Method and device for detecting communication quality of local area, and storage medium

Abstract

The invention provides a local area communication quality detection method and device and a storage medium, and the method comprises the steps: collecting a first signal quality value recorded during the communication of a 5G-R baseband chip and a second signal quality value recorded during the communication of a detector when a train runs along a line; constructing the first signal quality values into a first signal quality sequence according to the line; constructing the second signal quality values into a second signal quality sequence according to the line; collecting a target operation representing communication quality change for the mobile terminal in the train based on the wireless access point; constructing the target operation into a third signal quality sequence according to the line; correcting the second signal quality sequence into a fourth signal quality sequence of the line according to the first signal quality sequence and the third signal quality sequence; and mapping the fourth signal quality sequence on an electronic map to a local area through which the line passes. The embodiment of the invention improves the accuracy of detecting the quality of mobile communication signals in surrounding areas along the track.

Description

Technical Field

[0001] This invention belongs to the technical field of rail transit, and in particular relates to a method, device and storage medium for detecting communication quality in a local area. Background Technology

[0002] During the operation of high-speed rail, urban rail, and other rail transit trains, base stations along the track provide mobile communication services to passengers. Based on the demand for intelligent and information-based development of rail transit, the quality of mobile communication signals in the areas the train passes through is periodically detected during the train's operation. As a result, a heat map representing the quality of mobile communication signals in the surrounding area is added as a layer on the electronic map along the track, for reference by operators and passengers.

[0003] The quality of mobile communication signals along the railway line is affected by a variety of factors. For example, as the train speed increases, the Doppler frequency offset increases and the base station switching frequency increases, which will lead to a decrease in the quality of mobile communication signals. Also, if the train encounters weather such as rain, snow, fog, or sandstorms, the signal attenuation and electromagnetic interference of mobile communication signals will increase significantly, which will also lead to a decrease in the quality of mobile communication signals.

[0004] Therefore, there may be significant differences in the quality of mobile communication signals detected by different trains at different times in the same area along the track, resulting in low accuracy in detecting the quality of mobile communication signals in the area along the track. Summary of the Invention

[0005] In view of this, the present invention provides a method, device and storage medium for detecting the communication quality of a local area, so as to improve the accuracy of detecting the quality of mobile communication signals in the surrounding areas along the railway line.

[0006] A first aspect of the present invention provides a method for detecting communication quality in a local area, wherein a 5G-R baseband chip and a detector are deployed on a train, the detector comprising a mobile baseband chip, and the method comprising: As the train travels along the line, the first signal quality value recorded by the 5G-R baseband chip during communication and the second signal quality value recorded by the detector during communication are collected. Based on the described line, the first signal quality value is constructed into a first signal quality sequence; Based on the described line, the second signal quality value is constructed into a second signal quality sequence; Based on the target operation of collecting data representing changes in communication quality from mobile terminals in the train using wireless access points; Based on the described circuit, the target operation is constructed as a third signal quality sequence; Based on the first signal quality sequence and the third signal quality sequence, the second signal quality sequence is corrected to the fourth signal quality sequence of the line; The fourth signal quality sequence is mapped onto the local area through which the line passes on the electronic map.

[0007] A second aspect of the present invention provides a device for detecting communication quality in a local area, comprising a 5G-R baseband chip and a detector deployed on a train, wherein the detector includes a mobile baseband chip, and the device includes: The signal quality value acquisition module is used to acquire, when the train is traveling along the line, a first signal quality value recorded during communication by the 5G-R baseband chip and a second signal quality value recorded during communication by the detector; The first signal quality sequence construction module is used to construct a first signal quality sequence based on the first signal quality value according to the line. The second signal quality sequence construction module is used to construct a second signal quality sequence based on the second signal quality value according to the line. The target operation acquisition module is used to acquire target operations representing changes in communication quality from mobile terminals in the train based on wireless access points. The third signal quality sequence construction module is used to construct the target operation into a third signal quality sequence based on the line; The fourth signal quality sequence correction module is used to correct the second signal quality sequence into the fourth signal quality sequence of the line based on the first signal quality sequence and the third signal quality sequence. The fourth signal quality sequence mapping module is used to map the fourth signal quality sequence onto the local areas through which the line passes on the electronic map.

[0008] A third aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for detecting local area communication quality as described in the first aspect above.

[0009] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for detecting local area communication quality as described in the first aspect above.

[0010] A fifth aspect of the present invention provides a computer program product that, when run on a computer, causes the computer to perform the method for detecting local area communication quality as described in the first aspect above.

[0011] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In this embodiment, a 5G-R baseband chip and a detector are deployed on the train. The detector contains a mobile baseband chip. As the train travels along the line, it collects a first signal quality value recorded by the 5G-R baseband chip during communication and a second signal quality value recorded by the detector during communication. Based on the line, the first signal quality value is constructed into a first signal quality sequence. Based on the line, the second signal quality value is constructed into a second signal quality sequence. Based on the wireless access point, a target operation representing a change in communication quality is collected from the mobile terminal in the train. Based on the line, the target operation is constructed into a third signal quality sequence. Based on the first and third signal quality sequences, the second signal quality sequence is corrected into a fourth signal quality sequence for the line. The fourth signal quality sequence is mapped onto the local area traversed by the line on an electronic map. This embodiment uses the stable signal provided by 5G-R as the anchor point and the changing signal provided by user operation based on the wireless access point as the constraint to correct the quality sequence of the second signal collected by the mobile baseband chip. This reduces the impact of factors such as train speed and weather on the signal, reduces the difference in the quality of mobile communication signals detected by different trains at different times in the same area along the track, and improves the accuracy of detecting the quality of mobile communication signals in the area along the track. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of a method for detecting communication quality in a local area provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a signal reconstruction model provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a local area communication quality detection device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the present invention. However, those skilled in the art will recognize that the present application may be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted to avoid unnecessary detail that could obscure the description of the present application.

