Network search method and related products

Abstract

The embodiment of the invention relates to the technical field of communication, and discloses a network search method and related products, the method is applied to electronic equipment, and the method comprises the following steps: collecting service cell sequence information corresponding to the electronic equipment under the condition that the electronic equipment enters a target geofence; according to the service cell sequence information, a transit state corresponding to the electronic equipment is predicted, and the transit state is used for representing whether the position of the electronic equipment moves from the first area to the second area; if the transit state characterizes that the position of the electronic device moves from the first region to the second region, a public land mobile network (PLMN) of the second region is searched. By implementing the embodiment of the invention, the PLMN of the second region can be searched in advance under the condition of predicting that the electronic equipment is about to move from the first region to the second region, so that the switching speed of the PLMN is improved, and the network quality of the electronic equipment is further ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, in particular to a network search method and related products. BACKGROUND

[0002] To realize the online function, one way for the electronic device is to access a public land mobile network (PLMN).

[0003] In practice, it is found that when the electronic device moves from one area to another area, the network quality of the electronic device may be affected due to slow switching of the PLMN. SUMMARY

[0004] Embodiments of the present application disclose a network search method and related products, which can search the PLMN of a second area in advance in the case of predicting that the electronic device will move from a first area to the second area, so as to improve the switching speed of the PLMN and further ensure the network quality of the electronic device.

[0005] In a first aspect, the present application discloses a network search method, applied to an electronic device, and the method comprises:

[0006] In the case that the electronic device enters a target geofence, service cell sequence information corresponding to the electronic device is collected;

[0007] According to the service cell sequence information, a transit state corresponding to the electronic device is predicted, and the transit state is used to represent whether the location of the electronic device moves from a first area to a second area;

[0008] If the transit state represents that the location of the electronic device moves from the first area to the second area, a public land mobile network (PLMN) of the second area is searched.

[0009] In a second aspect, the present application discloses a network search device, applied to an electronic device, and the device comprises:

[0010] A collection unit, configured to collect service cell sequence information corresponding to the electronic device in the case that the electronic device enters a target geofence;

[0011] A prediction unit, configured to predict a transit state corresponding to the electronic device according to the service cell sequence information, and the transit state is used to represent whether the location of the electronic device moves from a first area to a second area;

[0012] The search unit is configured to search for the Public Land Mobile Network (PLMN) in the second region when the transit status indicates that the location of the electronic device has moved from the first region to the second region.

[0013] The third aspect of this application discloses an electronic device, including: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the network search method disclosed in the first aspect of this application.

[0014] The fourth aspect of this application discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the network search method disclosed in the first aspect of this application.

[0015] The fifth aspect of this application discloses a computer program product that, when run on a computer, causes the computer to perform some or all of the steps of any method of the first aspect of this application.

[0016] The sixth aspect of this application discloses an application publishing platform for publishing computer program products, wherein when the computer program products are run on a computer, the computer performs some or all of the steps of any one of the methods of the first aspect of this application.

[0017] Compared with related technologies, the embodiments of this application have the following beneficial effects:

[0018] In this embodiment, when an electronic device enters a target geofence, the serving cell sequence information corresponding to the electronic device can be collected. It is understood that the serving cell sequence information includes the serving cells where the electronic device has historically resided, which can characterize the movement trajectory of the electronic device. Based on this serving cell sequence information, the transit status of the electronic device can be predicted. The transit status indicates whether the electronic device's location has moved from a first region to a second region. If the transit status indicates that the electronic device's location has moved from the first region to the second region, the PLMN of the second region can be searched in advance to facilitate the electronic device's rapid switch to the PLMN of the second region during transit. This avoids prolonged periods of low network quality or no service for the electronic device during transit, thereby ensuring the network quality of the electronic device. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a web search method disclosed in an embodiment of this application;

[0021] Figure 2 This is a flowchart illustrating another web search method disclosed in an embodiment of this application;

[0022] Figure 3 This is a flowchart illustrating another web search method disclosed in an embodiment of this application;

[0023] Figure 4 This is a flowchart illustrating another web search method disclosed in an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of the structure of a network search device disclosed in an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] It should be noted that the terms "first," "second," "third," and "fourth," etc., used in the specification and claims of this application are used to distinguish different objects, not to describe a specific order. The terms "comprising" and "having," and any variations thereof, in the embodiments of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0028] This application discloses a network search method and related products, which can search for the PLMN in the second region in advance when it is predicted that an electronic device will move from the first region to the second region, so as to improve the switching speed of the PLMN and thus ensure the network quality of the electronic device.

[0029] The technical solution of this application will be described in detail below with reference to specific embodiments.

[0030] To more clearly describe the network search method disclosed in the embodiments of this application, the network switching method in related technologies will be described first.

[0031] In related technologies, when an electronic device is located in the boundary area between a first region and a second region, both the Visited Public Land Mobile Network (VPLMN) and the Home Public Land Mobile Network (HPLMN) will simultaneously cover the boundary area where the electronic device is currently located. Here, the VPLMN is the PLMN of the second region that the electronic device will visit, and the HPLMN is the PLMN of the first region where the electronic device is currently located, and the HPLMN is also the PLMN of the electronic device's home region.

[0032] As electronic devices leave the country (e.g., moving from region 1 to region 2), HPLMN coverage decreases while VPLMN coverage increases. Electronic devices then need to roam from HPLMN to VPLMN to switch PLMNs.

[0033] In inbound scenarios (e.g., when an electronic device moves from a second region to a first region), the electronic device needs to switch from the VPLMN to the HPLMMN. There are generally two switching methods: one is to re-search for the HPLMMN after the VPLMN loses connection; the second is to search for a high-priority PLMN. The electronic device's Subscriber Identification Module (SIM) card is usually configured with a high-priority PLMN search timer, with a duration between 6 minutes and 8 hours. When the electronic device connects to the VPLMN, it will periodically search for a high-priority PLMN according to the timer's set duration, thus returning to the HPLMMN. The high-priority PLMN can include the PLMN of the electronic device's home region (e.g., the HPLMMN) or other custom PLMNs.

[0034] In practice, it has been found that for outbound scenarios, electronic devices need to go through a process of weak signal and no service, resulting in slow roaming speeds (i.e., slow switching speeds from HPLMN to VPLMN), thus causing a poor network experience for users. In addition, in inbound scenarios, when electronic devices are in border areas, due to the better network signal of VPLMN, the electronic devices can continuously connect to VPLMN, making it difficult for them to lose network connection and connect to the home HPLMN. Furthermore, the default search interval of the high-priority PLMN search timer is relatively long, causing electronic devices to remain in VPLMN for a long time even when they are in the HPLMN coverage area, resulting in slow speeds to return to HPLMN. This does not conform to users' network usage habits, thus reducing the user's network experience.

[0035] The network search method disclosed in this application can be applied to various electronic devices, including but not limited to: portable electronic devices such as mobile phones and tablets, wearable devices such as smartwatches and smart bracelets, or other devices with communication functions, which are not limited here.

[0036] Optionally, when an electronic device enters a target geofence, its corresponding serving cell sequence information can be collected. This serving cell sequence information includes the serving cells the electronic device has historically resided in, representing its movement trajectory. Based on this information, the transit status of the electronic device can be predicted. The transit status indicates whether the electronic device has moved from a first region to a second region. If the transit status indicates a move from the first to the second region, the Public Land Mobile Network (PLMN) of the second region can be searched. This allows the electronic device to quickly switch to the PLMN of the second region during transit, avoiding prolonged periods of low network quality or no service, thus ensuring network quality. Furthermore, the HPLMN of the electronic device's home region can be searched in advance upon entry, enabling a quick switchback to the HPLMN upon entry, aligning with user network usage habits and improving the user's network experience.

