Method, device, electronic device and storage medium for determining quality of wireless network

Abstract

This application discloses a wireless network quality determination method, apparatus, electronic device, and storage medium. These methods, which pertain to the field of communications technology, address the problem of low accuracy in determining the quality of Wi-Fi networks by electronic devices. The method comprises: obtaining spatial feature information and network transmission feature information, the spatial feature information indicating the characteristics of the spatial scene in which the target wireless network resides, and the network transmission feature information indicating the characteristics of the network transmission parameters of the target wireless network; and determining the quality of the target wireless network based on the spatial feature information and the network transmission feature information.

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and specifically relates to a method, device, electronic device and storage medium for determining the quality of a wireless network. Background Art

[0002] Currently, when electronic devices communicate wirelessly via Wireless Fidelity (WiFi), they can determine the quality of the WiFi network in real time. If the WiFi network quality is poor, they can promptly switch from the WiFi network to the cellular network. When the WiFi network quality returns to normal, they can switch back to the cellular network to ensure that the electronic devices can communicate normally.

[0003] However, in the process of electronic devices judging the quality of WiFi networks in real time, they may be affected by the environment in which the electronic devices are located (for example, the presence of obstructions at the location of the electronic devices, interference from other devices, etc.), causing deviations in the judgment results of the electronic devices. As a result, the accuracy of the electronic devices in judging the quality of WiFi networks is low. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device, and storage medium for determining the quality of a wireless network, which can solve the problem of low accuracy of electronic devices in determining the quality of a WiFi network.

[0005] In order to solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for determining the quality of a wireless network, which method includes: obtaining spatial feature information and network transmission feature information, wherein the spatial feature information is used to indicate the characteristics of the spatial scene in which the target wireless network is located, and the network transmission feature information is used to indicate the characteristics of the network transmission parameters of the target wireless network; determining the quality of the target wireless network based on the spatial feature information and the network transmission feature information.

[0007] In a second aspect, embodiments of the present application provide a device for determining the quality of a wireless network. The device includes an acquisition module and a determination module. The acquisition module is configured to acquire spatial feature information and network transmission feature information, wherein the spatial feature information indicates characteristics of a spatial scene in which a target wireless network resides, and the network transmission feature information indicates characteristics of network transmission parameters of the target wireless network. The determination module is configured to determine the quality of the target wireless network based on the spatial feature information and network transmission feature information acquired by the acquisition module.

[0008] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0011] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the method described in the first aspect.

[0012] In an embodiment of the present application, spatial characteristic information indicating the spatial scene in which the target wireless network is located and network transmission characteristic information indicating the network transmission parameters of the target wireless network can be obtained. The quality of the target wireless network can then be determined based on the spatial characteristic information and the network transmission characteristic information. In this solution, since both the spatial characteristic information and the network transmission characteristic information can be obtained, the quality of the target wireless network can be determined based on the obtained spatial characteristic information and the network transmission characteristic information. This means that the quality of the target wireless network is judged based on the combined spatial characteristic information. This makes the quality judgment of the target wireless network more precise, thereby improving the accuracy of the judgment of the quality of the wireless network. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of a method for determining quality of a wireless network provided in an embodiment of the present application;

[0014] Figure 2 This is a schematic diagram of a process for extracting spatial feature vectors provided in an embodiment of the present application;

[0015] Figure 3 This is a flow chart of a network transmission feature vector extraction process provided by an embodiment of the present application;

[0016] Figure 4 This is a schematic diagram of a process for determining the quality of a target wireless network provided by an embodiment of the present application;

[0017] Figure 5 This is a flowchart of a neural network training method provided by an embodiment of the present application;

[0018] Figure 6 This is a schematic structural diagram of a device for determining quality of a wireless network provided in an embodiment of the present application;

[0019] Figure 7 This is one of the hardware structure diagrams of an electronic device provided in an embodiment of the present application;

[0020] Figure 8 This is the second hardware structure diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0023] The following describes in detail the method for determining the quality of a wireless network provided by the embodiment of the present application through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0024] The method for determining the quality of a wireless network in the embodiment of the present application can be applied to a scenario of determining the quality of a wireless network.