[0015] The technical solution of the present invention will be illustrated below through specific embodiments.

[0016] Reference Figure 1 The diagram illustrates a method for detecting communication quality in a local area according to an embodiment of the present invention, which may specifically include the following steps: Step 101: While the train is traveling along the line, collect the first signal quality value recorded during communication by the 5G-R baseband chip and the second signal quality value recorded during communication by the detector.

[0017] The train is equipped with 5G-R (5G-Railway, a railway mobile communication system based on 5G technology) baseband chips and detectors.

[0018] 5G-R is a dedicated railway network communication system designed to meet the operational and management needs of railway communications for internal railway use. In contrast, passengers typically connect to public network communication systems (i.e., the public internet) to access the internet. These two systems are independent and isolated, and their terminal devices are not interchangeable.

[0019] The 5G-R operates at a frequency of 2100MHz, with the uplink band at 1965MHz ~ 1975MHz and the downlink band at 2155MHz ~ 2165MHz. Each band has a bandwidth of 10MHz and uses FDD (Frequency Division Duplex) technology.

[0020] Rail transit lines require comprehensive signal coverage (i.e., wide-area coverage). During train operation, the communication systems and services involved include: train control systems, synchronous control and dispatching communication for heavy-haul trains, train route announcements, dispatching commands, and so on.

[0021] These communication systems and services ensure the normal operation of trains. 5G-R can meet the security and reliability requirements of communication (such as a latency of 150ms for the train control system) and provide highly reliable, low-latency communication scenarios.

[0022] The detector is equipped with mobile baseband chips, including 2G, 3G, 4G, and 5G mobile baseband chips, etc. As 2G and 3G networks are gradually phased out, the quality of mobile communication services based on 2G and 3G fluctuates more. Therefore, the frequency of detecting the communication quality of mobile communication services based on 2G and 3G can be appropriately increased.

[0023] In general, a specific detection program can be installed in a mobile terminal (such as a mobile phone) with a mobile baseband chip, and it can be used as a simple detector. It can then be placed in a train.

[0024] As the train travels along its route, the first signal quality value recorded by the 5G-R baseband chip at a preset first frequency can be queried. The first signal quality value represents the quality of the mobile communication signal received by the 5G-R baseband chip, such as SINR (signal-to-noise ratio), CSI (channel state information), BLER (block error rate), etc. It can be the value of a single parameter or the value of multiple parameters combined.

[0025] As the train travels along its route, the detector can query the second signal quality value recorded by the detector at a preset second frequency when communicating with the mobile baseband chip. The second signal quality value represents the quality of the mobile communication signal received by the baseband chip in the mobile terminal, such as RSSI (Received Signal Strength), RxQual (Received Quality Level), Ec / Io (Chip Energy to Interference Power Ratio), etc. It can be the value of a single parameter or the value of multiple parameters combined.

[0026] Step 102: Construct the first signal quality sequence based on the line's first signal quality value.

[0027] In this embodiment, multiple first signal quality values ​​can be spatiotemporally sorted according to the chronological order and the distribution of the lines to construct a first signal quality sequence.

[0028] Generally, a train line is an irregular line with multiple two-dimensional coordinates (i.e., longitude and latitude), each of which has been mapped to a one-dimensional coordinate.

[0029] For example, algorithms such as Douglas-Peucker can be used to preprocess (i.e. simplify) the two-dimensional coordinates of the line. During simplification, the two-dimensional coordinates of the line are transformed from the spherical coordinate system to the planar coordinate system by projection, and the planar coordinate system is normalized to obtain one-dimensional coordinates.

[0030] When the first signal quality value is collected at a certain moment, the two-dimensional coordinates of the train's position on the line at that moment can be recorded, so that the first signal quality value is associated with a certain two-dimensional coordinate of the line. At this time, the two-dimensional coordinate associated with the first signal quality value can be replaced with a one-dimensional coordinate, and the first signal quality value can be arranged into a first signal candidate sequence in the dimension of time.

[0031] Because trains accelerate, decelerate, or even stop on the line based on factors such as stations, the density distribution of the first signal candidate sequence in space is uneven. Considering that the quality of 5G-R-based mobile communication signals is relatively stable in a short time and within a small range, methods such as equidistant resampling, kernel density estimation-based adaptive resampling, and interpolation-assisted uniform resampling can be used to perform density adaptive resampling of the first signal candidate sequence in the one-dimensional coordinate dimension to obtain a first signal quality sequence with uniform density.

[0032] Step 103: Construct the second signal quality sequence based on the line's second signal quality values.

