Radio monitoring data analysis method, system and related equipment

Abstract

The invention relates to the technical field of radio monitoring, in particular to a radio monitoring data analysis method and system and related equipment, and the method comprises the steps: obtaining target data transmitted by radio equipment; sending the target data to a machine learning model, and performing feature extraction on the target data based on the machine learning model to obtain target features; judging whether the target feature meets a preset feature standard or not; if the target feature does not meet the preset feature standard, marking the target data as abnormal data; analyzing the abnormal data, and obtaining abnormal factors of the abnormal data; and obtaining a target processing scheme based on the abnormal factors. According to the invention, the processing effect of the radio monitoring data is improved, so that the condition of shortage of radio resources is relieved.

Description

Technical Field

[0001] The present application relates to the field of radio monitoring technology, and in particular to a radio monitoring data analysis method, system and related equipment. Background Art

[0002] With the rapid development of wireless communication technology, radio spectrum resources are becoming increasingly scarce. Daily radio monitoring is an important task in radio management. Carrying out daily radio monitoring and analyzing radio monitoring data are the basic basis for describing and evaluating radio environment conditions and conducting radio management. Therefore, the importance of radio monitoring data analysis in the fields of spectrum management, signal detection, interference identification, etc. is becoming increasingly prominent.

[0003] Traditional radio monitoring data relies on manual operations, mainly listening and manual analysis and processing. However, with the ever-developing communication technology, manual operations are unable to cope with such large amounts of complex data. Not only is the efficiency low, but the accuracy is also difficult to guarantee. As a result, the processing effect of radio monitoring data is far from meeting user needs, and the shortage of radio resources has not been well alleviated. Summary of the invention

[0004] In order to help improve the processing effect of radio monitoring data and thus alleviate the shortage of radio resources, the present application provides a radio monitoring data analysis method, system and related equipment.

[0005] In the first aspect, the present application provides a radio monitoring data analysis method, which adopts the following technical solution: A radio monitoring data analysis method, comprising: Acquire target data sent by radio equipment; Sending the target data to a machine learning model, and performing feature extraction on the target data based on the machine learning model to obtain target features; Determining whether the target feature meets a preset feature standard; If the target feature does not meet the preset feature standard, marking the target data as abnormal data; Analyzing the abnormal data and obtaining abnormal factors of the abnormal data; Based on the abnormal factors, a target processing solution is obtained.

[0006] By adopting the above technical solution, a machine learning model is used to extract features of the target data and obtain target features, and it is determined whether the target features meet the preset feature standards. If not, it means that the target data is abnormal, so the target data is marked as abnormal data, and the abnormal data is further analyzed, and the abnormal factors of the abnormal data are obtained. Finally, according to the abnormal factors, a corresponding target processing solution is generated to process the abnormal data; By using machine learning models to extract and analyze the features of target data without relying on manual operations, it not only helps to improve work efficiency, but also helps to improve the accuracy of data analysis results. At the same time, by analyzing different abnormal data, the target processing plan corresponding to the abnormal factors is selected, which helps to make the target processing plan more practical. By improving processing efficiency and improving the accuracy and practicality of data analysis, it helps to improve the processing effect of radio monitoring data, thereby alleviating the shortage of radio resources.

[0007] Optionally, extracting features from the target data to obtain target features includes: Acquire the signal type of the target data; Extracting features of the target data to obtain individual features of the target data, wherein the individual features include a target frequency, a modulation mode, a target level, a target bandwidth, and a signal period; Based on all the individual features, the target feature is obtained.

[0008] Optionally, the determining whether the target feature meets a preset feature standard includes: Determine whether all of the individual features meet the corresponding preset feature standards; If there is at least one of the single features that does not meet the corresponding preset feature standard, then it is determined that the target feature does not meet the preset feature standard; If all of the individual features meet the corresponding preset feature standards, it is determined that the target feature meets the preset feature standards.

[0009] Optionally, analyzing the abnormal data and obtaining abnormal factors of the abnormal data includes: Acquire real-time data and operation log corresponding to the target device that collects the target data; Based on the real-time data and the operation log, determining whether the target device has a device failure; If the target device has the device failure, marking the abnormal factor as a collection failure; If the target device does not have the device failure, determining whether the target data has data loss; If the target data has the data loss, marking the abnormal factor as a transmission failure; If the target data does not have the data loss, the abnormal factor is marked as an interference fault.

