Communication base station monitoring method and system based on artificial intelligence

Abstract

The invention provides a communication base station monitoring method and system based on artificial intelligence. The method comprises the following steps: acquiring operation and maintenance data of each component related to a first target base station; calculating a target fault degree; acquiring a historical fault type set; acquiring a first fault parameter from the first training set; acquiring a second fault parameter from the second training set; performing fault detection on each component of the first target base station according to the first fault parameter; acquiring a second target base station; fusing the first fault parameter and the second fault parameter to obtain a third fault parameter; performing fault detection on each component of the second target base station according to the third fault parameter; calculating to obtain a predicted fault probability of each component of the second target base station; according to the method, the data processing efficiency in the monitoring process can be improved, it is ensured that operation and maintenance personnel can maintain the communication base station in time, an accurate fault probability prediction result can be generated in combination with the dynamic change of the environment variable, and the operation and maintenance level can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of communication base stations, and specifically to a communication base station monitoring method and system based on artificial intelligence. Background Art

[0002] With the rapid development of my country's communications industry, the comprehensiveness of network coverage has been gradually improved, and the role of communication base stations has become increasingly prominent. They have functions such as communication coverage, engineering maintenance, transmission conversion, system expansion, and network access, and are responsible for providing customers with better call services. In the operation of base stations, the most important work is the daily operation and maintenance of base stations. Whether the operation and maintenance are normal is directly related to whether the business can be carried out smoothly. In order to achieve real-time monitoring of each communication base station, a management room is generally set up in each communication base station to monitor the parameters and status of each communication base station.

[0003] In the prior art, the parameters related to each component of the communication base station are first obtained by using a sensor device, and then the relevant parameters are sent to the management room, and then the relevant technical personnel check the various parameters; however, in the above process, there are at least the following problems: after receiving the various parameters, the operation and maintenance personnel in the management room will give priority to processing some emergency parameters due to the high redundancy of the parameters, and will postpone the processing of some general parameters, resulting in low response efficiency of general parameters, and also unable to timely discover possible faults. At this time, the operating status of the components will further deteriorate, causing the failure rate of the components to increase. If the operation and maintenance personnel cannot repair the components in time, the risk of failure of the communication base station will increase; at the same time, the operation and maintenance personnel can usually only analyze the parameter changes based on their own operation and maintenance experience, and it is difficult to cope with the dynamic changes in complex environments, such as the impact of sudden environmental changes and periodic environmental changes, and thus cannot make reliable and accurate predictions of possible faults, resulting in low operation and maintenance efficiency and high difficulty of operation and maintenance.

[0004] Therefore, developing a communication base station monitoring method and system based on artificial intelligence has important practical significance and broad application prospects. Summary of the invention

[0005] The purpose of this application is to provide an artificial intelligence-based communication base station monitoring method and system to improve the efficiency of data processing during the communication base station monitoring process, be able to cope with the dynamic changes in complex environments, and enhance the accuracy and explainability of fault prediction.

[0006] In a first aspect, an embodiment of the present application provides a communication base station monitoring method based on artificial intelligence, comprising: Acquire operation and maintenance data of various components related to the first target base station; Identify a corresponding feature factor set from the operation and maintenance data, where the feature factor set includes a fault feature factor set and a stable feature factor set; Obtaining the fault type of each component related to the first target base station according to the fault characteristic factor set; Calculate the target fault degree according to the fault characteristic factor set and the stability characteristic factor set; When the target fault degree reaches the fault degree threshold, a historical fault type set related to the first target base station is obtained, where the historical fault type set includes a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; Acquire first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; Acquire second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; When the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter; When the matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, obtaining a second target base station in the same preset space as the first target base station, and there is at least one second target base station in the preset space; Fusing the first fault parameter and the second fault parameter to obtain a third fault parameter; Perform fault detection on each component of the second target base station according to the third fault parameter to obtain the fault probability and environmental variables: According to the failure probability and the environmental variables, obtaining the failure probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period; After preprocessing the fault probability time series data and the environmental variable time series data, the pre-trained prediction model is input to obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

[0007] Optionally, the identifying a corresponding characteristic factor set from the operation and maintenance data, the characteristic factor set includes a fault characteristic factor set and a stability characteristic factor set, specifically including: Perform time domain processing on each operation and maintenance data to obtain a sequence set; A fault characteristic factor set and a stable characteristic factor set are obtained from the sequence set.

