Network connection method and apparatus for target device during movement

Abstract

Disclosed are a network connection method and apparatus for a target device during movement. The network connection method for a target device during movement comprises: collecting, in real time, a device signal state of a target device during movement, a plurality of pieces of location data, and network data which matches each piece of location data; by means of a pre-trained target generation model, processing the device signal state, the plurality of pieces of location data, and the network data which matches each piece of location data, and when it is predicted that the target device will encounter a network anomaly at the next location along a movement route, obtaining optimal network data which matches data at the next location; and transmitting the optimal network data to the target device, such that the target device uses the optimal network data to perform network connection.

Description

Networking methods and apparatus for target device during movement

[0001] Citation of relevant applications

[0002] This disclosure claims the entire benefits of Chinese Patent Application No. 202411464645.0, filed on October 18, 2024, with the State Intellectual Property Office of the People's Republic of China, entitled "Networking Method and Apparatus During the Movement of Target Device", the entire contents of which are incorporated herein by reference.

[0003] field

[0004] This disclosure generally relates to the field of neural network technology, and more specifically to networking methods and apparatus for target devices during movement.

[0005] background

[0006] With the increasing prevalence of smart wearable devices and smart cars, these devices, which heavily rely on cellular networks, place extremely high demands on network stability in mobile scenarios. Since they are not used in a fixed location, users often use these devices in constantly changing mobile environments. This characteristic leads to frequent switching between base stations during movement. However, this frequent switching between base stations often causes network drops, signal instability, and other mobility issues, directly impacting user experience.

[0007] Traditional solutions are often limited by the established framework of the 3GPP (3rd Generation Partnership Project) protocol, such as re-searching or cell reselection after a network loss, which may take a long time to restore the network.

[0008] Overview

[0009] In a first aspect, this disclosure provides a networking method for a target device during movement, comprising:

[0010] Real-time acquisition of device signal status, multiple location data, and network data matching each location data during the target device's movement;

[0011] The device signal status, multiple location data, and network data matching each location data are processed by a pre-trained target generation model. When a network anomaly is predicted at the next location of the target device's movement path, the optimal network data matching the next location data is obtained.

[0012] The optimal network data is transmitted to the target device so that the target device can use the optimal network data to connect to the network.

[0013] In some implementations, when a network anomaly is predicted at the next location of the target device along its movement path, the optimal network data for matching the data at the next location includes:

[0014] A target route is generated based on multiple location data and network data matching each location data.

[0015] If a network anomaly is predicted at the next location in the target route based on the current device signal status, it is determined whether the target route belongs to a preset set of learned routes, wherein the set of learned routes includes multiple complete routes with network anomalies learned by the target generation model.

[0016] If the target route belongs to a preset set of learned routes, then a set route matching the target route is selected from the set of learned routes.

[0017] The next location data in the set route is determined based on the current location data of the target device, and the optimal network data matching the next location data is determined. The set route includes the optimal network data matching the next location data of each abnormal location.

[0018] In some implementations, after determining whether the target route belongs to a preset set of learned routes, the method further includes:

[0019] If the target route does not belong to the preset set of learned routes, the network data for the next location data is determined by cell reselection or network re-search after a network failure.

[0020] In some implementations, after the optimal network data is transmitted to the target device, the networking method for the target device during its movement further includes:

[0021] Obtain the device signal status result after the target device connects to the network using the optimal network data, wherein the device signal status result is used to indicate whether to shorten the network recovery time of the target device;

[0022] After the target device moves to the next location, the updated location data and the network data matching each location data are determined.

[0023] The model performs self-learning based on the device signal status results, the updated multiple location data, and the network data matched for each location data.

[0024] In some implementations, the pre-training process of the target generation model includes:

[0025] When the sample device moves repeatedly on a set route, the behavior log of the sample device for each move is obtained. The behavior log includes the signal status of the sample device, multiple sample location data, and network data matching each sample location data.

[0026] If network anomalies are detected on the set route based on the signal status of multiple sample devices, and the number of network anomalies exceeds a preset threshold, then the abnormal location data in the set route is determined.

[0027] Determine the candidate network data to match the next location data of the abnormal location data, wherein the candidate network data to match the next location data is not exactly the same each time the sample device moves;

[0028] Determine the sample device signal state corresponding to each candidate network data, and select the sample network data corresponding to the best device signal state as the optimal network data for the next position data matching.

