Wireless signal quality monitoring method, system and equipment in mobile communication scene

Abstract

The invention discloses a wireless signal quality monitoring method, system and equipment in a mobile communication scene, and relates to the technical field of computer signal monitoring. The method comprises the following steps: collecting data, and constructing a signal quality generation state vector; executing the signal quality generation state vector to perform time sequence correlation modeling, and generating a signal quality generation track; performing quality inversion analysis, reversely mapping a wireless signal quality change result to a generation state component combination, and positioning a dominant generation path type; determining a signal quality generation reference system; carrying out comparative analysis on the signal quality generation track and the signal quality generation reference system, and establishing a comparative analysis result; and outputting a wireless signal quality monitoring result according to the comparative analysis result and the dominant generation path type. The technical problem that the reliability of the monitoring result is insufficient due to the fact that the wireless signal quality is difficult to monitor in a targeted mode by combining the mobile communication scene difference in the prior art is solved, and the technical effect of improving the reliability of the monitoring result is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer signal monitoring, in particular to a wireless signal quality monitoring method, system and device in a mobile communication scenario. BACKGROUND

[0002] With the rapid development of mobile communication technology, the communication demand of mobile terminals in high-speed mobile, cross-region handover and various complex environments is increasing, and the wireless signal quality has become one of the key factors affecting the communication service experience and network operation efficiency. The existing wireless signal quality monitoring technology is usually based on terminal side physical layer measurement indicators or simple statistical analysis methods, and independently or statically evaluates parameters such as signal strength, signal-to-noise ratio and bit error rate. This kind of method often ignores the correlation between terminal side wireless measurement data, link layer transmission behavior data and network side scheduling feedback data in actual application, and is difficult to reflect the dynamic formation mechanism of the evolution of wireless signal quality with time. In addition, in the process of mobile communication of computer equipment, the dominant factors causing the change of wireless signal quality in different communication scenarios are significantly different, and a single indicator or empirical threshold is difficult to accurately describe the cause of the change of signal quality. When the terminal is in a complex or rapidly changing mobile communication scenario, the existing technology is difficult to distinguish the signal quality fluctuations caused by terminal motion, link state change or network scheduling strategy, which is easy to cause distortion or misjudgment of the monitoring result. SUMMARY

[0003] The present application provides a wireless signal quality monitoring method, system and device in a mobile communication scenario, which solves the technical problem that it is difficult to monitor the wireless signal quality in combination with the differences of mobile communication scenarios in the prior art, resulting in insufficient reliability of the monitoring result.

[0004] In a first aspect, the present application provides a wireless signal quality monitoring method in a mobile communication scenario, the method comprising: In the process of mobile communication of computer equipment, terminal side wireless measurement data, link layer transmission behavior data and network side scheduling feedback data are collected, and a signal quality generation state vector for representing the formation mechanism of wireless signal quality is constructed based on the collected data; time series correlation modeling of the signal quality generation state vector is performed to generate a signal quality generation trajectory for describing the evolution of wireless signal quality with time; quality inversion analysis is performed using the signal quality generation trajectory to reversely map the observed wireless signal quality change result to the corresponding generation state component combination, and locate the dominant generation path type causing the current signal quality change; the mobile communication scenario in which the terminal is currently located is obtained, and the signal quality generation reference system corresponding to the mobile communication scenario is determined; the signal quality generation trajectory and the signal quality generation reference system are compared and analyzed to establish a comparison and analysis result; and the wireless signal quality monitoring result is output according to the comparison and analysis result and the dominant generation path type.

[0005] In a second aspect, the present application provides a wireless signal quality monitoring system in a mobile communication scenario, comprising: A data collection module collects terminal-side wireless measurement data, link layer transmission behavior data, and network-side scheduling feedback data during the mobile communication of the computer device, and constructs a signal quality generation state vector based on the collected data, the vector representing the formation mechanism of the wireless signal quality. A time sequence modeling module performs time sequence correlation modeling on the signal quality generation state vector, and generates a signal quality generation trajectory describing the evolution of the wireless signal quality over time. A quality inversion module performs quality inversion analysis using the signal quality generation trajectory, reversely maps the observed wireless signal quality change result to the corresponding combination of generation state components, and locates the dominant generation path type causing the current signal quality change. A scenario determination module determines the mobile communication scenario corresponding to the signal quality generation reference system. A comparative analysis module compares the signal quality generation trajectory with the signal quality generation reference system, and establishes a comparative analysis result. A result output module outputs the wireless signal quality monitoring result according to the comparative analysis result and the dominant generation path type.

[0006] In a third aspect, the present application provides an electronic device, comprising a memory for storing executable instructions, and a processor for executing the executable instructions stored in the memory to implement the wireless signal quality monitoring method in a mobile communication scenario provided by the present application.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: In the present application, the terminal-side wireless measurement data, the link layer transmission behavior data, and the network-side scheduling feedback data are collected during the mobile communication of the computer device, and a signal quality generation state vector is constructed based on the collected data, the vector representing the formation mechanism of the wireless signal quality. Then, time sequence correlation modeling is performed on the signal quality generation state vector, and a signal quality generation trajectory is generated to describe the evolution of the wireless signal quality over time. Further, quality inversion analysis is performed using the signal quality generation trajectory, the observed wireless signal quality change result is reversely mapped to the corresponding combination of generation state components, and the dominant generation path type causing the current signal quality change is located. Then, the mobile communication scenario corresponding to the signal quality generation reference system is determined, and the signal quality generation trajectory is compared with the signal quality generation reference system to establish a comparative analysis result. Finally, the wireless signal quality monitoring result is output according to the comparative analysis result and the dominant generation path type. The technical problem of the prior art that it is difficult to monitor the wireless signal quality in combination with the differences in the mobile communication scenario, resulting in insufficient reliability of the monitoring result, is solved, and the technical effect of improving the reliability of the monitoring result is achieved. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic flowchart of a wireless signal quality monitoring method in a mobile communication scenario provided in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of a wireless signal quality monitoring system in a mobile communication scenario provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0010] Figure labeling: Data acquisition module 11, time series modeling module 12, quality inversion module 13, scene determination module 14, comparative analysis module 15, result output module 16, processor 21, memory 22, input device 23, output device 24. Detailed Implementation

[0011] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0012] Example 1, as Figure 1 As shown in the figure, this application provides a method for monitoring wireless signal quality in a mobile communication scenario, wherein the method includes: During mobile communication of computer devices, wireless measurement data, link layer transmission behavior data, and network-side scheduling feedback data are collected from the terminal side. Based on the collected data, a signal quality generation state vector is constructed to characterize the formation mechanism of wireless signal quality.