[0008] Optionally, the method further comprises: performing fault detection on each component of the second target base station according to the third fault parameter to obtain a fault detection report; The fault detection report is transmitted to the operation and maintenance center for strategy analysis and optimization, and regional linkage operation and maintenance strategy parameters are obtained. Based on the regional linkage operation and maintenance strategy parameters, fault operation and maintenance management and control are performed on the areas of the first target base station and the second target base station.

[0009] Optionally, the method described above pre-trains the prediction model in the following manner: Acquire historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station; After preprocessing the historical fault probability time series data samples and the historical environmental variable time series data samples, the historical fault probability time series data samples and the historical environmental variable time series data samples are converted into fault probability supervised data and environmental variable supervised data respectively; The supervised data of failure probability and supervised data of environmental variables are input into the neural network for training, and the prediction model is obtained after reaching the preset training cutoff condition.

[0010] Optionally, the neural network based on the collaboration of high- and low-frequency cycles and environmental variables includes a sequentially connected data input module, a data preprocessing module, a high-frequency feature extraction module, a low-frequency feature extraction module, an environmental variable processing module, a feature fusion module, a recurrent neural network module and an output module.

[0011] Optionally, when the matching degree between the fault type and the first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter specifically includes: Calculate the matching degree between the fault type and the first historical fault type according to the matching degree measurement algorithm; When the matching degree reaches a first matching degree threshold, fault detection is performed on each target component according to the first fault parameter.

[0012] Optionally, calculating the degree of matching between the fault type and the first historical fault type according to a matching degree measurement algorithm specifically includes: Calculate a first state matrix of the fault type; calculating a second state matrix of the first historical fault type; Calculate the matching degree between the first state matrix and the second state matrix.

[0013] Optionally, the method further comprises: calculating a first fault correlation factor set related to the first target base station according to the historical fault type set, wherein the first fault correlation factor set comprises a plurality of first critical fault correlation factors and a plurality of second critical fault correlation factors; Acquire first weight parameters corresponding to each first critical fault-related factor from the first training set, wherein each first weight parameter corresponds to one first critical fault-related factor; Acquire second weight parameters corresponding to each second critical fault-related factor from the second training set, wherein each second weight parameter corresponds to one second critical fault-related factor; Calculating a first fault criticality parameter corresponding to the first critical fault correlation factor; calculating a second fault criticality parameter corresponding to the second critical fault correlation factor; Calculating a first fusion degree of each first fault criticality parameter and a second fault criticality parameter; A component whose first integration degree reaches an integration degree threshold is determined as a first key component of the first target base station.

[0014] Optionally, the method further includes: when the first fault criticality parameter is equal to 0 and the second fault criticality parameter is equal to 0, performing fault detection on the first target base station.

[0015] In a second aspect, an embodiment of the present application provides a communication base station monitoring system based on artificial intelligence, including: A first acquisition module, used to acquire operation and maintenance data of various components related to the first target base station; An identification module is used to identify a corresponding characteristic factor set from the operation and maintenance data, where the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set; A fault type acquisition module, used to obtain the fault type of each component related to the first target base station according to the fault characteristic factor set; A calculation module, used for calculating a target fault degree according to a fault characteristic factor set and a stability characteristic factor set; A second acquisition module is used to acquire a historical fault type set related to the first target base station when the target fault degree reaches the fault degree threshold, the historical fault type set including a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; A second acquisition module is used to acquire first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; A third acquisition module is used to acquire second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; A first fault detection module, configured to perform fault detection on each component of the first target base station according to a first fault parameter when the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold; a fourth acquisition module, configured to acquire, when a matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, a second target base station in the same preset space as the first target base station, wherein there is at least one second target base station in the preset space; A fusion module, used for fusing the first fault parameter and the second fault parameter to obtain a third fault parameter; The second fault detection module performs fault detection on each component of the second target base station according to the third fault parameter to obtain a fault probability and an environmental variable: A fifth acquisition module, used to acquire the fault probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period according to the fault probability and the environmental variable; A prediction module, used to pre-process the fault probability time series data and the environmental variable time series data, input the pre-trained prediction model, and obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