[0025] Currently, WiFi networks are one of the main wireless communication methods for electronic devices. When wirelessly communicating over WiFi networks, electronic devices can determine the quality of the WiFi network in real time. When the WiFi network quality is poor, they can promptly switch from the WiFi network to the cellular network. When the WiFi network quality returns to normal, they can switch back to the WiFi network to ensure normal communication. However, when electronic devices determine the quality of the WiFi network in real time, they may be affected by the environment in which the electronic device is located (for example, the presence of obstructions in the electronic device's location, interference from other devices, etc.), causing the electronic device's determination results to be biased. In the prior art, electronic devices determine the quality of the WiFi network mainly through the following methods: 1. Setting a threshold. The electronic device monitors multiple indicators of the WiFi network in real time. When at least one indicator exceeds a preset threshold, the WiFi network quality is judged to be abnormal. 2. Using artificial intelligence (AI) neural network technology to determine the quality of the WiFi network. The electronic device inputs WiFi network transmission information such as signal strength, link rate, packet loss rate, and number of packets sent and received into an AI model. The model outputs a quality score for the current WiFi network. If the score is less than the threshold, the WiFi network quality is judged to be abnormal. 3. When the foreground application freezes, the WiFi network quality is judged to be abnormal. However, the first method mentioned above, where electronic devices determine WiFi network quality by setting a threshold, is only applicable to a limited number of scenarios. The second method, where electronic devices use AI neural network technology to determine WiFi network quality, although applicable to more scenarios, only considers information such as signal strength and packet loss rate, and does not consider spatial characteristics, which is limited. The third method, where electronic devices determine WiFi network quality by whether the application is stuck, has a lag and cannot determine whether the WiFi network quality has returned to normal. As a result, the accuracy of electronic devices in determining WiFi network quality is low.

[0026] In the solution provided in the embodiments of the present application, spatial feature information indicating the spatial scene in which the target wireless network is located and network transmission feature information indicating the network transmission parameters of the target wireless network can be obtained. The quality of the target wireless network can then be determined based on the spatial feature information and the network transmission feature information. In this solution, since both the spatial feature information and the network transmission feature information can be obtained, the quality of the target wireless network can be determined based on the obtained spatial feature information and the network transmission feature information. This means that the quality of the target wireless network is judged based on the combined spatial feature information. This makes the quality judgment of the target wireless network more precise, thereby improving the accuracy of the judgment of the quality of the wireless network.

[0027] The present invention provides a method for determining the quality of a wireless network. Figure 1 FIG. 1 is a flow chart showing a method for determining the quality of a wireless network provided by an embodiment of the present application. Figure 1 As shown, the method for determining the quality of a wireless network provided in an embodiment of the present application may include the following steps 201 to 204.

[0028] Step 201: Acquire spatial feature information and network transmission feature information.

[0029] In an embodiment of the present application, the above-mentioned spatial feature information is used to indicate the characteristics of the spatial scene in which the target wireless network is located, and the network transmission feature information is used to indicate the characteristics of the network transmission parameters of the target wireless network.

[0030] Optionally, in an embodiment of the present application, the above-mentioned spatial feature information may be a spatial feature vector output by a neural network, and the network transmission feature information may be a network transmission feature vector output by a neural network.

[0031] Optionally, in an embodiment of the present application, the above step 201 can be specifically implemented through the following steps 201a and 201b.

[0032] Step 201a: Determine spatial feature information based on the channel state information (CSI) of the target wireless network.

[0033] Optionally, in an embodiment of the present application, the CSI of the target wireless network may be acquired, and then the CSI of the target wireless network may be processed to determine the spatial feature information.

[0034] Optionally, in the embodiment of the present application, the above step 201a can be specifically implemented through the following steps 201a1 and 201a2.

[0035] Step 201a1: Demodulate the signal received through the target wireless network to obtain the CSI of the target wireless network.

[0036] Optionally, in an embodiment of the present application, orthogonal frequency division multiplexing (OFDM) technology may be used to demodulate the received signal.