[0013] In the mobile communication process of the computer device, the terminal collects terminal-side wireless measurement data in real time through a wireless interface, the terminal-side wireless measurement data at least including reference signal received power, reference signal received quality, signal-to-noise ratio, channel quality indicator value and cell handover related measurement results; at the same time, link layer transmission behavior data is obtained from the link layer, the link layer transmission behavior data at least including packet retransmission times, modulation and coding scheme, scheduling interval, transmission delay and packet loss; and scheduling feedback data corresponding to the terminal is obtained from the network side, the network side scheduling feedback data at least including scheduling resource allocation proportion, time-frequency resource block allocation result, power control instruction and scheduling priority information. The terminal-side wireless measurement data, the link layer transmission behavior data and the network side scheduling feedback data collected are time-stamped aligned according to a unified time reference, and data synchronization is performed based on a preset sampling period to form a multi-source data set in the same time slice, wherein the preset sampling period is set to 100ms-1000ms, preferably 200ms or 500ms; the maximum time deviation threshold allowed by the time-stamped alignment is set to not more than 20% of the sampling period. For data of different sources, outlier rejection, missing value filling and normalization processing are performed respectively, wherein the outlier rejection adopts a three-sigma rule based on a sliding time window, and the sliding time window length is set to 5-10 sampling periods to eliminate the influence of dimension difference on subsequent modeling.

[0014] After completing the data preprocessing, according to the sequential action relationship of the environment state, the link state and the network scheduling state in the wireless signal quality forming process, the multi-source data set is sequentially combined, the terminal-side wireless measurement data reflecting the environment and channel state, the link layer transmission behavior data reflecting the link bearing state and the network side scheduling feedback data reflecting the resource control state are sequentially mapped into a plurality of generated state components, and are spliced according to the preset component order and dimension to obtain a signal quality generated state vector for characterizing the wireless signal quality forming mechanism. The signal quality generated state vector has fixed dimension and determined component meaning at each sampling time, and is used as the basis input for subsequent time series correlation modeling and signal quality generated trajectory construction.

[0015] Further, in the mobile communication process of the computer device, the terminal-side wireless measurement data, the link layer transmission behavior data and the network side scheduling feedback data are collected by combining event triggering and periodic collection strategies.

[0016] The periodic collection is used to obtain basic data reflecting normal evolution trend of wireless signal quality, and the event-triggered collection is used to obtain key data with high timeliness when wireless communication state changes significantly. Specifically, for terminal-side wireless measurement data, signal strength, signal-to-noise ratio, channel quality indicator and other measurement results are periodically obtained according to a preset periodic sampling interval, and the periodic sampling interval is preferably 100 ms to 1 s; when it is detected that the terminal performs cell switching, the reference signal receiving power drops by more than 3 dB in two continuous sampling periods, the signal-to-noise ratio drops by more than 5 dB, or the wireless link interruption recovers, and other preset events, the encryption collection of the terminal-side wireless measurement data is immediately triggered. For link layer transmission behavior data, the number of packet retransmissions, the delay and the packet loss are periodically summarized according to a preset statistical window (500 ms to 2 s); when the link layer detects that the number of retransmissions exceeds a preset retransmission threshold (for example, 3 times) in the statistical window, the average delay increases by more than 30% compared with the historical average, or the packet loss rate exceeds 5%, the event collection of the link layer transmission behavior data is triggered to capture the transient change of the link state. For network-side scheduling feedback data, resource allocation and power control related information is obtained according to a scheduling period (1 ms to 10 ms); when the network side adjusts the scheduling strategy, the number of resource blocks allocated to the terminal changes by more than a preset proportion (for example, 20%) in continuous scheduling periods, or the priority of the terminal changes, the event collection of the network-side scheduling feedback data is triggered.

[0017] For example, in a certain mobile communication process, the terminal is in an urban road mobile scenario, and the system sets the periodic collection period of terminal-side wireless measurement data, link layer transmission behavior data and network-side scheduling feedback data to be 100 milliseconds. When the data is collected at time 10:00:00.000 according to the periodic collection strategy, the terminal-side wireless measurement data shows that the reference signal received power is about -85 dBm, the reference signal received quality is about -9 dB, the signal-to-noise ratio is about 18 dB, and the channel quality indicator value is 11; the link layer transmission behavior data shows that the number of packet retransmissions in the statistical window is 1, the average transmission delay is about 25 milliseconds, and the packet loss rate is about 0.2%; the network-side scheduling feedback data shows that the terminal obtains a time-frequency resource block allocation ratio of about 20%, the modulation and coding mode used is 64QAM, and the transmit power control instruction is at a normal level. Subsequently, during the terminal movement, a cell switching event occurs at time 10:00:00.350, triggering the event collection mechanism, and the system immediately collects the corresponding multi-source data. The terminal-side wireless measurement data shows that the reference signal received power has dropped to about -97 dBm, the reference signal received quality has dropped to about -14 dB, the signal-to-noise ratio has dropped to about 6 dB, and the channel quality indicator value has dropped to 5; the link layer transmission behavior data shows that the number of packet retransmissions has risen to 6, the average transmission delay has risen to about 78 milliseconds, and the packet loss rate has risen to about 3.5%; the network-side scheduling feedback data shows that the time-frequency resource block allocation ratio has decreased to about 12%, the modulation and coding mode has been adjusted to 16QAM, and the transmit power control instruction has been power up. After time stamp alignment, abnormal value processing and normalization mapping of the above periodic collection data and event triggered data, the signal quality generation state vector corresponding to the time is constructed by combining the terminal-side wireless measurement data, the link layer transmission behavior data and the network-side scheduling feedback data in the predetermined order, which is used for subsequent time series correlation modeling and signal quality generation trajectory analysis, thereby realizing continuous description of the change process of wireless signal quality.

[0018] Further, constructing a signal quality generation state vector for representing the formation mechanism of wireless signal quality based on collected data includes: The terminal-side wireless measurement data, link layer transmission behavior data and network-side scheduling feedback data in the collected data are hierarchically processed according to the time resolution and data update period to generate multiple time scale data subsets; in each time scale data subset, data decorrelation processing and normalization mapping are performed to eliminate the dimensional differences and statistical coupling relationships between different data sources; the evolution order of environment-link-scheduling in the wireless signal quality formation process is obtained, and the order-constrained combination of the processed data subsets is performed according to the evolution order to construct a generation state component sequence; the weight allocation rule based on time consistency is applied to the generation state component sequence to form a signal quality generation state vector with fixed dimension and order constraint.

[0019] Preferably, according to the sampling frequency, time resolution and update cycle of each type of data, the data is divided into multiple time scale data subsets, wherein the time scale at least includes a short time scale (sampling period of 50-200 ms) for reflecting high-frequency data subsets of transient change characteristics, and a longer time scale (sampling period of 1-5 s) for reflecting low-frequency data subsets of trend change characteristics. In the data subsets of each time scale, the de-correlation processing and normalization mapping processing are respectively performed for data of different sources. The de-correlation processing adopts a feature screening method based on Pearson correlation coefficient, when the absolute value of the correlation coefficient of any two data features in the same time scale is greater than 0.8, the feature with larger information amount is retained and the weight of another feature is weakened; the normalization mapping processing adopts a minimum-maximum normalization method, which uniformly maps data of different physical meanings and dimension ranges to the [0, 1] numerical interval, so as to eliminate the dimension difference and numerical scale inconsistency between the terminal side, the link layer and the network side data.