[0016] Compared with the prior art, the communication base station monitoring method and system based on artificial intelligence provided by the present application obtain operation and maintenance data of each component related to the first target base station; identify the corresponding characteristic factor set from the operation and maintenance data, the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set; obtain the fault type of each component related to the first target base station according to the fault characteristic factor set; calculate the target fault degree according to the fault characteristic factor set and the stable characteristic factor set; when the target fault degree reaches the fault degree threshold, obtain the historical fault type set related to the first target base station, the historical fault type set includes a first training set and a second training set; the first training set includes a plurality of first historical fault types, the second The training set includes a plurality of second historical fault types; obtaining first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; obtaining second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; when the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter; when the matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, obtaining a second historical fault type in the same preset space as the first target base station; target base station, there is at least one second target base station in the preset space; the first fault parameter and the second fault parameter are integrated to obtain a third fault parameter; fault detection is performed on each component of the second target base station according to the third fault parameter to obtain fault probability and environmental variables: according to the fault probability and environmental variables, the fault probability time series data and environmental variable time series data of each component of the second target base station in a certain time period are obtained; after pre-processing the fault probability time series data and the environmental variable time series data, a pre-trained prediction model is input to obtain the predicted fault probability of each component of the second target base station in a future set time period; wherein the prediction model is based on the historical data of each component of the second target base station The historical fault probability time series data samples and the historical environmental variable time series data samples are trained on the neural network based on the collaboration of high and low frequency cycles and environmental variables; it can not only improve the efficiency of data processing in the monitoring process, ensure that the operation and maintenance personnel who operate and maintain the communication base station can perform timely maintenance on the communication base station according to the first fault parameter, the second fault parameter, and the third fault parameter to ensure the effective operation of the communication base station, but also can generate accurate fault probability prediction results in combination with the dynamic changes of environmental variables, can effectively respond to the impact of sudden environmental changes and periodic environmental changes, realize accurate prediction of communication base station failures, make the final prediction results more explainable, and help to improve the operation and maintenance level. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A flow chart of a communication base station monitoring method based on artificial intelligence provided by the present application is shown; Figure 2 A schematic diagram of a communication base station monitoring system based on artificial intelligence provided by the present application is shown; Figure 3 A schematic diagram of an electronic device provided by the present application is shown. DETAILED DESCRIPTION

[0018] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0019] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0020] In addition, the terms "first" and "second" etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0021] Please refer to Figure 1 , Figure 1 The communication base station monitoring method based on artificial intelligence provided by the embodiment of the present application includes the following steps: S101, acquiring operation and maintenance data of various components related to a first target base station, where the operation and maintenance data may include historical data and real-time data; S102, identifying a corresponding feature factor set from the operation and maintenance data, where the feature factor set includes a fault feature factor set and a stable feature factor set; specifically, automatic identification can be performed through feature extraction methods such as principal component analysis PCA and linear discriminant analysis LDA; S103, obtaining the fault type of each component related to the first target base station according to the fault characteristic factor set, such as by training a fault type identification model (support vector machine, random forest, gradient boosting decision tree, neural network); S104, calculating a target fault degree according to the fault feature factor set and the stable feature factor set, such as calculating the target fault degree by feature weighting; S105. When the target fault degree reaches the fault degree threshold, a historical fault type set related to the first target base station is obtained, where the historical fault type set includes a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; S106, acquiring first fault parameters corresponding to each first historical fault type from the first training set, where each first fault parameter corresponds to a first historical fault type; S107, acquiring second fault parameters corresponding to each second historical fault type from the second training set, where each second fault parameter corresponds to a second historical fault type; S108. When the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold, perform fault detection on each component of the first target base station according to the first fault parameter; S109. When the matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, obtain a second target base station in the same preset space as the first target base station, and there is at least one second target base station in the preset space; the preset space includes the first target base station and the second target base station, the preset space is a circle with a circumference radius R, and the center of the preset space is the first target base station; S110, fusing the first fault parameter and the second fault parameter (such as by weighted fusion calculation method) to obtain a third fault parameter; S111. Perform fault detection on each component of the second target base station according to the third fault parameter to obtain a fault probability and an environmental variable: S112, acquiring the fault probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period according to the fault probability and the environmental variable; S113, after preprocessing the fault probability time series data and the environmental variable time series data, inputting the pre-trained prediction model to obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