[0029] In some implementations, determining abnormal location data in the defined route includes:

[0030] Determine the location of the sample device on the set route each time a network anomaly occurs, and record the number of times each location appears;

[0031] If the number of times the route location appears exceeds a preset number, the data of the route location will be regarded as abnormal location data.

[0032] In some implementations, predicting a network anomaly on the target route based on the current device signal status includes:

[0033] If the target device is detected to exhibit at least one of the following behaviors: cell reselection, network disconnection and re-search, signal strength less than the strength threshold, or device power consumption greater than the power consumption threshold, then a network anomaly is predicted to exist on the target route.

[0034] Secondly, this disclosure provides a networking device for the target device during its movement, comprising:

[0035] The acquisition module is configured to acquire in real time the device signal status, multiple location data, and network data matching each location data of the target device during its movement.

[0036] The processing module is configured to process the device signal state, the multiple location data, and the network data matching each location data using a pre-trained target generation model, and to obtain the optimal network data matching the next location data when it is predicted that a network anomaly will occur at the next location of the target device in its movement path; and

[0037] The transmission module is configured to transmit the optimal network data to the target device so that the target device can use the optimal network data to connect to the network.

[0038] Thirdly, this disclosure provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus.

[0039] Fourthly, this disclosure also provides a computer storage medium storing computer-executable instructions for executing the networking method during the movement of the target device as described in this disclosure.

[0040] In some implementations, when the target generation model predicts that the target device will experience a network anomaly at the next location based on the collected data, it transmits the optimal network data for that next location to the target device in advance. The target device then directly uses the optimal network data to connect to the network, avoiding unnecessary steps such as cell reselection (e.g., signal monitoring, information collection, cell reselection condition judgment, and cell priority calculation) and re-searching for the network after a network loss (e.g., detecting and confirming service interruption, initializing the reconnection process, and searching for available networks), thus shortening the network recovery time.

[0041] Brief description of the attached figures

[0042] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0043] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0044] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0045] Figure 1 is a schematic diagram of a network connection system provided in an embodiment of this disclosure during the movement of a target device;

[0046] Figure 2 is a flowchart of a networking method during the movement of a target device according to an embodiment of this disclosure;

[0047] Figure 3 is a flowchart comparing the optimized scheme provided in an embodiment of this disclosure with the traditional cell reselection scheme;

[0048] Figure 4 is a flowchart comparing the optimized solution provided in an embodiment of this disclosure with the traditional network disconnection and re-search solution;

[0049] Figure 5 is a schematic diagram of the overall process of using the target generation model provided in an embodiment of this disclosure;

[0050] Figure 6 is a schematic diagram of the structure of a networking device during the movement of a target device according to an embodiment of this disclosure; and

[0051] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0052] Detailed Explanation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0054] The following disclosure provides numerous different embodiments or examples for implementing various structures of this disclosure. To simplify this disclosure, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of this disclosure. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0055] In one embodiment of this disclosure, the networking method during the movement of the target device can be applied to a hardware environment consisting of device 101 and server 103 as shown in FIG1. ​​As shown in FIG1, server 103 is connected to device 101 through a network and can be used to provide services to the device. A database 105 can be set up on the server or independently of the server to provide data storage services for server 103. The aforementioned network includes, but is not limited to, wide area network, metropolitan area network or local area network.

[0056] In some implementations, the device provided in this disclosure may specifically be a module capable of communication functions or a terminal device containing such a module. The device relies on a cellular network during movement. The terminal device may be a mobile terminal, a smart wearable device, a smart car, or a shared bicycle. The mobile terminal may specifically be at least one of a mobile phone, a tablet computer, or a laptop computer. The smart wearable device may specifically be a smartwatch. The module may specifically be a wireless communication module, such as any one of a 2G communication module, a 3G communication module, a 4G communication module, a 5G communication module, or an NB-IoT communication module.

[0057] This disclosure provides a method for networking during the movement of a target device, which can be applied to a server or the target device to shorten network recovery time.

[0058] This disclosure provides a detailed explanation of an embodiment applied to a server, as shown in Figure 2. The method includes the following steps:

[0059] Step 201: Real-time acquisition of device signal status, multiple location data, and network data matching each location data during the target device's movement;

[0060] Step 202: Process the device signal status, multiple location data, and network data matching for each location using a pre-trained target generation model. When a network anomaly is predicted at the next location of the target device's movement path, obtain the optimal network data for matching the next location data.