[0020] After completing the hierarchical processing and data preprocessing, the evolution sequence of the environment state, the link state and the network scheduling state in the wireless signal quality formation process is obtained, wherein the environment state corresponds to the terminal side wireless measurement data, the link state corresponds to the link layer transmission behavior data, the network scheduling state corresponds to the network side scheduling feedback data, and the evolution sequence is set as environment state-link state-network scheduling state. According to the evolution sequence, the processed different time scale data subsets are sequentially constrained and combined according to the preset order, and each type of data is mapped to a generated state component arranged in sequence to construct a generated state component sequence. In the generated state component sequence, according to the time consistency degree of each generated state component in a continuous time window, a weight distribution rule is applied to each generated state component, wherein the length of the continuous time window is set to 5-10 sampling periods; when the variance of the generated state component in the continuous time window is less than a preset stability threshold of 0.05, a higher weight of 0.6-0.8 is distributed, and when the variance of the generated state component is greater than or equal to the stability threshold, a lower weight of 0.2-0.4 is distributed. By weighted integration of the generated state component sequence, a signal quality generated state vector with fixed dimension, clear component sequence and weight constraint is finally formed, which is used to represent the formation mechanism of wireless signal quality and as an input for subsequent time series correlation modeling.

[0021] Further, based on the collected data, the signal quality generated state vector for representing the formation mechanism of wireless signal quality is constructed, which further includes: The credibility evaluation is performed based on numerical stability, change consistency and matching degree with the mobile communication scenario constraint condition of the corresponding generated state component in a continuous time window; and the corresponding signal quality generated state vector is marked according to the credibility evaluation result.

[0022] Preferably, in a continuous time window, each generated state component in the signal quality generated state vector is respectively evaluated in terms of numerical stability, change consistency and matching degree with the mobile communication scenario constraint condition. The window length of the continuous time window can be pre-set to 3-10 sampling periods, preferably 5 sampling periods. The numerical stability is used to represent whether the fluctuation amplitude of the generated state component in the continuous time window is within a pre-set stable range, and a stability index can be obtained by calculating the ratio of the standard deviation to the mean value of the generated state component in the time window. When the stability index is less than a pre-set stability threshold, it is determined that the generated state component has higher numerical stability, wherein the stability threshold can be pre-set to 0.2-0.5. The change consistency is used to represent whether the change trend of the generated state component remains consistent in direction or the change rate is continuous in the continuous time window. A change consistency index can be obtained by judging the consistent proportion of the change direction of the generated state component at adjacent sampling points in the time window. When the change direction consistent proportion is higher than a pre-set consistency threshold, it is determined that the change consistency meets the requirements, wherein the consistency threshold can be pre-set to 70%-90%. The matching degree with the mobile communication scenario constraint condition is used to represent whether the change characteristics of the generated state component meet the reasonable change range under the current mobile communication scenario of the terminal. The change amplitude and change rate of the generated state component can be compared with the reference interval corresponding to the mobile communication scenario. When the time proportion of the generated state component falling into the reference interval is higher than a pre-set matching degree threshold, it is determined that the matching degree meets the requirements, wherein the matching degree threshold can be pre-set to 80%-95%. Based on the evaluation results of the numerical stability, change consistency and matching degree, a credibility evaluation value is calculated for each generated state component. The credibility evaluation value can be obtained by weighted summation, and compared with a pre-set credibility threshold, wherein the credibility threshold can be pre-set to 0.6-0.8. If the credibility evaluation value of a generated state component is lower than the credibility threshold, it is determined that the generated state component has abnormality or uncertainty in the corresponding time window. According to the credibility evaluation result, the corresponding signal quality generated state vector is marked, which at least includes adding a credibility identifier or an abnormality identifier to the generated state vector, indicating that the generated state vector needs to be subjected to weight reduction, result prompt or abnormality processing in the subsequent time sequence correlation modeling or quality inversion analysis process. Through the marking process, the reliability and robustness of the subsequent signal quality monitoring result can be improved without affecting the overall structure of the signal quality generated state vector.

[0023] The numerical stability, change consistency and matching degree with the mobile communication scenario constraint condition of each generated state component in the signal quality generated state vector are evaluated, specifically including: first, in a continuous time window, the numerical sequence of each generated state component is extracted, and the mean, fluctuation amplitude or change range of the numerical sequence in the time window is calculated to represent the numerical stability of the generated state component. When the fluctuation amplitude is within a preset stable interval, it is determined that the generated state component has high numerical stability in the current time window; when the fluctuation amplitude exceeds the preset stable interval, it is determined that the numerical stability is low. Secondly, the change trend of the generated state component in the continuous time window is calculated, and the direction and rate of change of the numerical value between adjacent time points are calculated to represent the change consistency. When the change direction of the generated state component in the time window remains consistent, or the change rate continuously and smoothly changes between adjacent time points, it is determined that the generated state component has high change consistency; when the change direction frequently reverses or the change rate suddenly changes, it is determined that the change consistency is low. Further, the matching degree of the generated state component with the mobile communication scenario constraint condition is evaluated in combination with the current mobile communication scenario of the terminal. Specifically, according to the reasonable change range or constraint threshold value corresponding to different mobile communication scenarios, the numerical level, change amplitude and change rate of the generated state component in the current time window are compared with the constraint threshold value, and when the change characteristics of the generated state component meet the constraint condition of the mobile communication scenario, it is determined that the matching degree is high; when it does not meet the constraint condition, it is determined that the matching degree is low.

[0024] After completing the numerical stability, change consistency and matching degree with the mobile communication scenario constraint condition evaluation of each generated state component in the signal quality generated state vector, the evaluation results are comprehensively processed to generate the credibility evaluation value of the corresponding generated state component. Specifically, for each generated state component, the stability evaluation value, consistency evaluation value and matching degree evaluation value are obtained according to the numerical stability evaluation result, change consistency evaluation result and scene matching degree evaluation result in a continuous time window, wherein each evaluation value is mapped to a unified evaluation interval to represent the credibility of the generated state component in the corresponding evaluation dimension. On this basis, the stability evaluation value, consistency evaluation value and matching degree evaluation value are combined by weighting to obtain the credibility evaluation value of the generated state component. The weight of each evaluation dimension can be set according to the mobile communication scenario type or monitoring demand to reflect the relative importance of different evaluation dimensions to the credibility of the generated state component. When the credibility evaluation value is higher than a preset credibility threshold, the corresponding generated state component is determined to be a high credibility generated state component; when the credibility evaluation value is lower than the credibility threshold, the corresponding generated state component is determined to be a low credibility generated state component.