[0022] In step S102, the corresponding characteristic factor set is identified from the operation and maintenance data, and the characteristic factor set includes a fault characteristic factor set and a stability characteristic factor set, specifically including: Perform time domain processing on each operation and maintenance data to obtain a sequence set; Obtain a fault characteristic factor set and a stable characteristic factor set from the sequence set. The first fault characteristic factor includes the following information: Abnormal changes before the failure, such as sudden increase, sudden decrease, mode change, etc.; Characteristics of the fault when it occurs, such as the duration and magnitude of the fault condition; The recovery mode after a failure, such as the recovery speed and recovery degree.

[0023] The first stable signature factor includes the following information: The indicator levels when the system is operating normally, such as steady-state values, fluctuation range, etc.; Indicators of system stability, such as coefficient of variation, standard deviation, etc.

[0024] The above method can extract a set of feature factors that are helpful for fault prediction from operation and maintenance data. These feature factor sets will be used as inputs to the neural network to help the model learn the complex relationship between operation and maintenance data and system faults, thereby improving the accuracy and efficiency of fault prediction.

[0025] In step S112, fault detection is performed on each component of the second target base station according to the third fault parameter to obtain fault probability and environmental variables: specifically, based on the fault detection result, a statistical model (such as logistic regression) is used to calculate the failure probability of each component within a certain time period, and within the same time period, environmental variable data related to fault detection is collected. The environmental variables may include: physical environment (temperature, humidity, pressure, vibration, etc.) and operating environment (system load, operating mode, maintenance history, etc.).

[0026] The above-mentioned fault probability time series data is the time series data composed of the fault probability data within a certain period of time according to the set resolution. The resolution can be set to a specific time interval such as hour, day, week or month. For example, the fault probability data is counted as the fault probability time series data with a resolution of daily; similarly, the environmental variable time series data can be obtained.

[0027] In some specific implementations, the method further includes: performing fault detection on each component of the second target base station according to the third fault parameter to obtain a fault detection report; The fault detection report is transmitted to the operation and maintenance center for strategy analysis and optimization, and regional linkage operation and maintenance strategy parameters are obtained. Based on the regional linkage operation and maintenance strategy parameters, fault operation and maintenance management and control are performed on the areas of the first target base station and the second target base station.

[0028] The obtaining of regional linkage operation and maintenance strategy parameters includes: performing feature matching with a fault operation and maintenance strategy library based on the fault detection report to obtain a fault operation and maintenance strategy; According to the fault operation and maintenance strategy, a fault operation and maintenance strategy space is constructed, and the fault detection report is parameterized according to the fault operation and maintenance strategy space to obtain the operation and maintenance strategy parameter thresholds; Perform global optimization of parameters within the threshold of the operation and maintenance strategy parameters according to the preset search range to obtain the operation and maintenance strategy parameters; The operation and maintenance strategy parameters are linked and integrated according to the inspection sequence of the base stations to obtain the regional linkage operation and maintenance strategy parameters.

[0029] In this embodiment, the method described herein pre-trains the prediction model in the following manner: Obtain historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station; wherein, historical failure probability time series data samples: collect failure probability data of each component within a certain time range, these data usually exist in the form of time series, and record the probability of component failure at each time point or time period; historical environmental variable time series data samples: collect environmental variable data related to failure probability, such as temperature, humidity, pressure, etc., these data are also recorded in the form of time series.

[0030] After preprocessing (such as data cleaning and normalization) the historical fault probability time series data samples and the historical environmental variable time series data samples, the historical fault probability time series data samples and the historical environmental variable time series data samples are converted into fault probability supervised data and environmental variable supervised data respectively; The supervised data of failure probability and supervised data of environmental variables are input into the neural network for training, and the prediction model is obtained after reaching the preset training cutoff condition.