[0033] In this embodiment, multiple second signal quality values ​​can be spatiotemporally sorted according to the chronological order and the distribution of the lines to construct a second signal quality sequence.

[0034] When collecting the second signal quality value at a certain moment, the two-dimensional coordinates of the train's position on the line at that moment can be recorded, so that the second signal quality value is associated with a certain two-dimensional coordinate of the line. At this time, the two-dimensional coordinate associated with the second signal quality value can be replaced with a one-dimensional coordinate, and the second signal quality value can be arranged into a second signal candidate sequence in the dimension of time.

[0035] Because trains accelerate, decelerate, or even stop on the line based on factors such as stations, the density distribution of the second signal candidate sequence in space is uneven. Considering that the quality of 5G-R-based mobile communication signals is relatively stable in a short time and within a small range, methods such as equidistant resampling, kernel density estimation-based adaptive resampling, and interpolation-assisted uniform resampling can be used to perform density adaptive resampling of the second signal candidate sequence in the one-dimensional coordinate dimension to obtain a second signal quality sequence with uniform density.

[0036] Step 104: Collect target operations representing changes in communication quality from mobile terminals in the train based on the wireless access point.

[0037] The antennas in the train receive mobile communication signals (especially 4G and 5G signals) from public network base stations. The CPE (Customer Premises Equipment) in the train converts the mobile communication signals into WiFi (Wireless Fidelity) signals and distributes them to the wireless access points (APs) configured in each carriage of the train, providing onboard local area network services to the passengers in the train.

[0038] In many cases, when passengers on a train perceive changes in the communication quality of their mobile devices on the mobile network, they will switch between their own mobile network and the train's onboard local area network in search of a better service. Therefore, the target operation that indicates the change in communication quality can be collected by the AP (Access Point) from the mobile terminals on the train.

[0039] In the specific implementation, the target operation types include hotspot access operation and hotspot disconnection operation. Hotspot access operation means that the mobile terminal accesses the AP and uses the on-board local area network provided by the train. Hotspot disconnection operation means that the mobile terminal disconnects from the AP and uses its own mobile network.

[0040] Some passengers on the train are sensitive to communication quality and may probe between the train's onboard local area network (LAN) and their mobile device's own mobile communication network. If they perceive a deterioration in the communication quality of their mobile device's own mobile communication network, they may connect their mobile device to the train's access point (AP). Since multiple people use the train's LAN, it is prone to performance bottlenecks. Passengers on the train may try disconnecting the train's AP depending on the surrounding environment. If they notice that the communication quality of their mobile device's mobile communication network has recovered within a short period of time, they will continue to use their mobile device's mobile communication network; otherwise, they will reconnect their mobile device to the train's AP.

[0041] When a mobile terminal in the train is detected to be connected to a wireless access point, the first duration of the mobile terminal's connection to the wireless access point is recorded and compared with a preset first time threshold.

[0042] If the first duration is greater than or equal to the preset first time threshold, it indicates that the mobile terminal's access to the AP is stable. Passengers may feel that the communication quality of the vehicle's local area network is better than the communication quality of the mobile terminal's own mobile communication network. In this case, it is determined that a hotspot access operation indicating a change in communication quality from good to bad has been detected.

[0043] If the first duration is less than the preset first time threshold, it indicates that the operation of the mobile terminal accessing the AP is unstable. Passengers may not feel that the communication quality of the onboard local area network is better than the communication quality of the mobile terminal's own mobile communication network, so the operation of the mobile terminal accessing the wireless access point in the train is ignored.

[0044] When a mobile terminal in the train is detected to have disconnected from the wireless access point, the second duration of the disconnection is recorded and compared with a preset second time threshold.

[0045] If the second duration is greater than or equal to the preset second time threshold, it indicates that the operation of the mobile terminal disconnecting from the AP is stable. Passengers may feel that the communication quality of the mobile terminal's own mobile communication network is better than the communication quality of the vehicle's local area network. In this case, it is determined that a hotspot disconnection operation indicating that the communication quality has changed from poor to good has been detected.

[0046] If the second duration is less than the preset second time threshold, it indicates that the operation of the mobile terminal disconnecting the AP is unstable. Passengers may not feel that the communication quality of the mobile terminal's own mobile communication network is better than the communication quality of the onboard local area network, so the operation of the mobile terminal disconnecting the wireless access point in the train is ignored.

[0047] Step 105: Construct the target operation into a third signal quality sequence based on the line.

[0048] In this embodiment, the target operation generated by the mobile terminal in the train can be regarded as an inflection point representing the change in the line communication quality. Since the 2G base stations, 3G base stations, 4G base stations, and 5G base stations around the line all have the same service deployment needs, they are usually deployed according to the density of residents, which has reference value. Even if the target operation reflects the change in the communication quality of 4G base stations and 5G base stations, it can also reflect to some extent that 2G base stations and 3G base stations may have the same change in communication quality.

[0049] Therefore, multiple target operations can be spatiotemporally ordered according to the chronological order and the distribution of lines, thereby constructing a third signal quality sequence.

[0050] In one embodiment of the present invention, step 105 may include the following steps: Step 1051: Cluster target operations of the same type based on two-dimensional coordinates to obtain operation clusters.