[0061] Step 203: Transmit the optimal network data to the target device so that the target device can use the optimal network data to connect to the network.

[0062] In some implementations, when the target device moves along a route, the server collects the device signal status, multiple location data, and network data matching each location data in real time. Then, the above data is input into a pre-trained target generation model. The target generation model determines the current location of the target device and predicts that the target device will encounter network anomalies at the next location. The target generation model then processes the above data to obtain the optimal network data at the next location and transmits the optimal network data to the target device's modem. The target device then directly uses the optimal network data to connect to the network.

[0063] In some implementations, the mobile route includes multiple location data points, each with corresponding network data. This network data is at least one of a Public Land Mobile Network (PLMN), a frequency point, or a Physical Cell Identity (PCI). A PLMN is a network built and operated by a mobile network operator in a mobile communication system. It includes a core network, a radio access network, and user terminals, providing a wide range of mobile communication services to the public, such as voice calls, SMS, and data transmission. A frequency point refers to the specific frequency used by a wireless signal. Different frequencies correspond to different channels, used to distinguish and manage multiple wireless communication channels to avoid interference and conflicts. By selecting appropriate frequencies, the quality and efficiency of wireless communication can be improved. A PCI is used to uniquely identify a cell in an LTE (Long-Term Evolution Network) network. Each cell has a unique PCI value, used to distinguish and manage different cells. The PCI plays a crucial role in the LTE network, helping user equipment identify and connect to the correct cell, enabling efficient wireless communication.

[0064] In some implementations, device signal status includes network status, serving cell information, signal strength, and device power consumption. The following provides a detailed explanation of each device signal status.

[0065] Network status refers to the connection status between a device and a communication network. It typically includes the device's access status (e.g., connected, not connected), network type (e.g., 4G, 5G), IP address allocation, and data transmission rate. Network status reflects whether a device can successfully connect to the network and transmit data stably.

[0066] Serving cell information refers to the detailed information of the wireless cell that a device is currently connected to. In mobile communications, a cell is typically covered by a base station or a sector of a base station. Serving cell information includes the cell's identifier (such as PCI), frequency, etc. This information is crucial for device mobility and handover management because it helps devices smoothly hand over between different cells, maintaining communication continuity.

[0067] Signal strength refers to the strength of the wireless signal received by a device. If a network anomaly occurs, the signal strength of the target device will be greatly weakened.

[0068] Device power consumption refers to the electrical energy consumed by a device during operation. If a network anomaly occurs, the power consumption of the target device will increase significantly.

[0069] In some implementations, when the target generation model predicts that the target device will experience a network anomaly at the next location based on the collected data, it transmits the optimal network data for that next location to the target device in advance. The target device then directly uses the optimal network data to connect to the network, avoiding unnecessary steps such as cell reselection (e.g., signal monitoring, information collection, cell reselection condition judgment, and cell priority calculation) and re-searching for the network after a network loss (e.g., detecting and confirming service interruption, initializing the reconnection process, and searching for available networks), thus shortening the network recovery time.

[0070] One embodiment of this disclosure omits some unnecessary steps in both cell reselection and network re-search, as detailed below.

[0071] The traditional 3GPP steps for cell reselection are as follows: 1. Signal Monitoring: The mobile station continuously monitors the signal strength and system messages of the current serving cell and its neighboring cells. 2. Information Collection: Record and update the received signal level, system messages, and control messages of each neighboring cell. 3. Condition Judgment: Determine whether cell reselection is necessary based on preset triggering conditions and evaluation criteria. 4. Algorithm Calculation: If the reselection conditions are met, the mobile station uses a cell reselection algorithm to calculate the priority of each candidate cell. 5. Decision Execution: Based on the algorithm calculation results, select the neighboring cell with the highest priority as the new serving cell. Executing cell reselection includes updating the internal state and sending necessary signaling messages. 6. State Maintenance: The mobile station camps in the new serving cell and continues to monitor signal quality and system messages so that cell reselection can be performed again if needed.

[0072] For cell reselection, this embodiment replaces the key steps in the traditional process (1. signal monitoring, 2. information collection, 3. condition judgment, 4. algorithm calculation) with an AI model. The execution module is instructed to directly transmit the optimal network information obtained by the route learning module to the modem's underlying layer. In this way, the modem can pre-select the optimal cell as the target and directly select the cell based on the PCI, frequency point, and other cell information recommended by the AI ​​model, eliminating the need for steps including signal monitoring, information collection, condition judgment, and algorithm calculation, and avoiding the repetition of reselection actions.