[0037] Optionally, in an embodiment of the present application, when OFDM is used to demodulate the signal, a fast Fourier transform (FFT) can be performed on the subcarriers of different frequencies, that is, the time domain signal transmitted by the subcarrier is converted into a frequency domain signal. Then, since CSI is a discrete sampling of the channel frequency response (CFR), the sampling point of the CFR can be set to the center frequency of the subcarrier, thereby obtaining the CSI of the target wireless network while demodulating the signal;

[0038] Specifically, the center frequency is f k The CSI of the subcarrier can be expressed as: H(f K )=||H(f K )||e j·sin(∠H) ;

[0039] Among them, H(f) is called CFR, ||H(f k )|| represents amplitude, ∠H represents phase, and j represents a complex number; thus, the CSI of the target wireless network is:

[0040] CSI=[H(f1),H(f2),…,H(f N )] T

[0041] Wherein, K=1, 2, ..., N represents the number of OFDM subcarriers, and T represents matrix transpose.

[0042] It can be understood that if the bandwidth of the target wireless network is 20 MHz, it includes 64 subcarriers, so the acquired CSI is a 64-dimensional complex vector.

[0043] Step 201a2: Extract spatial feature information from the CSI through a neural network.

[0044] In the embodiment of the present application, spatial feature information can be extracted from the CSI through a neural network, that is, a spatial feature vector is obtained.

[0045] Optionally, in an embodiment of the present application, the above-mentioned neural network may be a multilayer perceptron (MLP), a convolutional neural network (CNN), etc.

[0046] It should be noted that the input layer of the neural network is used to receive input information, and the input information is called the input vector; the output layer of the neural network is used to output the result, and the output result is called the output vector.

[0047] Optionally, in the embodiment of the present application, Figure 2 As shown, the above step 201a2 can be specifically implemented through the following steps A1 to A3.

[0048] Step A1: Input 1024-dimensional CSI into the neural network.

[0049] Step A2: The neural network processes the input vector.

[0050] Step A3: The neural network outputs a 32-dimensional spatial feature vector.

[0051] Specifically, the above-mentioned input CSI is organized as follows: since the first 512 dimensions of the 1024-dimensional CSI are amplitude and the last 512 dimensions are phase; for a 20 MHz signal, the first 64 dimensions of the 512-dimensional amplitude or phase are the CSI corresponding to the 20 MHz channel, and the last 448 dimensions are padded with zeros; for a 40 MHz signal, the first 128 dimensions of the 512-dimensional amplitude or phase are the CSI corresponding to the 40 MHz channel, and the last 384 dimensions are padded with zeros; and so on, for an 80 MHz signal, the first 256 dimensions of the 512-dimensional amplitude or phase are the CSI corresponding to the 80 MHz channel, and the last 256 dimensions are padded with zeros; 160 MHz signals do not need to be padded with zeros.

[0052] It should be noted that the dimensions of the neural network input vector and output vector can be adjusted according to actual usage requirements, and the embodiments of this application do not limit this.

[0053] It can be understood that after demodulating the signal received through the target wireless network to obtain the CSI of the target wireless network (for example, a 64-dimensional complex vector), the 64-dimensional complex vector can be input into the neural network. After the neural network processes the input vector, it outputs a 32-dimensional spatial feature vector, thereby extracting the spatial feature information.

[0054] Step 201b: Determine network transmission characteristic information based on network transmission parameters of the target wireless network.

[0055] Optionally, in an embodiment of the present application, network transmission parameters of the target wireless network within multiple time periods may be obtained, and then the network transmission parameters of the target wireless network may be processed through a neural network to determine network transmission characteristic information.

[0056] Optionally, in an embodiment of the present application, the network transmission parameters of the above-mentioned target wireless network may include at least one of the following: signal strength, sending link rate, receiving link rate, number of sent data packets, number of sent data packet losses, number of sent data packet retransmissions, number of received data packets, number of received data packets frame check sequence code (Frame Check Sequences, FCS) errors, number of received beacon frames, Clear Channel Assessment (CCA) busy time ratio, sending data packet delay, Transmission Control Protocol (TCP) round-trip delay; it can be understood that when the network transmission parameters of the target wireless network include all of the above information, this information can be combined into a 12-dimensional vector.

