A method for real-time base station status monitoring based on LBS data stream signaling parsing

Abstract

This invention relates to the field of wireless communication, specifically to a method for real-time base station status monitoring based on LBS data stream signaling parsing. This method solves the technical problem of high misjudgment rates in base station status monitoring due to weak coupling between signaling characteristics and the actual base station status in existing technologies. The method includes: collecting and parsing LBS data stream signaling generated by mobile terminals within the current time neighborhood to obtain base station signal strength and user behavior data; the time neighborhood includes multiple collection times ending at the current time; determining the fluctuation characteristics of the base station signal within the time neighborhood based on the base station signal strength; analyzing the impact of user behavior on the base station signal within the time neighborhood based on the user behavior data and fluctuation characteristics; and determining the real-time status of the base station at the current time based on the fluctuation characteristics within the time neighborhood, the impact of user behavior on the base station signal, and the base station signal strength at the current time.

Description

Technical Field

[0001] This invention relates to the field of wireless communication, and specifically to a method for real-time status monitoring of base stations based on LBS data stream signaling parsing. Background Technology

[0002] In mobile networks, location-based services (LBS) data streams, as continuous location-related signaling generated by terminals, cover control plane messages for processes such as location updates, access / release, and handover. They naturally possess the characteristics of high timeliness, high coverage, and continuity, and can reflect the interaction patterns between terminals and base stations in real time. They also contain multi-dimensional information such as base station load, radio link quality, and mobility management. Through massive amounts of terminal behavior, they can reverse-describe the base station status in time and space, providing a rich perceptual foundation for base station status monitoring.

[0003] In recent years, signaling parsing technology based on LBS data streams has enabled real-time calculation of key indicators such as cell access success rate, handover success rate, paging response rate, and signal quality distribution without the need for additional probe deployment or invasive modifications. This supports a more refined, intelligent, and real-time base station status monitoring system.

[0004] However, in real network environments, there is no strict correspondence between signaling behavior and the actual physical state of base stations, and there is a clear weak coupling. Dynamic changes in the number of terminals and mobility modes (such as frequent handovers caused by high-speed mobile users) often cause drastic fluctuations in signaling characteristics, but these fluctuations do not necessarily indicate a fault in the base station itself, leading to a significant risk of misjudgment when relying solely on signaling characteristics for state judgment. Summary of the Invention

[0005] To address the high false positive rate in base station status monitoring caused by weak coupling between signaling features and the actual base station status in existing technologies, this invention aims to provide a real-time base station status monitoring method based on LBS data stream signaling parsing. The specific technical solution adopted is as follows:

[0006] Firstly, a method for real-time base station status monitoring based on LBS data stream signaling parsing is provided, comprising: collecting and parsing LBS data stream signaling generated by mobile terminals within the current time neighborhood to obtain base station signal strength and user behavior data; the time neighborhood includes multiple collection times ending at the current time; determining the fluctuation characteristics of the base station signal within the time neighborhood based on the base station signal strength; analyzing the impact of user behavior on the base station signal within the time neighborhood based on user behavior data and fluctuation characteristics; and determining the real-time status of the base station at the current time based on the fluctuation characteristics within the time neighborhood, the impact of user behavior on the base station signal, and the base station signal strength at the current time.

[0007] Based on the above technical solution, in the base station real-time status monitoring method based on LBS data stream signaling parsing provided by this invention, LBS data stream signaling within the time neighborhood at the current moment is collected and parsed to obtain base station signal strength and user behavior data. First, the fluctuation characteristics of the base station signal are determined, then the impact of user behavior on the base station signal is analyzed, and finally, the real-time status of the base station is determined by combining the fluctuation characteristics, impact, and the base station signal strength at the current moment. This method not only achieves real-time perception of the base station status by leveraging the high timeliness of LBS data stream signaling, but also effectively eliminates interference caused by user behavior by quantifying the effect of user behavior on signal fluctuations, avoiding misjudging signal fluctuations caused by user behavior as base station malfunctions, thereby improving the accuracy and reliability of base station status monitoring.

[0008] In conjunction with the first aspect above, in one possible implementation, the aforementioned user behavior data includes the number of users; the method for analyzing the impact of user behavior on base station signals within a time neighborhood based on user behavior data and fluctuation characteristics specifically includes: determining the first degree of influence of the number of users on signal fluctuations based on the number of users and fluctuation characteristics within a time neighborhood, as the degree of influence of user behavior on base station signals within a time neighborhood.

[0009] In conjunction with the first aspect above, in one possible implementation, the aforementioned user behavior data includes user location; the method for analyzing the impact of user behavior on base station signals within a time neighborhood based on user behavior data and fluctuation characteristics specifically includes: analyzing user distribution changes based on user location within a time neighborhood, and determining the second degree of impact of user distribution changes on signal fluctuations based on fluctuation characteristics, as the impact of user behavior on base station signals within a time neighborhood.