[0073] Figure 3 is a flowchart comparing the optimized scheme and the traditional cell reselection scheme. It can be seen that by replacing all four steps in the traditional scheme with the control module in this embodiment, the network disconnection time is reduced.

[0074] The traditional 3GPP steps for reconnecting to the network after a service interruption are as follows: 1. Detect and confirm service interruption: The modem continuously monitors its connection status with the network. Once a service interruption is detected, the modem recognizes that it is currently in an OOS (Out of Service) state and prepares to begin the reconnection process. 2. Initialize the reconnection process: Once the service interruption is confirmed, the modem automatically initiates the reconnection process, attempting to reconnect to the network. 3. Search for available networks: The modem searches for available networks based on a preset network priority list (such as a PLMN priority list). Scanning frequency bands and selecting networks may take some time, depending on the modem's hardware performance and the current network environment. 4. Initiate a network registration request: After finding an available network, the modem sends a registration request to that network. 5. Restore network service: Once registration is successful, the modem regains network service, including data transmission, voice calls, and other functions. At this point, the modem exits the OOS state and resumes normal use. 6. Status maintenance: The mobile station camps in the new serving cell and continues to monitor the network status.

[0075] For network re-searching after a network outage, this embodiment replaces the key steps in the traditional process (1. detecting and confirming service interruption, 2. initializing the reconnection process, 3. searching for available networks) with an AI model. It instructs the execution module to use the optimal network cell as the registration target and directly search for and register the network using the PLMN, PCI, frequency point, etc. recommended by the AI ​​model. This eliminates the need for steps such as detecting and confirming service interruption, initializing the reconnection process, and searching for available networks, thus avoiding the repetition of the re-selection action.

[0076] Figure 4 is a flowchart comparing the optimized solution with the traditional network disconnection and re-search solution. It can be seen that by replacing all three steps in the traditional solution with the control module in this embodiment, the device's recovery time after a network disconnection is improved, minimizing the user's perception of the disconnection and enhancing the user experience.

[0077] In some implementations, obtaining the optimal network data for the next location data match includes the following steps.

[0078] Step S11: Generate the target route based on multiple location data and the network data matching each location data;

[0079] Step S12: If a network anomaly is predicted at the next location in the target route based on the current device signal status, then determine whether the target route belongs to the preset set of learned routes, wherein the set of learned routes includes multiple complete routes with network anomalies learned by the target generation model.

[0080] Step S13: If the target route belongs to the preset set of learned routes, then select the set route that matches the target route from the set of learned routes.

[0081] Step S14: Determine the next location data in the set route based on the current location data of the target device, and determine the optimal network data to match the next location data. The set route includes the optimal network data to match the next location data of each abnormal location.

[0082] In some implementations, the target generation model generates a target route based on multiple location data points and matching network data for each location. The location data represents key locations the target device might pass through during its movement, while the matching network data includes key parameters such as public terrestrial mobile networks, frequency bands, and physical cell identifiers. The target route generated by the target generation model is not necessarily a complete route. For example, if a user needs to cross five intersections to get from home to work, a target route can be generated when the user reaches the second intersection; this target route is only a part of the complete route.

[0083] In some implementations, the target generation model analyzes the current device signal status. If it detects that the target device is exhibiting at least one of the following behaviors: cell reselection, network drop and re-search, signal strength less than a strength threshold, or device power consumption greater than a power consumption threshold, it predicts that there will be a network anomaly at the next location on the target route.

[0084] In some implementations, the target generation model can identify multiple routes with network anomalies by learning and analyzing a large amount of data, and save these routes into a set of learned routes. This set not only includes the routes themselves, but also records the specific locations where network anomalies may occur on each route and the corresponding optimal network data.

[0085] In some implementations, as the target device moves along a target route, the target generation model determines in real time whether the current target route belongs to the learned route set. If it does not, it means that the target route is a new route, and the target generation model cannot predict the data for the next location and the matching network data. In this case, the target device can only rely on traditional cell reselection or network re-search methods to determine the network data for the next location.

[0086] In some implementations, if the current target route belongs to the set of learned routes, the target generation model can still select a complete set of routes that match the target route from the set, even if the routes are not complete. This set of routes not only includes all the locations that the target device may pass through, but also specifically marks the optimal network data that matches the next location for each abnormal location.