[0051] When collecting target operations at a certain moment, the two-dimensional coordinates of the train's position on the line at that moment can be recorded, so that the target operation is associated with a certain two-dimensional coordinate of the line. At this time, clustering algorithms such as K-means and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) can be used to cluster target operations of the same type based on the two-dimensional coordinate degree, resulting in multiple operation clusters.

[0052] Step 1052: Calculate the confidence of all target operations in the operation cluster relative to the train.

[0053] In this embodiment, each operation cluster can be traversed, and for the same operation cluster, the confidence level of all target operations in the operation cluster in representing changes in communication quality in the current train environment can be evaluated.

[0054] In practical implementation, on the one hand, the first number of all target operations in the operation cluster can be counted.

[0055] On the other hand, with passenger authorization and other conditions, a second number of passengers of various age groups on the train can be counted.

[0056] The length of each age group is not necessarily equal. For example, one age group is 3-12 years old, another is 60-100 years old, and so on.

[0057] An adjustment coefficient is configured for each age group, which is the average number of mobile devices (such as mobile phones, tablets, smart glasses, laptops, etc.) carried by users in that age group.

[0058] Each adjustment coefficient exhibits a single-peak curve variation with each age group. That is, a peak value (e.g., 2.1) of the adjustment coefficient can be set for a certain age group (e.g., 25-35 years old). On one side of the peak value, the adjustment coefficient increases with the increase of age group (i.e., monotonically increasing), and on the other side of the peak value, the adjustment coefficient decreases with the increase of age group (i.e., monotonically decreasing).

[0059] For all age groups, the product of the second quantity and the corresponding adjustment coefficient is summed to obtain the third quantity.

[0060] Calculate the ratio between the first quantity and the third quantity, and use it as the confidence level of all target operations in the operation cluster relative to the train.

[0061] Step 1053: If the confidence level is greater than or equal to the preset confidence threshold, then replace the two-dimensional coordinates of the target operation associated with the nearest center point in the operation cluster with one-dimensional coordinates.

[0062] The confidence level of the target operation in the operation cluster is compared with a preset confidence threshold. If the confidence level is greater than or equal to the preset confidence threshold, it indicates that many passengers in the train are making the same network switch, and the confidence level of the target operation in the operation cluster is high. At this time, the distance between each target operation (two-dimensional coordinate) and the center point is calculated in the operation cluster. The two-dimensional coordinates associated with the target operation that is closest to the center point in the operation cluster (i.e., the target operation (two-dimensional coordinate) has the smallest distance to the center point) are replaced with one-dimensional coordinates. At this time, the target operation that is closest to the center point in the operation cluster represents the entire operation cluster, reducing data interference.

[0063] Step 1054: Configure the first value for the one-dimensional coordinates corresponding to the line to obtain the third signal candidate sequence.

[0064] In this embodiment, a first value (such as 0) can be configured for the one-dimensional coordinates corresponding to the line to obtain a third signal candidate sequence.

[0065] Step 1055: In the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster is corrected according to the type to obtain the third signal quality sequence.

[0066] In the third signal candidate sequence, the first value corresponding to each one-dimensional coordinate is traversed. The first value of the one-dimensional coordinate corresponding to the operation cluster can be modified according to the type of the target operation to represent the change in communication quality, thereby obtaining the third signal quality sequence.

[0067] In specific implementations, the types include hotspot access operations that indicate a change in communication quality from good to bad, and hotspot disconnect operations that indicate a change in communication quality from bad to good.

[0068] Therefore, in the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster of type hotspot access operation is corrected to the second value (such as -1), and the first value of the one-dimensional coordinate corresponding to the operation cluster of type connection disconnection operation is corrected to the third value (such as 1), thus obtaining the third signal quality.

[0069] In this sequence, the second value is less than the first value, and the third value is greater than the first value.

[0070] Step 106: Based on the first signal quality sequence and the third signal quality sequence, correct the second signal quality sequence to the fourth signal quality sequence of the line.

[0071] The 5G-R baseband chip has stronger anti-interference capabilities and provides a stable first signal quality sequence. Fluctuations in the first signal quality sequence can reflect the slight influence of factors such as train speed and weather to a certain extent, and can serve as an anchor point for communication quality. Passengers on the train provide a reliable third signal quality sequence based on AP operations, thereby uncovering potential inflection points in communication quality changes, which can serve as constraints on communication quality. Therefore, based on the first and third signal quality sequences, the second signal quality sequence is modified to a certain extent to obtain the fourth signal quality sequence of the line.

[0072] In one embodiment of the present invention, step 106 may include the following steps: Step 1061: Load the signal reconstruction model.

[0073] In this embodiment, a signal reconstruction model can be built and trained based on the Seq2Seq (Sequence-to-Sequence) architecture.

[0074] When training the signal reconstruction model, the historical first signal quality sequence, second signal quality sequence and third signal quality sequence are set as samples, and the second signal quality sequence can be labeled in various ways.

[0075] For example, the second signal quality sequence can be manually modified to obtain the fifth signal quality sequence, which can then be used as a label.

[0076] For example, high-performance detectors are installed on trains to detect the quality sequence of the fifth signal, which serves as a tag.

[0077] For example, multiple autonomous aerial vehicles carrying detectors can fly along a section of a route under normal weather conditions to detect the quality value of the third signal. Based on the route, multiple segments of the third signal quality value are spliced ​​together to construct a fifth signal quality sequence, which serves as a tag.

