Processing method and terminal equipment

Abstract

The invention provides a processing method and terminal equipment. The method comprises the following steps: obtaining a target network identifier based on a target model; wherein the target network identifier is a next network identifier to be connected with the terminal equipment, and the target network identifier is a network identifier obtained by reasoning of the target model; if the current network quality meets the switching condition, connecting with a network end indicated by the target network identifier based on the target network identifier; wherein if the current network quality meets the switching condition, the terminal equipment is located in the signal coverage range of the network end indicated by the target network identifier.

Description

Technical Field

[0001] The present application relates to but is not limited to the field of communication technology, and in particular to a processing method and terminal equipment. Background Art

[0002] In the related art, when the network quality of the terminal device is poor, the terminal device usually obtains at least one network identifier from a scanning mechanism to select a network identifier with good signal quality, and connects to the network end indicated by the network identifier with good signal quality. However, this process is only performed when the network quality of the terminal device is poor, and there is a problem of slow connection speed. At the same time, the network end indicated by the network identifier with good signal quality may cause network interruption, and there is a problem of poor network continuity. In addition, there is no model in the terminal device that has the function of predicting the target network identifier. Summary of the invention

[0003] In view of this, the embodiments of the present application at least provide a processing method and a terminal device.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The present application embodiment provides a processing method, including:

[0006] Obtaining a target network identifier based on the target model; wherein the target network identifier is the next network identifier to which the terminal device is to be connected, and the target network identifier is the network identifier inferred by the target model;

[0007] If the current network quality meets the switching conditions, the target network identifier is used to connect to the network end indicated by the target network identifier; wherein, if the current network quality meets the switching conditions, it indicates that the terminal device is already within the signal coverage range of the network end indicated by the target network identifier.

[0008] The present application provides a terminal device, including:

[0009] A memory for storing a target model;

[0010] A processing device, used to load a target model and obtain a target network identifier based on the target model; wherein the target network identifier is a next network identifier to be connected by the terminal device, and the target network identifier is a network identifier inferred by the target model;

[0011] The network communication device is used to connect with the network end indicated by the target network identifier based on the target network identifier if the current network quality meets the switching condition.

[0012] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0014] Figure 1 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 1 ;

[0015] Figure 2 A schematic diagram of the structure of network information provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 2 ;

[0017] Figure 4 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 3 ;

[0018] Figure 5 A schematic diagram of a generation model provided in an embodiment of the present application;

[0019] Figure 6 A schematic diagram of a terminal device update model provided in an embodiment of the present application;

[0020] Figure 7 A schematic diagram of a training model provided in an embodiment of the present application;

[0021] Figure 8 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0022] Fig. 9 A hardware entity schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0024] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0025] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0026] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those skilled in the art in the field to which the embodiments of the present application belong. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0027] In the related art, when the network quality of the terminal device is poor, the terminal device usually obtains at least one network identifier from a scanning mechanism to select a network identifier with good signal quality, and connects to the network end indicated by the network identifier with good signal quality. However, this process is only performed when the network quality of the terminal device is poor, and there is a problem of slow connection speed. At the same time, the network end indicated by the network identifier with good signal quality may cause network interruption, and there is a problem of poor network continuity. In addition, there is no model in the terminal device that has the function of predicting the target network identifier.

[0028] The embodiment of the present application provides a processing method, which obtains a target network identifier based on a target model, and then connects to the network end indicated by the target network identifier when the terminal device is already within the signal coverage range of the network end indicated by the target network identifier, wherein the target network identifier is the next network identifier to be connected by the terminal device. In this way, on the one hand, by obtaining the target network identifier through the target model, it is possible to accurately predict the next network identifier to be connected by the terminal device. Since the target network identifier is the most suitable next network identifier to be connected, the possibility of network interruption is reduced, thereby improving the continuity and stability of the network; on the other hand, when the current network quality meets the switching conditions, it can be directly connected to the network end indicated by the target network identifier, thereby improving the speed and efficiency of switching networks; at the same time, this method can be applied to different terminal devices, thereby improving the versatility of the processing method.

[0029] The method provided in the embodiment of the present application can be executed by an electronic device, wherein the electronic device can be a laptop, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device) and other types of terminals, and can also be implemented as a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0030] Figure 1 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 1 ,like Figure 1 As shown, the method includes steps S101 to S102, wherein:

[0031] Step S101, obtaining a target network identifier based on a target model; wherein the target network identifier is the next network identifier to which the terminal device is to be connected, and the target network identifier is the network identifier inferred by the target model.

[0032] Here, the target model has the function of inferring the network identification. In some embodiments, the target model is a trained model, and the model to be trained can be trained by collecting network information to obtain the target model. In some embodiments, the device for training the model can be a terminal device or other electronic device.

[0033] The network identifier is information that characterizes the network. In some embodiments, the network identifiers of different networks are different. The target network identifier may include, but is not limited to: a physical cell identifier (PCI), a cell identifier (also known as a Cell-ID), etc. The PCI is used to distinguish wireless signals from different cells, and there is no identical physical cell identifier within the coverage area of ​​the relevant cell. The cell identifier is used to identify the area covered by a cell. In some embodiments, the network identifier is related to the location information, and the network identifiers corresponding to different location information may be the same or different.

[0034] The method of obtaining the target network identifier may include, but is not limited to: obtaining the target network identifier by using a fitting function in the target model, obtaining the target network identifier by searching for parameters in the target model, etc. For example, the trained target model may include a fitting function, and the fitting function may output the target network identifier after receiving input data. For another example, the target model may store multiple network identifiers, and the network identifier corresponding to the current network identifier may be searched based on the current network identifier, and the network identifier corresponding to the current network identifier may be used as the target network identifier.