[0057] Optionally, in an embodiment of the present application, network transmission parameters of the target wireless network in multiple time periods may be continuously obtained as input information of the neural network.

[0058] For example, sampling can be performed five times continuously, and when the network transmission parameters sampled each time include all the above information, the network transmission parameters obtained at five consecutive sampling times can be combined into a 60-dimensional vector as the input vector of the neural network.

[0059] Optionally, in an embodiment of the present application, each sampling time period may be a time period of 5-10 seconds, which is not limited in the embodiment of the present application.

[0060] Optionally, in the embodiment of the present application, Figure 3 As shown, the above step 201b can be specifically implemented through the following steps B1 to B3.

[0061] Step B1: Input a 60-dimensional vector into the neural network.

[0062] Step B2: The neural network processes the input vector.

[0063] Step B3: The neural network outputs a 16-dimensional network transmission feature vector.

[0064] It can be understood that after the network transmission parameters of the target wireless network in multiple time periods (for example, a combined 60-dimensional vector) are used as the input vector of the neural network, the neural network can process the input vector and then output a 16-dimensional network transmission feature vector, thereby obtaining network transmission feature information.

[0065] Step 202: Determine the quality of the target wireless network based on the spatial characteristic information and the network transmission characteristic information.

[0066] Optionally, in an embodiment of the present application, after obtaining the spatial feature information and the network transmission feature information, the spatial feature information and the network transmission feature information may be processed to determine the quality of the target wireless network.

[0067] Optionally, in an embodiment of the present application, the above step 202 can be specifically implemented through the following steps 202a and 202b.

[0068] Step 202a: Fusion processing is performed on the spatial feature information and the network transmission feature information to obtain target feature information.

[0069] Optionally, in an embodiment of the present application, after obtaining spatial feature information and network transmission feature information (for example, a 32-dimensional spatial feature vector and a 16-dimensional network transmission feature vector), a vector splicing method can be used to process the spatial feature information and the network transmission feature information to obtain target feature information.

[0070] For example, the spatial feature information and the network transmission feature information may be concatenated using a Concat function.

[0071] Step 202b: Train the target feature information through a neural network to obtain a target quality score.

[0072] In the embodiment of the present application, the target quality score is used to indicate the quality of the target wireless network.

[0073] Optionally, in an embodiment of the present application, the target feature information can be input into the neural network so that the neural network can train the target feature information, and then after the neural network outputs the result information, the quality score of the target wireless network is calculated through the activation function (Soft Version Of Max, Softmax).

[0074] It can be understood that when the quality result output by the neural network is a 2-dimensional vector, a Softmax calculation can be performed to obtain the quality score of the target wireless network.

[0075] Optionally, in an embodiment of the present application, the quality score of the target wireless network is in the range of [0, 1]. When the quality score of the target wireless network is closer to 1, the quality of the target wireless network is better.

[0076] For example, when the quality score of the target wireless network is less than or equal to 0.3, the quality of the target wireless network is determined to be poor; when the quality score of the target wireless network is greater than 0.3 and less than or equal to 0.6, the quality of the target wireless network is determined to be medium; and when the quality score of the target wireless network is greater than 0.6, the quality of the target wireless network is determined to be good.

[0077] Optionally, in the embodiment of the present application, Figure 4 As shown, the above step 202 can be specifically implemented through the following steps C1 to C5.

[0078] Step C1: Concatenate the 32-dimensional spatial feature vector and the 16-dimensional network transmission feature vector using the Concat function to obtain a target feature vector.

[0079] Step C2: input the target feature vector into the neural network.

[0080] Step C3: The neural network processes the target feature vector.

[0081] Step C4: The neural network outputs result information.

[0082] Step C5: Calculate the result information through Softmax to obtain the quality score of the target wireless network.