[0010] In conjunction with the first aspect above, in one possible implementation, the aforementioned user behavior data includes the number of users and user locations; the method for analyzing the impact of user behavior on base station signals within a time neighborhood based on user behavior data and fluctuation characteristics specifically includes: determining the first degree of influence of the number of users on signal fluctuations based on the number of users and fluctuation characteristics within the time neighborhood; analyzing changes in user distribution based on user locations within the time neighborhood, and determining the second degree of influence of changes in user distribution on signal fluctuations based on fluctuation characteristics; and determining the degree of influence of user behavior on base station signals within the time neighborhood based on the first degree of influence and the second degree of influence.

[0011] In conjunction with the first aspect mentioned above, in one possible implementation, the method for determining the first degree of influence of user quantity on signal fluctuation based on the number of users and fluctuation characteristics within the time neighborhood specifically includes: constructing a user quantity sequence and a fluctuation characteristic sequence in time order, respectively, based on the user quantity sequence and the fluctuation characteristic sequence; determining the actual coupling relationship between changes in the number of users and signal fluctuation within the time neighborhood based on the correlation between the user quantity sequence and the fluctuation characteristic sequence; determining the first degree of influence of user quantity on signal fluctuation based on the coupling deviation between the actual coupling relationship and the reference coupling relationship; the reference coupling relationship is a reference relationship determined based on the user quantity sequence and the fluctuation characteristic sequence within a historical time period longer than the time neighborhood.

[0012] In conjunction with the first aspect above, in one possible implementation, the method for analyzing user distribution changes based on user locations within a time neighborhood and determining the degree of second impact of user distribution changes on signal fluctuations, specifically includes: for each moment, determining the distance between the user locations of multiple users within the base station coverage area and the base station location, and comparing the distance changes of each user in adjacent moments; determining the user distribution changes at each moment based on the distance changes of multiple users; constructing a user distribution change sequence by sequentially processing the user distribution changes within the time neighborhood; and determining the degree of second impact of user distribution changes on signal fluctuations based on the correlation between the user distribution change sequence and the fluctuation feature sequence; the fluctuation feature sequence is constructed by sequentially processing the fluctuation features within the time neighborhood.

[0013] In conjunction with the first aspect above, in one possible implementation, the method for determining the real-time state of a base station based on fluctuation characteristics in the time neighborhood, the impact of user behavior on the base station signal, and the current base station signal strength specifically includes: determining the initial fluctuation anomaly value of the base station at the current moment based on the fluctuation characteristics in the time neighborhood and the current base station signal strength; correcting the initial fluctuation anomaly value based on the impact of user behavior on the base station signal in the time neighborhood to obtain the corrected fluctuation anomaly value; and determining the real-time state of the base station at the current moment based on the corrected fluctuation anomaly value.

[0014] In conjunction with the first aspect above, in one possible implementation, the method for determining the real-time status of the base station based on the corrected fluctuation anomaly value specifically includes: if the corrected fluctuation anomaly value is greater than or equal to a preset anomaly threshold, the real-time status of the base station at the current moment is determined to be an abnormal state; if the corrected fluctuation anomaly value is less than the preset anomaly threshold, the real-time status of the base station at the current moment is determined to be a normal state.

[0015] In conjunction with the first aspect above, in one possible implementation, the method further includes: generating an anomaly report under abnormal conditions; the anomaly report includes the time of the anomaly occurrence, the fluctuation range of the base station signal strength, and the change characteristics of user behavior data; and performing network diagnosis, parameter optimization, or communication trajectory analysis based on the anomaly report.

[0016] In conjunction with the first aspect above, in one possible implementation, the method for determining the fluctuation characteristics of a base station signal within a time neighborhood based on the base station signal strength specifically includes: for each moment, determining the change in base station signal strength between adjacent moments; and determining the fluctuation characteristics of the base station signal based on the change in signal strength within the time neighborhood.

[0017] Secondly, a base station real-time status monitoring device based on LBS data stream signaling parsing is provided, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is used to execute the instructions to implement the actions described in the first aspect and any possible implementation thereof. This base station real-time status monitoring device based on LBS data stream signaling parsing can be an electronic device or a chip within an electronic device.

[0018] Thirdly, a computer-readable storage medium is provided, in which instructions are stored, which, when executed on a base station real-time status monitoring device based on LBS data stream signaling parsing, cause the base station real-time status monitoring device based on LBS data stream signaling parsing to perform the actions described in the first aspect and any possible implementation thereof.

[0019] Fourthly, a computer program product containing instructions is provided, which, when running on a base station real-time status monitoring device based on LBS data stream signaling parsing, causes the base station real-time status monitoring device based on LBS data stream signaling parsing to perform the actions described in the first aspect and any possible implementation thereof.