[0035] In some embodiments, the information output by the target model may include, but is not limited to, a target network identifier, other data, etc. The other data is used to indicate that the target model has not successfully inferred the target network identifier. The representation of other data may include, but is not limited to, representing other data by numbers, representing other data by letters, etc. For example, when other data is represented by numbers, the number 0 may be used as other data. For another example, when other data is represented by letters, NULL may be used as other data.

[0036] In some implementations, multiple successfully connected network identifiers may be obtained, and based on the multiple successfully connected network identifiers and the target model, the target network identifier may be obtained, wherein the multiple successfully connected network identifiers include the currently connected network identifier.

[0037] In some implementations, the target model may use multiple successfully connected network identifiers to obtain feature information of multiple successfully connected network identifiers, and then determine the target network identifier according to the feature information of the multiple successfully connected network identifiers.

[0038] Step S102, if the current network quality meets the switching condition, connect to the network end indicated by the target network identifier based on the target network identifier; wherein, if the current network quality meets the switching condition, it indicates that the terminal device is already within the signal coverage range of the network end indicated by the target network identifier.

[0039] Here, network quality is a parameter used to measure the performance of the network end indicated by the network identifier of the current connection. Network quality may include, but is not limited to, signal strength, stability, signal to interference plus noise ratio (SINR), etc. In some embodiments, network quality may include other information that can determine signal strength or signal to noise ratio. Signal strength refers to the strength of the signal in the wireless transmission network. The signal strength can be any suitable size, for example, -40dBm (decibel milliwatt), -80dBm, etc. In some embodiments, the smaller the absolute value of the signal strength, the better the corresponding network quality. Stability refers to the continuity and reliability of the network connection. In some embodiments, the higher the stability, the better the corresponding network quality. SINR refers to the ratio of the strength of the received useful signal to the strength of the received interference signal. SINR can be any suitable size, for example, 40dB (decibel), 30dB, etc. In some embodiments, the larger the SINR, the better the corresponding network quality.

[0040] In some embodiments, the current network quality satisfies the switching condition, indicating that the terminal device is already within the signal coverage of the network end indicated by the target network identifier, and the signal strength of the network end indicated by the network identifier currently connected to the terminal device is lower than the first threshold value, and the signal strength of the network end indicated by the target network identifier is higher than the second threshold value. The first threshold value can be any suitable size, for example, -90dBm, -100dBm, etc. The second threshold value can be any suitable size, for example, -70dBm, -80dBm, etc. In some embodiments, the first threshold value and the second threshold value can be the same or different.

[0041] In some implementations, the terminal device may send a measurement report to the base station. When the current network quality meets the switching conditions, the base station sends a switching instruction to the terminal device, so that the terminal device connects to the network end indicated by the target network identifier based on the switching instruction.

[0042] In some implementations, when generating a measurement report, the terminal device may increase the network quality of the network end indicated by the target network identifier in the measurement report to a preset value, thereby ensuring that the terminal device can connect to the network end indicated by the target network identifier. The preset value may be any suitable value, for example, -40dBm, -50dBm, etc.

[0043] In some implementations, if the terminal device fails to connect to the network end indicated by the target network identifier, it can connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0044] In some embodiments, if the current network quality meets the switching conditions and the target model fails to successfully infer the target network identifier, the terminal device can connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0045] In some embodiments, the target network identifier is at least one continuous network identifier inferred by a target model processing multiple successfully connected network identifiers, and the at least one continuous network identifier represents a target path. Therefore, each time the current network quality meets the switching condition, it is connected to a network end represented by a target network identifier in the sorting order of the at least one continuous network identifier.

[0046] In an embodiment of the present application, a target network identifier is obtained based on a target model, and then when the terminal device is already within the signal coverage range of the network end indicated by the target network identifier, the network end indicated by the target network identifier is connected, wherein the target network identifier is the next network identifier to which the terminal device will connect. In this way, on the one hand, by obtaining the target network identifier through the target model, it is possible to accurately predict the next network identifier to which the terminal device will connect. Since the target network identifier is the next network identifier that is most suitable for connection, the possibility of network interruption is reduced, thereby improving the continuity and stability of the network; on the other hand, when the current network quality meets the switching conditions, it can be directly connected to the network end indicated by the target network identifier, thereby improving the speed and efficiency of switching networks; at the same time, this method can be applied to different terminal devices, thereby improving the versatility of the processing method.

[0047] In some embodiments, step S101 includes steps S101a to S101b, wherein:

[0048] Step S101a, obtaining multiple successfully connected network identifiers; wherein the multiple successfully connected network identifiers include the currently connected network identifier.

[0049] Here, the multiple successfully connected network identifiers refer to the network identifiers that the terminal device is connected to at a historical moment. In some embodiments, the multiple successfully connected network identifiers can represent the path that the terminal device has passed. In some embodiments, the multiple successfully connected network identifiers before the moment of performing the network service can be obtained when the terminal device performs the network service.

[0050] The method of obtaining multiple successfully connected network identifiers may include but is not limited to: reading multiple successfully connected network identifiers from the internal storage system of the terminal device, reading multiple successfully connected network identifiers from the cloud, etc. For example, the network identifiers collected by the terminal device can be stored in the internal storage system of the terminal device, and multiple successfully connected network identifiers can be read by reading data from the internal storage system. For another example, the cloud can store a large amount of data, and the terminal device can upload the successfully connected network identifier to the cloud, which can not only improve the reliability and security of the network identifier, but also read multiple successfully connected network identifiers through the cloud.

[0051] In some implementations, the terminal device may construct a data channel for implementing the target network service in response to the target instruction, thereby obtaining multiple network identifiers that have been successfully connected before constructing the data channel for implementing the target network service. The target network service may include, but is not limited to, call service, data transmission service, etc.

[0052] Step S101b, obtaining a target network identifier based on multiple successfully connected network identifiers and a target model; wherein the target network identifier is a network identifier inferred by the target model by processing multiple successfully connected network identifiers.