[0010] Optionally, obtaining a target processing solution based on the abnormal factor includes: If the abnormal factor is the transmission failure, obtaining a data loss rate; Determining whether the data loss rate exceeds a first ratio threshold; If the data loss rate does not exceed the first ratio threshold, obtaining the number of intervals corresponding to the data loss interval; Determining whether the number of intervals exceeds a preset number threshold; If the number of intervals does not exceed the preset number threshold, determining whether the data loss rate exceeds a second ratio threshold; If the data loss rate exceeds a second ratio threshold, reacquiring the target data; If the data loss rate exceeds the second ratio threshold, reacquiring the target data; If there is no data loss rate exceeding the second ratio threshold, the target data is corrected.

[0011] Optionally, after determining whether the number of intervals exceeds a preset number threshold, the method further includes: If the number of intervals exceeds the preset number threshold, obtaining the data loss rates corresponding to different data loss intervals; Determine whether the data loss rate exceeds the second ratio threshold; If the data loss rate exceeds the second ratio threshold, the target data is corrected.

[0012] Optionally, the step of obtaining a target processing solution based on the abnormal factor further includes: If the abnormal factor is the interference fault, obtaining a common time node of the abnormal data; Determine whether the frequently occurring time node meets a preset time rule; If the frequently occurring time node satisfies the preset time rule, obtaining the interference source, and determining whether the interference source is a natural interference source; If the interference source is the natural interference source, processing the target data based on a preset rule; If the interference source is not the natural interference source, obtaining the location of the interference source; An alarm is issued based on the location of the interference source.

[0013] In a second aspect, the present application also discloses a radio monitoring data analysis system, which adopts the following technical solution: A radio monitoring data analysis system, comprising: A first acquisition module, used for acquiring target data sent by a radio device; A feature extraction module, used to send the target data to a machine learning model, and extract features from the target data based on the machine learning model to obtain target features; A feature judgment module is used to judge whether the target feature meets the preset feature standard; an abnormal marking module, which is used to mark the target data as abnormal data if the target feature does not meet the preset feature standard; A data analysis module, used to analyze the abnormal data and obtain abnormal factors of the abnormal data; The second acquisition module is used to acquire a target processing solution based on the abnormal factor.

[0014] By adopting the above technical solution, a machine learning model is used to extract features of the target data and obtain target features, and it is determined whether the target features meet the preset feature standards. If not, it means that the target data is abnormal, so the target data is marked as abnormal data, and the abnormal data is further analyzed, and the abnormal factors of the abnormal data are obtained. Finally, according to the abnormal factors, a corresponding target processing solution is generated to process the abnormal data; By using machine learning models to extract and analyze the features of target data without relying on manual operations, it not only helps to improve work efficiency, but also helps to improve the accuracy of data analysis results. At the same time, by analyzing different abnormal data, the target processing plan corresponding to the abnormal factors is selected, which helps to make the target processing plan more practical. By improving processing efficiency and improving the accuracy and practicality of data analysis, it helps to improve the processing effect of radio monitoring data, thereby alleviating the shortage of radio resources.

[0015] In a third aspect, the present application provides a computer device, which adopts the following technical solution: An intelligent terminal comprises a memory and a processor, wherein the memory is used to store a computer program that can be run on the processor, and when the processor loads the computer program, the method of the first aspect is executed.

[0016] By adopting the above technical solution, a computer program is generated based on the method of the first aspect and stored in a memory to be loaded and executed by a processor, thereby manufacturing an intelligent terminal based on the memory and the processor for user convenience.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program, and when the computer program is loaded by a processor, the method of the first aspect is executed.

[0018] By adopting the above technical solution, a computer program is generated based on the method of the first aspect and stored in a computer-readable storage medium so as to be loaded and executed by a processor. The computer-readable storage medium facilitates the readability and storage of the computer program.