[0031] In this embodiment, the neural network based on high-low frequency cycles and environmental variables collaboration includes a data input module, a data preprocessing module, a high-frequency feature extraction module, a low-frequency feature extraction module, an environmental variable processing module, a feature fusion module, a recurrent neural network module and an output module connected in sequence, as follows: Data input module: responsible for receiving input data, including high-frequency and low-frequency signals, environmental variables and other data sources; Data preprocessing module: used for data cleaning and standardization; High-frequency feature extraction module: used to capture short-term and local patterns in time series and convert time series into frequency domain to extract high-frequency components; Low-frequency feature extraction module: used to capture long-term dependencies in time series and extract low-frequency trends and seasonal components of time series; Environmental variable processing module: includes an embedding layer and a fully connected layer. The embedding layer is used to convert categorical environmental variables into vectors of fixed dimensions, and the fully connected layer is used to perform nonlinear transformations on numerical environmental variables. Feature fusion module: used to concatenate and fuse high- and low-frequency feature vectors with environmental variable feature vectors in terms of dimensions; Recurrent neural network module: further processes the fused feature sequence to capture complex temporal relationships.

[0032] Output module: Converts the fused information into the required output results according to the requirements of specific tasks.

[0033] In step S108, when the matching degree between the fault type and the first historical fault type reaches a first matching degree threshold, fault detection is performed on each component of the first target base station according to the first fault parameter, specifically including: According to the matching degree measurement algorithm, the matching degree between the fault type and the first historical fault type is calculated; the measurement method may specifically adopt calculation methods such as cosine similarity, Euclidean distance, Manhattan distance, and Jaccard similarity coefficient; When the matching degree reaches a first matching degree threshold, fault detection is performed on each target component according to the first fault parameter.

[0034] Through the above method, the current fault similar to the first historical fault type can be effectively identified, and the component can be detected according to specific fault parameters, thereby improving the accuracy and efficiency of fault detection.

[0035] In some implementations, calculating the degree of matching between the fault type and the first historical fault type according to a matching degree measurement algorithm specifically includes: Calculate the first state matrix of the fault type; the first state matrix is ​​a matrix representing the current state of the fault type, usually including the states of multiple features or parameters; these features may include the time, frequency, impact range, related sensor readings, etc. of the fault occurrence; Calculate a second state matrix of the first historical fault type; the second state matrix is ​​similar to the first state matrix, and the second state matrix can also represent the state of the first historical fault type; Calculating the matching degree between the first state matrix and the second state matrix may specifically include: Align the two matrices to ensure that the same features are compared; Apply the metric algorithm and get a matching score.

[0036] In some embodiments, the method further comprises: calculating a first fault correlation factor set related to the first target base station according to the historical fault type set, wherein the first fault correlation factor set comprises a plurality of first critical fault correlation factors and a plurality of second critical fault correlation factors; Acquire first weight parameters corresponding to each first critical fault-related factor from the first training set, wherein each first weight parameter corresponds to one first critical fault-related factor; Acquire second weight parameters corresponding to each second critical fault-related factor from the second training set, wherein each second weight parameter corresponds to one second critical fault-related factor; Calculating a first fault criticality parameter corresponding to the first critical fault correlation factor; calculating a second fault criticality parameter corresponding to the second critical fault correlation factor; Calculating the first fusion degree of each first fault criticality parameter and the second fault criticality parameter; the first fusion degree is a comprehensive indicator used to evaluate the comprehensive impact of each fault criticality parameter; The component whose first integration degree reaches the integration degree threshold is determined as the first key component of the first target base station. Through the above method, the most critical component in the base station can be effectively identified, so as to carry out targeted maintenance and monitoring to ensure the stable operation of the base station.

[0037] In some embodiments, the method further includes: when the first fault criticality parameter is equal to 0 and the second fault criticality parameter is equal to 0, performing fault detection on the first target base station. Through this detailed fault detection process, the risk of the base station can be more comprehensively evaluated to further ensure the safety and reliability of the base station.