[0078] In addition, cross-entropy can be used as the loss function, and Adam (Adaptive Moment Estimation) can be used as the optimizer.

[0079] like Figure 2 As shown, the signal reconstruction model includes a first encoder, a second encoder, a third encoder, a fusion module, and a decoder.

[0080] In the signal reconstruction model, the first encoder, the second encoder, and the third encoder are all encoders in the Seq2Seq architecture. They are responsible for encoding the input sequence (i.e., the first signal quality sequence, the second signal quality sequence, and the third signal quality sequence) into a fixed-length context vector to capture global information of the input sequence.

[0081] The fusion module in the signal reconstruction model is a new structure added on the basis of the Seq2Seq architecture, which is responsible for fusing the context vector output by the encoder.

[0082] The decoder in the signal reconstruction model is a decoder in the Seq2Seq architecture. Its connection is modified from the encoder in the Seq2Seq architecture to a fusion module. The context vector fused by the fusion module is used as the initial input to gradually generate the output sequence (i.e. the fourth signal quality sequence).

[0083] Step 1062: Input the first signal quality sequence into the first encoder and encode it into the first signal feature.

[0084] For example, the first encoder includes structures such as LSTM (Long Short Term Memory), GRU (Gate Recurrent Unit), Linear (linear layer), or combinations thereof.

[0085] The first signal quality sequence is input into the first encoder, which extracts temporal features from the first signal quality sequence, thereby encoding the first signal quality sequence into a first signal feature with uniform dimension.

[0086] Step 1063: Input the second signal quality sequence into the second encoder and encode it into the second signal feature.

[0087] For example, the second encoder includes structures such as LSTM, GRU, Linear, or combinations thereof.

[0088] The second signal quality sequence is input into the second encoder, which extracts temporal features from the second signal quality sequence, thereby encoding the second signal quality sequence into second signal features with uniform dimensions.

[0089] Step 1064: Input the third signal quality sequence into the third encoder and encode it as the third signal feature.

[0090] For example, the third encoder includes structures such as LSTM, GRU, Linear, or combinations thereof.

[0091] The third signal quality sequence is input into the third encoder, which extracts temporal features from the third signal quality sequence, thereby encoding the third signal quality sequence into third signal features with uniform dimensions.

[0092] Step 1065: Input the first signal feature, the second signal feature and the third signal feature into the fusion module and fuse them into multimodal signal features.

[0093] In this embodiment, the first signal feature, the second signal feature, and the third signal feature are input into the fusion module. The fusion module interacts with the first signal feature, the second signal feature, and the third signal feature to fuse them into multimodal signal features.

[0094] For example, such as Figure 2 As shown, the fusion module is a multi-head attention module, which includes multiple head structures and linear layers.

[0095] The multiple head structures in the multi-head attention module can be divided into a stable reference head, an inflection point calibration head, and a global fusion head.

[0096] Taking equal distribution as an example, the multi-head attention module includes 6 head structures, with 2 head structures set as stable reference heads, 2 head structures set as inflection point calibration heads, and 2 head structures set as global fusion heads.

[0097] In addition to even distribution, the number of various head structures can be dynamically adjusted according to the actual reconstruction effect. For example, if the demand for stability is high, the number of stable reference heads can be increased; if the demand for inflection points is high, the number of inflection point calibration heads can be increased, and so on.

[0098] In this example, the first signal feature, the second signal feature, and the third signal feature can be concatenated to form the fourth signal feature, thereby improving the comprehensiveness of the information.

[0099] In the partial header structure (i.e., the stable reference header), the second signal feature is used as the query matrix and the first signal feature is used as the key matrix and value matrix to generate the first reference signal feature. The second signal feature is then aligned with the stable first signal feature to learn its stable characteristics and correct the fluctuations of the second signal feature.

[0100] In the partial head structure (i.e., the inflection point calibration head), a second reference signal feature is generated using the second signal feature as the query matrix and the third signal feature as the key and value matrix. This allows the second signal feature to reference the features of the third signal feature at the inflection point, thus avoiding excessive smoothing and loss of key inflection points.

[0101] In the partial head structure, the second signal feature is used as the query matrix, and the fourth signal feature is used as the key matrix and value matrix to generate the third reference signal feature. This integrates the global information of the three sequences, balances stability and inflection point features, and avoids the information limitations of a single head structure.

[0102] The first reference signal feature, the second reference signal feature, and the third reference signal feature are concatenated (Concat) to form the fourth reference signal feature; In the linear layer, the fourth signal feature is mapped to a multimodal signal feature in a specified dimension.

[0103] Step 1066: Input the multimodal signal features into the decoder for decoding to obtain the fourth signal quality sequence.

[0104] For example, the decoder includes structures such as LSTM, GRU, Linear, or combinations thereof.

[0105] The multimodal signal features are input into the decoder, which extracts temporal features from the multimodal signal features and maps them into a new sequence, thereby decoding the multimodal signal features into a fourth signal quality sequence.

[0106] Step 107: Map the fourth signal quality sequence onto the local areas through which the line passes on the electronic map.