[0019] In summary, this application includes the following beneficial technical effects: By using machine learning models to extract and analyze the features of target data without relying on manual operations, it not only helps to improve work efficiency, but also helps to improve the accuracy of data analysis results. At the same time, by analyzing different abnormal data, the target processing plan corresponding to the abnormal factors is selected, which helps to make the target processing plan more practical. By improving processing efficiency and improving the accuracy and practicality of data analysis, it helps to improve the processing effect of radio monitoring data, thereby alleviating the shortage of radio resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a main flow chart of a radio monitoring data analysis method according to an embodiment of the present application; Figure 2 is a flowchart of steps S201 to S203; Figure 3 is a flowchart of steps S301 to S303; Figure 4 is a flowchart of steps S401 to S406; Figure 5 is a flowchart of steps S501 to S507; Figure 6 is a flowchart of steps S601 to S603; Figure 7 is a flowchart of steps S701 to S706; Figure 8 It is a module diagram of a radio monitoring data analysis system according to an embodiment of the present application.

[0021] Description of reference numerals: 1. First acquisition module; 2. Feature extraction module; 3. Feature judgment module; 4. Abnormal marking module; 5. Data analysis module; 6. Second acquisition module. DETAILED DESCRIPTION

[0022] In a first aspect, the present application discloses a radio monitoring data analysis method.

[0023] Reference Figure 1 , a radio monitoring data analysis method, comprising steps S101 to S106: Step S101: Acquire target data sent by a radio device.

[0024] Specifically, the target data is data monitored by a radio data monitoring device. In this embodiment, the target data is sent by a radio device.

[0025] Step S102: Send the target data to the machine learning model, and extract features of the target data based on the machine learning model to obtain target features.

[0026] Specifically, the machine learning model is a pre-set learning model trained with a large amount of radio data, and is used for feature extraction and data analysis of target data.

[0027] Step S103: Determine whether the target feature meets the preset feature standard.

[0028] Specifically, the preset feature standard is a pre-set judgment standard for judging whether the target data is legal and normal data according to the target feature. In this embodiment, the preset feature standard corresponds to the target feature.

[0029] Step S104: If the target feature does not meet the preset feature standard, the target data is marked as abnormal data.

[0030] Specifically, in this embodiment, abnormal data refers to data that is illegal or abnormal.

[0031] Step S105: Analyze the abnormal data and obtain the abnormal factors of the abnormal data.

[0032] Specifically, the abnormal factors are factors that cause the target data to be abnormal. In this embodiment, the abnormal factors include acquisition failure, transmission failure, interference failure, etc.

[0033] Step S106: Based on the abnormal factors, obtain a target processing solution.

[0034] Specifically, in this embodiment, the target processing scheme is a scheme for processing abnormal data generated according to abnormal factors. The radio monitoring data analysis method provided in this embodiment uses a machine learning model to extract features from target data and obtain target features, and determines whether the target features meet preset feature standards. If not, it indicates that the target data is abnormal, so the target data is marked as abnormal data, and the abnormal data is further analyzed, and the abnormal factors of the abnormal data are obtained. Finally, according to the abnormal factors, a corresponding target processing solution is generated to process the abnormal data; By using machine learning models to extract and analyze the features of target data without relying on manual operations, it not only helps to improve work efficiency, but also helps to improve the accuracy of data analysis results. At the same time, by analyzing different abnormal data, the target processing plan corresponding to the abnormal factors is selected, which helps to make the target processing plan more practical. By improving processing efficiency and improving the accuracy and practicality of data analysis results, it helps to improve the processing effect of radio monitoring data, thereby alleviating the shortage of radio resources.

[0035] Reference Figure 2 In one implementation of this embodiment, in step S102, feature extraction is performed on the target data to obtain the target feature, including steps S201 to S203: Step S201: Acquire the signal type of target data.

[0036] Specifically, in this embodiment, the signal types include broadcast signals, base station signals of communication operators, satellite communication signals, and the like.

[0037] Step S202: extracting features from the target data to obtain individual features of the target data.

[0038] Specifically, the target data includes a plurality of individual features, where an individual feature is a single feature corresponding to the target data. In this embodiment, the individual features include a target frequency, a modulation mode, a target level, a target bandwidth, and a signal period.

[0039] Step S203: Acquire target features based on all individual features.

[0040] Specifically, in this embodiment, the target feature is the collection of all individual features.