[0025] For example, in the case of wireless signal quality monitoring of a terminal in a city road mobile communication scenario, terminal-side wireless measurement data, link layer transmission behavior data and network-side scheduling feedback data are collected in a time window of 5s with a sampling period of 1s. In the time window, the sampling sequence of the reference signal received power in the terminal-side wireless measurement data is -88dBm, -87dBm, -89dBm, -88dBm, -87dBm, and the sampling sequence of the signal-to-noise ratio is 15dB, 16dB, 15dB, 16dB, 15dB. The fluctuation amplitude of the reference signal received power in the time window is 2dB, which does not exceed the preset stability threshold of 3dB, the change direction remains consistent, and it is within the reasonable signal range of the city road mobile communication scenario. Based on the above numerical stability, change consistency and scenario constraint matching, the numerical stability evaluation value, change consistency evaluation value and scenario matching degree evaluation value corresponding to the generated state component are calculated according to the preset evaluation mapping rule, and the evaluation values are all in the high value range of the preset evaluation interval, which is used to represent that the generated state component has a high degree of credibility in the current time window. In the same time window, the packet retransmission number in the link layer transmission behavior data is 1, 1, 2, 1, 1, and the corresponding transmission delay is 28ms, 30ms, 35ms, 29ms, 30ms. The retransmission number has a small overall fluctuation but rises at individual sampling times, and the numerical stability and change consistency evaluation results are at a medium level, and still satisfy the link load constraint condition in the city road scenario, and the corresponding scenario matching degree evaluation result is at a medium-high level. The network-side scheduling feedback data shows that the time-frequency resource proportion allocated to the terminal remains between 15% and 18% in the time window, the modulation and coding level is basically stable, and no scheduling strategy switching event occurs, and the numerical stability, change consistency and matching degree with the city road mobile communication scenario are all high. Based on the above evaluation results, the numerical stability evaluation value, change consistency evaluation value and scenario matching degree evaluation value of each generated state component are mapped to a unified evaluation interval, and are combined by weighting according to the preset weight, to obtain the credibility evaluation value of the terminal-side wireless measurement generated state component, which is about 0.90, the credibility evaluation value of the link layer generated state component is about 0.75, and the credibility evaluation value of the network-side scheduling generated state component is about 0.92. Further, the credibility evaluation value is compared with the preset credibility threshold of 0.80, the terminal-side wireless measurement generated state component and the network-side scheduling generated state component are marked as high-credibility generated state components, and the link layer generated state component is marked as a general-credibility generated state component, and the marking results are attached to the corresponding signal quality generated state vector, so that in the subsequent time sequence correlation modeling and quality inversion analysis process, the participation weight of the generated state component is adjusted or an abnormal prompt is triggered according to the credibility of the generated state component, thereby improving the reliability and stability of the wireless signal quality monitoring result.

[0026] The signal quality generation state vector is used to perform time correlation modeling to generate a signal quality generation trajectory describing the evolution of wireless signal quality over time.

[0027] Further, the signal quality generation state vector is used to perform time correlation modeling to generate a signal quality generation trajectory describing the evolution of wireless signal quality over time, including: The signal quality generation state vector corresponding to the mobile communication scenario during data collection is obtained, and a set of time correlation parameters corresponding to the scenario is determined according to the mobile communication scenario; according to the set of time correlation parameters, time alignment and correlation window division are performed on the signal quality generation state vectors at consecutive time points to form a sequence of generation state vectors under the constraint of the scenario; in the sequence of generation state vectors, the evolution increment between adjacent signal quality generation state vectors is calculated based on the change rate threshold and the correlation window length corresponding to the mobile communication scenario; the sequence of generation state vectors is processed by using the evolution increment and the evolution discrimination rule corresponding to the mobile communication scenario to perform continuous evolution constraint and scenario trigger mutation marking; and a signal quality generation trajectory is constructed according to the processed sequence of generation state vectors.

[0028] Preferably, the mobile communication scenario identifier corresponding to each signal quality generation state vector during the data acquisition period is obtained. The mobile communication scenario identifier characterizes the current communication state type of the terminal, and includes at least one of the following: stationary or low-speed mobile scenario, high-speed mobile scenario, dense cell coverage scenario, or frequent handover scenario. Based on the mobile communication scenario identifier, a set of time-series association parameters pre-associated with that scenario is invoked. The time-series association parameter set includes at least parameters such as time alignment tolerance, association window length, and change rate threshold. The time alignment tolerance in the time-series association parameter set is preset based on the timestamp accuracy of the acquired data, preferably 5ms to 50ms; the association window length is set according to the changing characteristics of the mobile communication scenario, preferably 1s to 3s in low-speed or stationary scenarios, and preferably 100ms to 500ms in high-speed mobile or frequent handover scenarios. After determining the set of time-series correlation parameters, time alignment processing is performed on the signal quality generator vectors acquired at consecutive time points according to the time-series correlation parameter set to eliminate time offsets caused by different data sources and sampling periods. The time-aligned generator vectors are then divided into windows based on a preset correlation window length to form a generator vector sequence that satisfies the constraints of the mobile communication scenario. In this generator vector sequence, based on the rate of change threshold and correlation window length corresponding to the mobile communication scenario, the evolution increment between signal quality generator vectors at adjacent time points is calculated one by one. This evolution increment characterizes the magnitude and direction of change of the wireless signal quality formation state over continuous time. The rate of change threshold limits the maximum allowable change magnitude between adjacent signal quality generator vectors. Its value is determined based on historical statistical results or empirical rules, preferably the mean of the rate of change of the Euclidean distance between generator vectors plus one to two standard deviations. When the evolution increment between adjacent generator vectors exceeds the rate of change threshold, it is determined that the continuous evolution condition is not met. Furthermore, using the evolutionary increment and combining it with the evolutionary discrimination rules corresponding to the mobile communication scenario, continuous evolution constraint processing is performed on the generated state vector sequence to determine whether the changes in the generated state vector over time satisfy the reasonable evolution conditions under the scenario. When the evolutionary increment exceeds the change rate threshold of the corresponding scenario, a scenario-triggered mutation marker is applied to the corresponding time point to indicate abnormal changes or state abrupt changes in wireless signal quality. The evolutionary discrimination rules include at least a continuity discrimination rule and a mutation discrimination rule. The continuity discrimination rule is used to determine whether the evolutionary increment maintains the same direction or slow change characteristics within a continuous association window. The mutation discrimination rule is used to determine whether the evolutionary increment experiences a sudden increase or decrease within a single association window. When the mutation discrimination rule is satisfied, a scenario-triggered mutation marker is applied to the corresponding time point.After completing the continuous evolution constraint and mutation labeling processing, the generated state vector sequence and its corresponding evolution increment and mutation label are correlated and integrated in chronological order to construct a signal quality generation trajectory describing the evolution of wireless signal quality over time. This signal quality generation trajectory serves as the foundational data for subsequent quality inversion analysis and scene comparison analysis.

[0029] By performing quality inversion analysis using the signal quality generation trajectory, the observed wireless signal quality changes are mapped inversely to the corresponding generator state component combinations, thus identifying the dominant generation path type that causes the current signal quality change.

[0030] Furthermore, performing quality inversion analysis using the signal quality generation trajectory includes: In the signal quality generation trajectory, trajectory change features characterizing the amplitude, duration, and recovery characteristics of wireless signal quality changes are extracted. These trajectory change features are then correlated and matched with the evolution features of each generator component in the signal quality generation vector within the corresponding time period to construct a correspondence between the trajectory change features and the generator components. Based on this correspondence, the contribution index of each generator component to the current wireless signal quality change is calculated. The distribution results of the contribution index are used to locate the dominant generation path type that causes the current signal quality change.