[0037] Based on this, the network search method and related products disclosed in the embodiments of this application will be introduced below.

[0038] Please see Figure 1 , Figure 1 This is a flowchart illustrating a network search method disclosed in an embodiment of this application. Optionally, this method can be applied to the aforementioned electronic device or other executing entities, and is not limited thereto. Optionally, the method may include the following steps:

[0039] 102. When an electronic device enters the target geofence, collect the serving cell sequence information corresponding to the electronic device.

[0040] In this embodiment, the target geofence can correspond to a target area, and the target geofence is used to determine whether an electronic device enters the target area. Optionally, the target area can be a border area between multiple regions, such as a border area between two or three countries, or a border area between different regions of the same country, etc., which is not limited here.

[0041] Optionally, the border area may include port areas, border line areas, etc., without limitation. Among them, the port area refers to a transportation hub with infrastructure and inspection and supervision agencies, which is responsible for inspecting and providing services for the legal entry and exit of personnel, goods and means of transport into and out of the country (customs, border).

[0042] Optionally, the target geofence can be set by the developers based on extensive development experience. The target geofence can be stored in advance on the electronic device or on the server corresponding to the electronic device, without any limitation.

[0043] In some optional embodiments, the target geofence may be generated based on pre-collected big data. Optionally, the pre-collected big data may include cell sequence information, geographic coordinate information, etc., for the border area, and is not limited thereto. The cell sequence information may include various network parameters of the cell, including but not limited to: Radio Access Technology (RAT) information, Absolute Radio Frequency Channel Number (ARFCN) information, Physical Cell Identity (PCI), Tracking Area Code (TAC), Cell Identity (CID), Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Mobile Country Code (MCC), Mobile Network Code (MNC), and one or more of Signal-to-Interference plus Noise Ratio (SINR) and dwell time, and is not limited thereto.

[0044] RAT refers to the technologies and protocols that enable communication between user equipment (UE) and radio access network (RAN), including 2G / 3G / 4G / 5G, Wi-Fi, WiMAX, etc.

[0045] ARFCN is a unique identifier for a radio frequency channel, used for initial cell search and frequency planning.

[0046] PCI is used to uniquely identify a cell at the physical layer and is determined by the primary synchronization signal (PSS) and secondary synchronization signal (SSS).

[0047] A TAC is used to identify a tracking area. Multiple cells can belong to the same TAC. It is the basic unit of location management and paging.

[0048] A CID is a globally unique identifier assigned to each cell in a network, used for network management and cell identification.

[0049] RSRP is the reference signal power from the serving cell measured by the terminal, reflecting the signal strength, and is measured in dBm.

[0050] RSRQ is a measure of the quality of the reference signal, which is the ratio of RSRP to RSSI, measured in dB, and is used for cell selection and handover.

[0051] MCC consists of three digits and is used to uniquely identify a country or region;

[0052] MNC consists of two or three digits and is used to identify a mobile network operator within a country.

[0053] SINR is a key indicator for measuring signal quality. It represents the ratio of useful signal to interference and noise. The higher the value, the better the channel quality.

[0054] Dwell time refers to the duration for which an electronic device is connected to the corresponding cell.

[0055] In a cellular network, a cell is the basic coverage unit that divides a geographical area. Each cell is served by a base station or a portion of a base station (such as a sector antenna). It is the smallest manageable unit of service in mobile communications, and electronic devices can establish connections and communicate with the network within a cell.

[0056] In one optional embodiment, the target geofence may contain multiple cell units, each cell unit containing N second cells, where N can be an integer greater than or equal to 2; optionally, the combination of N second cells contained in each cell unit is different.

[0057] For example, the target geofence may include: {{second cell A, second cell B}, {second cell C, second cell D}, {second cell B, second cell C}...{second cell D, second cell E}}, without limitation.

[0058] Each second cell may include one or more first network parameters, which may include one or more of the various network parameters described above. For example, the first network parameters may include a combination of MCC, MNC, TAC, and CID, such as 460|00|1|111, which is not limited here.

[0059] Optionally, the electronic device can collect N first cells where the electronic device continuously resides, and match the N first cells with each cell unit contained in the target geofence in sequence; if the N first cells match any cell unit among the multiple cell units contained in the target geofence, it is determined that the electronic device has entered the target geofence.

[0060] Optionally, if the electronic device matches N first cells with all N second cells contained in any cell cell, it can determine that N first cells match the cell cell. Optionally, if the electronic device matches the first network parameters of a first cell with the first network parameters of a second cell, it can determine that the first cell and the second cell are matched.

[0061] By implementing the above method, electronic devices can generate target geofences based on the information of a second cell near the border area. Then, it can determine whether the electronic device has entered the target geofence based on whether the first cell where the electronic device is stationed matches the second cell of the target geofence. This method can efficiently and stably determine whether the electronic device has entered the target geofence.

[0062] In some alternative embodiments, the target geofence may include multiple target geographic coordinates, which may be multiple geographic coordinates contained within the border area. Optionally, the multiple geographic coordinates may include multiple geographic coordinates corresponding to the regional outline of the border area, and / or multiple geographic coordinates within the border area, which is not limited herein.

[0063] Optionally, the electronic device can obtain its real-time geographic coordinates; if the real-time geographic coordinates of the electronic device match one or more geographic coordinates of the target geofence (which may contain multiple target geographic coordinates), then it can be determined that the electronic device has entered the target geofence.

[0064] By implementing the above method, electronic devices can determine whether they have entered a target geofence by using their real-time geographic coordinates. This method can efficiently and stably determine whether an electronic device has entered a target geofence, and it is easy to implement, thus reducing the difficulty and cost of implementation.

[0065] In this embodiment, when an electronic device determines that it has entered a target geofence, it can collect the serving cell sequence information corresponding to the electronic device. The serving cell corresponding to the electronic device can be a cell where the electronic device has camped; the serving cell sequence information can include second network parameters of multiple serving cells where the electronic device has camped. Optionally, the second network parameters can include one or more of the network parameters described above. In one embodiment, the second network parameters can include one or more of RAT, ARFCN, PCI, TAC, CID, RSRP, RSRQ, and camping duration, which are not limited here.

[0066] Optionally, the multiple serving cells included in the serving cell sequence information can be serving cells located in the same region. Optionally, the multiple serving cells can be serving cells corresponding to the first region. For example, if the electronic device is at a border crossing from country A to country B, then the multiple serving cells included in the serving cell sequence information all belong to serving cells of country A; and if the electronic device is at a border crossing from country B back to country A, then the multiple serving cells included in the serving cell sequence information all belong to serving cells of country B, without limitation.

[0067] Using the above method, the electronic device can collect the serving cell sequence information corresponding to the current first region before it can collect the cells of the second region it is about to visit. This information can then be used to predict whether the electronic device will move from the first region to the second region.

[0068] 104. Based on the serving cell sequence information, predict the transit status of the electronic device. The transit status is used to characterize whether the location of the electronic device has moved from the first region to the second region.

[0069] In this embodiment, the serving cells in the serving cell sequence information can be ordered according to the order of their dwell times. Then, the electronic device can determine the order in which it has successively stayed in the serving cells based on the serving cell sequence information, and predict the corresponding transit status of the electronic device based on the order of the served cells it has stayed in.

[0070] It is understandable that the order in which electronic devices have camped on serving cells can reflect their movement trajectory and direction of behavior. Therefore, the transit status of electronic devices can be predicted based on the order in which they have camped on serving cells.