[0020] The present invention has the following beneficial effects:

[0021] By collecting LBS data stream signaling within the current time neighborhood and parsing the base station signal strength and user behavior data, the fluctuation characteristics of the base station signal are first determined, then the impact of user behavior on the base station signal is analyzed, and finally, the real-time status of the base station is determined by combining the fluctuation characteristics, impact, and the base station signal strength at the current time. This approach not only leverages the high timeliness of LBS data stream signaling to achieve real-time perception of the base station status, but also effectively eliminates interference caused by user behavior by quantifying the effect of user behavior on signal fluctuations. This avoids misjudging signal fluctuations caused by user behavior as base station malfunctions, thereby improving the accuracy and reliability of base station status monitoring. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart of a base station real-time status monitoring method based on LBS data stream signaling parsing is provided as an embodiment of the present invention;

[0024] Figure 2 A flowchart illustrating another method for real-time base station status monitoring based on LBS data stream signaling parsing, provided as an embodiment of the present invention;

[0025] Figure 3 A flowchart illustrating another method for real-time base station status monitoring based on LBS data stream signaling parsing, provided as an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the hardware structure of a base station real-time status monitoring device based on LBS data stream signaling parsing, provided as an embodiment of the present invention. Detailed Implementation

[0027] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a base station real-time status monitoring method based on LBS data stream signaling parsing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0029] The following description, in conjunction with the accompanying drawings, details the specific scheme of a base station real-time status monitoring method based on LBS data stream signaling parsing provided by the present invention.

[0030] Please see Figure 1 The diagram illustrates a method flowchart for real-time base station status monitoring based on LBS data stream signaling parsing, according to an embodiment of the present invention. This method includes:

[0031] S1. Collect and parse the LBS data stream signaling generated by mobile terminals in the current time neighborhood to obtain base station signal strength and user behavior data.

[0032] First, a signaling acquisition module is deployed on the core network side. This module captures LBS data stream signaling (i.e., control plane signaling data) generated by mobile terminals during access, camping, handover, paging, and location updates in real time. This achieves non-intrusive signaling data acquisition, which does not change the existing network architecture and can cover all scenarios of terminal-base station interaction signaling, ensuring the comprehensiveness and timeliness of data sources.

[0033] Using the current time as the end time, multiple consecutive historical acquisition times (such as the previous 10 acquisition times) are selected to form a time neighborhood, providing continuous data samples with temporal correlation for subsequent analysis and avoiding interference from the randomness of data at a single moment. Through the aforementioned signaling acquisition module, LBS data stream signaling generated by all mobile terminals within this time neighborhood is acquired synchronously, covering the complete signaling dataset of the time neighborhood.

[0034] Next, the collected raw LBS data stream signaling is input into the protocol parsing engine. This engine, based on the 3rd Generation Partnership Project (3GPP) standard protocol, performs layer-by-layer parsing and field extraction of the signaling to obtain base station signal strength and user behavior data. The user behavior data includes one or more of the following: user number and user location. Specifically, this includes: extracting base station signal strength from base station information, extracting the user number from the number of accessing users information, and extracting user location (including GPS latitude and longitude information, and location information corresponding to the base station location area code (LAC) / cell identity (CID)) from the user trajectory LBS data. Base station signal strength reflects the radio link quality of the base station, the number of users reflects the scale of terminals accessing the base station, and user location reflects the spatial distribution of the terminals.

[0035] Finally, the obtained base station signal strength, user count, and user location data are preprocessed as follows: timestamp calibration is performed to align signaling data from different collection times with a unified time reference; duplicate record filtering is performed to remove redundant signaling data generated by the same terminal in the same interaction process; associated session reconstruction is performed to associate scattered signaling data into a complete terminal-base station interaction session; and structured processing is performed to organize various types of data into standardized field formats. This eliminates data bias, redundancy, and dispersion, resulting in high-quality base station signal strength and user behavior data (including user count and user location).

[0036] S2. Determine the fluctuation characteristics of the base station signal within the time neighborhood based on the base station signal strength.

[0037] Analyzing the continuous changes in base station signal strength indicators over a period of time can reflect the stability of the base station signal. Under normal circumstances, the signal strength curve of a healthy base station should exhibit low fluctuations, strong continuity, and a smooth trend. However, when a base station experiences real-time anomalies (such as degradation of the RF unit power amplifier, poor feeder contact, main control board failure, increased interference, etc.), the signal strength often manifests as intermittent drops, sharp jumps, or frequent fluctuations in a short period of time, directly reflecting a decline in network operation quality.

[0038] In some implementations, the base station signal strengths within the time neighborhood are arranged chronologically according to the time of data collection, forming an ordered sequence of base station signal strengths. Then, for each time moment, the change in base station signal strength between adjacent time moments is determined. Finally, based on the change in signal strength within the time neighborhood, the fluctuation characteristics of the base station signal are determined, expressed as:

[0039]

[0040] In the formula, Indicates the first Fluctuation characteristics of base station signals within the time neighborhood of a given moment; Indicates the number of data collection moments within the time neighborhood; Indicates the first Within the time neighborhood of the i-th time moment The base station signal strength at each moment; Indicates the first Within the time neighborhood of time i, the i-th The base station signal strength at each moment.

[0041] It represents the change in base station signal strength between adjacent moments, that is, the absolute difference between the base station signal strength at two adjacent moments in the base station signal strength sequence. It only reflects the magnitude of the change and eliminates interference from the direction of signal rise and fall.