[0083] An embodiment of the present application provides a method for determining the quality of a wireless network, which can obtain spatial characteristic information indicating the spatial scene in which a target wireless network is located and network transmission characteristic information indicating the network transmission parameters of the target wireless network, and then determine the quality of the target wireless network based on the spatial characteristic information and the network transmission characteristic information. In this solution, since the spatial characteristic information and the network transmission characteristic information can be obtained, the quality of the target wireless network can be obtained based on the obtained spatial characteristic information and the network transmission characteristic information. That is, the quality of the target wireless network is judged by integrating the spatial characteristic information, making the quality judgment of the target wireless network more accurate, thereby improving the accuracy of judging the quality of the wireless network.

[0084] Optionally, in the embodiment of the present application, the method for determining the quality of a wireless network provided in the embodiment of the present application may further include the following steps 301 to 303.

[0085] Step 301: Determine a first loss function based on the wireless network quality of the i-th training sample, the probability that the wireless network of the i-th training sample is abnormal, and the probability that the wireless network of the i-th training sample is normal.

[0086] In the embodiment of the present application, 1≤i≤N, i is an integer, and N is the total number of training samples.

[0087] Optionally, in an embodiment of the present application, a first loss function and a second loss function may be used to train a neural network, and the first loss function may be a loss function for judging wireless network quality.

[0088] Specifically, the calculation formula of the first loss function is as follows:

[0089]

[0090] Where N represents the number of training samples, β i represents the wireless network quality of the i-th sample, Z i1 ' represents the probability of abnormality in the wireless network of the i-th training sample, Z i2 ' represents the probability that the wireless network of the i-th training sample is normal.

[0091] It can be understood that a normal wireless network means that the wireless network is in a stable state, there will be no lag when the user uses the electronic device, and the electronic device transmits data normally.

[0092] Step 302: Based on the number of spatial scenes of N training samples, the spatial feature information of the i-th training sample and the α-th training sample, i The second loss function is determined by the similarity between the spatial scenes and the similarity between the spatial feature information of the i-th training sample and the M spatial scenes.

[0093] In the embodiment of the present application, the α i The spatial scene is the spatial scene corresponding to the i-th training sample, α is the mapping function, and M is the total number of spatial scenes.

[0094] Optionally, in an embodiment of the present application, the above-mentioned second loss function can be a loss function for spatial scene recognition, and the loss function for spatial scene recognition can be any one of the following: softmax loss, triplet loss, cosFace, arcFace, etc., or other loss functions that can be used for classification tasks, which is not limited in the embodiment of the present application.

[0095] Specifically, the calculation formula of the second loss function is as follows:

[0096]

[0097] Where N represents the number of training samples, It is represented by the spatial feature information of the i-th training sample and the α-th i The similarity of spatial scenes, It is expressed as the similarity between the spatial feature information of the i-th training sample and M spatial scenes;

[0098] Among them, M represents the total number of spatial scenes of training samples, x i represents the spatial feature information of the i-th training sample, W is the weight function of 32×M, and W j represents the jth column of the W matrix, b j Represents the spatial vector of the jth spatial scene, W αi represents the αth αth matrix of Wi Column, b αi Indicates the αth i The spatial vector of a spatial scene, T represents the matrix transpose.

[0099] Among them, a column in the W matrix represents a spatial scene, so the j-th column in the W matrix is ​​used to indicate the j-th spatial scene, and the α-th column in the W matrix is ​​used to indicate the j-th spatial scene. i Column is used to indicate the αth i A spatial scene;

[0100] Where b is a vector corresponding to the number of spatial scenes. When the number of spatial scenes is M, b is an M-dimensional vector; b j Then it is the jth number in the M-dimensional vector, that is, b j It can be expressed as the spatial vector of the j-th spatial scene, b αi It can be expressed as the αth i A spatial vector of a spatial scene.

[0101] Step 303: Train a neural network based on the first loss function and the second loss function.

[0102] Optionally, in the embodiment of the present application, according to the first loss function and the second loss function, the calculation formula of the neural network obtained by training is as follows:

[0103] L=L quality +α·L space

[0104] Among them, α is the mapping function.

[0105] Optionally, in the embodiment of the present application, Figure 5 As shown, the above step 303 can be specifically implemented through the following steps S1 to S10.

[0106] Step S1: Input 1024-dimensional CSI into the neural network.

[0107] Step S2: Process the CSI through a neural network.