[0087] In some implementations, assuming a home-to-work route with five intersections, the third and fourth intersections are prone to network anomalies. When the target device is at the second intersection, the target generation model can accurately predict the impending network anomaly at the third intersection and transmit the optimal network data for that intersection to the target device in advance. Thus, when the device reaches the third intersection, it avoids the cumbersome process of searching for a new network or serving cell after a network outage and can directly connect, ensuring continuous and stable communication.

[0088] This dynamic network optimization method, based on a target generation model and a set of learned routes, can predict network anomalies at a certain location and transmit the optimal network data for the next location to the device in advance. The device does not need to go through the process of searching for a network or serving cell again after a network outage, and can directly connect to the network, shortening the duration of network anomalies and improving the user experience.

[0089] In some implementations, the target generation model comprises five modules: an equipment information recording module, a business monitoring module, a route learning module, a control module, and an execution module. The specific functions of each module are as follows.

[0090] Device information recording module: Deployed within the target device, responsible for collecting the target device's location data (location coordinates during device movement) and network data (PLMN, frequency point, PCI) for each location as it moves along the route.

[0091] Service monitoring module: Real-time monitoring of terminal device status (such as network status, serving cell information, signal strength, device power consumption, etc.).

[0092] Route learning module: It includes three functions. The first function is to construct a network route based on the network information and location data collected by the device information recording module. The second function is to determine which location on which route the device will experience an abnormal status, based on the status of the device recorded by the service monitoring module (such as network status, serving cell information, signal strength, device power consumption, etc.), and send the network abnormality result to the control module.

[0093] Control module: Determines whether the current route belongs to the route learning module. If it does, it sends an instruction to the execution module and transmits the relevant network data to the execution module when there is a potential network anomaly risk on the route.

[0094] Execution Module: Receives instructions from the control module and executes corresponding measures. Before the device reaches an area that may trigger cell reselection or network drop, it transmits optimal network information, including PLMN, frequency point, and PCI, to the device's modem layer. This operation aims to enable the modem to prioritize this optimal network information for network selection or cell camping, thereby avoiding unnecessary steps such as network measurement and re-searching after a network drop, ensuring the continuity and stability of the device's network.

[0095] In some implementations, after transmitting the optimal network data to the target device, the method further includes the following steps:

[0096] Step S21: Obtain the device signal status result after the target device connects to the network using the optimal network data, wherein the device signal status result is used to indicate whether to shorten the network recovery time of the target device;

[0097] Step S22: After the target device moves to the next location, determine the updated location data and the network data matching each location data; and

[0098] Step S23: Perform model self-learning based on the device signal status results, the updated multiple location data, and the network data matched for each location data.

[0099] In some implementations, the target device obtains a signal status result after moving to the next location and connecting to the network. This signal status result is a key indicator that reflects the network connection quality of the target device at that location. If the signal status result shows that the network recovery time has shortened, it indicates that the current network connection strategy is effective and can be continued or fine-tuned. Conversely, if the signal status result is unsatisfactory, the network connection strategy needs to be adjusted and optimized.

[0100] In some implementations, after the target device moves to the next location, multiple updated location data and network data matching each location data are determined. The updated location data is simply the addition of one location data, while the other original location data remain unchanged. These will serve as input data for the model's self-learning.

[0101] In some implementations, the model learns itself based on device signal status results, updated multiple location data, and network data matched to each location. During this process, the target generation model uses machine learning algorithms to analyze and process the input data, identifying factors that significantly impact network recovery time. By continuously adjusting and optimizing model parameters, the target generation model can gradually improve the accuracy and reliability of its predictions, thereby providing more precise and efficient network connectivity strategies for the target device.

[0102] In related technologies, when a network device moves along a fixed line, it may encounter network anomalies at fixed locations each time it moves along the line. Then, it will perform a complete cell reselection or network re-search for the anomaly. This disclosure, through the continuous self-learning mechanism of the model, can improve itself in response to abnormal network phenomena, realize the continuous optimization and improvement of the network connection strategy of the target device, improve the quality and efficiency of wireless communication, and enhance the user experience.

[0103] Figure 5 is a schematic diagram of the overall process used in the target generation model, including the following execution steps.

[0104] 1. Device registration with networks. As devices move, they may enter new network coverage areas or leave their original service area. In this case, the device needs to register with networks multiple times in order to establish connections with new networks and maintain communication.

[0105] 2. The device information recording module is responsible for collecting network data (PLMN, frequency point, PCI, etc.) and location data (location coordinates of the device during movement).