[0041] The radio monitoring data analysis method provided in this embodiment extracts single features of the target data according to the signal type of the target data, and then combines all the single features to generate target features; extracting features from panel data from multiple directions and different dimensions helps to make the target features more comprehensive, and analyzing according to the target features helps to more quickly and accurately obtain the corresponding target processing solution to process the target data, thereby improving the processing effect of the radio monitoring data and alleviating the shortage of radio resources.

[0042] Reference Figure 3 In one implementation of this embodiment, step S103 determines whether the target feature meets the preset feature standard, including steps S301 to S303: Step S301: Determine whether all individual features meet the corresponding preset feature standards.

[0043] Specifically, in this embodiment, different individual features correspond to different preset feature standards. Therefore, all individual features are compared with the corresponding preset feature standards respectively to determine whether all individual features meet the corresponding preset feature standards.

[0044] Step S302: If there is at least one single feature that does not meet the corresponding preset feature standard, it is determined that the target feature does not meet the preset feature standard.

[0045] Step S303: If all individual features meet the corresponding preset feature standards, it is determined that the target feature meets the preset feature standards.

[0046] Specifically, if there is at least one single feature that does not meet the corresponding preset feature standard, it means that not all single features meet the corresponding preset feature standard. Therefore, it is judged that the target feature does not meet the preset feature standard. Only when all single features meet the corresponding preset feature standard, it is judged that the target feature meets the preset feature standard.

[0047] The radio monitoring data analysis method provided in this embodiment compares all individual features with the corresponding preset feature standards respectively, so as to determine whether the target feature meets the preset feature standards. Only when all individual features meet the corresponding preset feature standards, the target feature is determined to meet the preset feature standards. Through multiple judgments, it helps to improve the accuracy and practicality of the data analysis results.

[0048] Reference Figure 4 In one implementation of this embodiment, step S105 analyzes the abnormal data and obtains the abnormal factors of the abnormal data, including steps S401 to S406: Step S401: Acquire the real-time data and operation log corresponding to the target device for collecting target data.

[0049] Specifically, the real-time data is data used to characterize the operating status of the target device in real time, and the operation log is historical data used to characterize the operating status of the target device. In this embodiment, the real-time data becomes historical data as time changes.

[0050] Step S402: Based on the real-time data and the operation log, determine whether the target device has a device failure.

[0051] Specifically, the real-time data and the operation log are compared with the equipment standard data respectively, so as to determine whether the target equipment has equipment failure. In this embodiment, the equipment standard data is a preset standard for characterizing that the target data is legal and normal data.

[0052] Step S403: If the target device has a device failure, the abnormal factor is marked as a collection failure.

[0053] Specifically, the target device is used to collect target data. If the target device has a device failure, it will cause errors in the target device when monitoring and collecting radio data, thereby causing abnormalities in the target data. Therefore, when the target device has a device failure, the abnormal factor is marked as a collection failure. In this embodiment, the device failure includes damage or aging of the sensor of the target device.

[0054] Step S404: If the target device does not have a device failure, determine whether there is data loss in the target data.

[0055] Specifically, in this embodiment, whether there is data loss in the target data can be determined by performing a data volume check and a data continuity check on the target data.

[0056] Step S405: If there is data loss in the target data, the abnormal factor is marked as a transmission failure.

[0057] Specifically, in this embodiment, after the target data is collected, the target data will be transmitted to the machine learning model for analysis. If there is data loss in the target data and there is no device failure in the target device, it is very likely that loss occurred during the data transmission process. Therefore, the abnormal factor is marked as a transmission failure.

[0058] Step S406: If there is no data loss in the target data, the abnormal factor is marked as an interference fault.

[0059] Specifically, in this embodiment, if there is neither equipment failure nor data loss, it is very likely that the target data is interfered with by an interference source during data collection and / or output, resulting in abnormality in the target data, and therefore the abnormal factor is marked as an interference failure.

[0060] The radio monitoring data analysis method provided in this embodiment analyzes and determines the specific type of abnormal factor corresponding to the target data through multiple judgments. By knowing the specific type, it helps to more accurately select the corresponding target processing solution to process the abnormal data, thereby helping to improve the processing effect of the radio monitoring data and alleviate the situation of tight radio resources.