[0038] Further, determining the component whose first integration degree reaches the integration degree threshold as the first key component of the first target base station specifically includes: Calculating a first fusion degree of each first fault criticality parameter and a second fault criticality parameter; fusing (for example, weighted fusion) the two first fusion degrees to obtain a second fusion degree; The component whose second integration degree reaches the integration degree threshold is determined as the first key component of the first target base station.

[0039] Through this process, components that are critical to the operation of the base station can be identified, and the failure of these components may have a significant impact on the overall performance of the base station. Identifying these critical components helps the operation and maintenance team prioritize and ensure the reliability of these components, thereby improving the stability and service quality of the entire base station system.

[0040] Further, determining the component whose second integration degree reaches the integration degree threshold as the first key component of the first target base station specifically includes: Calculating a first fusion degree of each first fault criticality parameter and a second fault criticality parameter; fusing (for example, weighted fusion) the two first fusion degrees to obtain a second fusion degree; A component with a second integration degree greater than or equal to 0 is determined as a first key component of the first target base station.

[0041] This process ensures that all components that have a significant impact on the operation of the base station are identified as much as possible, so that maintenance and monitoring can be carried out in a targeted manner.

[0042] Compared with the prior art, the communication base station monitoring method and system based on artificial intelligence provided by the present application obtain operation and maintenance data of each component related to the first target base station; identify the corresponding characteristic factor set from the operation and maintenance data, the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set; obtain the fault type of each component related to the first target base station according to the fault characteristic factor set; calculate the target fault degree according to the fault characteristic factor set and the stable characteristic factor set; when the target fault degree reaches the fault degree threshold, obtain the historical fault type set related to the first target base station, the historical fault type set includes a first training set and a second training set; the first training set includes a plurality of first historical fault types, the second The training set includes a plurality of second historical fault types; obtaining first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; obtaining second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; when the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter; when the matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, obtaining a second historical fault type in the same preset space as the first target base station; target base station, there is at least one second target base station in the preset space; the first fault parameter and the second fault parameter are integrated to obtain a third fault parameter; fault detection is performed on each component of the second target base station according to the third fault parameter to obtain fault probability and environmental variables: according to the fault probability and environmental variables, the fault probability time series data and environmental variable time series data of each component of the second target base station in a certain time period are obtained; after pre-processing the fault probability time series data and the environmental variable time series data, a pre-trained prediction model is input to obtain the predicted fault probability of each component of the second target base station in a future set time period; wherein the prediction model is based on the historical data of each component of the second target base station The historical fault probability time series data samples and the historical environmental variable time series data samples are trained on the neural network based on the collaboration of high and low frequency cycles and environmental variables; it can not only improve the efficiency of data processing in the monitoring process, ensure that the operation and maintenance personnel who operate and maintain the communication base station can perform timely maintenance on the communication base station according to the first fault parameter, the second fault parameter, and the third fault parameter to ensure the effective operation of the communication base station, but also can generate accurate fault probability prediction results in combination with the dynamic changes of environmental variables, can effectively respond to the impact of sudden environmental changes and periodic environmental changes, realize accurate prediction of communication base station failures, make the final prediction results more explainable, and help to improve the operation and maintenance level.