[0106] 3. The service monitoring module monitors the status of terminal devices in real time (such as network status, serving cell information, signal strength, device power consumption, etc.).

[0107] 4. The route learning module constructs a network route based on the information collected by the device information recording module and the service monitoring module, detects whether there are potential network anomaly risks at a certain location, and sends the network anomaly results to the control module.

[0108] 5. If the control module determines that there is no network anomaly, it returns to step 1. If a network anomaly is determined, it checks whether the current line belongs to a line already learned by the route learning module. If it does, it sends an instruction to the execution module and transmits the network data for the next location to the execution module.

[0109] 6. Before the device reaches an area that may trigger cell reselection or network drop, the execution module transmits the optimal network information, including PLMN, frequency point, PCI, etc., to the device's modem layer.

[0110] 7. After the execution module finishes, the device information recording module records the latest location data and network data, and the service monitoring module monitors the device signal status in real time and feeds the results back to the route learning module in step 4 and the control module in step 5 to train the machine learning algorithm and improve the intelligent model.

[0111] In some implementations, this disclosure utilizes AI algorithms to monitor the operating route of the device and the quality of network services in real time and make intelligent decisions. This can help users select the optimal network data in advance on abnormal network routes, effectively reduce the number of cell reselections, shorten the time for network loss and re-search, and effectively reduce users' perception of network anomalies, thereby improving the user experience.

[0112] Furthermore, in traditional solutions, the solution to poor serving cell signal is to trigger a cell reselection mechanism. This mechanism involves steps such as terminal measurement, network policy, and terminal decision-making. Frequent measurement and reselection are not only time-consuming but also significantly increase device power consumption. The solution to network connection interruption is to trigger a network disconnection re-search mechanism. The entire network disconnection re-search process involves detecting network disconnection, triggering re-search, searching for available networks, attempting to connect, and handling connection success or failure. Each network disconnection re-search requires executing the complete steps, and this mechanism also suffers from the drawbacks of long execution time and increased device power consumption. This disclosure can also reduce device power consumption by shortening the network recovery time.

[0113] In some implementations, the pre-training process of the target generation model includes the following steps.

[0114] Step S31: When the sample device moves repeatedly on the set route, obtain the behavior log of the sample device for each move. The behavior log includes the signal status of the sample device, multiple sample position data, and network data matching each sample position data.

[0115] Step S32: If network anomalies are detected on the set route based on the signal status of multiple sample devices, and the number of network anomalies exceeds a preset threshold, then the abnormal location data in the set route is determined.

[0116] Step S33: Determine the candidate network data for the next location data matching of the abnormal location data, wherein the candidate network data for the next location data matching of the sample device is not completely the same each time the device moves; and

[0117] Step S34: Determine the sample device signal state corresponding to each candidate network data, and select the sample network data corresponding to the best device signal state as the optimal network data for the next location data matching.

[0118] To ensure the accuracy and reliability of the target generation model, it needs to be adequately pre-trained. This process typically involves repeatedly moving the sample device along a set route and collecting behavioral logs for each movement. These logs contain rich information, such as the signal status of the sample device, data from multiple sample locations, and network data matched to each location, providing a solid foundation for subsequent analysis and training.

[0119] It is worth noting that the sample device may use different network data at the same location each time it moves. This diversity allows for the recording of the device signal status at that location under different network data, thus facilitating the selection of the optimal network data for that same location in the future.

[0120] The server acquires signal states from multiple sample devices as they move. Analysis of these signal states reveals anomalies such as multiple cell reselections, multiple network drops and re-searches, multiple signal decreases, or multiple increases in power consumption, indicating multiple network anomalies on that line. To further pinpoint the location of the anomalies, the server queries the location of the sample device each time a network anomaly occurs and identifies the repeatedly occurring locations as the anomaly locations.

[0121] In some implementations, it is assumed that the sample device travels along a set route 100 times, and network anomalies occur 80 of those times. Of these 80 anomalies, 77 occur at the third intersection, while the remaining three occur at the first, second, and fourth intersections, respectively. Analysis suggests that these three anomalies may be coincidental, and the third intersection is identified as the anomaly location.

[0122] Once an anomaly location on the set route is identified, the optimal network data needs to be selected for the next location. Since multiple candidate network data points may match the same location, the server queries the sample device signal status at that location each time the device moves. By comparing the device signal status under different network data points, the candidate network data with the best sample device signal status is selected as the optimal network data.