[0053] Here, multiple successfully connected network identifiers can be input into the target model as input information, so that the target model outputs a target network identifier according to the multiple successfully connected network identifiers to obtain the target network identifier. The method of obtaining the target network identifier may include but is not limited to: obtaining the target network identifier by using a fitting function in the target model, obtaining the target network identifier by finding parameters in the target model, etc.

[0054] In some embodiments, each time the terminal device connects to the network end indicated by the target network identifier, the target network identifier is added to the network identifiers that have been successfully connected, thereby reacquiring multiple network identifiers that have been successfully connected, and again obtaining a new target network identifier based on the multiple network identifiers that have been successfully connected and the target model.

[0055] In some implementations, the target model may use multiple successfully connected network identifiers to obtain feature information of multiple successfully connected network identifiers, and then determine the target network identifier according to the feature information of the multiple successfully connected network identifiers.

[0056] In the implementation manner of the present application, the target network identifier is obtained through multiple successfully connected network identifiers and the target model, and then after connecting to the new network end, multiple successfully connected network identifiers are re-obtained for prediction again, reducing the possibility of network interruption, thereby ensuring network continuity.

[0057] In some embodiments, the method further comprises step S103, wherein:

[0058] Step S103, if the current network quality meets the switching condition and the target model fails to successfully infer the target network identifier, connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0059] Here, the target model fails to infer the target network identifier successfully, which may be that the information output by the target model is other data. In some embodiments, the other data may be represented by numbers, letters, etc.

[0060] The scanning mechanism refers to the process by which the terminal device obtains the network identifier corresponding to the current location information. In some implementations, the connection network identifier and the target network identifier may be the same or different.

[0061] In some implementations, at least one network identifier and a network quality corresponding to the at least one network identifier may be obtained through a scanning mechanism, and a network identifier with good network quality is selected from the at least one network identifier as a connection network identifier.

[0062] In some embodiments, the terminal device can send a measurement report to the base station. When the current network quality meets the switching conditions, the terminal device obtains a connection network identifier based on a scanning mechanism, and the base station sends a switching instruction to the terminal device, so that the terminal device is connected to the network end indicated by the connection network identifier based on the switching instruction.

[0063] In some embodiments, at least one network identifier can be obtained through a scanning mechanism, and the at least one network identifier can be added to multiple successfully connected network identifiers to obtain at least one network identifier sequence to be detected, and the at least one network identifier sequence to be detected is input into the target model, and the target model can output at least one detection result. The detection result represents whether continuous target network services can be performed using at least one network identifier sequence to be detected. The detection results may include, but are not limited to: continuous, discontinuous. In some embodiments, the detection results can be represented by numbers, for example, the number 1 can represent that the detection result is continuous, and the number 0 can represent that the detection result is discontinuous.

[0064] In the implementation manner of the present application, when the target model fails to successfully infer the target network identifier, the network identifier is obtained through a scanning mechanism and the network end is connected, thereby ensuring that there is always the next network identifier that needs to be connected, thereby improving the continuity of the network.

[0065] In some implementations, before obtaining the target network identifier based on the target model, the method further includes steps S104 to S105, wherein:

[0066] Step S104, in response to the target instruction, constructing a data channel for implementing the target network service.

[0067] Here, the target instruction is an instruction that triggers the construction of a data channel for implementing the target network service. In some embodiments, an instruction is the smallest functional unit of the terminal device. The set of all instructions of the terminal device constitutes the instruction system of the terminal device, also known as an instruction set. The target instruction can be obtained from the instruction set.

[0068] The target network service is the network service performed by the terminal device. The target network service may include but is not limited to: call service, data transmission service, etc. The data channel is the path that data passes through during the transmission and processing process, and can transmit data that realizes the target network service.

[0069] In some embodiments, the target instruction is a set of binary codes, and the target instruction includes an operation code field and an address code field. The operation code field is used to indicate the operation that the terminal device needs to perform, and the address code field is used to indicate the location where the terminal device needs to perform the operation.

[0070] In some embodiments, the target instruction includes target information required for constructing a data channel for implementing the target network service. In response to the target instruction, the target information can be read from the target instruction, so as to construct a data channel for implementing the target network service based on the target information. The target information may include, but is not limited to, an Internet Protocol (IP) address, a port number, a protocol type, etc. An IP address is a unified address format provided by the Internet Protocol for identifying a terminal device. The port number can be used to distinguish between different applications or services running on a terminal device, thereby ensuring that data can be transmitted correctly. The protocol type can specify the communication protocol required to implement the target network service.

[0071] Step S105, obtaining multiple successfully connected network identifiers before building a data channel for implementing the target network service; wherein the multiple successfully connected network identifiers include the currently connected network identifier.

[0072] Here, when constructing a data channel to implement the target network service, the terminal device can execute the target network service, thereby obtaining multiple successfully connected network identifiers before constructing the data channel to implement the target network service, to ensure that the target model can be used to infer the target network identifier when the target network service starts.

[0073] In some embodiments, the current network identifier can be obtained as a successfully connected network identifier when executing the target network service, and at least one successfully connected network identifier can be continuously obtained during the process of executing the target network service, and then the target network identifier is obtained based on multiple successfully connected network identifiers obtained during the process of executing the target network service and the target model.

[0074] In an implementation manner of the present application, by constructing a data channel for implementing the target network service in response to a target instruction, and then obtaining multiple network identifiers that have been successfully connected before constructing the data channel for implementing the target network service, the network continuity of the terminal device when performing network services is ensured, thereby enhancing the user experience.

[0075] In some implementations, the target network identifier is at least one continuous network identifier inferred by the target model processing multiple successfully connected network identifiers, and the at least one continuous network identifier represents the target path. Step S102 includes step S121, wherein:

[0076] Step S121 : Each time the current network quality satisfies the switching condition, a connection is made to a network end represented by a target network identifier in the order of at least one continuous network identifier.