[0061] Reference Figure 5 In one implementation of this embodiment, step S106 obtains a target processing solution based on abnormal factors, including steps S501 to S507: Step S501: If the abnormal factor is a transmission failure, the data loss rate is obtained.

[0062] Specifically, the data loss rate is the percentage of missing data to the total data. In this embodiment, the target device collects data at fixed time intervals. For example, the target device is set to collect data once per second. During the monitoring process of one hour (3600 seconds), there should be 3600 data points under normal circumstances. If the final data points are 3500, the data loss rate is (3600-3500) ÷ 3600 × 100% = 0.278%.

[0063] Step S502: Determine whether the data loss rate exceeds a first ratio threshold.

[0064] Specifically, the first ratio threshold is a pre-set criterion for determining whether the data loss rate is too high. In this embodiment, the first ratio threshold may be 1% or 0.5%, etc., and may also be set according to actual conditions and user needs.

[0065] Step S503: If the data loss rate does not exceed the first ratio threshold, the number of intervals corresponding to the data loss interval is obtained.

[0066] Specifically, the data loss interval is the location interval of the lost data, and the interval number is the number of data loss intervals. In this embodiment, the target data can be numbered according to the acquisition time node. If data loss occurs, one data point may be lost, or multiple data points may be lost. For example, the data is numbered from 1 to 3600. If data points 18 and 50 to 52 do not exist, it indicates that data points 18 and 50 to 52 are lost. Since data points 50 to 52 are continuous, they are divided into one data loss interval, so the number of intervals corresponding to the data loss interval is 2.

[0067] Step S504: Determine whether the number of intervals exceeds a preset number threshold.

[0068] Specifically, the preset number threshold is a pre-set criterion for determining whether the number of intervals is too large. In this embodiment, the preset number threshold may be 1.

[0069] Step S505: If the number of intervals does not exceed the preset number threshold, determine whether the data loss rate exceeds the second ratio threshold.

[0070] Specifically, if the number of intervals does not exceed the preset number threshold, it indicates that there is only one data loss interval, and therefore all lost data points are within the data loss interval; the second ratio threshold is a pre-set judgment standard for determining whether the data loss rate corresponding to a single data loss interval is too large. In this embodiment, the second ratio threshold can be 0.2% or 0.1%, etc., and can also be set according to actual conditions and user needs.

[0071] Step S506: if the data loss rate exceeds the second ratio threshold, reacquire the target data.

[0072] Specifically, in this embodiment, if the data loss rate exceeds the second ratio threshold, it indicates that the data loss rate corresponding to the single data loss interval is too large, so there is a large abnormality in the target data, and therefore the target data needs to be reacquired.

[0073] Step S507: If the data loss rate does not exceed the second ratio threshold, the target data is corrected.

[0074] Specifically, in this embodiment, if the data loss rate does not exceed the second ratio threshold, it indicates that the data loss rate corresponding to the single data loss interval is small, so the target data can be corrected without reacquiring the target data.

[0075] The radio monitoring data analysis method provided in this embodiment determines the specific circumstances of the data loss interval and the data loss rate through multiple judgments, and then selects the corresponding target processing method according to the corresponding specific circumstances, which helps to more accurately select the corresponding target processing solution to process the abnormal data, thereby helping to improve the processing effect of the radio monitoring data and alleviate the situation of tight radio resources.

[0076] Reference Figure 6 In one implementation of this embodiment, after determining whether the number of intervals exceeds a preset number threshold in step S504, the following steps are included: Step S601: if the number of intervals exceeds a preset number threshold, then the data loss rates corresponding to different data loss intervals are obtained.

[0077] Specifically, in this embodiment, if the number of intervals exceeds the preset number threshold, it indicates that the number of intervals is greater than 1, that is, there are multiple data loss intervals, and therefore it is necessary to obtain the data loss rate corresponding to each data loss interval.

[0078] Step S602: Determine whether there is a data loss rate exceeding a second ratio threshold.

[0079] Specifically, in this embodiment, the data loss rates corresponding to all data loss intervals are compared with the second ratio threshold respectively, so as to determine whether there is a data loss rate exceeding the second ratio threshold.

[0080] Step S603: if the data loss rate exceeds the second ratio threshold, the target data is acquired again.