[0042] Summing the variation amplitudes of all adjacent moments within the time neighborhood yields the total variation amplitude of the base station signal strength within that time neighborhood. Then, dividing the total variation amplitude by the number of adjacent moments within the time neighborhood... (By limiting the number of time intervals N>1 in the time neighborhood to avoid the denominator being zero), what is obtained is the average value of the signal intensity change amplitude between adjacent time intervals, i.e., the th... Fluctuation characteristics of base station signals within the time neighborhood at each moment .

[0043] S3. Based on user behavior data and fluctuation characteristics, analyze the impact of user behavior on base station signals within the time neighborhood.

[0044] Changes in base station signal quality may be caused by the base station's own hardware status or abnormal radio resources, but user-side behavior can also significantly affect signal strength statistics. With changes in the number of users, fluctuations in service load, and users concentrating in areas with weak coverage, the signal strength reported by terminals may show an overall decrease, increased fluctuations, or distribution shifts. Without correlation analysis with user access behavior, these phenomena can easily be misjudged as base station failures or coverage degradation. By constructing a coupling model between user behavior and base station signal strength indicators, it is possible to identify whether signal changes originate from changes in user behavior, effectively eliminating the interference of user-side factors on signal statistics. This fundamentally improves the monitoring's ability to discern the true state of base stations, avoids false anomalies caused by user behavior, and thus significantly improves the accuracy, interpretability, and robustness of base station state identification.

[0045] In some implementations, if user behavior data only includes the number of users, the degree of influence of the number of users on signal fluctuations can be determined based on the number of users and fluctuation characteristics within the time neighborhood, and this degree can be used as the influence of user behavior on base station signals within the time neighborhood.

[0046] The method for determining the degree of primary influence of the number of users on signal fluctuations can be found in the description in S31 below, and will not be repeated here.

[0047] In other implementations, if user behavior data only includes user location, changes in user distribution can be analyzed based on user location within the time neighborhood, and combined with fluctuation characteristics, the degree of secondary impact of changes in user distribution on signal fluctuations can be determined as the degree of impact of user behavior on base station signals within the time neighborhood.

[0048] The method for determining the degree of the second impact of changes in user distribution on signal fluctuations can be found in the description in S32 below, and will not be repeated here.

[0049] In other implementations, combining Figure 1 ,like Figure 2As shown, if the user behavior data includes both the number of users and their location, the method described in S3 above can be implemented using the following steps S31 to S33, which are explained in detail below:

[0050] S31. Based on the number of users and fluctuation characteristics within the time neighborhood, determine the degree of first influence of the number of users on signal fluctuations.

[0051] In some implementations, the number of users and fluctuation characteristics in the time neighborhood are first used to construct user number sequences and fluctuation characteristic sequences in time order, respectively, thus transforming discrete single-moment data into structured time-series samples.

[0052] Next, based on the correlation between the user count sequence and the fluctuation characteristic sequence, the actual coupling relationship between changes in the number of users and signal fluctuations within the time neighborhood is determined. Specifically, a pre-defined time series similarity analysis algorithm (such as the dynamic time warping (DTW) algorithm) is used to calculate the correlation between the user count sequence and the fluctuation characteristic sequence. The correlation result is then transformed into the actual coupling relationship between changes in the number of users and signal fluctuations within the time neighborhood, which can be expressed as:

[0053]

[0054] In the formula, Indicates the first The actual coupling relationship between the change in the number of users in the time neighborhood at a given moment and signal fluctuations; Represents a sequence of user counts; This represents a sequence of fluctuation characteristics.

[0055] This represents the DTW distance between the user count sequence and the fluctuation characteristic sequence. The larger the distance, the lower the correlation between the sequences.

[0056] By negating the DTW distance using a negative sign, and then normalizing the negated result using the natural exponential function exp to map it to the interval (0, 1), we obtain the th... The actual coupling relationship between the change in the number of users in the time neighborhood at a given moment and signal fluctuations The correlation between two sequences is quantified into a specific indicator, which intuitively reflects the correlation strength between the number of users in the current time neighborhood and signal fluctuations. The final result is negatively correlated with the DTW distance between the sequences. The smaller the distance, the higher the correlation, and the tighter the actual coupling relationship (the larger the value).

[0057] Then, retrieve the user number sequence and fluctuation feature sequence within a historical time period longer than the current time neighborhood (if the time neighborhood is 1 hour, the historical time period can be close to 1 day), and use the same algorithm to calculate the degree of correlation between the two to obtain the benchmark coupling relationship between changes in the number of users and signal fluctuations.

[0058] It should be noted that in long-term historical data, non-user interference factors of base stations (such as equipment failure, external interference, etc.) are usually occasional and short-lived, while user behavior is continuous and normalized. Long-term statistical analysis will dilute the impact of occasional non-user factors, and the baseline coupling relationship obtained is essentially the normal correlation between signal fluctuations and changes in the number of users under the continuous influence of user behavior, which is used to represent the typical characteristics when user behavior dominates signal fluctuations.