[0071] For example, if an electronic device stays in the following cells in sequence during a single transit: cell a (cell in the first region), cell b (cell in the first region), cell c (cell in the first region), and cell d (cell in the second region), then if the serving cell sequence information is: cell a (cell in the first region), cell b (cell in the first region), and cell c (cell in the first region), then it can be predicted that the electronic device will move from the first region to the second region.

[0072] In this embodiment of the application, the transit status of the electronic device can be predicted by using the serving cell sequence information of the first region before the electronic device has passed through the territory and before cell information of the second region to which it is going has been collected.

[0073] In this embodiment of the application, the predicted transit status represents the possibility that the electronic device may be moved from the first region to the second region in the future, rather than representing that the electronic device has already been moved from the first region to the second region.

[0074] The first region and the second region can be different countries or regions; or the first region and the second region can be different regions of the network's MCC; or the first region and the second region can be different regions of the same country, without any limitation.

[0075] 106. If the transit status indicates that the location of the electronic device has moved from the first region to the second region, then search for the public land mobile network (PLMN) in the second region.

[0076] In this embodiment of the application, if the predicted transit status indicates that the location of the electronic device has moved from the first region to the second region, it means that the electronic device may be about to move to the second region. In this case, the electronic device can search for the PLMN of the second region in advance before the electronic device enters the second region.

[0077] In this embodiment, when an electronic device finds a PLMN in the second region, it can switch to the PLMN in the second region without moving to the second region. This avoids the electronic device experiencing low network quality or no service for an extended period, thus ensuring the network quality of the electronic device.

[0078] By implementing the methods disclosed in the above embodiments, when an electronic device enters a target geofence, it can collect the serving cell sequence information corresponding to the electronic device. It is understood that the serving cell sequence information includes the serving cells where the electronic device has historically resided, which can characterize the movement trajectory of the electronic device. Based on this serving cell sequence information, the transit status of the electronic device can be predicted. The transit status indicates whether the electronic device's location has moved from a first region to a second region. If the transit status indicates that the electronic device's location has moved from the first region to the second region, the PLMN of the second region can be searched in advance to facilitate the electronic device's rapid switching to the PLMN of the second region during transit. This avoids prolonged periods of low network quality or no service for the electronic device during transit, thereby ensuring the network quality of the electronic device.

[0079] Please see Figure 2 , Figure 2 This is a flowchart illustrating another network search method disclosed in an embodiment of this application. Optionally, this method can be applied to the aforementioned electronic device or other executing entities, and is not limited thereto. Optionally, the method may include the following steps:

[0080] 202. When an electronic device enters the target geofence, collect the serving cell sequence information corresponding to the electronic device.

[0081] As an optional implementation, if the number of cells included in the serving cell sequence information collected within the fourth time period is greater than or equal to a number threshold, the electronic device can predict the corresponding transit status based on the serving cell sequence information.

[0082] The fourth duration can be set by developers based on extensive development experience; typical values ​​may include 25 minutes, 30 minutes, or 40 minutes, etc., and are not limited here. The quantity threshold can also be set by developers based on extensive development experience, and is not limited here.

[0083] By implementing the above method, electronic devices can predict the transit status of their corresponding devices based on the service cell sequence information, provided that a sufficient number of serving cell information has been collected. This ensures that the data used for prediction is sufficiently rich, thereby improving the accuracy of the subsequent predicted transit status.

[0084] In one optional embodiment, the quantity threshold can be greater than or equal to the number of cells required as input to the target prediction model. It is understood that when an electronic device uses the target prediction model to predict its transit status, the number of cells in the collected serving cell sequence information must meet the input requirements of the target prediction model to ensure its proper functioning and thus improve the accuracy of the transit status predicted by the target prediction model.

[0085] Optionally, when the electronic device collects the serving cell sequence information corresponding to the electronic device, it can perform a first data preprocessing on the collected serving cell sequence information to obtain the first data preprocessed serving cell sequence information; then the electronic device can predict the corresponding transit status based on the first data preprocessed serving cell sequence information.

[0086] Optionally, the first data preprocessing may include data outlier verification, normalization, and other processing operations, which are not limited here.

[0087] In another optional embodiment, if the number of cells included in the serving cell sequence information collected by the electronic device within the fourth time period is less than a number threshold, the electronic device will not perform the step of predicting the corresponding transit status of the electronic device based on the serving cell sequence information.

[0088] By implementing the above method, if the electronic device cannot collect enough serving cell information within the fourth time period, it will not make a prediction, thus avoiding obtaining a low-accuracy transit status and preventing the electronic device from accidentally switching its PLMN.

[0089] 204. Input the serving cell sequence information into the target prediction model to predict the transit status of the electronic device. The target prediction model is trained based on multiple sample cell sequence information and the actual transit status corresponding to each sample cell sequence information.

[0090] In this embodiment of the application, the target prediction model can be deployed in an electronic device. When the electronic device collects the serving cell sequence information corresponding to the electronic device, it can call the target prediction model and input the serving cell sequence information into the target prediction model.

[0091] In some alternative embodiments, the target prediction model can be deployed on a server corresponding to the electronic device. The electronic device can send the collected serving cell sequence information to the server, and then the server can input the serving cell sequence information into the target prediction model to obtain the transit status corresponding to the electronic device, and feed back the transit status corresponding to the electronic device to the electronic device.

[0092] In this embodiment of the application, the target prediction model can be a model used to predict the transit status of electronic devices based on serving cell sequence information.

[0093] By implementing the above method, electronic devices can predict the corresponding transit status of electronic devices through a target prediction model based on the real-time serving cell sequence information collected by the electronic devices. Since the target prediction model is trained on real sample data, its prediction results are more consistent with the real results, thereby improving the accuracy of the predicted transit status.

[0094] Optionally, the target prediction model can be obtained by training the model to be trained based on multiple sample service cell sequence information and the actual transit states corresponding to each sample service cell sequence information. Optionally, the model to be trained can include a neural network model, which can include any one of the following: Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), etc., without limitation.

[0095] Optionally, the multiple sample serving cell sequence information and the corresponding real transit status of each sample serving cell sequence information can be collected by the sample collection device. The sample collection device can be the aforementioned electronic equipment, or a device other than electronic equipment. For example, the sample collection device can be the equipment of a professional data collector, or it can be a device carried by other ordinary users; no limitation is made here.

[0096] Optionally, when the sample collection device detects entry into any geofence, it can collect service cell sequence information. After determining that the sample collection device has moved from the first region to the second region (i.e., the sample collection device has actually crossed the border), the sample collection device can stop collecting service cell information, and determine the service cell sequence information collected during this period as sample service cell sequence information, and determine the actual crossing status corresponding to the sample service cell sequence information as moving from the first region to the second region.

[0097] Optionally, the sample collection device can determine whether to move from the first region to the second region if the MCC of the connected PLMN changes.

[0098] Optionally, after the sample collection device has moved from the first area to the second area, it may continue collecting data for a first duration before ceasing to collect serving cell information. The first duration can be set by the developers based on extensive development experience; typical values ​​may include 15 minutes, 20 minutes, etc., and are not limited here.

[0099] By implementing the above method, the sequence information of the service cell can be maintained during the period when the sample collection equipment passes through the area, thereby ensuring the richness and completeness of the collected data.

[0100] In some alternative embodiments, the multiple sample serving cell sequence information may be historical serving cell sequence information collected when electronic devices actually pass through the area in the past, and this is not limited here.

[0101] Furthermore, the sample acquisition device can send multiple sample service cell sequence information and the real transit status corresponding to each sample service cell sequence information to the model training device. The model training device can be the aforementioned electronic device, or the server corresponding to the electronic device, or the development device of the developers, without any limitation.