[0077] Here, the number of target network identifiers may be any appropriate size, for example, 1, 3, etc. In some implementations, since different network identifiers correspond to different location information, at least one continuous network identifier may represent the target path.

[0078] In some implementations, when the number of the target network identifier is one, a direct connection may be made to the network end represented by the target network identifier.

[0079] In some embodiments, when the number of network identifiers inferred by the target model after processing multiple successfully connected network identifiers is two or more, the target model may use the most frequently used network identifier among the two or more network identifiers as the target network identifier, and correspondingly, the number of target network identifiers inferred by the target model is one.

[0080] In some implementations, when the number of target network identifiers is two or more, the terminal device may select a network end connection represented by a target network identifier with good network quality according to the network quality of the target network identifier.

[0081] Exemplarily, multiple successfully connected network identifiers include: PCI A, PCI B, PCI C, PCID, PCI E, PCI F, PCI G. At least one continuous network identifier inferred by processing multiple successfully connected network identifiers through the target model can be PCI H, or PCI H and PCIO.

[0082] In some embodiments, the number of multiple successfully connected network identifiers is fixed. Whenever a connection is made to a network end represented by a target network identifier, the target network identifier is added to the multiple successfully connected network identifiers. At the same time, the earliest connected network identifier among the multiple successfully connected network identifiers is removed, thereby updating the multiple successfully connected network identifiers.

[0083] Exemplarily, multiple successfully connected network identifiers include: PCI A, PCI B, PCI C, PCID, PCI E, PCI F, PCI G. At least one continuous network identifier inferred by processing multiple successfully connected network identifiers through the target model is PCI H. The multiple successfully connected network identifiers are updated, and PCI B, PCI C, PCID, PCI E, PCIF, PCI G, PCI H are used as multiple successfully connected network identifiers.

[0084] In some implementations, after the multiple successfully connected network identifiers are updated, the updated multiple successfully connected network identifiers are re-input into the target model to obtain a new target network identifier.

[0085] In some embodiments, when the target network identifier is at least one continuous network identifier inferred by the target model processing multiple network identifiers that have been successfully connected, the target model can output the target network identifier continuously in sequence, thereby ensuring that each time the current network quality meets the switching conditions, it is connected to the network end represented by a target network identifier in the sorting order of at least one continuous network identifier.

[0086] The process of connecting to a network end represented by a target network identifier may refer to the specific implementation of step S102.

[0087] In an implementation manner of the present application, multiple continuous target network identifiers are obtained, so that the network is switched sequentially each time the current network quality meets the switching condition. Multiple target network identifiers can be obtained through one prediction, which reduces the amount of data processed by the target model, thereby saving computing resources.

[0088] In some embodiments, the method further comprises step S106, wherein:

[0089] Step S106: The target model obtains characteristic information of the multiple successfully connected network identifiers using the multiple successfully connected network identifiers.

[0090] Here, the characteristic information of the multiple successfully connected network identifiers is information used to determine the target network identifier. The characteristic information may include but is not limited to: path information of the multiple successfully connected network identifiers, frequency information of the multiple successfully connected network identifiers, etc.

[0091] In some implementations, a first correspondence between a network identifier and characteristic information may be established in the target model, and characteristic information of a plurality of successfully connected network identifiers may be determined through the first correspondence.

[0092] In some embodiments, the model to be trained can be trained to obtain the target model. During implementation, network information can be collected, and then the model to be trained can be trained through the network information. The network information may include, but is not limited to: identification information of multiple successfully connected network identifiers of the target network service that has been carried out, identification information of multiple successfully connected network identifiers of the target network service that has been carried out and has been interrupted, and the execution result of the target network service that has been carried out. The identification information may include, but is not limited to: the frequency points of multiple successfully connected network identifiers, the signal strength of multiple successfully connected network identifiers, the reference signal received power (RSRP) of multiple successfully connected network identifiers, the reference signal received quality (RSRQ) of multiple successfully connected network identifiers, etc. The execution result includes, but is not limited to: success, failure. In some embodiments, the execution result can be represented by a number, for example, the number 1 can represent the execution result as success, and the number 0 can represent the execution result as failure. In some embodiments, the number of RSRPs of multiple successfully connected network identifiers and the number of RSRQs of multiple successfully connected network identifiers is multiple.

[0093] Figure 2 A schematic diagram of a network information structure provided in an embodiment of the present application, such as Figure 2 As shown, the network information 20 includes a first PCI identifier 21, a second PCI identifier 22, and an nth PCI identifier 23. Each of the above PCI identifiers includes multiple RSRPs and RSRQs.

[0094] In some embodiments, each target network service that has been carried out corresponds to multiple network identifiers that have been successfully connected, and the multiple network identifiers that have been successfully connected corresponding to each target network service that has been carried out can be used as a network identifier training sequence. Then, according to the execution result, the multiple network identifier training sequences are divided into a first sequence set including multiple network identifier training sequences and a second sequence set including multiple network identifier training sequences, and the model parameters of the model to be trained are updated at least once according to the first sequence set, the second sequence set and the remaining network information to obtain the target model. Among them, the first sequence set includes the network identifier training sequence corresponding to the target network service that has been carried out and the execution result of the target network service that has been carried out is successful. The second sequence set includes the network identifier training sequence corresponding to the target network service that has been carried out and the execution result of the target network service that has been carried out is a failure. The updating method of the model parameters may include but is not limited to at least one of the gradient descent method, the momentum update method, the Newton momentum method, etc.

[0095] In some embodiments, the network identification training sequence in the first sequence set has label information. The target training network identification can be obtained through the first network identification training sequence in the second sequence set and the model to be trained, and then the second network identification training sequence corresponding to the first network identification training sequence is determined in the first sequence set, and then the loss value is determined according to the label information corresponding to the second network identification training sequence and the target training network identification, and the model parameters of the model to be trained are updated at least once by the loss value to obtain the target model. The loss value may include but is not limited to MSE (mean squared error, Mean Squared Error) loss, MAE (mean absolute error, Mean Absolute Error) loss, RMSE (Root Mean Squared Error, root mean square error) loss, etc.