[0031] Preferably, a target time interval for changes in wireless signal quality is determined within the signal quality generation trajectory, and trajectory change features characterizing the changes in wireless signal quality are extracted within this target time interval. The trajectory change features include at least the amplitude of the wireless signal quality change, reflecting the degree to which the signal quality deviates from the normal level; the duration of the change, reflecting the length of time the abnormal or degraded signal quality state is maintained; and the change recovery characteristics, reflecting the speed and trend of the signal quality recovering from the abnormal state to a stable state. The amplitude of the wireless signal quality change can be quantified by the change in Reference Signal Received Quality (RSRQ) or Channel Quality Indicator (CQI), the duration of the change can be set to the length of time during which the stability threshold is continuously not met, and the change recovery characteristics can be characterized by the time required for the signal quality index to recover to the stable interval or the change slope. After obtaining the trajectory change features, a signal quality generation state vector sequence corresponding to the target time interval is extracted, and the evolution characteristics of each generation state component in the generation state vector within the corresponding time period are further obtained. These evolution characteristics include at least the amplitude, rate, and duration of change of the generation state components. The trajectory change features are correlated and matched one by one with the evolution features of each generator component to construct a correspondence between the trajectory change features and the generator components, which is used to describe the degree of correlation between the changes of different generator components and the overall signal quality change. The change rate can be defined as the difference between the generator component values ​​in adjacent sampling periods, and the change persistence can be defined as the number of time windows in which the generator component continuously exceeds a preset change threshold. Based on the correspondence, the contribution index of each generator component to the current wireless signal quality change is calculated. The contribution index is used to quantify the extent to which the evolution features of the generator components participate in and influence the wireless signal quality change process. A contribution distribution result is formed based on the contribution index corresponding to each generator component. The contribution index can be calculated based on the correlation between the generator component change amplitude and the trajectory change amplitude, the overlap ratio of change time sequence, or the normalized weighted result, and the contribution index is normalized to the [0, 1] interval. Furthermore, based on the contribution distribution results, generator components with contribution values ​​exceeding a preset threshold are selected. Combining the temporal order and continuity of these generator components, a combined analysis is performed to identify the dominant generation path type causing the current change in wireless signal quality. The preset threshold can be set between 0.6 and 0.8. When the contribution value of a single generator component or a combination of generator components exceeds the preset threshold, it is determined to be the dominant generation path. If multiple generator components simultaneously meet the threshold condition, the dominant generation path type is determined according to their order of appearance and duration priority.

[0032] Based on the correspondence between the trajectory change characteristics and the generator components, the contribution index of each generator component to the current wireless signal quality change is calculated. Specifically, firstly, a target time interval for the change in wireless signal quality is determined, and within this target time interval, the amplitude, duration, and recovery characteristics of the wireless signal quality change are obtained as a baseline description of the trajectory change characteristics. Secondly, for each generator component, within the same target time interval, the amplitude, duration, and trend characteristics of the numerical change of the generator component are calculated. The amplitude of the generator component's change is obtained by comparing the maximum and minimum values ​​of the generator component within the target time interval; the duration of the generator component's change is obtained by statistically analyzing the length of time the generator component continuously deviates from its stable interval; and the trend of the generator component's change is determined by judging whether the generator component continuously increases, continuously decreases, or changes first and then stabilizes within the target time interval. After obtaining the evolutionary characteristics of the generator components, amplitude matching calculations are performed on the amplitude of the generator component changes and the amplitude of the wireless signal quality changes. Temporal overlap calculations are also performed on the duration of the generator component changes and the duration of the wireless signal quality changes. Finally, trend consistency judgments are made on the trend of the generator component changes and the trend of the wireless signal quality changes. Amplitude matching measures the closeness between the intensity of the generator component changes and the intensity of the signal quality changes; temporal overlap measures the degree of temporal overlap between abnormal changes in the generator component and abnormal changes in the signal quality; and trend consistency determines whether the direction of the generator component changes is consistent with the direction of the signal quality changes. Based on the calculation results of these three dimensions, corresponding amplitude matching scores, temporal overlap scores, and trend consistency scores are generated for each generator component. These three scores are then combined according to a preset weighting rule to obtain a comprehensive contribution evaluation value for the generator component to the current wireless signal quality change. Finally, the comprehensive contribution evaluation values ​​of all generator components are normalized to ensure that the contribution indicators of each generator component are within a uniform numerical range, thus forming a set of contribution indicators for each generator component to the current wireless signal quality change. The contribution index is used to characterize the relative influence of different generator state components on the current changes in wireless signal quality, and provides a quantitative basis for determining the dominant generation path type in the future.

[0033] Obtain the current mobile communication scenario of the terminal and determine the signal quality generation reference system corresponding to the mobile communication scenario.

[0034] Based on terminal-side wireless measurement data, link-layer transmission behavior data, and network-side scheduling feedback data, the current communication state of the terminal is determined. This scenario determination includes at least a comprehensive analysis of the terminal's movement state, cell handover frequency, channel stability, and network load characteristics to identify the current mobile communication scenario type. The mobile communication scenario type includes at least one of the following: stationary or low-speed movement scenario, high-speed movement scenario, dense user access scenario, and frequent cell handover scenario. Specifically, based on a comprehensive analysis of the terminal's displacement speed, number of cell handovers, reference signal received power fluctuation amplitude, and link-layer retransmission rate within a continuous 5-second time window, a stationary or low-speed movement scenario is determined when the terminal's average movement speed is less than 3 km / h and the number of cell handovers is less than or equal to 1; a high-speed movement or frequent handover scenario is determined when the terminal's average movement speed is greater than 60 km / h or at least 3 cell handovers occur within 10 seconds; and a dense user access scenario is determined when the downlink resource block occupancy rate is greater than 80% within the scheduling period and the terminal's average scheduling interval is greater than a preset threshold.

[0035] After determining the mobile communication scenario type, a pre-associated signal quality generation reference system is invoked. This reference system characterizes the typical generation state and normal evolution range of wireless signal quality under the corresponding mobile communication scenario. It includes at least the distribution characteristics of the generation state vector, the evolution characteristics of the generation trajectory, and the rate of change constraints obtained from historical monitoring data or long-term statistical analysis under that scenario. Specifically, for stationary or low-speed mobile scenarios, the rate of change threshold for each component in the generation state vector is set to no more than 1.5 times the corresponding standard deviation; for high-speed mobile or frequent handover scenarios, the rate of change threshold is set to no more than 3 times the corresponding standard deviation; for dense user access scenarios, the rate of change threshold is dynamically relaxed to a range of 2 to 4 times the standard deviation based on the scheduling load. Specifically, based on the mobile communication scenario type, a reference system matching the current scenario is selected from a pre-stored set of scenario reference systems, and this reference system is mapped to a set of reference parameters consistent with the dimension of the signal quality generation trajectory for subsequent comparative analysis. This set of reference parameters is used at least to define the normal fluctuation range and reasonable evolution path of wireless signal quality under the corresponding mobile communication scenario.

[0036] The signal quality generation trajectory is compared and analyzed with the signal quality generation reference system to establish the comparison and analysis results.