[0081] Specifically, in this embodiment, if there is a data loss rate exceeding the second ratio threshold, it means that the data loss rate corresponding to a single data loss interval exceeds the second ratio threshold, which has a greater impact on the target data, so the target data needs to be reacquired.

[0082] Step S604: If there is no data loss rate exceeding the second ratio threshold, the target data is corrected.

[0083] Specifically, in this embodiment, if there is no data loss rate exceeding the second ratio threshold, it indicates that the data loss rates corresponding to all single data loss intervals are small, so the target data can be corrected without reacquiring the target data. The radio monitoring data analysis method provided in this embodiment, when the number of intervals exceeds a preset number threshold, determines whether the data loss rate of each data loss interval exceeds a preset second threshold. If exceeded, the target data is reacquired, which helps to improve the accuracy of the radio monitoring data analysis results. If not exceeded, the target data is corrected, which helps to improve data processing efficiency.

[0084] Reference Figure 7 In one implementation of this embodiment, in step S106, based on the abnormal factors, obtaining the target processing solution also includes steps S701 to S706: Step S701: If the abnormal factor is an interference fault, obtain the time nodes at which the abnormal data often occurs.

[0085] Specifically, in this embodiment, the frequently occurring time node is the time node where the abnormal situation often occurs, for example, between 9:00 and 10:00 in the morning.

[0086] Step S702: Determine whether the frequently occurring time nodes meet the preset time rules.

[0087] Specifically, in this embodiment, the preset time rule is a pre-set time rule, such as appearing in every specific time period, or appearing at fixed time intervals, etc.

[0088] Step S703: If the frequently occurring time node satisfies the preset time rule, the interference source is obtained, and it is determined whether the interference source is a natural interference source.

[0089] Specifically, the interference source can be obtained through spectrum analysis, signal strength change analysis, modulation mode analysis, and device association analysis, and it can be determined whether the interference source is a natural interference source. In this embodiment, the natural interference source is an interference source existing in nature, such as lightning, solar activity, static electricity, cosmic rays, and electromagnetic fields.

[0090] Step S704: If the interference source is a natural interference source, the target data is processed based on a preset rule.

[0091] Specifically, the preset rules are pre-set rules for processing target data when the interference source is a natural interference source. In this embodiment, different natural interference sources correspond to different preset rules.

[0092] Step S705: If the interference source is not a natural interference source, the location of the interference source is obtained.

[0093] Specifically, in this embodiment, if the interference source is not a natural interference source, then the interference source must be man-made, and the location of the interference source can be found according to methods such as the interference source positioning method and the interference source tracking method.

[0094] Step S706: issuing an alarm based on the location of the interference source.

[0095] Specifically, in this embodiment, after the location of the interference source is determined, an alarm is issued according to the location, thereby helping relevant personnel to deal with the interference source in a timely manner.

[0096] The radio monitoring data analysis method provided in this embodiment selects the corresponding target processing method to process the target data or interference source according to the different types of interference sources, which helps to improve the processing efficiency. Moreover, by processing the interference source, it helps to improve the processing effect of the radio monitoring data, thereby alleviating the situation of tight radio resources.

[0097] In a second aspect, the present application also discloses a radio monitoring data analysis system.

[0098] Reference Figure 8 , a radio monitoring data analysis system, comprising: A first acquisition module, used for acquiring target data sent by a radio device; A feature extraction module is used to send the target data to the machine learning model, and extract features of the target data based on the machine learning model to obtain target features; A feature judgment module is used to judge whether the target feature meets the preset feature standard; Anomaly marking module, if the target feature does not meet the preset feature standard, the anomaly marking module is used to mark the target data as abnormal data; A data analysis module is used to analyze abnormal data and obtain abnormal factors of the abnormal data; The second acquisition module is used to acquire a target processing solution based on abnormal factors.

[0099] In a third aspect, an embodiment of the present application discloses an intelligent terminal, including a memory and a processor, wherein the memory is used to store a computer program that can be run on the processor, and when the processor loads the computer program, a radio monitoring data analysis method of the above embodiment is executed.

[0100] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium, wherein when the computer program is loaded by a processor, a radio monitoring data analysis method of the above embodiment is executed.