[0102] Optionally, the model training device can perform a second data preprocessing on multiple sample service cell sequence information and the corresponding real transit status of each sample service cell sequence information. Optionally, the second data preprocessing may include one or more of the following operations: data partitioning, data cleaning, feature extraction, outlier handling, and normalization, which are not limited here.

[0103] Furthermore, the model training device can train the model to be trained based on the multiple sample service cell sequence information after the second data preprocessing and the real transit status corresponding to each sample service cell sequence information, so as to obtain multiple prediction models.

[0104] Optionally, since prediction models are typically used to predict whether electronic devices will cross the border when they have not yet crossed, the MCC of the serving cell sequence information collected by electronic devices in practical applications is usually the same (because they have not yet crossed the border). Therefore, when training the prediction model, the model training device can extract sample serving cell sequence information before the MCC change and the actual crossing state corresponding to each sample serving cell sequence information. Based on the sample serving cell sequence information before the MCC change and the actual crossing state corresponding to each sample serving cell sequence information, the model to be trained is trained to obtain multiple prediction models, thereby improving the accuracy of the prediction model in predicting the crossing state.

[0105] In one optional embodiment, data partitioning may include: partitioning multiple sample serving cell sequence information and the actual transit status corresponding to each sample serving cell sequence information according to different geofences and / or different PLMN operators, so as to obtain sample data sets corresponding to each geofence and / or operator, each sample data set containing sample serving cell sequence information corresponding to the corresponding geofence and / or operator, and the actual transit status corresponding to each sample serving cell sequence information.

[0106] Optionally, the operator corresponding to the sample serving cell sequence information can be determined based on the MCC and / or MNC included in the sample serving cell sequence information. Optionally, the geofence corresponding to the sample serving cell sequence information can be determined based on one or more of the MCC, MNC, TAC, and CID included in the sample serving cell sequence information.

[0107] For example, suppose that the multiple sample serving cell sequence information includes sample serving cell sequence information of a first operator collected from a first port and a second port respectively, and sample serving cell sequence information of a second operator collected from a first port and a second port respectively;

[0108] The sample serving cell sequence information can then be divided into sample serving cell sequence information corresponding to the first port and the first operator, sample serving cell sequence information corresponding to the first port and the second operator, sample serving cell sequence information corresponding to the second port and the first operator, and sample serving cell sequence information corresponding to the second port and the second operator, without any further limitation.

[0109] In one optional embodiment, the model training device can train prediction models corresponding to multiple geofences based on the sample service cell sequence information corresponding to multiple geofences and the actual transit status corresponding to each of the service sample cell sequence information.

[0110] Optionally, the target prediction model can be the one that matches the geographic identifier corresponding to the target geofence from among multiple prediction models. The geographic identifier is used to distinguish different target geofences and may include the target geofence number, the name of the region corresponding to the target geofence, etc., without limitation.

[0111] Optionally, the multiple prediction models are the prediction models corresponding to the multiple geofences mentioned above.

[0112] Optionally, the electronic device can acquire the identification information corresponding to the target geofence and determine the prediction model that matches the identification information corresponding to the target geofence among multiple prediction models as the target prediction model.

[0113] By implementing the above method, electronic devices can call a target prediction model that matches the target geofence to predict the transit status of the electronic devices. Since the target prediction model is trained on the target geofence, the prediction results of the target prediction model are more consistent with the actual situation of the target geofence, thereby improving the accuracy of the predicted transit status.

[0114] In another alternative embodiment, the model training device can train multiple prediction models based on sample service cell sequence information corresponding to multiple geofences and operators, and the actual transit status corresponding to each of the service sample cell sequence information. Each prediction model is matched with a geofence and an operator.

[0115] For example, the prediction models corresponding to the first port and the first operator, the prediction models corresponding to the first port and the second operator, the prediction models corresponding to the second port and the first operator, and the prediction models corresponding to the second port and the second operator are not limited here.

[0116] Optionally, the target prediction model can be a prediction model that matches both the geographic identifier corresponding to the target geofence and the operator of the PLMN currently connected to the electronic device, among multiple prediction models.

[0117] Optionally, the multiple prediction models can be trained based on the sample service cell sequence information corresponding to multiple geofences and operators, and the actual transit status corresponding to each of the service sample cell sequence information, as described above.

[0118] Optionally, the electronic device can obtain the geographic identifier corresponding to the target geofence and the operator of the PLMN currently connected to the electronic device, and then determine the prediction model that matches both the geographic identifier corresponding to the target geofence and the operator of the PLMN currently connected to the electronic device as the target prediction model.

[0119] By implementing the above method, electronic devices can call a target prediction model that matches both the target geofence and the operator of the PLMN currently connected to the electronic device to predict the transit status of the electronic device. Since the target prediction model is trained on the target geofence and the operator of the PLMN currently connected to the electronic device, the prediction results of the target prediction model are more consistent with the actual situation of the target geofence and the operator, thereby improving the accuracy of the predicted transit status.

[0120] In one optional embodiment, data partitioning may include: partitioning multiple sample serving cell sequence information and the actual transit status corresponding to each sample serving cell sequence information according to the exit status or the entry status, so as to obtain sample serving cell sequence information corresponding to the exit status and the actual transit status corresponding to each sample serving cell sequence information, as well as sample serving cell sequence information corresponding to the entry status and the actual transit status corresponding to each sample serving cell sequence information.

[0121] Optionally, the model training device can train an outbound prediction model for use when leaving the country based on the sample service cell sequence information corresponding to the outbound status and the actual transit status corresponding to each sample service cell sequence information; and the model training device can train an inbound prediction model for use when entering the country based on the sample service cell sequence information corresponding to the inbound status and the actual transit status corresponding to each sample service cell sequence information.

[0122] Optionally, when an electronic device is leaving the country, it can invoke the outbound prediction model; when an electronic device is entering the country, it can invoke the inbound prediction model.

[0123] In another optional embodiment, data partitioning may include: dividing multiple sample serving cell sequence information and the actual transit status corresponding to each sample serving cell sequence information according to the home region or non-home region, so as to obtain sample serving cell sequence information corresponding to the home region and the actual transit status corresponding to each sample serving cell sequence information, as well as sample serving cell sequence information corresponding to the non-home region and the actual transit status corresponding to each sample serving cell sequence information.

[0124] Optionally, the model training device can train a first sub-model based on the sample service cell sequence information corresponding to the home region and the actual transit status corresponding to each sample service cell sequence information; and the model training device can train a second sub-model based on the sample service cell sequence information corresponding to the non-home region and the actual transit status corresponding to each sample service cell sequence information.

[0125] Optionally, if the electronic device is currently located in the first region, which is the region to which the electronic device belongs, the collected serving cell sequence corresponding to the electronic device can be input into the first sub-model;

[0126] Region of origin refers to the geographical area associated with a user (such as a mobile phone user) when registering or signing a contract with an operator's network. For example, if a user obtains a phone card in country A, then the region of origin for the user when using the phone card is country A.

[0127] In another optional embodiment, if the electronic device is currently in a non-home region in the first region, the collected serving cell sequence corresponding to the electronic device can be input into the second sub-model.

[0128] In this context, non-home regions refer to regions other than the home region. For example, if the home region of an electronic device is country A, then countries B and C are non-home regions.

[0129] By implementing the above method, considering that the network architecture and network conditions may be different in different countries and regions, corresponding prediction models can be trained for sample data from both the home and non-home regions. Subsequently, the corresponding target prediction model can be used to predict the transit status, so that the prediction results are more in line with the actual situation, thereby improving the accuracy of the predicted transit status.