[0096] In some embodiments, the loss value may be calculated using the Pearson Linear Correlation Coefficient (PLCC), the Spearman Rank-order Correlation Coefficient (SRCC), the Kendall Rank-order Correlation Coefficient (KRCC), etc.

[0097] In some embodiments, it can be determined based on the loss value whether the model parameters of the target model need to be updated. For example, the loss value is compared with a threshold value. When the loss value is greater than the threshold value, the model parameters of the target model are updated, and then the target training network identifier and the loss value are determined to determine whether the model parameters of the target model need to be further updated. When the model parameters of the target model do not need to be updated, the target model after the final update is determined as the target model to be used in the end; when the loss value is not greater than the threshold value, the target model is determined as the target model to be used in the end. For another example, the loss value is compared with the last loss value. When the loss value is different from the last loss value, the model parameters of the target model are updated; when the loss value is substantially equal to the last loss value, the target model is determined as the target model to be used in the end.

[0098] In the implementation manner of the present application, the target network identifier is determined by obtaining characteristic information of multiple successfully connected network identifiers through the target model, thereby improving the accuracy of the target network identifier.

[0099] Figure 3 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 1 ,like Figure 3 As shown, the method includes steps S201 to S203, wherein:

[0100] Step S201, obtaining a target network identifier based on a target model; wherein the target network identifier is the next network identifier to which the terminal device is to be connected, and the target network identifier is the network identifier inferred by the target model.

[0101] Step S202, if the current network quality meets the switching conditions, connect to the network end indicated by the target network identifier based on the target network identifier; wherein, if the current network quality meets the switching conditions, it indicates that the terminal device is already within the signal coverage range of the network end indicated by the target network identifier.

[0102] Here, step S201 to step S202 correspond to the aforementioned step S101 to step S102, and during implementation, reference may be made to the specific implementation of the aforementioned step S101 to step S102.

[0103] Step S203, if the connection with the network end indicated by the target network identifier is unsuccessful, connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0104] Here, the connection network identifier and the target network identifier are different network identifiers.

[0105] In some embodiments, an unsuccessful connection to the network end indicated by the target network identifier may be due to: the terminal device does not move along the path indicated by the target network identifier, so that the terminal device cannot be located within the signal coverage range of the network end indicated by the target network identifier, and therefore, the terminal device fails to connect to the network end indicated by the target network identifier.

[0106] In some implementations, the failure to connect to the network end indicated by the target network identifier may be that the network end corresponding to the target network identifier does not support network connection, and therefore the terminal device fails to connect to the network end indicated by the target network identifier.

[0107] In some embodiments, when connecting to the network end indicated by the target network identifier, a connection result can be obtained, and then whether the connection to the network end indicated by the target network identifier is successful can be determined based on the connection result. The connection result may include, but is not limited to: success, failure. The way of expressing the connection result may include, but is not limited to: expressing the connection result by numbers, expressing the connection result by letters, etc. For example, when the connection result is expressed by numbers, the number 1 can indicate that the connection result is successful. For another example, when the connection result is expressed by letters, the letter N can indicate that the connection result is unsuccessful.

[0108] In some embodiments, priorities may be set for the target network identifier and the connection network identifier. The priority of the target network identifier may be any suitable level, such as a first priority, a second priority, etc. The priority of the connection network identifier may be any suitable level, such as a second priority, a third priority, etc. In some embodiments, the priority of the target network identifier is higher than the priority of the connection network identifier.

[0109] In some implementations, the target network identifier can be obtained through the target model while the connection network identifier can be obtained through the scanning mechanism. Then, according to the priority of the target network identifier and the priority of the connection network identifier, the network end indicated by the target network identifier with a higher priority is selected for connection. If the connection with the network end indicated by the target network identifier is unsuccessful, the connection is then based on the connection network identifier and the network end indicated by the connection network identifier.

[0110] In some implementations, the connection network identifier can be first obtained through a scanning mechanism, and then the target network identifier can be obtained through a target model, and then the network end indicated by the target network identifier with a higher priority can be selected for connection according to the priority of the target network identifier and the priority of the connection network identifier. If the connection with the network end indicated by the target network identifier is unsuccessful, the connection is then based on the connection network identifier and the network end indicated by the connection network identifier.

[0111] The process of connecting to the network end indicated by the connection network identifier may refer to the specific implementation of step S103.

[0112] In an embodiment of the present application, when the network end indicated by the target network identifier fails to connect, the network end corresponding to the network identifier obtained through the connection scanning mechanism ensures that the terminal device can continue to have the next network identifier to be connected, thereby ensuring the continuity of the network.

[0113] The following describes the application of the processing method provided in the embodiment of the present application in a practical scenario.

[0114] In the related art, when the network quality of the terminal device is poor, the terminal device usually obtains at least one network identifier from a scanning mechanism to select a network identifier with good signal quality, and connects to the network end indicated by the network identifier with good signal quality. However, this process is only performed when the network quality of the terminal device is poor, and there is a problem of slow connection speed. At the same time, the network end indicated by the network identifier with good signal quality may cause network interruption, and there is a problem of poor network continuity. In addition, there is no model in the terminal device that has the function of predicting the target network identifier.