[0123] During the pre-training process of the target generation model, the locations where network anomalies may occur are identified by recording and analyzing the repeated movements of sample devices along a set route, and the optimal network data for the next location is determined.

[0124] In some implementations, the location of the target generation model is flexible; it can be integrated inside the target device or deployed on a remote server, such as in the cloud. This design allows the target generation model to adapt to different use cases and needs.

[0125] When a target generation model is set up in a target device, that device itself becomes a combination of the sample device and the target device. In this case, the target generation model is trained based on routes repeatedly traveled by the device. After training, the target generation model can be directly applied to the target device to provide services to the device itself. This self-learning and self-optimization capability greatly improves the stability and communication efficiency of the target device in complex network environments.

[0126] If the target generation model is hosted on a server, the sample devices and the target devices can be different. In this case, the target generation model can be trained based on network route data from multiple sample devices, resulting in a more comprehensive and generalized network optimization model. This model can provide services not only to a single target device but also to other devices, such as tourist routes and high-speed rail lines. By deploying the target generation model on a cloud server, resource sharing and optimization can be achieved. Multiple devices can jointly utilize this model to improve their network connection quality and stability. Simultaneously, the powerful computing and storage capabilities of the cloud server provide strong support for the training and application of the target generation model.

[0127] This disclosure provides a networking device for the target device during movement, as shown in Figure 6. The device includes:

[0128] The acquisition module 601 is configured to acquire in real time the device signal status, multiple location data, and network data matching each location data of the target device during its movement.

[0129] Processing module 602 is configured to process device signal status, multiple location data, and network data matching each location data using a pre-trained target generation model, and to obtain the optimal network data matching the next location data when a network anomaly is predicted to occur at the next location of the target device in its movement path; and

[0130] The transmission module 603 is configured to transmit optimal network data to the target device so that the target device can use the optimal network data to connect to the network.

[0131] In some implementations, the processing module 602 is configured as follows:

[0132] Generate a target route based on multiple location data and network data matching each location data;

[0133] If a network anomaly is predicted at the next location in the target route based on the current device signal status, it is determined whether the target route belongs to the preset set of learned routes. The set of learned routes includes multiple complete routes with network anomalies learned by the target generation model.

[0134] If the target route belongs to the preset set of learned routes, then select the set route that matches the target route from the set of learned routes;

[0135] The next location data in the set route is determined based on the current location data of the target device, and the optimal network data matching the next location data is determined. The set route includes the optimal network data matching the next location data of each abnormal location.

[0136] In some implementations, the networking device during the movement of the target device is further configured to:

[0137] If the target route does not belong to the preset set of learned routes, the network data for the next location will be determined by cell reselection or network re-search after a network failure.

[0138] In some implementations, the device is also configured to:

[0139] Obtain the device signal status result after the target device connects to the network using the optimal network data. The device signal status result is used to indicate whether to shorten the network recovery time of the target device.

[0140] After the target device moves to the next location, the updated location data and the network data matching each location data are determined; and

[0141] The model learns itself based on the device signal status results, updated multiple location data, and network data matched for each location data.

[0142] In some implementations, the networking device during the movement of the target device is further configured to:

[0143] When the sample device moves repeatedly on the set route, the behavior log of the sample device for each move is obtained. The behavior log includes the signal status of the sample device, multiple sample location data, and network data matching each sample location data.

[0144] If network anomalies are detected on the set route based on the signal status of multiple sample devices, and the number of network anomalies exceeds a preset threshold, then the abnormal location data in the set route is determined.

[0145] Determine the candidate network data for the next location data matching of the abnormal location data, wherein the candidate network data for the next location data matching of the sample device is not completely the same each time the device moves;

[0146] Determine the sample device signal state corresponding to each candidate network data, and select the sample network data corresponding to the best device signal state as the optimal network data for the next location data matching.

[0147] In some implementations, the networking device during the movement of the target device is further configured to:

[0148] Determine the location of the sample device on the set route each time a network anomaly occurs, and record the number of times each route location appears;

[0149] If the number of times a route location appears exceeds a preset number, the route location data will be considered as abnormal location data.

[0150] In some implementations, the device is also configured to:

[0151] If the target device is detected to exhibit at least one of the following behaviors: cell reselection, network disconnection and re-search, signal strength less than the strength threshold, or device power consumption greater than the power consumption threshold, then a network anomaly is predicted to exist on the target route.