[0059] Furthermore, the coupling deviation between the actual coupling relationship and the reference coupling relationship (i.e., the absolute difference between the actual coupling relationship and the reference coupling relationship) is calculated and expressed as:

[0060]

[0061] In the formula, Indicates the first The actual coupling relationship between the change in the number of users in the neighborhood at a given time moment and signal fluctuations; This represents the baseline coupling relationship between changes in the number of users and signal fluctuations. Indicates the first The coupling deviation between the actual coupling relationship and the reference coupling relationship within the time neighborhood at a given moment. The smaller the coupling deviation, the closer the current association is to the typical user-dominated state, and the greater the influence of the number of users on signal fluctuations.

[0062] Finally, based on the coupling deviation between the actual coupling relationship and the reference coupling relationship, the degree of primary influence of the number of users on signal fluctuations is determined, which can be expressed as:

[0063]

[0064] In the formula, Indicates the first The degree of influence of the number of users in the neighborhood at a given moment on signal fluctuations; Indicates the first The coupling deviation between the actual coupling relationship and the reference coupling relationship within the time neighborhood at each instant; Indicates the first Fluctuation characteristics of base station signals within the time neighborhood of a given moment; It represents the average value of the fluctuation characteristics of base station signals over a historical period. The standard deviation represents the fluctuation characteristics of base station signals over a historical period.

[0065] This value represents the deviation of the signal fluctuation characteristics in the current time neighborhood from the historical average fluctuation characteristics, eliminating the influence of positive and negative values ​​and retaining only the amplitude information. The larger the value, the more obvious the abnormal phenomenon of the current signal fluctuation.

[0066] Dividing by the standard deviation normalizes the absolute deviation to a relative deviation, characterizing the normalized deviation of the current signal fluctuation characteristics from the historical average level (dimensionless), thus eliminating the influence of dimensions and historical fluctuation dispersion.

[0067] This characterizes the degree to which the current correlation closely resembles the typical state of fluctuations in user behavior-driven signals. The smaller the value (i.e., the lower the degree of correlation deviation), the greater the degree of influence.

[0068] Finally, the normalized deviation of the signal fluctuations is integrated with the user-dominant proximity of the correlation, and then normalized to the [0, 1] interval using a normalization function, such as min-max, to obtain the [0, 1] interval. The degree of influence of the number of users in the neighborhood at a given time on signal fluctuations. The closer the value is to 1, the higher the correlation between the deviation of the current signal fluctuation and "user behavior-driven" behavior, and the stronger the influence of the number of users on the signal fluctuation. The closer the value is to 0, the lower the correlation between the deviation of the current signal fluctuation and user-driven behavior, and the weaker the influence of the number of users.

[0069] S32. Analyze user distribution changes based on user locations within the time neighborhood, and combine this with fluctuation characteristics to determine the degree of the second impact of user distribution changes on signal fluctuations.

[0070] Changes in the number of users can cause fluctuations in base station signal strength. Furthermore, changes in the spatial distribution of users can also cause fluctuations. For example, during peak traffic hours, users move at high speeds along the road with vehicles, causing drastic changes in user distribution within the base station's coverage area in a short period, resulting in significant signal load instability. By measuring the distance between the user's location and the center of the base station's coverage area at each monitoring moment, the degree of change in user distribution within the base station can be obtained through changes in distance.

[0071] In some implementations, the distance between the location of multiple users within the base station's coverage area and the base station's location is first determined for each time moment, and the distance change of each user in adjacent time moments is compared. Specifically, for each user, the absolute difference between the distance data of two adjacent collection times in the time neighborhood is calculated sequentially to obtain the distance change of each user in adjacent time moments, which is used to quantify the spatial movement amplitude of a single user and reflect the degree of change of the user's position relative to the base station.

[0072] Next, based on the distance changes of multiple users, the user distribution changes at each time point are determined, as follows:

[0073]

[0074] In the formula, Indicates the first Changes in user distribution of base stations within a neighborhood at a given time point; Indicates the first The number of users within the base station coverage area in the time neighborhood at a given time (in special cases, if there are no users within the base station coverage area in the time neighborhood, i.e., M=0, it is assumed that user behavior does not respond to the base station signal, and no formula calculation is required). This represents the number of time points collected within the time neighborhood of each time point (by limiting the number of time points in the time neighborhood to N > 1, we avoid the denominator being zero). Indicates the first The user in the first Within the neighborhood of the i-th time point The distance between the location of the base station at each moment; Indicates the first The user in the first Within the neighborhood of the i-th time point The distance between the location of the base station at any given time.

[0075] Indicates the first The absolute difference in distance data between two adjacent collection times within the time neighborhood of a user is the distance change.

[0076] For the The average spatial mobility of a user within its time neighborhood is obtained by averaging all distance changes within that time neighborhood.