[0115] The embodiment of the present application provides a processing method, which obtains a target network identifier based on a target model, and then connects to the network end indicated by the target network identifier when the terminal device is already within the signal coverage range of the network end indicated by the target network identifier, wherein the target network identifier is the next network identifier to be connected by the terminal device. In this way, on the one hand, by obtaining the target network identifier through the target model, it is possible to accurately predict the next network identifier to be connected by the terminal device. Since the target network identifier is the most suitable next network identifier to be connected, the possibility of network interruption is reduced, thereby improving the continuity and stability of the network; on the other hand, when the current network quality meets the switching conditions, it can be directly connected to the network end indicated by the target network identifier, thereby improving the speed and efficiency of switching networks; at the same time, this method can be applied to different terminal devices, thereby improving the versatility of the processing method.

[0116] Figure 4 A schematic diagram of an implementation process of a processing method provided in an embodiment of the present application Figure 3 ,like Figure 4 As shown, the method includes steps S301 to S310, wherein:

[0117] Step S301, collecting network information of terminal devices;

[0118] Step S302, extracting a first sequence set and a second sequence set from network information;

[0119] Step S303, using the model to be trained, obtaining a target training network identifier based on the first network identifier training sequence in the second sequence set;

[0120] Step S304, determining a second network identification training sequence corresponding to the first network identification training sequence in the first sequence set;

[0121] Step S305, determining a loss value based on the label information corresponding to the second network identification training sequence and the target training network identification;

[0122] Step S306, updating the model parameters of the model to be trained at least once according to the loss value to obtain a target model;

[0123] Step S307, in response to the target instruction, constructing a data channel for implementing the target network service;

[0124] Step S308, obtaining multiple successfully connected network identifiers before building a data channel to implement the target network service;

[0125] Step S309, obtaining a target network identifier based on multiple successfully connected network identifiers and target models;

[0126] Step S310, when the signal strength of the network end indicated by the network identifier currently connected to the terminal device is lower than the first threshold value, and the signal strength of the network end indicated by the target network identifier is higher than the second threshold value, connect to the network end indicated by the target network identifier based on the target network identifier.

[0127] Figure 5 A schematic diagram of a generation model provided in an embodiment of the present application, such as Figure 5 As shown, where:

[0128] Complete model development;

[0129] Get network information 51;

[0130] Model training is completed through network information 51, and then the target model 52 is obtained.

[0131] In the above process, since the target model is trained through network information, the accuracy of the target model can be improved, and the target network identity can be accurately predicted.

[0132] Figure 6 A schematic diagram of a terminal device update model provided in an embodiment of the present application, such as Figure 6 As shown, where:

[0133] After the model development is completed, the network information 51 is continuously extracted during the use of the terminal device 61, and then the model can be trained through the network information 51, and the model parameters of the target model 52 are updated at least once, so that the target model can more accurately predict the target network identifier.

[0134] Figure 7 A schematic diagram of a training model provided in an embodiment of the present application, such as Figure 7 As shown, where:

[0135] Input the training data 71 into the denoising autoencoder 72 for preprocessing to obtain preprocessed training data 73;

[0136] The preprocessed training data 73 is input into the deep learning neural network 74 for training to obtain a target model 75, wherein the deep learning neural network 74 includes a one-dimensional convolutional neural network 741 and a long short-term memory network 742.

[0137] Here, the training data may include but is not limited to: a network identification training sequence corresponding to a target network service whose execution result is successful, a network identification training sequence corresponding to a target network service whose execution result is failed, etc.

[0138] Denoising Autoencoder (DAE) is a special type of autoencoder that aims to learn a more effective representation of input data by removing noise from the data. The training data is preprocessed by DAE to remove abnormal or unstructured training data. In some embodiments, if a specific network identification sequence (corresponding to the aforementioned multiple successfully connected network identifications) or a related sequence does not appear multiple times in the training data, the specific network identification sequence or the related sequence does not form a significant feature, and the specific network identification sequence or the related sequence will be eliminated.

[0139] One-dimensional convolutional neural network (1D Convolutional Neural Network, 1D-CNN) is a variant of convolutional neural network, mainly good at processing one-dimensional data with sequential characteristics. This network structure is suitable for processing data with sequential characteristics in time or space, such as time series analysis, text processing, etc. In this application, 1D-CNN is mainly used to process tasks related to the characteristics of network identification sequences.

[0140] Long Short-Term Memory (LSTM) is a time-recurrent neural network that is good at capturing long-term dependencies in sequence data, capturing the context and logic in sequence data. The network identification sequence in this application has context and directionality, and the introduction of LSTM is beneficial to improving training accuracy.

[0141] It should be noted that the embodiment of the training model provided by the present application has obvious advantages, which can enable the target model to achieve an accuracy of 80% to 90% when inferring the target network identifier. After machine learning, the target model can predict the target network identifier based on multiple input network identifiers that have been successfully connected. During implementation, the present application does not limit the training method of the target model, and the target model can also be trained by other methods.

[0142] Based on the above embodiments, the present application also provides a terminal device, Figure 8 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the terminal device 800 includes:

[0143] Memory 801, used for storing target models;

[0144] The processing device 802 is used to load the target model and obtain the target network identifier based on the target model; wherein the target network identifier is the next network identifier to be connected by the terminal device, and the target network identifier is the network identifier inferred by the target model;

[0145] The network communication device 803 is used to connect with the network end indicated by the target network identifier based on the target network identifier if the current network quality meets the switching condition.

[0146] Here, the memory is a memory component for storing data and instructions, etc. In some embodiments, the memory can be divided into a read-only memory (ROM) and a random access memory (RAM) according to the usage type of the memory.

[0147] The target model has the function of inferring the network identification. In some embodiments, the target model is a trained model, and the model to be trained can be trained by collecting network information to obtain the target model. In some embodiments, the device for training the model can be a terminal device or other electronic device. In some embodiments, the target model can be loaded into the memory through Over-the-Air Technology (OTA). OTA is a technology for remote management of mobile terminal devices and SIM card data through the air interface of mobile communications.