[0037] Specifically, a dimensionality consistency check is performed on the signal quality generation trajectory and the signal quality generation reference system to ensure that the generated state vectors at each time point in the generation trajectory are consistent with the reference parameters in the generation reference system in terms of component dimensions, order, and weight meaning. After completing the dimensionality consistency check, the signal quality generation trajectory is mapped to the time window corresponding to the signal quality generation reference system in chronological order. The time window is a sliding window of a preset time length, which can be set to 1s to 5s, preferably 2s. Within each time window, the generated state vector at the corresponding time point in the generation trajectory is compared and analyzed with the corresponding baseline generated state vector or baseline distribution interval in the generation reference system. Specifically, the difference between the numerical amplitude of each component of the generated state vector and the baseline mean of the corresponding component in the generation reference system is calculated, and the difference is normalized to obtain the amplitude deviation. The rate of change of the generated state vector at adjacent time points is compared with a preset rate of change threshold in the generation reference system. The rate of change threshold is preset according to different mobile communication scenarios. For example, in low-speed or stationary scenarios, the rate of change threshold is set to no more than 1.2 times the baseline rate of change, and in high-speed mobile scenarios, the rate of change threshold is set to no more than 1.5 times the baseline rate of change. The evolution trend of the generated state vector within a continuous time window is judged to be consistent with the typical evolution trend in the generation reference system. When the evolution direction is inconsistent for more than three consecutive time windows, it is determined to be a trend deviation. When the amplitude deviation of the generated state vector within the time window is less than the preset deviation threshold, the rate of change does not exceed the rate of change threshold of the corresponding scenario, and the evolution trend is consistent with the generation reference system, it is determined to be a scenario-consistent evolution. The amplitude deviation threshold can be set to ±10% of the baseline mean. When the generated state vector meets any deviation condition, it is determined to be a scenario-deviation evolution. Based on the above comparison process, the deviation of the signal quality generation trajectory in different time periods is summarized and analyzed to form a comparative analysis result that characterizes the difference between the signal quality generation state and the scene reference benchmark. The comparative analysis result includes at least the deviation position, deviation degree, and deviation duration of the generation trajectory in the time dimension, which serves as the basis for subsequent wireless signal quality monitoring result output.

[0038] Based on the comparative analysis results and the dominant generated path type, output the wireless signal quality monitoring results.

[0039] Based on the comparative analysis results, the deviation characteristics of the signal quality generation trajectory relative to the signal quality generation reference system are obtained, including the time and location of the deviation, the magnitude of the deviation, and the duration of the deviation. The magnitude of the deviation is characterized by the normalized deviation value of the generated state vector relative to the mean of the reference system within the corresponding time window. A normalized deviation value greater than 0.15 is considered a slight deviation, and greater than 0.30 is considered a significant deviation. The duration of the deviation is counted by the number of consecutive deviation windows. When the number of consecutive deviation windows is not less than 3 (corresponding to a time length of not less than 1.5 seconds), the wireless signal quality is determined to be in an abnormal state. Furthermore, the type of wireless signal quality anomaly is determined by combining the dominant generation path type. Specifically, an anomaly is classified as follows: when the contribution of environment-related generative components in the dominant generation path is not less than 50%, it is determined to be an environment-dominated anomaly; when the contribution of link-layer generative components is not less than 50%, it is determined to be a link-dominated anomaly; when the contribution of network scheduling-related generative components is not less than 50%, it is determined to be a scheduling-dominated anomaly; and when the contribution of any two types of generative components is not less than 30%, it is determined to be a multi-factor coupled anomaly. After determining the anomaly type, the trajectory deviation characteristics reflected in the comparative analysis results are correlated and integrated with the dominant generation path type to generate a monitoring result parameter set for characterizing the type of wireless signal quality anomaly and its generation mechanism attribution results. The monitoring result parameter set includes at least the deviation degree index of the signal quality anomaly, the anomaly duration index, the dominant generation path identifier, and the corresponding mobile communication scenario information. Finally, according to the preset result organization rules, the monitoring result parameter set is structured and encapsulated to output the wireless signal quality monitoring results. This enables the monitoring results to simultaneously reflect the abnormal performance of wireless signal quality and its corresponding generation mechanism attribution results, thereby providing a basis for subsequent network optimization, fault location, or strategy adjustment.

[0040] Furthermore, based on the comparative analysis results and the dominant generated path type, the wireless signal quality monitoring results are output, including: Based on the comparative analysis results, a trajectory offset index reflecting the degree to which the current wireless signal quality deviates from the signal quality generation reference system is calculated; the trajectory offset index is associated and combined with the dominant generation path type to form a monitoring result parameter set characterizing the degree and cause of wireless signal quality anomalies; the monitoring result parameter set is structured and encapsulated according to preset result organization rules to generate wireless signal quality monitoring results containing the degree of quality offset, the dominant generation path identifier, and corresponding scene information.

[0041] Preferably, based on the comparative analysis results, a trajectory offset index is calculated to reflect the degree of deviation of the current wireless signal quality from the signal quality generation reference system. The trajectory offset index quantifies the deviation of the signal quality generation trajectory from the corresponding scenario reference in terms of numerical amplitude, rate of change, or evolution trend. The trajectory offset index is calculated as follows: within the same association window, the Euclidean distance or weighted absolute difference between the signal quality generation state vector and the corresponding reference generation state vector in the signal quality generation reference system is calculated, and the deviation results within a continuous time window are accumulated or averaged to obtain the trajectory offset value. When the trajectory offset value is greater than or equal to a preset offset judgment threshold, it is determined that the current wireless signal quality has an abnormal deviation. The offset judgment threshold is determined based on historical normal communication data statistics, preferably a numerical range corresponding to the average historical trajectory offset value plus one to two standard deviations. After obtaining the trajectory offset index, it is associated and combined with the dominant generation path type to simultaneously reflect the severity of the wireless signal quality anomaly and its causes. Specifically, when the trajectory offset index is within a preset first offset interval, it is determined to be a slight anomaly; when the trajectory offset index is within a preset second offset interval, it is determined to be a moderate anomaly; and when the trajectory offset index exceeds a preset third offset interval, it is determined to be a severe anomaly. The boundary values ​​of each offset interval are set based on the statistical distribution of historical monitoring data in the corresponding mobile communication scenario. Finally, the monitoring result parameter set is structured and encapsulated according to preset result organization rules to generate wireless signal quality monitoring results. The result organization rules include at least arranging the monitoring result parameters in the order of "timestamp-trajectory offset index-anomaly level-dominant generation path identifier-mobile communication scenario identifier," and outputting them in a structured data format. This ensures that the generated wireless signal quality monitoring results clearly include information on the degree of wireless signal quality offset, the dominant generation path identifier, and the corresponding mobile communication scenario information, facilitating subsequent analysis, display, or decision-making applications of the wireless communication status. Furthermore, based on the stability of the trajectory offset degree and the dominant generation path type, instantaneous monitoring results and time-cumulative monitoring results are generated respectively, and wireless signal quality monitoring results are generated based on the instantaneous monitoring results and the time-cumulative monitoring results.