[0130] 206. If the transit status indicates that the location of the electronic device has moved from the first region to the second region, then search for the public land mobile network (PLMN) in the second region.

[0131] As an optional implementation, when the electronic device moves from a first region to a second region in a transit state, the prediction of the corresponding transit state of the electronic device may be stopped within a first time period.

[0132] The first duration can be set by the developers based on their extensive development experience. Typical values ​​may include half an hour, one hour, or two hours, etc., and are not limited here.

[0133] In this embodiment of the application, the location of the electronic device moving from the first region to the second region may indicate that the electronic device is in an outbound or inbound state, or that the MCC of the PLMN to which the electronic device is connected has changed, which is not limited here.

[0134] It should be noted that if the predicted transit status indicates that the electronic device will move from the first region to the second region, the electronic device may move to the second region in a short period of time. If the electronic device continues to predict its transit status during this process, it may predict that the electronic device will move from the second region to the first region after it has moved to the second region. This may cause the electronic device to start searching for the PLMN of the first region, which may lead to the electronic device switching back to the PLMN of the first region shortly after entering the second region. This is obviously not in line with the user's network usage needs.

[0135] By implementing the above method, electronic devices can stop predicting the transit outcome for a certain period of time when the predicted transit status indicates that the electronic device will be transiting. This reduces the frequency of the electronic device's use of the prediction function, thereby reducing the power consumption of the electronic device. It also avoids the electronic device frequently switching PLMNs, thus ensuring the network stability of the electronic device and improving the user's network experience.

[0136] In one optional implementation, the predictive function of the electronic device can be turned off. Alternatively, if the predictive function of the electronic device is not turned off, the electronic device can predict the transit status corresponding to the electronic device based on the collected serving cell sequence information corresponding to the electronic device.

[0137] Correspondingly, when the prediction function of the electronic device is turned off, the electronic device does not predict the transit status of the electronic device based on the collected serving cell sequence information of the electronic device.

[0138] By implementing the above method, electronic devices can choose to disable the prediction function to prevent them from predicting the transit status of their corresponding electronic devices based on the collected serving cell sequence information, thereby improving the controllability and flexibility of the method.

[0139] As an optional implementation, if the number of times the electronic device predicts the transit status corresponding to the electronic device within the second time period is greater than or equal to the number threshold, and the location of the electronic device does not move from the first region to the second region within the second time period, then the prediction function of the electronic device is turned off.

[0140] Optionally, the second duration can be set by the developers based on extensive development experience; typical values ​​may include 3 days, one week, or one month, and are not limited here. The number of times threshold can also be set by the developers based on extensive development experience, and is not limited here.

[0141] Optionally, if the MCC corresponding to the serving cell where the electronic device is stationed does not change during the second time period, it can be determined that the location of the electronic device did not move from the first region to the second region during the second time period.

[0142] It should be noted that users residing within the target geofence, or workers operating within it, will have their electronic devices frequently predicting their transit status due to prolonged exposure. However, these users do not actually transit, and their devices do not require PLMN switching. To address this, the predictive function of electronic devices used by users permanently residing within the target geofence can be disabled. This avoids frequent predictive actions by the devices, reducing power consumption. Furthermore, it prevents frequent PLMN switching, maintaining network stability and improving the user experience.

[0143] In some alternative embodiments, the way an electronic device disables its predictive function may include disabling the predictive function for a fifth duration and then re-enabling it.

[0144] Optionally, the fifth duration can be set by the developers based on extensive development experience. Typical values ​​include half a month, one month, or two months, and are not limited here.

[0145] By implementing the above method, since the prediction function may be turned off automatically by the electronic device or actively turned off by the user, turning off the prediction function may not meet the user's long-term usage needs. Therefore, the prediction function can be turned off only for a certain period of time, thereby avoiding the electronic device from turning off the prediction function for a long time and improving the user experience.

[0146] In another optional embodiment, if a shutdown command instructing the electronic device to disable its predictive function is received, then the predictive function of the electronic device is disabled. Optionally, if an activation command instructing the electronic device to enable its predictive function is received, then the predictive function of the electronic device is enabled.

[0147] By implementing the above method, electronic devices can flexibly turn their predictive functions on or off according to input switching commands, thereby improving the controllability and flexibility of the method.

[0148] Optionally, the above-mentioned prediction function may further include: inputting the serving cell sequence information corresponding to the electronic device into the target prediction model, so as to predict the transit status corresponding to the electronic device through the target prediction model.

[0149] Implementing the methods disclosed in the above embodiments, if the transit status represents the electronic device's location moving from a first region to a second region, the PLMN of the second region can be searched in advance to facilitate the electronic device's rapid switching to the PLMN of the second region during transit, avoiding prolonged periods of low network quality or no service, thus ensuring the network quality of the electronic device; furthermore, if the electronic device cannot collect sufficient serving cell information within a fourth time period, no prediction is made to avoid obtaining a transit status with low accuracy, thereby preventing the electronic device from mistakenly switching its PLMN; furthermore, the electronic device can predict its corresponding transit status using a target prediction model based on the real-time serving cell sequence information collected by the electronic device. Since the target prediction model is trained on real sample data, its prediction results are more consistent with the actual results, thereby improving the accuracy of the predicted transit status; furthermore, the electronic device can call a target prediction model that matches the target geofence to predict its transit status. Since the target prediction model is trained on the target geofence, its prediction results are more consistent with the actual situation of the target geofence, thereby improving the accuracy of the predicted transit status; and furthermore.

[0150] Considering the potential differences in network architecture and conditions across different countries and regions, corresponding prediction models can be trained using sample data from both home and non-home regions. These models can then be used to predict transit states, making the predictions more consistent with reality and improving accuracy. Furthermore, electronic devices can stop predicting their transit status for a certain period when the predicted transit state indicates they will be transiting. This reduces the frequency of prediction usage, lowering power consumption and preventing frequent PLMN switching, thus ensuring network stability and improving user experience. Additionally, electronic devices can choose to disable prediction to prevent them from predicting transit states based on collected serving cell sequence information, increasing controllability and flexibility. The prediction function can also be disabled for devices of users permanently residing within the target geofence, further reducing power consumption and minimizing PLMN switching, thus maintaining network stability and improving user experience.

[0151] Please see Figure 3 , Figure 3This is a flowchart illustrating another network search method disclosed in this application. Optionally, this method can be applied to the aforementioned electronic device or other execution entities, and is not limited thereto. Optionally, the method may include the following steps:

[0152] 302. When an electronic device enters the target geofence, collect the serving cell sequence information corresponding to the electronic device.

[0153] 304. Based on the serving cell sequence information, predict the transit status of the electronic device. The transit status is used to characterize whether the location of the electronic device has moved from the first region to the second region.

[0154] 306. If the transit status indicates that the location of the electronic device has moved from the first region to the second region, then obtain the network quality information and / or network service status corresponding to the electronic device.

[0155] In this embodiment, the network quality information corresponding to the electronic device may include various parameters used to characterize the network quality of the electronic device. Optionally, the network quality information may include RSRP or RSRQ, etc., which are not limited here.

[0156] In one optional embodiment, network quality information may include: the average RSRP over a sixth time period, or the average RSRQ over a seventh time period. The sixth and seventh time periods can be set by developers based on numerous development suggestions; typical values ​​may include 3 seconds, 5 seconds, or 6 seconds, etc. The sixth and seventh time periods may be the same or different, and are not limited thereto. The average values ​​of RSRP and RSRQ over a certain time period provide a more accurate representation of network quality.