[0043] In the above-mentioned embodiment, a communication base station monitoring method based on artificial intelligence is provided. Correspondingly, the present application also provides a communication base station monitoring system based on artificial intelligence. Figure 2 As shown, the communication base station monitoring system based on artificial intelligence provided in the embodiment of the present application can implement the above-mentioned communication base station monitoring method based on artificial intelligence, and the communication base station monitoring system based on artificial intelligence can be implemented by software, hardware, or a combination of software and hardware. For example, the communication base station monitoring system based on artificial intelligence can include integrated or separate functional modules or units to perform the corresponding steps in the above-mentioned methods, including: A first acquisition module 101 is used to acquire operation and maintenance data of various components related to the first target base station; An identification module 102 is used to identify a corresponding characteristic factor set from the operation and maintenance data, where the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set; A fault type acquisition module 103, configured to obtain the fault type of each component related to the first target base station according to the fault characteristic factor set; A calculation module 104, configured to calculate a target fault degree according to a fault characteristic factor set and a stability characteristic factor set; A second acquisition module 105 is used to acquire a historical fault type set related to the first target base station when the target fault degree reaches the fault degree threshold, the historical fault type set including a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; A second acquisition module 106, configured to acquire first fault parameters corresponding to each first historical fault type from the first training set, wherein each first fault parameter corresponds to a first historical fault type; A third acquisition module 107, configured to acquire second fault parameters corresponding to each second historical fault type from the second training set, wherein each second fault parameter corresponds to a second historical fault type; A first fault detection module 108, configured to perform fault detection on each component of the first target base station according to a first fault parameter when the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold; A fourth acquisition module 109 is configured to acquire, when a matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, a second target base station in the same preset space as the first target base station, wherein there is at least one second target base station in the preset space; A fusion module 110, configured to fuse the first fault parameter and the second fault parameter to obtain a third fault parameter; The second fault detection module 111 performs fault detection on each component of the second target base station according to the third fault parameter to obtain a fault probability and an environmental variable: A fifth acquisition module 112, configured to acquire, according to the failure probability and the environmental variable, the failure probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period; The prediction module 113 is used to pre-process the fault probability time series data and the environmental variable time series data, input the pre-trained prediction model, and obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

[0044] The system provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0045] The embodiment of the present application also provides an electronic device corresponding to the method provided in the above embodiment, and the electronic device can be an electronic device used for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the above method.

[0046] Please refer to Figure 3 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 3 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and the processor 200 executes the method provided in any of the aforementioned embodiments of the present application when running the computer program.

[0047] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 203 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0048] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The method disclosed in any implementation of the above-mentioned embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.

[0049] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0050] The electronic device provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by them.

[0051] The present application also provides a computer-readable storage medium corresponding to the method provided in the above-mentioned embodiment, on which a computer program (ie, a program product) is stored. When the computer program is executed by a processor, the method provided in any of the above-mentioned embodiments is executed.

[0052] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0053] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application.

Claims

1. A communication base station monitoring method based on artificial intelligence, characterized in that: The following steps are involved: Acquire operation and maintenance data of various components related to the first target base station; Identify a corresponding feature factor set from the operation and maintenance data, where the feature factor set includes a fault feature factor set and a stable feature factor set; Obtaining the fault type of each component related to the first target base station according to the fault characteristic factor set; Calculate the target fault degree according to the fault characteristic factor set and the stability characteristic factor set; When the target fault degree reaches the fault degree threshold, a historical fault type set related to the first target base station is obtained, where the historical fault type set includes a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; Acquire first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; Acquire second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; When the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter; When the matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, obtaining a second target base station in the same preset space as the first target base station, and there is at least one second target base station in the preset space; Fusing the first fault parameter and the second fault parameter to obtain a third fault parameter; Perform fault detection on each component of the second target base station according to the third fault parameter to obtain the fault probability and environmental variables: According to the failure probability and the environmental variables, obtaining the failure probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period; After preprocessing the fault probability time series data and the environmental variable time series data, the pre-trained prediction model is input to obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

2. The method according to claim 1, characterized in that The corresponding characteristic factor set is identified from the operation and maintenance data, and the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set, specifically including: Perform time domain processing on each operation and maintenance data to obtain a sequence set; A fault characteristic factor set and a stable characteristic factor set are obtained from the sequence set.

3. The method according to claim 1, characterized in that Also includes: Performing fault detection on each component of the second target base station according to the third fault parameter to obtain a fault detection report; The fault detection report is transmitted to the operation and maintenance center for strategy analysis and optimization, and regional linkage operation and maintenance strategy parameters are obtained. Based on the regional linkage operation and maintenance strategy parameters, fault operation and maintenance management and control are performed on the areas of the first target base station and the second target base station.

4. The method according to claim 1, characterized in that The prediction model is pre-trained as follows: Acquire historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station; After preprocessing the historical fault probability time series data samples and the historical environmental variable time series data samples, the historical fault probability time series data samples and the historical environmental variable time series data samples are converted into fault probability supervised data and environmental variable supervised data respectively; The supervised data of failure probability and supervised data of environmental variables are input into the neural network for training, and the prediction model is obtained after reaching the preset training cutoff condition.