[0148] The network identifier is information that characterizes the network. In some embodiments, different networks have different network identifiers. The target network identifier may include, but is not limited to, PCI, cell identification code, etc. The method for obtaining the target network identifier may include, but is not limited to, obtaining the target network identifier by using a fitting function in a target model, obtaining the target network identifier by finding parameters in a target model, etc.

[0149] Network quality is a parameter used to measure the performance of the network end indicated by the network identifier of the current connection. Network quality may include but is not limited to: signal strength, stability, SINR, etc. Signal strength can be any suitable value, for example, -40dBm, -80dBm, etc. SINR can be any suitable value, for example, 40dB, 30dB, etc.

[0150] In the implementation mode of the present application, the processing device loads the target model from the target model stored in the memory, obtains the target network identifier based on the target model, and then connects to the network end indicated by the target network identifier through the network communication device when the terminal device is already located in the signal coverage range of the network end indicated by the target network identifier, wherein the target network identifier is the next network identifier to be connected by the terminal device. In this way, on the one hand, by obtaining the target network identifier through the target model, it is possible to accurately predict the next network identifier to be connected by the terminal device. Since the target network identifier is the next network identifier that is most suitable for connection, the possibility of network interruption is reduced, thereby improving the continuity and stability of the network; on the other hand, when the current network quality meets the switching conditions, it can directly connect to the network end indicated by the target network identifier, thereby improving the speed and efficiency of switching networks.

[0151] In some implementations, the network communication device 803 is further used to configure a target network identifier and configure a signal strength of the target network identifier, so that the network communication device is successfully connected to the network end indicated by the target network identifier based on the target network identifier.

[0152] Here, the signal strength of the target network identifier can be any suitable value, for example, -40dBm, -50dBm, etc. In some embodiments, the network communication device can configure the target network identifier and the signal strength of the target network identifier through an application programming interface (Application Programming Interface, API). Using some predefined functions such as API, it is possible to provide applications and developers with the ability to access a set of routines based on certain software or hardware to configure the target network identifier and the signal strength of the target network identifier.

[0153] In some embodiments, the network communication device can send a measurement report to the base station. When the current network quality meets the switching conditions, the base station sends a switching instruction to the network communication device, so that the network communication device is connected to the network end indicated by the target network identifier based on the switching instruction.

[0154] In some implementations, the network communication device may configure the network quality of the network end indicated by the target network identifier in the measurement report to a preset value, thereby ensuring that the terminal device can connect to the network end indicated by the target network identifier. The preset value may be any suitable value, for example, -40dBm, -50dBm, etc.

[0155] In some embodiments, the target network identifier can be obtained through the target model while the connection network identifier can be obtained through the scanning mechanism. The network communication device can configure the network quality of the network end indicated by the connection network identifier in the measurement report to a preset value, wherein the network quality of the network end indicated by the configured connection network identifier is lower than the network quality of the network end indicated by the target network identifier, thereby ensuring that the terminal device can connect to the network end indicated by the target network identifier.

[0156] In the implementation manner of the present application, the network communication device configures the target network identifier and the signal strength of the target network identifier so that the network communication device is successfully connected to the network end indicated by the target network identifier, thereby improving the success rate of the network connection.

[0157] In some embodiments, the network communication device 803 is also used to preferentially connect to the network end indicated by the target network identifier based on the target network identifier when the current network quality meets the switching conditions; if the connection to the network end indicated by the target network identifier is unsuccessful and / or the target model fails to successfully infer the target network identifier, connect to the network end indicated by the connected network identifier based on the connected network identifier; wherein the connected network identifier is a network identifier obtained based on a scanning mechanism.

[0158] Here, the network quality may include but is not limited to: signal strength, stability, SINR, etc. In some embodiments, the current network quality satisfies the switching condition, indicating that the terminal device is already within the signal coverage range of the network end indicated by the target network identifier, and the signal strength of the network end indicated by the network identifier currently connected to the terminal device is lower than the first threshold value, and the signal strength of the network end indicated by the target network identifier is higher than the second threshold value.

[0159] In some implementations, the terminal device may send a measurement report to the base station. When the current network quality meets the switching conditions, the base station sends a switching instruction to the terminal device, so that the terminal device connects to the network end indicated by the target network identifier based on the switching instruction.

[0160] The target model fails to infer the target network identifier successfully, which may be the case where the target model outputs other data. In some embodiments, the other data may be represented by numbers, letters, etc.

[0161] In some embodiments, an unsuccessful connection to the network end indicated by the target network identifier may be due to: the terminal device does not move along the path indicated by the target network identifier, so that the terminal device cannot be located within the signal coverage range of the network end indicated by the target network identifier, and therefore, the terminal device fails to connect to the network end indicated by the target network identifier.

[0162] In some implementations, the failure to connect to the network end indicated by the target network identifier may be that the network end corresponding to the target network identifier does not support network connection, and therefore the terminal device fails to connect to the network end indicated by the target network identifier.

[0163] In some implementations, at least one network identifier and a network quality corresponding to the at least one network identifier may be obtained through a scanning mechanism, and a network identifier with good network quality is selected from the at least one network identifier as a connection network identifier.

[0164] In an embodiment of the present application, the network communication device gives priority to connecting to the network end indicated by the target network identifier inferred by the target model when the current network quality meets the switching conditions. When the connection with the network end indicated by the target network identifier is unsuccessful and / or the target model fails to successfully infer the target network identifier, the network identifier is obtained through a scanning mechanism and the network end is connected, thereby ensuring that the next network identifier that needs to be connected is always available, thereby improving the continuity of the network.

[0165] In some embodiments, the processing device 802 is further used to obtain multiple successfully connected network identifiers; wherein the multiple successfully connected network identifiers include the currently connected network identifier; based on the multiple successfully connected network identifiers and the target model, obtain the target network identifier; wherein the target network identifier is the network identifier inferred by processing the multiple successfully connected network identifiers with the target model.

