119] As a preferred implementation, the relevant information of the new movement trajectory prediction information includes at least one of the following information: time information, cause information, real movement trajectory information and identification information of the second network node; wherein,

[0120] The time information is the generation time of the movement trajectory prediction information and / or the generation time of the new movement trajectory prediction information;

[0121] The reason information is the triggered moving trajectory prediction update condition;

[0122] The real mobile trajectory information includes at least one of the following information: a real cell sequence within the range of the first network node, the previous real network node, the previous real cell, the next real network node, and the next real cell; the real network node is the node actually entered by the terminal, and the real cell is the cell actually entered by the terminal.

[0123] As a preferred implementation, the first information sending module 21 is specifically used for:

[0124] When there is a communication interface between the first network node and the second network node, sending first information to the second network node through the communication interface;

[0125] When there is no communication interface between the first network node and the second network node, the first information is forwarded to the second network node via an intermediate network node having a communication interface.

[0126] By adopting the technical means of the embodiment of the present invention, in the scenario of multi-node terminal mobile trajectory prediction, the conditions for the intermediate network node to judge whether the prediction information needs to be updated, and the information interaction process between network nodes after the new prediction information is generated are optimized. After receiving the mobile trajectory prediction information predicted by the previous network node, the intermediate network node judges whether the original prediction information has expired according to the actual situation, and promptly provides more accurate and reliable prediction information when it is invalid or about to expire, effectively avoiding the subsequent target network node from performing operations such as resource reservation or switching decision based on erroneous prediction information. At the same time, after the new mobile trajectory prediction information is generated, the first information is sent to the network node that generates the original mobile trajectory prediction information to inform the network node that the mobile trajectory prediction information has been updated and the relevant information of the new mobile trajectory prediction information, so that the network node can promptly know that its own trajectory prediction information is replaced by the prediction information of other nodes, and obtain the effective first information for iterative optimization of the prediction model deployed by itself when it is replaced, and can also avoid the network node from being in a state of waiting for other nodes to feedback the real mobile trajectory information for a long time, causing unnecessary waste of resources, and effectively improving the cell switching performance and user experience.

[0127] It should be noted that an information transmission device provided in an embodiment of the present invention is used to execute all process steps of an information transmission method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0128] See also Figure 6 , is a structural diagram of an information transmission device provided in an embodiment of the present invention. The embodiment of the present invention also provides an information transmission device 30, including a processor 31, a memory 32, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the information transmission method described in any one of the above embodiments.

[0129] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the information transmission method as described in any one of the above embodiments.

[0130] An embodiment of the present invention further provides a computer program product, which includes a computer program or computer instructions. When the computer program or the computer instructions are executed by a processor, the information transmission method described in any one of the above embodiments is implemented.

[0131] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0132] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An information transmission method, characterized in that: Applied to a first network node, the method comprises: Sending first information to a second network node; wherein the second network node is a network node that generates original movement trajectory prediction information, and the first information includes indication information for indicating updated movement trajectory prediction information and / or relevant information of new movement trajectory prediction information; And / or, sending second information to a third network node; wherein the third network node is a network node located after the first network node on the actual mobile trajectory or a network node located after the first network node in the new mobile trajectory prediction information, and the second information includes relevant information of the original mobile trajectory prediction information or relevant information of the new mobile trajectory prediction information.

2. The information transmission method according to claim 1, characterized in that: The method further comprises: When it is determined that the movement trajectory prediction update condition is met, generating relevant information of new movement trajectory prediction information; the movement trajectory prediction update condition is at least one of the following conditions: The first update condition is that the original movement trajectory prediction information exceeds the validity period; The second update condition is that the original movement trajectory prediction information does not match the actual movement trajectory of the terminal; The third updating condition is that the remaining predicted trajectories in the original movement trajectory prediction information are insufficient.

3. The information transmission method according to claim 1, characterized in that: The relevant information of the new mobile trajectory prediction information includes a predicted target network node sequence, a target cell sequence within the range of each target network node and / or a residence time of the terminal in each cell.

4. The information transmission method according to claim 1, characterized in that: The first information includes at least one of the following information: time information, reason information, real movement track information and identification information of the second network node; wherein, The time information is the generation time of the original movement trajectory prediction information and / or the generation time of the new movement trajectory prediction information; The reason information is the triggered moving trajectory prediction update condition; The real mobile trajectory information includes at least one of the following information: a real cell sequence within the range of the first network node, the previous real network node, the previous real cell, the next real network node, and the next real cell; the real network node is the node actually entered by the terminal, and the real cell is the cell actually entered by the terminal.

5. The information transmission method according to claim 2, characterized in that: Before generating new movement trajectory prediction information and / or sending first information to the second network node when determining that the movement trajectory prediction update condition is met, the method further includes: Receive original movement trajectory prediction information of the terminal generated by the second network node; wherein the movement trajectory prediction information includes a predicted target network node sequence and / or a target cell sequence within the range of each target network node.

6. The information transmission method according to claim 2, characterized in that: Determining whether the first update condition is met includes: When the residence time is greater than the preset effective time of the original mobile trajectory prediction information, it is determined that the original mobile trajectory prediction information exceeds the validity period; wherein the residence time is the time during which the terminal has resided in the target cell within the target network node range in the original mobile trajectory prediction information.

7. The information transmission method according to claim 2, characterized in that: Determining whether the second update condition is met includes: When the next target network node or target cell predicted in the original moving trajectory prediction information is inconsistent with the next real network node or real cell actually switched by the terminal, it is determined that the original moving trajectory prediction information is inconsistent with the real moving trajectory of the terminal.

8. The information transmission method according to claim 2, characterized in that: Determining whether the third update condition is met includes: When the number of remaining nodes is less than a preset node number threshold, or the number of remaining cells is less than a preset cell number threshold, it is determined that the remaining predicted trajectories in the original mobile trajectory prediction information are insufficient; wherein the number of remaining nodes or the number of remaining cells is the number of target network nodes or target cells after the first network node in the original mobile trajectory prediction information.

9. The information transmission method according to claim 1, characterized in that: The sending the first information to the second network node includes: When there is a communication interface between the first network node and the second network node, sending first information to the second network node through the communication interface; When there is no communication interface between the first network node and the second network node, the first information is forwarded to the second network node via an intermediate network node having a communication interface.

10. The information transmission method according to any one of claims 1 to 9, characterized in that: After receiving the first information, the second network node can update the movement trajectory prediction model deployed by itself according to the first information.

11. An information transmission device, characterized in that: Applied to a first network node, the device includes: A first information sending module, configured to send first information to a second network node; wherein the second network node is a network node that generates original movement trajectory prediction information, and the first information includes indication information for indicating updated movement trajectory prediction information and / or relevant information of new movement trajectory prediction information; and / or, The second information sending module is used to send second information to a third network node; wherein the third network node is a network node located after the first network node on the actual movement trajectory or a network node located after the first network node in the new movement trajectory prediction information, and the second information includes relevant information of the original movement trajectory prediction information or relevant information of the new movement trajectory prediction information.

12. An information transmission device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the information transmission method according to any one of claims 1 to 10 when executing the computer program.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the information transmission method according to any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product comprises a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, the information transmission method according to any one of claims 1 to 10 is implemented.

Images