[0042] The degree of trajectory deviation can be quantified by a trajectory deviation index, which can be represented, for example, by the normalized deviation between the current generated state vector and the center value of the corresponding signal quality generation reference system, with a value range of 0 to 1. When the trajectory deviation index is greater than or equal to 0.3 and less than 0.6, it is judged as a slight deviation; when the trajectory deviation index is greater than or equal to 0.6 and less than 0.8, it is judged as a moderate deviation; and when the trajectory deviation index is greater than or equal to 0.8, it is judged as a severe deviation.

[0043] The time window corresponding to the instantaneous monitoring result is set to, for example, 1 to 3 sampling periods. When the trajectory offset index exceeds the corresponding deviation threshold within the time window, the instantaneous monitoring result is generated. The time window corresponding to the cumulative monitoring result is set to, for example, 30 seconds to 5 minutes. It is obtained by performing cumulative statistics or weighted average calculation on the trajectory offset index within the time window.

[0044] The stability of the dominant generation path type can be evaluated by the number of times or the proportion of its consecutive occurrence within the time cumulative monitoring window. For example, when the proportion of the same dominant generation path type occurring within the time window is greater than or equal to 70%, the dominant generation path type is determined to be a stable path; when the proportion is less than 70%, it is determined to be an unstable path.

[0045] When generating wireless signal quality monitoring results, if the instantaneous monitoring result indicates a moderate or severe deviation and the corresponding dominant generation path type is a stable path, the time-cumulative monitoring result is used as the main output; if the instantaneous monitoring result indicates a slight deviation or the dominant generation path type is unstable, the instantaneous monitoring result is used as the main output, or both the instantaneous monitoring result and the time-cumulative monitoring result are output simultaneously.

[0046] In summary, the embodiments of this application have at least the following technical effects: In mobile communication using computer devices, wireless measurement data from the terminal side, link-layer transmission behavior data, and network-side scheduling feedback data are collected. Based on the collected data, a signal quality generation state vector is constructed to characterize the formation mechanism of wireless signal quality. Next, time-series correlation modeling is performed on the signal quality generation state vector to generate a signal quality generation trajectory describing the evolution of wireless signal quality over time. Furthermore, quality inversion analysis is performed using the signal quality generation trajectory, mapping the observed wireless signal quality changes back to the corresponding generation state component combinations to identify the dominant generation path type causing the current signal quality change. Then, the current mobile communication scenario of the terminal is obtained, and the corresponding signal quality generation reference system is determined. The signal quality generation trajectory is compared and analyzed with the signal quality generation reference system to establish a comparative analysis result. Finally, the wireless signal quality monitoring result is output based on the comparative analysis result and the dominant generation path type. This solves the technical problem in existing technologies where it is difficult to conduct targeted monitoring of wireless signal quality based on differences in mobile communication scenarios, leading to insufficient reliability of monitoring results, and achieves the technical effect of improving the reliability of monitoring results.

[0047] Example 2, based on the same inventive concept as the wireless signal quality monitoring method in the mobile communication scenario in the foregoing examples, such as... Figure 2 As shown, this application provides a wireless signal quality monitoring system for mobile communication scenarios, wherein the system includes: Data Acquisition Module 11: During mobile communication of computer equipment, it collects wireless measurement data, link layer transmission behavior data, and network-side scheduling feedback data from the terminal side, and constructs a signal quality generation state vector to characterize the formation mechanism of wireless signal quality based on the collected data; Temporal Modeling Module 12: It performs temporal correlation modeling on the signal quality generation state vector to generate a signal quality generation trajectory describing the evolution of wireless signal quality over time; Quality Inversion Module 13: It performs quality inversion analysis using the signal quality generation trajectory, and maps the observed wireless signal quality change results back to the corresponding generation state component combination to locate the dominant generation path type that causes the current signal quality change; Scene Determination Module 14: It obtains the mobile communication scene where the terminal is currently located and determines the signal quality generation reference system corresponding to the mobile communication scene; Comparison Analysis Module 15: It compares and analyzes the signal quality generation trajectory with the signal quality generation reference system to establish a comparison analysis result; Result Output Module 16: It outputs the wireless signal quality monitoring result based on the comparison analysis result and the dominant generation path type.

[0048] Furthermore, the data acquisition module 11 is used to perform the following methods: The terminal-side wireless measurement data, link-layer transmission behavior data, and network-side scheduling feedback data collected are processed hierarchically according to time resolution and data update cycle to generate multiple time-scale data subsets. Within each time-scale data subset, data decorrelation processing and normalization mapping are performed to eliminate dimensional differences and statistical coupling between different data sources. The evolutionary order of environment-link-scheduling in the wireless signal quality formation process is obtained. Based on this evolutionary order, the processed data subsets are combined with sequential constraints to construct a generator state component sequence. A time-consistent weight allocation rule is applied to the generator state component sequence to form a signal quality generator state vector with fixed dimensions and sequential constraints.

[0049] Furthermore, the timing modeling module 12 is used to perform the following methods: The process involves: acquiring the mobile communication scenario identifier corresponding to the signal quality generator state vector during data acquisition; determining the time-series correlation parameter set corresponding to the scenario based on the mobile communication scenario identifier; performing time alignment and correlation window division on the signal quality generator state vectors at consecutive time points according to the time-series correlation parameter set to form a generator state vector sequence under scenario constraints; calculating the evolution increment between adjacent signal quality generator state vectors in the generator state vector sequence based on the change rate threshold and correlation window length corresponding to the mobile communication scenario; applying the evolution increment and the evolution discrimination rule corresponding to the mobile communication scenario to the generator state vector sequence for continuous evolution constraints and scenario-triggered mutation marking processing; and constructing a signal quality generation trajectory based on the processed generator state vector sequence.

[0050] Furthermore, the quality inversion module 13 is used to perform the following method: In the signal quality generation trajectory, trajectory change features characterizing the amplitude, duration, and recovery characteristics of wireless signal quality changes are extracted. These trajectory change features are then correlated and matched with the evolution features of each generator component in the signal quality generation vector within the corresponding time period to construct a correspondence between the trajectory change features and the generator components. Based on this correspondence, the contribution index of each generator component to the current wireless signal quality change is calculated. The distribution results of the contribution index are used to locate the dominant generation path type that causes the current signal quality change.

[0051] Furthermore, the result output module 16 is used to perform the following method: Based on the comparative analysis results, a trajectory offset index reflecting the degree to which the current wireless signal quality deviates from the signal quality generation reference system is calculated; the trajectory offset index is associated and combined with the dominant generation path type to form a monitoring result parameter set characterizing the degree and cause of wireless signal quality anomalies; the monitoring result parameter set is structured and encapsulated according to preset result organization rules to generate wireless signal quality monitoring results containing the degree of quality offset, the dominant generation path identifier, and corresponding scene information.

[0052] Furthermore, the result output module 16 is used to perform the following method: Based on the degree of trajectory deviation and the stability of the dominant generated path type, instantaneous monitoring results and time-accumulated monitoring results are generated respectively, and wireless signal quality monitoring results are generated based on the instantaneous monitoring results and the time-accumulated monitoring results.

[0053] Furthermore, the data acquisition module 11 is used to perform the following methods: In the process of mobile communication of computer equipment, the collection of terminal-side wireless measurement data, link layer transmission behavior data and network-side scheduling feedback data adopts a strategy of combining event triggering and periodic collection.