[0108] Step S3: The neural network outputs a 32-dimensional spatial feature vector.

[0109] Step S4: input 60-dimensional network transmission information into the neural network.

[0110] Step S5: Process the network transmission information through the neural network.

[0111] Step S6: The neural network outputs a 16-dimensional network transmission feature vector.

[0112] Step S7: Concatenate the 32-dimensional spatial feature vector and the 16-dimensional network transmission feature vector using the Concat function.

[0113] Step S8: Obtain the target feature vector after splicing and input it into the neural network.

[0114] Step S9: Process the target feature vector through a neural network.

[0115] Step S10: The neural network outputs a 2-dimensional vector.

[0116] Optionally, in the embodiment of the present application, the output 2-dimensional vector may be subjected to a Softmax calculation to obtain a target wireless network quality score.

[0117] Optionally, in an embodiment of the present application, when training a neural network through a loss function, after inputting the training sample into the neural network and processing the training sample through the neural network to obtain a predicted score, the difference between the predicted score and the true score, that is, the loss value, can be calculated through the above-mentioned loss function. Then, after obtaining the loss value, the neural network updates the various parameters in the neural network through back propagation. Specifically, when the neural network updates the various parameters through back propagation, the first loss function affects all parameters in the neural network, and the second loss function affects parameters related to spatial features; so as to reduce the loss between the true score and the predicted score, so that the predicted score moves closer to the true score, thereby achieving the purpose of training the neural network.

[0118] It should be noted that the wireless network quality determination method provided in the embodiments of the present application can be executed by an electronic device, a wireless network quality determination device, or a control module in a wireless network quality determination device. In the embodiments of the present application, the wireless network quality determination device provided in the embodiments of the present application is described by taking an electronic device executing the wireless network quality determination method as an example.

[0119] Figure 6 FIG. 1 shows a possible structural diagram of a device for determining the quality of a wireless network involved in an embodiment of the present application. Figure 6 As shown, the wireless network quality determination device 70 may include: an acquisition module 71 and a determination module 72 .

[0120] Acquisition module 71 is configured to acquire spatial characteristic information and network transmission characteristic information. The spatial characteristic information indicates characteristics of the spatial scene in which the target wireless network resides, and the network transmission characteristic information indicates characteristics of network transmission parameters of the target wireless network. Determination module 72 is configured to determine the quality of the target wireless network based on the spatial characteristic information and network transmission characteristic information acquired by acquisition module 71.

[0121] An embodiment of the present application provides a device for determining the quality of a wireless network. Since spatial feature information and network transmission feature information can be obtained, the quality of a target wireless network can be obtained based on the obtained spatial feature information and the network transmission feature information. That is, the quality of the target wireless network is judged by integrating the spatial feature information, making the quality judgment of the target wireless network more accurate, thereby improving the accuracy of judging the quality of the wireless network.

[0122] In a possible implementation, the acquisition module 71 is specifically configured to determine the spatial characteristic information according to the channel state information CSI of the target wireless network; and determine the network transmission characteristic information according to the network transmission parameters of the target wireless network.

[0123] In a possible implementation, the acquisition module 71 is specifically configured to demodulate a signal received through the target wireless network to obtain the CSI of the target wireless network; and extract spatial feature information from the CSI through a neural network.

[0124] In one possible implementation, the above-mentioned determination module 72 is specifically used to fuse the spatial feature information and the network transmission feature information to obtain target feature information; and train the target feature information through a neural network to obtain a target quality score, which is used to indicate the quality of the target wireless network.

[0125] In a possible implementation, the wireless network quality determination device 70 provided in the embodiment of the present application further includes: a training module. The above-mentioned determination module 72 is further used to determine the first loss function based on the wireless network quality of the i-th training sample, the probability that the wireless network of the i-th training sample is abnormal, and the probability that the wireless network of the i-th training sample is normal; and based on the number of spatial scenes of the N training samples, the spatial feature information of the i-th training sample and the α-th training sample, the first loss function is determined. i The similarity between the spatial scenes and the spatial feature information of the i-th training sample and the M spatial scenes is used to determine the second loss function. i The spatial scene is the spatial scene corresponding to the i-th training sample, α is the mapping function, and M is the total number of spatial scenes. The training module is configured to train a neural network based on the first loss function and the second loss function determined by the determination module 72. Here, 1≤i≤N, i is an integer, and N is the total number of training samples.