[0101] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A radio monitoring data analysis method, characterized in that: include: Acquire target data sent by radio equipment; Sending the target data to a machine learning model, and performing feature extraction on the target data based on the machine learning model to obtain target features; Determining whether the target feature meets a preset feature standard; If the target feature does not meet the preset feature standard, marking the target data as abnormal data; Analyzing the abnormal data and obtaining abnormal factors of the abnormal data; Based on the abnormal factors, a target processing solution is obtained.

2. A radio monitoring data analysis method according to claim 1, characterized in that: The feature extraction of the target data to obtain the target feature comprises: Acquire the signal type of the target data; Extracting features of the target data to obtain individual features of the target data, wherein the individual features include a target frequency, a modulation mode, a target level, a target bandwidth, and a signal period; Based on all the individual features, the target feature is obtained.

3. A radio monitoring data analysis method according to claim 2, characterized in that: The determining whether the target feature meets the preset feature standard includes: Determine whether all of the individual features meet the corresponding preset feature standards; If there is at least one of the single features that does not meet the corresponding preset feature standard, then it is determined that the target feature does not meet the preset feature standard; If all of the individual features meet the corresponding preset feature standards, it is determined that the target feature meets the preset feature standards.

4. A radio monitoring data analysis method according to claim 1, characterized in that: The analyzing the abnormal data and obtaining the abnormal factors of the abnormal data includes: Acquire real-time data and operation log corresponding to the target device that collects the target data; Based on the real-time data and the operation log, determining whether the target device has a device failure; If the target device has the device failure, marking the abnormal factor as a collection failure; If the target device does not have the device failure, determining whether the target data has data loss; If the target data has the data loss, marking the abnormal factor as a transmission failure; If the target data does not have the data loss, the abnormal factor is marked as an interference fault.

5. A radio monitoring data analysis method according to claim 4, characterized in that: The obtaining of a target processing solution based on the abnormal factor includes: If the abnormal factor is the transmission failure, obtaining a data loss rate; Determining whether the data loss rate exceeds a first ratio threshold; If the data loss rate does not exceed the first ratio threshold, obtaining the number of intervals corresponding to the data loss interval; Determining whether the number of intervals exceeds a preset number threshold; If the number of intervals does not exceed the preset number threshold, determining whether the data loss rate exceeds a second ratio threshold; If the data loss rate exceeds a second ratio threshold, reacquiring the target data; If the data loss rate does not exceed the second ratio threshold, the target data is corrected.

6. A radio monitoring data analysis method according to claim 5, characterized in that: After determining whether the number of intervals exceeds a preset number threshold, the method further includes: If the number of intervals exceeds the preset number threshold, obtaining the data loss rates corresponding to different data loss intervals; Determine whether the data loss rate exceeds the second ratio threshold; If the data loss rate exceeds the second ratio threshold, reacquiring the target data; If there is no data loss rate exceeding the second ratio threshold, the target data is corrected.

7. A radio monitoring data analysis method according to claim 4, characterized in that: The obtaining of a target processing solution based on the abnormal factor further comprises: If the abnormal factor is the interference fault, obtaining a common time node of the abnormal data; Determine whether the frequently occurring time node meets a preset time rule; If the frequently occurring time node satisfies the preset time rule, obtaining the interference source, and determining whether the interference source is a natural interference source; If the interference source is the natural interference source, processing the target data based on a preset rule; If the interference source is not the natural interference source, obtaining the location of the interference source; An alarm is issued based on the location of the interference source.

8. A radio monitoring data analysis system, characterized in that: include: A first acquisition module, used for acquiring target data sent by a radio device; A feature extraction module, used to send the target data to a machine learning model, and extract features from the target data based on the machine learning model to obtain target features; A feature judgment module is used to judge whether the target feature meets the preset feature standard; an abnormal marking module, which is used to mark the target data as abnormal data if the target feature does not meet the preset feature standard; A data analysis module, used to analyze the abnormal data and obtain abnormal factors of the abnormal data; The second acquisition module is used to acquire a target processing solution based on the abnormal factor.

9. An intelligent terminal, comprising a memory and a processor, characterized in that: The memory is used to store a computer program that can be run on the processor, and when the processor loads the computer program, it executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded by a processor, the method according to any one of claims 1 to 7 is executed.

Images