[0157] In this embodiment of the application, the network service status is used to characterize whether the PLMN of the electronic device is providing normal service.

[0158] In one optional embodiment, the electronic device can obtain network quality information and / or network service status within an eighth duration. The eighth duration can be set by developers based on extensive development experience, and typical values ​​may include 25 minutes, 30 minutes, or 40 minutes, without limitation herein.

[0159] 308. If the network quality information corresponding to the electronic device is lower than the network quality threshold, and / or the network service status indicates that the mobile network of the electronic device cannot provide normal service, then search for the public land mobile network (PLMN) in the second region.

[0160] In this embodiment, the network quality threshold can be set by developers based on extensive development experience. Optionally, the network quality thresholds corresponding to different types of network quality information can be different. Optionally, typical values ​​for the network quality threshold corresponding to RSRP may include 115dBm, 118dBm, or 120dBm, etc., and are not limited here. Typical values ​​for the network quality threshold corresponding to RSRQ may include 15dB, 18dB, or 20dB, etc., and are not limited here.

[0161] In this embodiment of the application, considering that the electronic device searches for the PLMN of the second region, one purpose is that the electronic device is currently in a weak network state (i.e., low network quality) and needs to switch to the PLMN of the second region with higher network quality to improve the network experience of the electronic device user.

[0162] By implementing the above method, when the electronic device moves from the first region to the second region according to the predicted transit status, it can be further determined whether the electronic device is in a weak network state based on the network quality information and network service status of the electronic device. If the electronic device is in a weak network state, the PLMN of the second region is searched, thereby improving the network quality of the electronic device as soon as possible and improving the network experience of the electronic device users.

[0163] In another optional implementation, if the network quality information corresponding to the electronic device is not lower than the network quality threshold within the third time period, and / or the network service status indicates that the electronic device's PLMN is providing normal service, then the step of searching for the PLMN of the second region is not performed.

[0164] As mentioned earlier, one purpose of electronic devices searching for a second-region PLMN is to switch to a second-region PLMN with higher network quality when the device is currently in a weak network state, thereby improving the user's network experience. By implementing the method described above, if the electronic device is not in a weak network state, it can skip the step of searching for a second-region PLMN, thus saving power consumption. Furthermore, it avoids subsequent PLMN switching operations, maintaining network stability and ensuring a good user experience.

[0165] In one optional embodiment, if the network quality information corresponding to the electronic device is not lower than the network quality threshold within a third time period, and / or the network service status indicates that the PLMN of the electronic device is providing normal service, and the second region is the region to which the electronic device belongs, then the electronic device searches for the PLMN of the second region.

[0166] It should be noted that users of electronic devices are usually more accustomed to using the PLMN of their home region. Therefore, if the second region that the electronic device is about to go to is the PLMN of the electronic device's home region, even if the electronic device is not in a weak network state, the electronic device can still perform a search for the PLMN of the second region. This allows the electronic device to switch back to the PLMN of its home region more quickly, which is more in line with the user's network usage habits and improves the user's network experience.

[0167] As an optional implementation, if the electronic device fails to find the PLMN of the second region, it reduces the interval between searches for the PLMN of the second region.

[0168] In this embodiment, the electronic device can search for the PLMN of the second region at certain intervals. If the PLMN of the second region is not found, the electronic device can reduce the interval between searches to search for the PLMN of the second region more frequently, thereby increasing the probability of finding the PLMN of the second region.

[0169] In one optional embodiment, the electronic device can use a PLMN search timer to search for the PLMN of the second region at certain intervals. The duration of the PLMN search timer is the interval for searching the PLMN; the default duration of the PLMN search timer is typically set by developers based on extensive development experience, and typical values ​​include any value between 6 minutes and 8 hours, which is not limited here.

[0170] To address this, the electronic device can increase the frequency of searching for PLMNs in the second region by reducing the duration of its PLMN search timer, thereby increasing the probability of finding a PLMN in the second region. For example, the duration of the PLMN search timer can be reduced from 6 minutes to 1 minute, but this is not a limitation.

[0171] In this embodiment, the PLMN search timer may include a high-priority PLMN search timer, which is used to search for high-priority PLMNs. The high-priority PLMN can be set by developers based on extensive development experience, or by users based on actual usage needs. Optionally, the high-priority PLMN may include the PLMN of the electronic device's home region, the PLMN with the most remaining network traffic resources, or the PLMN with the highest network quality; these are not limited here.

[0172] In one optional embodiment, the second region can be the home region of the electronic device, thereby reducing the interval between searching the PLMN of the second region. This allows the electronic device to switch back to the PLMN of the home region more quickly, which is more in line with the user's network usage habits and improves the user's network experience.

[0173] Implementing the methods disclosed in the above embodiments, if the transit status indicates that the electronic device's location moves from the first region to the second region, the PLMN of the second region can be searched in advance. This facilitates the electronic device's rapid switching to the PLMN of the second region during transit, avoiding prolonged periods of low network quality or no service, thus ensuring the network quality of the electronic device. Furthermore, when the predicted transit status indicates that the electronic device's location moves from the first region to the second region, the network quality information and network service status of the electronic device can be used to determine whether the electronic device is in a weak network state. If the electronic device is in a weak network state, the PLMN of the second region is searched, thereby quickly improving the network quality of the electronic device and enhancing the user's network experience. If the electronic device is not in a weak network state, the step of searching for the PLMN of the second region can be omitted, thereby saving the power consumption of the electronic device. In addition, subsequent PLMN switching operations can be avoided, thus maintaining the network stability of the electronic device and ensuring the user's network experience. Moreover, the electronic device can reduce the interval between searching for the PLMN of the second region, allowing for more frequent searches, thereby increasing the probability of finding the PLMN of the second region.

[0174] To more clearly describe the network search method disclosed in the embodiments of this application, the following is combined with... Figure 4 This paper introduces the web search method. Figure 4 This is a flowchart illustrating another network search method disclosed in an embodiment of this application. Optionally, this method can be applied to the aforementioned electronic device or other execution entities, and is not limited thereto. Optionally, the method may include the following steps:

[0175] 402. Obtain the N first cells where the electronic device continuously resides, and match the N first cells with the target geofence corresponding to the port;

[0176] 404. Based on the matching results of the N first cells and the target geofences corresponding to the port, determine whether the electronic device is within the target geofence of the port. If yes, proceed to step 406; otherwise, end this process.

[0177] 406. Determine if the target prediction model is blocked. If yes, end this process; otherwise, proceed to step 408.

[0178] 408. Collect serving cell sequence information within the fourth time period (e.g., 30 minutes) and perform the first data preprocessing on the serving cell sequence information;

[0179] 410. Call the target prediction model and input the processed serving cell sequence information into the target prediction model;

[0180] 412. Predict the transit status of the electronic device using the target prediction model; if the transit status indicates that the electronic device is leaving the country, proceed to step 414; if the transit status indicates that the electronic device is entering the country, proceed to step 422.

[0181] The transit status is used to indicate whether the location of the electronic device has moved from the first region to the second region. If the first region is the region to which the electronic device belongs, the transit status indicates that the electronic device has left the country. If the first region is not the region to which the electronic device belongs, the transit status indicates that the electronic device has entered the country.

[0182] 414. Start a timer with a duration of eight hours (e.g., 30 minutes); if the timer reaches the eighth hour, end this process.

[0183] 416. If the timer has not reached the eighth hour, collect network quality information and / or network service status of the electronic device;

[0184] 418. If the network quality information is lower than the network quality threshold, and / or the network service status indicates that the mobile network of the electronic device cannot provide normal service, then search for the PLMN in the second region.