[0126] The wireless network quality determination device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in an electronic device. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It can also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), an ATM, or an kiosks, etc., and the embodiment of the present application does not specifically limit it.

[0127] The wireless network quality determination device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0128] The wireless network quality determination device provided in the embodiment of the present application can implement each process implemented in the above method embodiment, and to avoid repetition, it will not be described here.

[0129] Alternatively, as Figure 7 As shown, an embodiment of the present application also provides an electronic device 900, including a processor 901 and a memory 902, wherein the memory 902 stores a program or instruction that can be run on the processor 901, and when the program or instruction is executed by the processor 901, the various steps of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0130] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0131] Figure 8 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present application.

[0132] The electronic device 100 includes but is not limited to components such as a radio frequency unit 101 , a network module 102 , an audio output unit 103 , an input unit 104 , a sensor 105 , a display unit 106 , a user input unit 107 , an interface unit 108 , a memory 109 , and a processor 110 .

[0133] Those skilled in the art will understand that the electronic device 100 may also include a power source (such as a battery) to power each component, and the power source may be logically connected to the processor 110 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be repeated here.

[0134] Among them, the processor 110 is used to obtain spatial feature information and network transmission feature information, where the spatial feature information is used to indicate the characteristics of the spatial scene in which the target wireless network is located, and the network transmission feature information is used to indicate the characteristics of the network transmission parameters of the target wireless network; and determine the quality of the target wireless network based on the spatial feature information and the network transmission feature information.

[0135] An embodiment of the present application provides an electronic device that can obtain spatial feature information and network transmission feature information. Therefore, the quality of the target wireless network can be obtained based on the obtained spatial feature information and the network transmission feature information. That is, the quality of the target wireless network is judged by integrating the spatial feature information, making the quality judgment of the target wireless network more accurate, thereby improving the accuracy of judging the quality of the wireless network.

[0136] Optionally, the processor 110 is specifically configured to determine the spatial characteristic information according to the channel state information CSI of the target wireless network; and determine the network transmission characteristic information according to the network transmission parameters of the target wireless network.

[0137] Optionally, the processor 110 is specifically configured to demodulate a signal received through the target wireless network to obtain a CSI of the target wireless network; and extract spatial feature information from the CSI through a neural network.

[0138] Optionally, the processor 110 is specifically used to fuse the spatial feature information and the network transmission feature information to obtain target feature information; and train the target feature information through a neural network to obtain a target quality score, which is used to indicate the quality of the target wireless network.

[0139] Optionally, the processor 110 is further configured to determine a first loss function based on the wireless network quality of the i-th training sample, the probability that the wireless network of the i-th training sample is abnormal, and the probability that the wireless network of the i-th training sample is normal; and determine a first loss function based on the number of spatial scenes of the N training samples, the spatial feature information of the i-th training sample, and the α-th training sample. i The similarity between the spatial scenes and the spatial feature information of the i-th training sample and the M spatial scenes is used to determine the second loss function. i The spatial scene is the spatial scene corresponding to the i-th training sample, α is the mapping function, and M is the total number of spatial scenes; and according to the first loss function and the second loss function, a neural network is trained to obtain the neural network; wherein 1≤i≤N, i is an integer, and N is the total number of training samples.

[0140] The electronic device provided in the embodiment of the present application can implement each process implemented in the above method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0141] The beneficial effects of various implementations in this embodiment can be specifically referred to the beneficial effects of the corresponding implementations in the above method embodiment. To avoid repetition, they will not be described here.

[0142] It should be understood that in an embodiment of the present application, the input unit 104 may include a graphics processing unit (GPU) 1041 and a microphone 1042, and the graphics processor 1041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 106 may include a display panel 1061, and the display panel 1061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 107 includes a touch panel 1071 and at least one of other input devices 1072. The touch panel 1071 is also called a touch screen. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Other input devices 1072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0143] The memory 109 can be used to store software programs and various data. The memory 109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 109 may include a volatile memory or a non-volatile memory, or the memory 109 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM), and a direct memory bus random access memory (DRRAM). The memory 109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0144] Processor 110 may include one or more processing units. Optionally, processor 110 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 110.