[0166] In some embodiments, the network communication device 803 is also used to connect to the network end indicated by the connection network identifier based on the connection network identifier if the connection with the network end indicated by the target network identifier is unsuccessful; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0167] In some embodiments, the network communication device 803 is also used to connect to the network end indicated by the connection network identifier based on the connection network identifier if the current network quality meets the switching conditions and the target model fails to successfully infer the target network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

[0168] In some embodiments, the processing device 802 is further used to construct a data channel for implementing the target network service in response to the target instruction; obtain multiple successfully connected network identifiers before constructing the data channel for implementing the target network service; wherein the multiple successfully connected network identifiers include the currently connected network identifier.

[0169] In some embodiments, the target network identifier is at least one continuous network identifier inferred by a target model processing multiple successfully connected network identifiers, and the at least one continuous network identifier represents a target path; the network communication device 803 is also used to connect to a network end represented by a target network identifier in the sorting order of the at least one continuous network identifier each time the current network quality meets the switching condition.

[0170] In some implementations, the target model uses multiple successfully connected network identifiers to obtain feature information of multiple successfully connected network identifiers.

[0171] The description of the above terminal device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the terminal device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0172] It should be noted here that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the same or similar aspects can be referenced to each other. The description of the above device, storage medium, computer program and computer program product embodiments is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiments of the device, storage medium, computer program and computer program product of this application, please refer to the description of the method embodiment of this application for understanding.

[0173] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0174] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the above method when executing the computer program.

[0175] The embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the above method when executed by a processor. The computer-readable storage medium may be transient or non-transient.

[0176] The embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, some or all of the steps in the above method are implemented. The computer program product can be implemented specifically by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) and the like.

[0177] It should be noted that Fig. 9 A schematic diagram of a hardware entity of an electronic device provided in an embodiment of the present application is shown in the figure. As shown in the figure, the hardware entity of the electronic device 900 includes: a processor 901, a communication interface 902 and a memory 903, wherein:

[0178] The processor 901 generally controls the overall operation of the electronic device 900 .

[0179] The communication interface 902 may enable the electronic device 900 to communicate with other terminals or servers via a network.

[0180] The memory 903 is configured to store instructions and applications executable by the processor 901, and can also cache data to be processed or processed by the processor 901 and each module in the electronic device 900 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM). Data transmission between the processor 901, the communication interface 902 and the memory 903 can be carried out through the bus 904.

[0181] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0182] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of each step / process mentioned above does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The serial numbers of the embodiments of the present application mentioned above are for description only and do not represent the advantages and disadvantages of the embodiments.

[0183] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0184] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0185] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0186] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0187] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, read-only memories, magnetic disks or optical disks.

[0188] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0189] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A processing method, the method include: Obtaining a target network identifier based on the target model; wherein the target network identifier is a next network identifier to which the terminal device is to be connected, and the target network identifier is a network identifier inferred by the target model; If the current network quality meets the switching conditions, the terminal device is connected to the network end indicated by the target network identifier based on the target network identifier; wherein, if the current network quality meets the switching conditions, it indicates that the terminal device is already within the signal coverage range of the network end indicated by the target network identifier.

2. The method according to claim 1, wherein the target network identifier is obtained based on the target model. include: Obtaining multiple successfully connected network identifiers; wherein the multiple successfully connected network identifiers include the currently connected network identifier; Based on the multiple successfully connected network identifiers and the target model, the target network identifier is obtained; wherein the target network identifier is a network identifier inferred by the target model through processing the multiple successfully connected network identifiers.

3. The method according to claim 1, further comprising: include: If the current network quality meets the switching condition, connecting to the network end indicated by the target network identifier based on the target network identifier; If the connection with the network end indicated by the target network identifier is unsuccessful, connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

4. The method according to claim 1, further comprising: include: If the current network quality meets the switching condition and the target model fails to successfully infer the target network identifier, connect to the network end indicated by the connection network identifier based on the connection network identifier; wherein the connection network identifier is a network identifier obtained based on a scanning mechanism.

5. The method according to any one of claims 2 to 4, before obtaining the target network identifier based on the target model, the method further comprises: include: In response to the target instruction, a data channel for implementing the target network service is constructed; A plurality of successfully connected network identifiers before building a data channel for implementing the target network service is obtained; wherein the plurality of successfully connected network identifiers includes a currently connected network identifier.

6. The method according to claim 5, wherein the target network identifier is at least one continuous network identifier inferred by the target model processing the multiple successfully connected network identifiers, the at least one continuous network identifier represents the target path, and if the current network quality meets the switching condition, the target network identifier is connected to the network end indicated by the target network identifier based on the target network identifier. include: Each time the current network quality satisfies the switching condition, the network end represented by a target network identifier is connected in the order of the at least one continuous network identifier.

7. The method according to claim 6, further comprising: include: The target model uses the multiple successfully connected network identifiers to obtain feature information of the multiple successfully connected network identifiers.

8. A terminal device, include: A memory for storing a target model; A processing device, used to load the target model and obtain a target network identifier based on the target model; wherein the target network identifier is a next network identifier to be connected by the terminal device, and the target network identifier is a network identifier inferred by the target model; The network communication device is used to connect to the network end indicated by the target network identifier based on the target network identifier if the current network quality meets the switching condition.

9. The terminal device according to claim 8, The network communication device is further used to configure the target network identifier and configure the signal strength of the target network identifier, so that the network communication device is successfully connected to the network end indicated by the target network identifier based on the target network identifier.

10. The terminal device according to claim 9, The network communication device is further configured to preferentially connect to the network end indicated by the target network identifier based on the target network identifier when the current network quality satisfies the switching condition, and if the connection to the network end indicated by the target network identifier is unsuccessful and / or the target model fails to successfully infer the target network identifier, connect to the network end indicated by the connection network identifier based on the connection network identifier; in, The connection network identifier is a network identifier obtained based on a scanning mechanism.

Images