[0185] 420. Switch to the PLMN in the second region;

[0186] 422. Start a timer with a duration of eight hours (e.g., 30 minutes); if the timer reaches the eighth hour, end this process.

[0187] 424. If the timer has not reached the eighth hour, collect network quality information and / or network service status of the electronic device;

[0188] 426. If the network quality information is lower than the network quality threshold, and / or the network service status indicates that the mobile network of the electronic device cannot provide normal service, then search for the PLMN in the second region.

[0189] 428. Switch to the PLMN of the second region? If yes, end this process; if no, reduce the duration of the high-priority search timer.

[0190] 430. If a PLMN in the second region is found, switch to the PLMN in the second region.

[0191] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a network search device disclosed in an embodiment of this application. Optionally, this device can be applied to the aforementioned electronic device or other execution entities, without limitation. Optionally, the device may include a data acquisition unit 502, a prediction unit 504, and a search unit 506, wherein:

[0192] The acquisition unit 502 is used to acquire the serving cell sequence information corresponding to the electronic device when the electronic device enters the target geofence;

[0193] The prediction unit 504 is used to predict the transit status of the electronic device based on the serving cell sequence information. The transit status is used to characterize whether the location of the electronic device has moved from the first region to the second region.

[0194] Search unit 506 is used to search for the public land mobile network (PLMN) in the second region when the location of an electronic device representing a transit status moves from the first region to the second region.

[0195] By implementing the above-described device, when an electronic device enters a target geofence, the device's corresponding serving cell sequence information can be collected. It is understood that the serving cell sequence information includes the serving cells where the electronic device has historically resided, which can characterize the electronic device's movement trajectory. Based on this serving cell sequence information, the transit status of the electronic device can be predicted. The transit status indicates whether the electronic device's location has moved from a first region to a second region. If the transit status indicates that the electronic device's location has moved from a first region to a second region, the PLMN of the second region can be searched in advance. This allows the electronic device to quickly switch to the PLMN of the second region during transit, avoiding prolonged periods of low network quality or no service, thus ensuring the network quality of the electronic device.

[0196] As an optional implementation, the prediction unit 504 is also used to input the serving cell sequence information into the target prediction model so as to predict the transit status of the electronic device through the target prediction model. The target prediction model is trained based on multiple sample serving cell sequence information and the actual transit status corresponding to each serving sample cell sequence information.

[0197] By implementing the above-mentioned device, electronic devices can predict the corresponding transit status of electronic devices through a target prediction model based on the real-time serving cell sequence information collected by the electronic devices. Since the target prediction model is trained based on real sample data, its prediction results are more consistent with the real results, thereby improving the accuracy of the predicted transit status.

[0198] As an optional implementation, the target prediction model is the one among multiple prediction models that matches the geographic identifier corresponding to the target geofence; or,

[0199] The target prediction model is a prediction model that matches both the geographic identifier corresponding to the target geofence and the operator of the PLMN currently connected to by the electronic device among multiple prediction models.

[0200] By implementing the above device, the electronic device can call a target prediction model that matches the target geofence and the operator of the PLMN currently connected to the electronic device to predict the transit status of the electronic device. Since the target prediction model is trained on the target geofence and the operator of the PLMN currently connected to the electronic device, the prediction results of the target prediction model are more consistent with the actual situation of the target geofence and the operator, thereby improving the accuracy of the predicted transit status.

[0201] As an optional implementation, the target prediction model includes a first sub-model and a second sub-model. The first sub-model is trained based on the sample cell sequence information corresponding to the home region, and the second sub-model is trained based on the sample cell sequence information corresponding to the visited region.

[0202] The prediction unit 504 is further configured to input the serving cell sequence into the first sub-model if the first region is the home region of the electronic device; or,

[0203] If the first region is the non-home region of the electronic device, then the serving cell sequence is input into the second sub-model.

[0204] When implementing the above-mentioned device, considering that the network architecture and network conditions may be different in different countries and regions, corresponding prediction models can be trained for sample data from both the home and non-home regions. Subsequently, the corresponding target prediction model can be used to predict the transit status, so that the prediction results are more in line with the actual situation, thereby improving the accuracy of the predicted transit status.

[0205] As an optional implementation method, Figure 5 The illustrated device may also include a stop unit (not shown), wherein:

[0206] The stopping unit is used to stop predicting the transit status of an electronic device within a first time period if, after predicting the transit status of the electronic device based on the serving cell sequence information, the transit status indicates that the location of the electronic device has moved from the first region to the second region.

[0207] By implementing the above-mentioned device, when the predicted transit status indicates that the electronic device will transit, the electronic device can stop predicting the transit result for a certain period of time. This can reduce the frequency of the electronic device's use of the prediction function, reduce the power consumption of the electronic device, and avoid the electronic device frequently switching PLMNs, thereby ensuring the network stability of the electronic device and improving the user's network experience.

[0208] As an optional implementation, the prediction unit 504 is also used to predict the transit status of the electronic device based on the serving cell sequence information when the prediction function of the electronic device is not turned off. The prediction function is the function of predicting the transit status of the electronic device based on the serving cell sequence information of the electronic device.

[0209] By implementing the above device, the electronic device can choose to turn off the prediction function to prevent the electronic device from predicting the transit status of the electronic device based on the collected serving cell sequence information of the electronic device, thereby improving the controllability and flexibility of the method.

[0210] As an optional implementation method, Figure 5 The illustrated device may also include a closing unit (not shown), wherein:

[0211] The shutdown unit is configured to disable the prediction function of the electronic device if, within a second time period, the number of times the electronic device predicts the corresponding transit status of the electronic device is greater than or equal to a threshold number, and the location of the electronic device has not moved from the first region to the second region within the second time period; or...

[0212] Upon receiving a command to disable the predictive function of an electronic device, disable the predictive function of the electronic device.

[0213] Implementing the above-mentioned device can disable the prediction function of electronic devices of users who reside within the target geofence for extended periods, thereby avoiding frequent execution of prediction functions by electronic devices and reducing power consumption. In addition, it can also prevent electronic devices from frequently switching PLMNs, thus maintaining network stability and improving the user's network experience.

[0214] As an optional implementation, the search unit 506 is also used to obtain network quality information and / or network service status corresponding to the electronic device; and if the network quality information is lower than the network quality threshold and / or the network service status indicates that the mobile network of the electronic device cannot provide normal service, then the search unit searches for a public land mobile network (PLMN) in a second region.

[0215] By implementing the above-mentioned device, when the electronic device moves from the first region to the second region in the predicted transit state, it can be further determined whether the electronic device is in a weak network state based on the network quality information and network service status of the electronic device. If the electronic device is in a weak network state, the PLMN of the second region is searched, thereby improving the network quality of the electronic device as soon as possible and improving the network user experience of the electronic device.

[0216] As an optional implementation method, Figure 5 The illustrated device may also include a blocking unit (not shown), wherein:

[0217] The prohibition unit is used to prevent the step of searching for the public land mobile network (PLMN) of the second area from being performed if the network quality information does not fall below the network quality threshold within a third time period and / or the network service status indicates that the electronic device's PLMN is providing normal service.

[0218] By implementing the above device, if the electronic device is not in a weak network state, the electronic device does not need to perform the step of searching for the PLMN of the second region, thereby saving the power consumption of the electronic device. In addition, it can also avoid the subsequent operation of switching PLMN, thereby maintaining the network stability of the electronic device and ensuring the user's network experience.