[0152] As shown in FIG7, this embodiment of the present disclosure provides an electronic device, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 communicate with each other through the communication bus 704.

[0153] Memory 703 is configured to store computer programs;

[0154] When the processor 701 is configured to execute a program stored in the memory 703, it implements the networking method for the target device during movement as described in this disclosure.

[0155] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the networking method for the target device during movement as described in this disclosure.

[0156] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0158] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also mean including the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0159] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for networking during the movement of the target device, comprising: Real-time acquisition of device signal status, multiple location data, and network data matching each location data during the target device's movement; The device signal status, multiple location data, and network data matching each location data are processed by a pre-trained target generation model. When it is predicted that a network anomaly will occur at the next location of the target device in the movement route, the optimal network data matching the next location data is obtained. as well as The optimal network data is transmitted to the target device so that the target device can use the optimal network data to connect to the network.

2. The networking method for a target device during movement as described in claim 1, wherein when it is predicted that a network anomaly will occur at the next location of the target device in the movement route, obtaining the optimal network data for data matching at the next location includes: A target route is generated based on multiple location data and network data matching each location data. If a network anomaly is predicted at the next location in the target route based on the current device signal status, it is determined whether the target route belongs to a preset set of learned routes, wherein the set of learned routes includes multiple complete routes with network anomalies learned by the target generation model. If the target route belongs to a preset set of learned routes, then a set route matching the target route is selected from the set of learned routes. The next location data in the set route is determined based on the current location data of the target device, and the optimal network data matching the next location data is determined. The set route includes the optimal network data matching the next location data of each abnormal location.

3. The networking method during the movement of the target device as described in claim 2, wherein after determining whether the target route belongs to a preset set of learned routes, the method further includes: If the target route does not belong to the preset set of learned routes, the network data for the next location data is determined by cell reselection or network re-search after a network failure.

4. The networking method for a target device during movement as described in any one of claims 1 to 3, wherein after transmitting the optimal network data to the target device, the method further comprises: Obtain the device signal status result after the target device connects to the network using the optimal network data, wherein the device signal status result is used to indicate whether to shorten the network recovery time of the target device; After the target device moves to the next location, updated location data and network data matching each location data are determined; and The model performs self-learning based on the device signal status results, the updated multiple location data, and the network data matched for each location data.

5. The networking method during the movement of the target device as described in claim 1, wherein the pre-training process of the target generation model includes: When the sample device moves repeatedly on a set route, the behavior log of the sample device for each move is obtained. The behavior log includes the signal status of the sample device, multiple sample location data, and network data matching each sample location data. If network anomalies are detected on the set route based on the signal status of multiple sample devices, and the number of network anomalies exceeds a preset threshold, then the abnormal location data in the set route is determined. Determine the candidate network data to match the next location data of the abnormal location data, wherein the candidate network data to match the next location data is not exactly the same each time the sample device moves; Determine the sample device signal state corresponding to each candidate network data, and select the sample network data corresponding to the best device signal state as the optimal network data for the next position data matching.

6. The networking method for the target device during movement as described in claim 5, wherein determining abnormal location data in the set route includes: Determine the location of the sample device on the set route each time a network anomaly occurs, and record the number of times each location appears; If the number of times the route location appears exceeds a preset number, the data of the route location will be regarded as abnormal location data.

7. The networking method for a target device during movement as described in any one of claims 2 to 6, wherein predicting a network anomaly on the target route based on the current device signal status includes: If the target device is detected to exhibit at least one of the following behaviors: cell reselection, network disconnection and re-search, signal strength less than the strength threshold, or device power consumption greater than the power consumption threshold, then a network anomaly is predicted to exist on the target route.

8. A networking device during the movement of the target equipment, comprising: The acquisition module is configured to acquire in real time the device signal status, multiple location data, and network data matching each location data of the target device during its movement. The processing module is configured to process the device signal status, the multiple location data, and the network data matched by each location data through a pre-trained target generation model, and to obtain the optimal network data for the next location data when it is predicted that a network anomaly will occur at the next location of the target device in the moving route. The transmission module is configured to transmit the optimal network data to the target device so that the target device can use the optimal network data to connect to the network.

9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein, The processor, the communication interface, and the memory communicate with each other via the communication bus; Memory, configured to store computer programs; When a processor is configured to execute a program stored in memory, it implements the networking method during the movement of the target device as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the networking method for a target device during movement as described in any one of claims 1 to 7.

Images