[0054] Furthermore, the data acquisition module 11 is used to perform the following methods: A credibility assessment is performed based on the numerical stability, consistency of change, and matching degree with the constraints of the mobile communication scenario of the corresponding generator components within a continuous time window; the corresponding signal quality generator vector is then labeled based on the credibility assessment results.

[0055] Example 3, Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3 Taking a processor 21 as an example, the processor 21, memory 22, input device 23, and output device 24 in an electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0056] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the wireless signal quality monitoring method in the mobile communication scenario in this embodiment of the invention. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, thereby realizing the wireless signal quality monitoring method in the aforementioned mobile communication scenario.

[0057] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for monitoring radio signal quality in a mobile communication scenario, characterized by The method comprises: In the process of mobile communication of the computer device, terminal side wireless measurement data, link layer transmission behavior data and network side scheduling feedback data are collected, a signal quality generation state vector for representing the formation mechanism of wireless signal quality is constructed based on the collected data; The signal quality generation state vector is executed for time sequence correlation modeling, and a signal quality generation trajectory for describing the time evolution of wireless signal quality is generated; The signal quality generation trajectory is used for quality inversion analysis, and the observed wireless signal quality change result is reversely mapped to the corresponding generation state component combination to locate the dominant generation path type causing the current signal quality change; A mobile communication scene in which the terminal is currently located is obtained, and a signal quality generation reference system corresponding to the mobile communication scene is determined; The signal quality generation trajectory and the signal quality generation reference system are compared and analyzed, and a comparison analysis result is established; According to the comparison analysis result and the dominant generation path type, a wireless signal quality monitoring result is output.

2. The method of claim 1, wherein the method further comprises: Based on the collected data, a signal quality generation state vector for representing the formation mechanism of wireless signal quality is constructed, comprising: The terminal side wireless measurement data, the link layer transmission behavior data and the network side scheduling feedback data in the collected data are respectively processed in layers according to the time resolution and the data update period, and a plurality of time scale data subsets are generated; In each time scale data subset, data decorrelation processing and normalization mapping are respectively performed to eliminate the dimensional differences and statistical coupling relationships between different data sources; The evolution sequence of environment-link-scheduling in the wireless signal quality formation process is obtained, and the sequentially constrained combination of the processed data subsets is performed according to the evolution sequence to construct a generation state component sequence; The generation state component sequence is subjected to a weight distribution rule based on time consistency to form a signal quality generation state vector with fixed dimension and sequential constraint.

3. The method of claim 1, wherein the method further comprises: The signal quality generation state vector is executed for time sequence correlation modeling to generate a signal quality generation trajectory for describing the time evolution of wireless signal quality, comprising: The mobile communication scene identifier corresponding to the signal quality generation state vector during the collection of data is obtained, and a set of time sequence correlation parameters corresponding to the scene is determined according to the mobile communication scene identifier; According to the set of time sequence correlation parameters, time alignment and correlation window division of the signal quality generation state vectors at continuous time points are performed to form a generation state vector sequence under the constraint of the scene; In the generation state vector sequence, the evolution increment between adjacent signal quality generation state vectors is calculated based on the change rate threshold and the correlation window length corresponding to the mobile communication scene; The generation state vector sequence is subjected to continuous evolution constraint and scene trigger mutation marking processing by using the evolution increment and the evolution discrimination rule corresponding to the mobile communication scene; The signal quality generation trajectory is constructed according to the processed generation state vector sequence.

4. The method of claim 1, wherein the method further comprises: The signal quality generation trajectory is used for quality inversion analysis, comprising: In the signal quality generation trajectory, trajectory change characteristics representing the change amplitude, change duration and change recovery characteristics of wireless signal quality are extracted; The trajectory change feature is matched with the evolution feature of each generated state component in the signal quality generation state vector in the corresponding time period, and a corresponding relationship between the trajectory change feature and the generated state component is constructed; Based on the corresponding relationship, the contribution degree index of each generated state component to the current wireless signal quality change is calculated; The distribution result of the contribution degree index is used to locate the dominant generated path type that causes the current signal quality change.

5. The method of claim 1, wherein, According to the comparison analysis result and the dominant generated path type, a wireless signal quality monitoring result is output, including: According to the comparison analysis result, a trajectory deviation index reflecting the degree of deviation of the current wireless signal quality from the signal quality generation reference system is calculated; The trajectory deviation index and the dominant generated path type are associated and combined to form a monitoring result parameter set representing the degree of wireless signal quality abnormality and the cause of the abnormality; According to a preset result organization rule, the monitoring result parameter set is structured and packaged to generate a wireless signal quality monitoring result containing the quality deviation degree, the dominant generated path identification, and the corresponding scene information.

6. The method of claim 5, wherein the step of determining the signal quality of the received signal comprises the steps of: According to the stability of the trajectory deviation degree and the dominant generated path type, instantaneous monitoring results and time-accumulated monitoring results are generated, and wireless signal quality monitoring results are generated according to the instantaneous monitoring results and the time-accumulated monitoring results.

7. The method of claim 1, wherein the method further comprises: In the mobile communication process of the computer device, the terminal-side wireless measurement data, the link layer transmission behavior data, and the network-side scheduling feedback data are collected by using a combination strategy of event triggering and periodic collection.

8. The method of claim 1, wherein, Based on the collected data, a signal quality generation state vector is constructed to represent the formation mechanism of the wireless signal quality, including: Based on the numerical stability, change consistency, and matching degree with the mobile communication scene constraint condition of the corresponding generated state component in the continuous time window, a credibility evaluation is performed; According to the credibility evaluation result, a corresponding signal quality generation state vector is labeled.

9. A wireless signal quality monitoring system in a mobile communication scenario, characterized by The system for implementing the wireless signal quality monitoring method in the mobile communication scene according to any one of claims 1-8, the system comprising: A data collection module: in the mobile communication process of the computer device, terminal-side wireless measurement data, link layer transmission behavior data, and network-side scheduling feedback data are collected, and a signal quality generation state vector is constructed based on the collected data to represent the formation mechanism of the wireless signal quality; A time series modeling module: the signal quality generation state vector is subjected to time series correlation modeling to generate a signal quality generation trajectory for describing the evolution of the wireless signal quality over time; A quality inversion module: the signal quality generation trajectory is used to perform quality inversion analysis, and the observed wireless signal quality change result is mapped back to the corresponding generated state component combination to locate the dominant generated path type that causes the current signal quality change; A scene determination module: the mobile communication scene in which the terminal is currently located is obtained, and the signal quality generation reference system corresponding to the mobile communication scene is determined; A comparison analysis module: the signal quality generation trajectory and the signal quality generation reference system are compared and analyzed to establish a comparison analysis result; A result output module: according to the comparison analysis result and the dominant generated path type, a wireless signal quality monitoring result is output.

10. An electronic device, comprising: The electronic device comprises: a memory for storing executable instructions; a processor for executing the executable instructions stored in the memory to implement the wireless signal quality monitoring method in the mobile communication scenario according to any one of claims 1-8.

Images