[0219] As an optional implementation method, Figure 5 The illustrated device may also include a lowering unit (not shown), wherein:

[0220] The reduction unit is used to reduce the interval between searches for the public land mobile network (PLMN) of the second region if no PLMN of the second region is found after searching for it.

[0221] If the PLMN of the second region is not found when the above device is implemented, the electronic device can reduce the interval between searching for the PLMN of the second region, so as to search for the PLMN of the second region more frequently, thereby increasing the probability of finding the PLMN of the second region.

[0222] As an optional implementation, the target geofence contains multiple cell units, and each cell unit contains N second cells, where N is an integer greater than or equal to 2; Figure 5 The apparatus shown may also include a determining unit (not shown), wherein:

[0223] The determining unit is configured to acquire N first cells in which the electronic device continuously resides before acquiring the serving cell sequence information corresponding to the electronic device when the electronic device enters the target geofence; and, if the N first cells match any cell unit among the multiple cell units contained in the target geofence, then determine that the electronic device has entered the target geofence.

[0224] By implementing the above-mentioned device, the electronic device can generate a target geofence based on the information of a second cell near the border area. Then, it can determine whether the electronic device has entered the target geofence based on whether the first cell where the electronic device is stationed matches the second cell of the target geofence. This method can efficiently and stably determine whether the electronic device has entered the target geofence.

[0225] As an optional implementation, the prediction unit 504 is also used to predict the transit status of the electronic device based on the serving cell sequence information when the number of cells included in the serving cell sequence information collected within the fourth time period is greater than or equal to a number threshold.

[0226] By implementing the above-mentioned device, the electronic device can predict the transit status corresponding to the electronic device based on the service cell sequence information after collecting information from a sufficient number of serving cells. This ensures that the data used for prediction is sufficiently rich, thereby improving the accuracy of the subsequent predicted transit status.

[0227] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. For example... Figure 6 As shown, the electronic device may include: a memory 601 storing executable program code; and a processor 602 coupled to the memory 601; wherein the processor 602 calls the executable program code stored in the memory 601 to execute the network search method disclosed in the above embodiments.

[0228] This application discloses a computer-readable storage medium storing a computer program that causes a computer to execute the network search methods disclosed in the above embodiments.

[0229] This application also discloses an application publishing platform, which is used to publish computer program products. When the computer program products are run on a computer, the computer performs some or all of the steps of the methods described in the above method embodiments.

[0230] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Those skilled in the art should also recognize that the embodiments described in the specification are optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0231] In the various embodiments of this application, it should be understood that the sequence number of each process does not necessarily imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0232] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they can be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0233] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0234] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-accessible memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several requests to cause a computer device (which can be a personal computer, server, or network device, specifically a processor in the computer device) to execute some or all of the steps of the methods described in the various embodiments of this application.

[0235] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0236] The network search method and related products disclosed in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A network search method characterized by, The method is applied to an electronic device, and comprises: In a case where the electronic device enters a target geofence, service cell sequence information corresponding to the electronic device is collected; According to the service cell sequence information, a transit state corresponding to the electronic device is predicted, the transit state being used to represent whether a location of the electronic device moves from a first region to a second region; If the transit state represents that the location of the electronic device moves from the first region to the second region, a public land mobile network (PLMN) of the second region is searched.

2. The method of claim 1, wherein, The prediction of the transit state corresponding to the electronic device according to the service cell sequence information comprises: The service cell sequence information is input into a target prediction model to predict the transit state corresponding to the electronic device by the target prediction model, the target prediction model being trained according to a plurality of sample service cell sequence information and a real transit state corresponding to each of the sample service cell sequence information.

3. The method of claim 2, wherein, The target prediction model is a prediction model that matches a geographic identifier corresponding to the target geofence among a plurality of prediction models; or The target prediction model is a prediction model that matches both the geographic identifier corresponding to the target geofence and an operator of a PLMN currently accessed by the electronic device among a plurality of prediction models.

4. The method of claim 2, wherein, The target prediction model comprises a first sub-model and a second sub-model, the first sub-model being trained according to sample cell sequence information corresponding to a home region, and the second sub-model being trained according to sample cell sequence information corresponding to a visited region; The input of the service cell sequence information into the target prediction model comprises: If the first region is a home region of the electronic device, the service cell sequence is input into the first sub-model; If the first region is a non-home region of the electronic device, the service cell sequence is input into the second sub-model.

5. The method of claim 1, wherein, After the prediction of the transit state corresponding to the electronic device according to the service cell sequence information, the method further comprises: If the transit state represents that the location of the electronic device moves from the first region to the second region, the prediction of the transit state corresponding to the electronic device is stopped within a first time length.

6. The method of claim 1, wherein, The prediction of the transit state corresponding to the electronic device according to the service cell sequence information comprises: In a case where a prediction function of the electronic device is not closed, the transit state corresponding to the electronic device is predicted according to the service cell sequence information, the prediction function being a function of predicting the transit state corresponding to the electronic device according to the service cell sequence information corresponding to the electronic device.

7. The method of claim 1, wherein, The method further comprises: If a number of times of predicting the transit state corresponding to the electronic device by the electronic device within a second time length is greater than or equal to a threshold value, and the location of the electronic device does not move from the first region to the second region within the second time length, the prediction function of the electronic device is closed; or If a closing instruction indicating that the prediction function of the electronic device is closed is received, the prediction function of the electronic device is closed.

8. The method of claim 1, wherein, The searching the public land mobile network (PLMN) of the second region comprises: obtaining network quality information corresponding to the electronic device and / or a network service state; if the network quality information is lower than a network quality threshold and / or the network service state indicates that the mobile network of the electronic device cannot normally serve, searching the public land mobile network (PLMN) of the second region.

9. The method of claim 8, wherein, The method further comprises: if the network quality information is not lower than the network quality threshold and / or the network service state indicates that the PLMN of the electronic device normally serves within a third time length, not performing the step of searching the public land mobile network (PLMN) of the second region.

10. The method of claim 1, wherein; After the searching the public land mobile network (PLMN) of the second region, the method further comprises: if no PLMN of the second region is searched, reducing the interval time length of searching the PLMN of the second region.

11. The method of claim 1, wherein, The target geographic fence comprises a plurality of cell units, each of the cell units comprising N second cells, the N being an integer greater than or equal to 2; Before the electronic device enters the target geographic fence, the method further comprises: obtaining N first cells in which the electronic device continuously resides; if the N first cells match any cell unit in the plurality of cell units comprised by the target geographic fence, determining that the electronic device enters the target geographic fence.

12. The method of claim 1, wherein, The predicting the transit state corresponding to the electronic device according to the service cell sequence information comprises: if the number of cells comprised by the service cell sequence information collected within a fourth time length is greater than or equal to a number threshold, predicting the transit state corresponding to the electronic device according to the service cell sequence information.

13. A network search apparatus, characterized by comprising: The device applied to an electronic device comprises: a collection unit configured to collect service cell sequence information corresponding to the electronic device when the electronic device enters a target geographic fence; a prediction unit configured to predict a transit state corresponding to the electronic device according to the service cell sequence information, the transit state being used to indicate whether the position of the electronic device moves from a first region to a second region; a searching unit configured to search a public land mobile network (PLMN) of the second region when the transit state indicates that the position of the electronic device moves from the first region to the second region.

14. An electronic device, comprising: The computer program product comprises a memory in which an executable program code is stored, and a processor coupled to the memory; wherein the processor invokes the executable program code stored in the memory to execute the method according to any one of claims 1-12.

15. A computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the method according to any one of claims 1-12.

16. A computer program product, characterised in that, The computer program product comprises a computer program, which is executed by the processor to implement the method according to any one of claims 1-12.

Images