[0077] The average spatial mobility of all users is taken to obtain the overall user distribution change within the base station coverage area in the time neighborhood. The representation is the first Within a time neighborhood of a given moment, the average dynamic change in the spatial distribution of users within the base station's coverage area is used to quantify the overall fluctuation of user spatial location.

[0078] Then, the user distribution changes corresponding to each moment within the time neighborhood are constructed into a user distribution change sequence according to time order. At the same time, the base station signal fluctuation characteristics within the time neighborhood are arranged in the order of the same moment to form a fluctuation characteristic sequence.

[0079] Finally, based on the correlation between the user distribution change sequence and the fluctuation characteristic sequence, the degree of the second impact of user distribution change on signal fluctuation is determined, expressed as:

[0080]

[0081] In the formula, ; This represents a sequence of changes in user distribution. .

[0082] express The impact of changes in user distribution within the time neighborhood at a given time point on signal fluctuations, i.e., the Pearson correlation coefficient, is used. A larger absolute value of the coefficient indicates a stronger linear correlation between changes in user distribution and signal fluctuations. Therefore, the absolute value of the Pearson correlation coefficient is used as... The range is [0, 1].

[0083] S33. Determine the degree of influence of user behavior on base station signal within the time neighborhood based on the first degree of influence and the second degree of influence.

[0084] In some implementations, the impact of user behavior on base station signals within the time neighborhood is determined as follows:

[0085]

[0086] In the formula, Indicates the first The degree of influence of the number of users in the neighborhood at a given moment on signal fluctuations; Indicates the first The degree of the second impact of changes in user distribution within the time neighborhood at a given moment on signal fluctuations; Indicates the first The impact of user behavior on base station signal within a given time neighborhood.

[0087] The calculation logic for the average of the two can reflect the impact of user behavior on the signal in two dimensions. When the influence of quantity and the influence of distribution are both high, the overall impact of user behavior on the signal is strong. The value ranges of the first and second influence are both [0, 1], and the value range of the final mean is also [0, 1].

[0088] S4. Determine the real-time status of the base station at the current moment based on the fluctuation characteristics in the time neighborhood, the impact of user behavior on the base station signal, and the base station signal strength at the current moment.

[0089] Anomalies in base station signals or access metrics do not necessarily indicate hardware failure or wireless resource deterioration at the base station itself. They may be illusory fluctuations caused by external factors such as a sudden increase in the number of users, users concentrated in areas with weak coverage, changes in service models, changes in mobile speed, or changes in environmental obstruction. If user behavior-driven signaling changes are not differentiated, many phenomena not caused by the base station will be misjudged as real faults, leading to false alarms, excessive maintenance, and even wasted operational resources. By introducing coupled analysis between user behavior and base station signal strength, it is possible to identify whether signaling fluctuations are caused by user-side factors and correct initially detected anomalies, thereby filtering out false alarms, improving the accuracy of base station status monitoring, avoiding misleading operational decisions, improving overall network stability and operational efficiency, and achieving accurate and reliable judgment of the true operating status of base stations.

[0090] In some implementation methods, combined Figure 1 ,like Figure 3 As shown, the method in S4 above can be specifically implemented through the following steps S41 to S43, which are explained in detail below:

[0091] S41. Based on the fluctuation characteristics in the time neighborhood and the base station signal strength at the current moment, determine the initial fluctuation anomaly value of the base station at the current moment.

[0092] In some implementations, the base station signal fluctuation characteristics (reflecting the severity of signal fluctuations) within the time neighborhood and the base station signal strength at the current moment (reflecting signal quality) are retrieved. The initial fluctuation anomaly value of the base station signal at the current moment is calculated, and the degree of anomaly in the current operating state of the base station is intuitively quantified, as follows:

[0093]

[0094] In the formula, Indicates the first The initial fluctuation anomaly value of the base station signal at each moment; Indicates the first The fluctuation characteristics of base station signals within the time neighborhood of a given moment are positively correlated with fluctuation anomalies. Indicates the first The base station signal strength at any given time is negatively correlated with fluctuation anomalies.

[0095] Depending on the intensity of the fluctuation and poor signal quality The degree of increase is synchronous, and then the product is mapped to the interval [0, 1] by a normalization function, such as min-max, to obtain the th... The initial fluctuation anomaly value of the base station signal at each moment is considered; the larger the value, the more severe the anomaly. Specifically, when the signal strength of a running base station is zero, it is usually due to equipment display abnormalities or misreading caused by insufficient measurement accuracy. Such values ​​can be discarded as anomalies and the measurement repeated.

[0096] S42. Correct the initial fluctuation anomaly value based on the impact of user behavior on the base station signal in the time neighborhood to obtain the corrected fluctuation anomaly value.

[0097] In some implementations, false anomalies caused by user behavior are identified by assessing the impact of user behavior on base station signals within the time neighborhood, and anomaly correction operations are performed, as follows:

[0098]

[0099] In the formula, Indicates the first The abnormal fluctuation correction value of the base station signal at each moment; Indicates the first Abnormal fluctuations in base station signals at specific times; Indicates the first The impact of user behavior on base station signal within a given time neighborhood.