[0107] In this embodiment, the same line can be detected multiple times to obtain multiple fourth signal quality sequences. The multiple fourth signal quality sequences are superimposed (e.g., weighted summation, where the weights decay over time) to obtain the final fourth signal quality sequence. The fourth signal quality sequence is then mapped onto the local area traversed by the line on the train-related electronic map in the form of a layer.

[0108] Furthermore, weather and other information for local areas along the route can be added as layers to the train-related electronic map.

[0109] In certain services, some content in the train-related electronic map can be made available to a group of users, allowing them to assess the communication quality of passengers on the train in real time based on the train-related electronic map.

[0110] In this embodiment, a 5G-R baseband chip and a detector are deployed on the train. The detector contains a mobile baseband chip. As the train travels along the line, it collects a first signal quality value recorded by the 5G-R baseband chip during communication and a second signal quality value recorded by the detector during communication. Based on the line, the first signal quality value is constructed into a first signal quality sequence. Based on the line, the second signal quality value is constructed into a second signal quality sequence. Based on the wireless access point, a target operation representing a change in communication quality is collected from the mobile terminal in the train. Based on the line, the target operation is constructed into a third signal quality sequence. Based on the first and third signal quality sequences, the second signal quality sequence is corrected into a fourth signal quality sequence for the line. The fourth signal quality sequence is mapped onto the local area traversed by the line on an electronic map. This embodiment uses the stable signal provided by 5G-R as the anchor point and the changing signal provided by user operation based on the wireless access point as the constraint to correct the quality sequence of the second signal collected by the mobile baseband chip. This reduces the impact of factors such as train speed and weather on the signal, reduces the difference in the quality of mobile communication signals detected by different trains at different times in the same area along the track, and improves the accuracy of detecting the quality of mobile communication signals in the area along the track.

[0111] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0112] Reference Figure 3 The diagram illustrates a local area communication quality detection device according to an embodiment of the present invention. A 5G-R baseband chip and a detector are deployed on a train. The detector includes a mobile baseband chip. Specifically, the device may include the following modules: The signal quality value acquisition module 301 is used to acquire, when the train is traveling along the line, a first signal quality value recorded during communication by the 5G-R baseband chip and a second signal quality value recorded during communication by the detector; The first signal quality sequence construction module 302 is used to construct a first signal quality sequence based on the first signal quality value according to the line. The second signal quality sequence construction module 303 is used to construct a second signal quality sequence based on the second signal quality value according to the line. The target operation acquisition module 304 is used to acquire target operations representing changes in communication quality based on the mobile terminal in the train using a wireless access point. The third signal quality sequence construction module 305 is used to construct the target operation into a third signal quality sequence based on the line. The fourth signal quality sequence correction module 306 is used to correct the second signal quality sequence into the fourth signal quality sequence of the line based on the first signal quality sequence and the third signal quality sequence. The fourth signal quality sequence mapping module 307 is used to map the fourth signal quality sequence onto the local area through which the line passes on the electronic map.

[0113] In one embodiment of the present invention, the line has multiple two-dimensional coordinates, each of which has been mapped to a one-dimensional coordinate, the first signal quality value is associated with the two-dimensional coordinates, and the second signal quality value is associated with the two-dimensional coordinates; The first signal quality sequence construction module 302 is further configured to: Replace the two-dimensional coordinates associated with the first signal quality value with the one-dimensional coordinates; The first signal quality values ​​are arranged into a first signal candidate sequence along the time dimension; The first signal candidate sequence is subjected to density adaptive resampling along the dimension of the one-dimensional coordinate to obtain the first signal quality sequence; The second signal quality sequence construction module 303 is also used for: Replace the two-dimensional coordinates associated with the first signal quality value with the one-dimensional coordinates; The second signal quality values ​​are arranged into a second signal candidate sequence along the time dimension; The second signal candidate sequence is subjected to density adaptive resampling along the one-dimensional coordinate to obtain the second signal quality sequence.

[0114] In one embodiment of the present invention, the type of the target operation includes a hotspot access operation and a hotspot disconnection operation; the target operation acquisition module 304 is further configured to: When a mobile terminal in the train is detected to be connected to a wireless access point, the first duration of the mobile terminal's connection to the wireless access point is recorded. If the first duration is greater than or equal to a preset first time threshold, then it is determined that a hotspot access operation indicating a change in communication quality from good to bad has been detected. When it is detected that a mobile terminal in the train disconnects from the wireless access point, the second duration of the disconnection of the mobile terminal from the wireless access point is recorded. If the second duration is greater than or equal to a preset second time threshold, then it is determined that a hotspot disconnection operation indicating a change in communication quality from poor to good has been detected.

[0115] In one embodiment of the present invention, the line has multiple two-dimensional coordinates, each of which has been mapped to a one-dimensional coordinate, and the target operation is associated with the two-dimensional coordinates; The third signal quality sequence construction module 305 is also used for: Based on the two-dimensional coordinates, the target operations of the same type are clustered to obtain operation clusters; Calculate the confidence level of all target operations in the operation cluster relative to the train; If the confidence level is greater than or equal to a preset confidence threshold, then the two-dimensional coordinates associated with the target operation closest to the center point in the operation cluster are replaced with the one-dimensional coordinates. A first value is assigned to the one-dimensional coordinates corresponding to the line to obtain a third signal candidate sequence; In the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster is corrected according to the type to obtain the third signal quality sequence.