[0145] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0146] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0147] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0148] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0149] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0150] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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 statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0152] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A method for determining the quality of a wireless network, characterized in that: The method comprises: Acquire spatial feature information and network transmission feature information, wherein the spatial feature information is used to indicate characteristics of a spatial scene in which a target wireless network is located, the characteristics of the spatial scene in which the target wireless network is located are used to characterize the physical environment in which the electronic device is located, and the network transmission feature information is used to indicate characteristics of network transmission parameters of the target wireless network; determining the quality of the target wireless network based on the spatial characteristic information and the network transmission characteristic information; The determining the quality of the target wireless network according to the spatial characteristic information and the network transmission characteristic information includes: fusing the spatial feature information and the network transmission feature information to obtain target feature information; Training the target feature information through a neural network to obtain a target quality score, where the target quality score is used to indicate the quality of the target wireless network; The method further comprises: Determining a first loss function according to the wireless network quality of the i-th training sample, the probability that the wireless network of the i-th training sample is abnormal, and the probability that the wireless network of the i-th training sample is normal; According to the number of spatial scenes of N training samples, the spatial feature information of the i-th training sample and the spatial feature information of the α-th training sample, i The similarity between the spatial features of the i-th training sample and the M spatial scenes is used to determine the second loss function. The α-th i The spatial scene is the spatial scene corresponding to the i-th training sample, α is the mapping function, and M is the total number of spatial scenes; The neural network is obtained by training according to the first loss function and the second loss function; Where 1≤i≤N, i is an integer, and N is the total number of training samples.

2. The method according to claim 1, characterized in that The obtaining of spatial feature information and network transmission feature information includes: Determining the spatial characteristic information according to the channel state information CSI of the target wireless network; The network transmission characteristic information is determined according to the network transmission parameters of the target wireless network.

3. A device for determining the quality of a wireless network, characterized in that: The wireless network quality determination device includes: an acquisition module and a determination module; The acquisition module is configured to acquire spatial feature information and network transmission feature information, wherein the spatial feature information is used to indicate features of a spatial scene in which a target wireless network is located, the features of the spatial scene in which the target wireless network is located are used to characterize a physical environment in which an electronic device is located, and the network transmission feature information is used to indicate features of network transmission parameters of the target wireless network; The determining module is configured to determine the quality of the target wireless network based on the spatial feature information and the network transmission feature information acquired by the acquiring module; The determination module is specifically configured to fuse the spatial feature information and the network transmission feature information to obtain target feature information; and train the target feature information through a neural network to obtain a target quality score, where the target quality score is used to indicate the quality of the target wireless network; The wireless network quality determination apparatus further includes: a training module; The determination module is further configured to determine a first loss function based on the wireless network quality of the i-th training sample, the probability that the wireless network of the i-th training sample is abnormal, and the probability that the wireless network of the i-th training sample is normal, where N is the total number of training samples; and based on the number of spatial scenes of the N training samples, the spatial feature information of the i-th training sample, and the α-th training sample. i The similarity between the spatial features of the i-th training sample and the M spatial scenes is used to determine the second loss function. The α-th i The spatial scene is the spatial scene corresponding to the i-th training sample, α is the mapping function, and M is the total number of spatial scenes; The training module is configured to train the neural network according to the first loss function and the second loss function determined by the determination module; Wherein, 1≤i≤N, and i is an integer.

4. The device according to claim 3, characterized in that The acquisition module is specifically configured to determine the spatial characteristic information according to the channel state information CSI of the target wireless network; and determine the network transmission characteristic information according to the network transmission parameters of the target wireless network.

5. An electronic device, characterized in that: The system comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method for determining the quality of a wireless network according to any one of claims 1 to 2.

6. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method for determining the quality of a wireless network according to any one of claims 1 to 2 are implemented.

Images