[0100] The greater the user influence ( (The larger the value) The smaller the value, the greater the decay of the initial outlier.

[0101] S43. Determine the real-time status of the base station at the current moment based on the corrected fluctuation anomaly value.

[0102] The corrected fluctuation anomalies have eliminated false anomalies caused by user behavior, thus avoiding misjudging signal fluctuations caused by user behavior as base station failures.

[0103] In some implementations, if the corrected fluctuation anomaly value is greater than or equal to a preset anomaly threshold (obtained by calibration based on the fluctuation anomaly values ​​corresponding to the normal and abnormal states of historical base stations, such as 0.6), the real-time state of the base station at the current moment is determined to be an abnormal state; if the corrected fluctuation anomaly value is less than the preset anomaly threshold, the real-time state of the base station at the current moment is determined to be a normal state.

[0104] Furthermore, this method can also generate anomaly reports under abnormal conditions. The anomaly report includes the time of the anomaly, the fluctuation range of the base station signal strength, the changing characteristics of user behavior data, and the potential anomaly types identified using existing technologies. Based on the anomaly report, network diagnostics (analyzing whether there is signal attenuation in the base station hardware or external interference sources by combining signal fluctuation amplitude), parameter optimization (adjusting base station coverage, signal transmission power, and other parameters based on user distribution changes), or communication trajectory analysis (tracing the communication records of terminals during the same period by combining the time of the anomaly with user behavior characteristics) can be performed.

[0105] Based on the above technical solution, by collecting LBS data stream signaling in the current time neighborhood and parsing the base station signal strength and user behavior data, the fluctuation characteristics of the base station signal are first determined, then the impact of user behavior on the base station signal is analyzed, and finally the real-time status of the base station is determined by combining the fluctuation characteristics, impact, and the base station signal strength at the current time. This not only achieves real-time perception of the base station status by leveraging the high timeliness of LBS data stream signaling, but also effectively eliminates interference caused by user behavior by quantifying the effect of user behavior on signal fluctuations, avoiding the situation where signal fluctuations caused by user behavior are misjudged as base station faults, thereby improving the accuracy and reliability of base station status monitoring.

[0106] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0108] In this embodiment of the invention, the base station real-time status monitoring device based on LBS data stream signaling parsing can be divided into functional units according to the above method example. For example, each function can be divided into its own functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0109] This invention also provides a hardware structure diagram of a base station real-time status monitoring device based on LBS data stream signaling parsing, see [link / reference]. Figure 4The base station real-time status monitoring device 400 based on LBS data stream signaling parsing includes a processor 401, and optionally, a memory 402 connected to the processor 401.

[0110] In the first possible implementation, see Figure 4 The base station real-time status monitoring device 400 based on LBS data stream signaling parsing also includes a transceiver 403. The processor 401, memory 402, and transceiver 403 are connected via a bus. The transceiver 403 is used to communicate with other devices or communication networks. Optionally, the transceiver 403 may include a transmitter and a receiver. The device in the transceiver 403 that implements the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of the present invention. The device in the transceiver 403 that implements the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of the present invention.

[0111] Based on the first possible implementation method Figure 4 The structural diagram shown can be used to illustrate the structure of the base station real-time status monitoring device based on LBS data stream signaling parsing involved in the above embodiments.

[0112] in, Figure 4 This can also be illustrated by the system chip in a base station real-time status monitoring device based on LBS data stream signaling parsing. In this case, the actions performed by the aforementioned base station real-time status monitoring device based on LBS data stream signaling parsing can be implemented by this system chip. The specific actions performed can be found above and will not be repeated here.

[0113] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in this embodiment can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0114] The processor in this invention may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., which are various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a standalone semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may be integrated with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a System-on-a-Chip (SoC), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), or logic circuits that implement dedicated logic operations.

[0115] The memory in the embodiments of the present invention may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0116] This invention also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0117] This invention also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0118] This invention also provides a chip, which includes a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0119] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0120] Although the invention has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings and the disclosure, will understand and implement other variations of the disclosed embodiments in carrying out the claimed invention. In this invention, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several of the functions listed in this invention.

[0121] Although the invention has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made therein without departing from the spirit and scope of the invention. Accordingly, this specification and drawings are merely illustrative of the invention and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if such modifications and modifications of the invention fall within the scope of the invention and its equivalents, the invention is also intended to include such modifications and modifications.

Claims

1. A base station real-time state monitoring method based on LBS data stream signaling analysis, characterized in that, The method comprises: collecting and analyzing LBS data stream signaling generated by a mobile terminal in a time neighborhood of a current time to obtain base station signal strength and user behavior data; the time neighborhood comprises a plurality of collection times ending at the current time; for each time, determine the signal strength change of the base station signal strength in adjacent times, and take the average of the signal strength changes of the plurality of collection times in the time neighborhood as the fluctuation characteristics of the base station signal; analyze the influence degree of user behavior on the base station signal in the time neighborhood according to the user behavior data and the fluctuation characteristics; the user behavior data includes at least one of the number of users and the location of users; if the user behavior data includes the number of users, the influence degree is the first influence degree of the number of users on the signal fluctuation; if the user behavior data includes the location of users, the influence degree is the second influence degree of the change of user distribution on the signal fluctuation; if the user behavior data includes the number of users and the location of users, the influence degree is the average of the first influence degree and the second influence degree; determine the real-time state of the base station at the current time according to the fluctuation characteristics and the influence degree of user behavior on the base station signal in the time neighborhood, and the base station signal strength at the current time.