[0116] In one embodiment of the present invention, the third signal quality sequence construction module 305 is further configured to: Count the first number of all target operations in the operation cluster; The second number of passengers in each age group on the train is counted; each age group is configured with an adjustment coefficient, and each adjustment coefficient changes with the age group in a single-peak curve. The third quantity is obtained by summing the products of the second quantity and the adjustment coefficient. The ratio between the first quantity and the third quantity is calculated as the confidence level of all target operations in the operation cluster relative to the train.

[0117] In one embodiment of the present invention, the type includes a hotspot access operation representing a change in communication quality from good to bad and a hotspot disconnection operation representing a change in communication quality from bad to good; the third signal quality sequence construction module 305 is further configured to: In the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster of the type hotspot access operation is corrected to the second value, and the first value of the one-dimensional coordinate corresponding to the operation cluster of the type connection disconnection operation is corrected to the third value, so as to obtain the third signal quality sequence. Wherein, the second value is less than the first value, and the third value is greater than the first value.

[0118] In one embodiment of the present invention, the fourth signal quality sequence correction module 306 is further configured to: Load a signal reconstruction model; the signal reconstruction model includes a first encoder, a second encoder, a third encoder, a fusion module, and a decoder; The first signal quality sequence is input into the first encoder and encoded as a first signal feature; The second signal quality sequence is input into the second encoder and encoded into a second signal feature; The third signal quality sequence is input into the third encoder and encoded as a third signal feature; The first signal feature, the second signal feature, and the third signal feature are input into the fusion module and fused into a multimodal signal feature; The multimodal signal features are input into the decoder for decoding to obtain the fourth signal quality sequence.

[0119] In one embodiment of the present invention, the fusion module is a multi-head attention module, which includes multiple head structures and a linear layer; The fourth signal quality sequence correction module 306 is also used for: The first signal feature, the second signal feature, and the third signal feature are concatenated to form a fourth signal feature; In part of the header structure, a first reference signal feature is generated using the second signal feature as a query matrix and the first signal feature as a key matrix and a value matrix. In part of the header structure, a second reference signal feature is generated using the second signal feature as a query matrix and the third signal feature as a key matrix and a value matrix. In part of the header structure, a third reference signal feature is generated using the second signal feature as a query matrix and the fourth signal feature as a key matrix and a value matrix. The first reference signal feature, the second reference signal, and the third reference signal feature are concatenated to form a fourth reference signal feature; In the linear layer, the fourth signal feature is mapped to a multimodal signal feature.

[0120] This invention provides a local area communication quality detection device. By using this local area communication quality detection device, the steps in the aforementioned local area communication quality detection method embodiments can be implemented.

[0121] It should be noted that the module division in the various local area communication quality detection devices provided in the above embodiments is illustrative and only represents a logical functional division. In actual implementation, other division methods may also be used. Furthermore, the functional modules in the various embodiments of this invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0122] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the embodiments of the present invention can be embodied in the form of a computer program product, which is stored in a computer storage medium and includes several instructions to cause an electronic device or processor to execute all or part of the steps of the methods in the various embodiments of the present invention. The aforementioned computer storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] Furthermore, the local area communication quality detection device and the local area communication quality detection method provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0124] Reference Figure 4 The diagram illustrates an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device in this embodiment of the invention includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described method embodiment for detecting local area communication quality. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-described device embodiment for detecting local area communication quality.

[0125] For example, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which can be used to describe the execution process of the computer program in the electronic device.

[0126] The electronic device may be a desktop computer, a cloud server, or other computing device. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 4 This is merely one example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0127] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0128] The memory can be an internal storage unit of the electronic device, such as a hard drive or RAM. Alternatively, it can be an external storage device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory can include both internal and external storage units. The memory is used to store the computer program and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output.

[0129] This invention also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for detecting local area communication quality as described in the foregoing embodiments.

[0130] This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for detecting local area communication quality as described in the foregoing embodiments.

[0131] This invention also discloses a computer program product that, when run on a computer, causes the computer to execute the local area communication quality detection method described in the foregoing embodiments.

[0132] The embodiments described above are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting communication quality in a local area, characterized in that, A 5G-R baseband chip and a detector are deployed on the train, the detector containing a mobile baseband chip. The method includes: As the train travels along the line, the first signal quality value recorded by the 5G-R baseband chip during communication and the second signal quality value recorded by the detector during communication are collected. Based on the described line, the first signal quality value is constructed into a first signal quality sequence; Based on the described line, the second signal quality value is constructed into a second signal quality sequence; Based on the target operation of collecting data representing changes in communication quality from mobile terminals in the train using wireless access points; Based on the described circuit, the target operation is constructed as a third signal quality sequence; Based on the first signal quality sequence and the third signal quality sequence, the second signal quality sequence is corrected to the fourth signal quality sequence of the line; The fourth signal quality sequence is mapped onto the local area through which the line passes on the electronic map.