2. The base station real-time state monitoring method of claim 1, wherein, The user behavior data includes the number of users; analyzing the influence degree of user behavior on the base station signal in the time neighborhood according to the user behavior data and the fluctuation characteristics comprises: determining the first influence degree of the number of users on the signal fluctuation according to the number of users and the fluctuation characteristics in the time neighborhood as the influence degree of user behavior on the base station signal in the time neighborhood.

3. The base station real-time state monitoring method of claim 1, wherein, The user behavior data includes the location of users; analyzing the influence degree of user behavior on the base station signal in the time neighborhood according to the user behavior data and the fluctuation characteristics comprises: determining the second influence degree of the change of user distribution on the signal fluctuation according to the analysis of the change of user distribution based on the location of users in the time neighborhood and combining the fluctuation characteristics as the influence degree of user behavior on the base station signal in the time neighborhood.

4. The base station real-time state monitoring method of claim 1, wherein, The user behavior data includes the number of users and the location of users; analyzing the influence degree of user behavior on the base station signal in the time neighborhood according to the user behavior data and the fluctuation characteristics comprises: determining the first influence degree of the number of users on the signal fluctuation according to the number of users and the fluctuation characteristics in the time neighborhood; determining the second influence degree of the change of user distribution on the signal fluctuation according to the analysis of the change of user distribution based on the location of users in the time neighborhood and combining the fluctuation characteristics; determining the influence degree of user behavior on the base station signal in the time neighborhood according to the first influence degree and the second influence degree.

5. The base station real-time state monitoring method according to claim 2 or 4, characterized by, determining the first influence degree of the number of users on the signal fluctuation according to the number of users and the fluctuation characteristics in the time neighborhood comprises: constructing a number of users sequence and a fluctuation characteristics sequence according to the number of users and the fluctuation characteristics in the time neighborhood in sequence respectively; determining the actual coupling relationship between the change of the number of users and the signal fluctuation in the time neighborhood according to the correlation between the number of users sequence and the fluctuation characteristics sequence; According to the coupling deviation of the actual coupling relationship and the reference coupling relationship, a first influence degree of the number of users on signal fluctuation is determined; the reference coupling relationship is a reference relationship determined according to a sequence of the number of users and a sequence of fluctuation characteristics in a historical time period longer than the time neighborhood.

6. The base station real-time state monitoring method according to claim 3 or 4, characterized by, According to the user position in the time neighborhood, a second influence degree of user distribution change on signal fluctuation is determined in combination with the fluctuation characteristics, including: For each time point, the distance between the user position of a plurality of users in the coverage of the base station and the base station position is determined, and the distance change amount of each user at adjacent time points is compared; According to the distance change amount of the plurality of users, the user distribution change at each time point is determined; The user distribution change in the time neighborhood is constructed into a sequence of user distribution changes in time sequence; According to the correlation between the sequence of user distribution changes and the sequence of fluctuation characteristics, the second influence degree of user distribution change on signal fluctuation is determined; the sequence of fluctuation characteristics is constructed in time sequence by the fluctuation characteristics in the time neighborhood.

7. The method of claim 1, wherein the method further comprises: According to the fluctuation characteristics in the time neighborhood and the influence degree of user behavior on the base station signal, and the base station signal strength at the current time point, the real-time state of the base station at the current time point is determined, including: According to the fluctuation characteristics in the time neighborhood and the base station signal strength at the current time point, an initial fluctuation abnormal value of the base station at the current time point is determined; According to the influence degree of user behavior on the base station signal in the time neighborhood, the initial fluctuation abnormal value is corrected to obtain a corrected fluctuation abnormal value; According to the corrected fluctuation abnormal value, the real-time state of the base station at the current time point is determined.

8. The base station real-time state monitoring method of claim 7, wherein, According to the corrected fluctuation abnormal value, the real-time state of the base station at the current time point is determined, including: If the corrected fluctuation abnormal value is greater than or equal to a preset abnormal threshold, it is determined that the real-time state of the base station at the current time point is an abnormal state; If the corrected fluctuation abnormal value is less than the preset abnormal threshold, it is determined that the real-time state of the base station at the current time point is a normal state.

9. The base station real-time state monitoring method of claim 8, wherein, The method further includes: An abnormal report is generated in the abnormal state; the abnormal report includes the time point of abnormal occurrence, the fluctuation amplitude of the base station signal strength, and the change characteristics of the user behavior data; According to the abnormal report, network diagnosis, parameter optimization or communication trajectory analysis is performed.

Images