2. The method according to claim 1, characterized in that, The line has multiple two-dimensional coordinates, each of which has been mapped to a one-dimensional coordinate. The first signal quality value is associated with the two-dimensional coordinates, and the second signal quality value is associated with the two-dimensional coordinates. The step of constructing a first signal quality sequence based on the first signal quality value according to the line includes: Replace the two-dimensional coordinates associated with the first signal quality value with the one-dimensional coordinates; The first signal quality values ​​are arranged into a first signal candidate sequence along the time dimension; The first signal candidate sequence is subjected to density adaptive resampling along the dimension of the one-dimensional coordinate to obtain the first signal quality sequence; The step of constructing a second signal quality sequence based on the second signal quality value according to the line includes: Replace the two-dimensional coordinates associated with the first signal quality value with the one-dimensional coordinates; The second signal quality values ​​are arranged into a second signal candidate sequence along the time dimension; The second signal candidate sequence is subjected to density adaptive resampling along the one-dimensional coordinate to obtain the second signal quality sequence.

3. The method according to claim 1, characterized in that, The types of the target operations include hotspot access operations and hotspot disconnection operations; the target operations that collect information on changes in communication quality from mobile terminals in the train based on the wireless access point include: When a mobile terminal in the train is detected to be connected to a wireless access point, the first duration of the mobile terminal's connection to the wireless access point is recorded. If the first duration is greater than or equal to a preset first time threshold, then it is determined that a hotspot access operation indicating a change in communication quality from good to bad has been detected. When it is detected that a mobile terminal in the train disconnects from the wireless access point, the second duration of the disconnection of the mobile terminal from the wireless access point is recorded. If the second duration is greater than or equal to a preset second time threshold, then it is determined that a hotspot disconnection operation indicating a change in communication quality from poor to good has been detected.

4. The method according to claim 1, characterized in that, The line has multiple two-dimensional coordinates, each of which has been mapped to a one-dimensional coordinate, and the target operation is associated with the two-dimensional coordinates; The step of constructing the target operation into a third signal quality sequence based on the line includes: Based on the two-dimensional coordinates, the target operations of the same type are clustered to obtain operation clusters; Calculate the confidence level of all target operations in the operation cluster relative to the train; If the confidence level is greater than or equal to a preset confidence threshold, then the two-dimensional coordinates associated with the target operation closest to the center point in the operation cluster are replaced with the one-dimensional coordinates. A first value is assigned to the one-dimensional coordinates corresponding to the line to obtain a third signal candidate sequence; In the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster is corrected according to the type to obtain the third signal quality sequence.

5. The method according to claim 4, characterized in that, The calculation of the confidence level of all target operations in the operation cluster relative to the train includes: Count the first number of all target operations in the operation cluster; The second number of passengers in each age group on the train is counted; each age group is configured with an adjustment coefficient, and each adjustment coefficient changes with the age group in a single-peak curve. The third quantity is obtained by summing the products of the second quantity and the adjustment coefficient. The ratio between the first quantity and the third quantity is calculated as the confidence level of all target operations in the operation cluster relative to the train.

6. The method according to claim 4, characterized in that, The types include hotspot access operations representing a change in communication quality from good to bad, and hotspot disconnect operations representing a change in communication quality from bad to good; the third signal quality sequence is obtained by correcting the first value of the one-dimensional coordinate corresponding to the operation cluster in the third signal candidate sequence according to the type, including: In the third signal candidate sequence, the first value of the one-dimensional coordinate corresponding to the operation cluster of the type hotspot access operation is corrected to the second value, and the first value of the one-dimensional coordinate corresponding to the operation cluster of the type connection disconnection operation is corrected to the third value, so as to obtain the third signal quality sequence. Wherein, the second value is less than the first value, and the third value is greater than the first value.

7. The method according to any one of claims 1-6, characterized in that, The step of correcting the second signal quality sequence to a fourth signal quality sequence of the line based on the first signal quality sequence and the third signal quality sequence includes: Load a signal reconstruction model; the signal reconstruction model includes a first encoder, a second encoder, a third encoder, a fusion module, and a decoder; The first signal quality sequence is input into the first encoder and encoded as a first signal feature; The second signal quality sequence is input into the second encoder and encoded into a second signal feature; The third signal quality sequence is input into the third encoder and encoded as a third signal feature; The first signal feature, the second signal feature, and the third signal feature are input into the fusion module and fused into a multimodal signal feature; The multimodal signal features are input into the decoder for decoding to obtain the fourth signal quality sequence.

8. The method according to claim 7, characterized in that, The fusion module is a multi-head attention module, which includes multiple head structures and a linear layer; The step of inputting the first signal feature, the second signal feature, and the third signal feature into the fusion module and fusing them into multimodal signal features includes: The first signal feature, the second signal feature, and the third signal feature are concatenated to form a fourth signal feature; In part of the header structure, a first reference signal feature is generated using the second signal feature as a query matrix and the first signal feature as a key matrix and a value matrix. In part of the header structure, a second reference signal feature is generated using the second signal feature as a query matrix and the third signal feature as a key matrix and a value matrix. In part of the header structure, a third reference signal feature is generated using the second signal feature as a query matrix and the fourth signal feature as a key matrix and a value matrix. The first reference signal feature, the second reference signal, and the third reference signal feature are concatenated to form a fourth reference signal feature; In the linear layer, the fourth signal feature is mapped to a multimodal signal feature.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for detecting local area communication quality as described in any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for detecting local area communication quality as described in any one of claims 1-8.

Images