5. The method according to claim 1, characterized in that: The neural network based on the coordination of high- and low-frequency cycles and environmental variables includes a sequentially connected data input module, a data preprocessing module, a high-frequency feature extraction module, a low-frequency feature extraction module, an environmental variable processing module, a feature fusion module, a recurrent neural network module and an output module.

6. The method according to claim 1, characterized in that When the matching degree between the fault type and the first historical fault type reaches a first matching degree threshold, performing fault detection on each component of the first target base station according to the first fault parameter specifically includes: Calculate the matching degree between the fault type and the first historical fault type according to the matching degree measurement algorithm; When the matching degree reaches a first matching degree threshold, fault detection is performed on each component of the first target base station according to the first fault parameter.

7. The method according to claim 6, characterized in that The calculating the matching degree between the fault type and the first historical fault type according to the matching degree measurement algorithm specifically includes: Calculate a first state matrix of the fault type; calculating a second state matrix of the first historical fault type; Calculate the matching degree between the first state matrix and the second state matrix.

8. The method according to claim 1, characterized in that Also includes: Calculating a first fault correlation factor set related to the first target base station according to the historical fault type set, wherein the first fault correlation factor set includes a plurality of first critical fault correlation factors and a plurality of second critical fault correlation factors; Acquire first weight parameters corresponding to each first critical fault-related factor from the first training set, wherein each first weight parameter corresponds to one first critical fault-related factor; Acquire second weight parameters corresponding to each second critical fault-related factor from the second training set, wherein each second weight parameter corresponds to one second critical fault-related factor; Calculating a first fault criticality parameter corresponding to the first critical fault correlation factor; calculating a second fault criticality parameter corresponding to the second critical fault correlation factor; Calculating a first fusion degree of each first fault criticality parameter and a second fault criticality parameter; A component whose first integration degree reaches an integration degree threshold is determined as a first key component of the first target base station.

9. The method according to claim 8, characterized in that Also includes: When the first fault criticality parameter is equal to 0 and the second fault criticality parameter is equal to 0, fault detection is performed on the first target base station.

10. The communication base station monitoring system based on artificial intelligence is characterized by: include: A first acquisition module, used to acquire operation and maintenance data of various components related to the first target base station; An identification module is used to identify a corresponding characteristic factor set from the operation and maintenance data, where the characteristic factor set includes a fault characteristic factor set and a stable characteristic factor set; A fault type acquisition module, used to obtain the fault type of each component related to the first target base station according to the fault characteristic factor set; A calculation module, used for calculating a target fault degree according to a fault characteristic factor set and a stability characteristic factor set; A second acquisition module is used to acquire a historical fault type set related to the first target base station when the target fault degree reaches the fault degree threshold, the historical fault type set including a first training set and a second training set; the first training set includes a plurality of first historical fault types, and the second training set includes a plurality of second historical fault types; A second acquisition module is used to acquire first fault parameters corresponding to each first historical fault type from the first training set, each first fault parameter corresponding to a first historical fault type; A third acquisition module is used to acquire second fault parameters corresponding to each second historical fault type from the second training set, each second fault parameter corresponding to a second historical fault type; A first fault detection module, configured to perform fault detection on each component of the first target base station according to a first fault parameter when the matching degree between the fault type and a first historical fault type reaches a first matching degree threshold; a fourth acquisition module, configured to acquire, when a matching degree between the fault type and a second historical fault type reaches a second matching degree threshold, a second target base station in the same preset space as the first target base station, wherein there is at least one second target base station in the preset space; A fusion module, used for fusing the first fault parameter and the second fault parameter to obtain a third fault parameter; The second fault detection module performs fault detection on each component of the second target base station according to the third fault parameter to obtain a fault probability and an environmental variable: A fifth acquisition module, used to acquire the fault probability time series data and the environmental variable time series data of each component of the second target base station within a certain time period according to the fault probability and the environmental variable; A prediction module, used to pre-process the fault probability time series data and the environmental variable time series data, input the pre-trained prediction model, and obtain the predicted fault probability of each component of the second target base station within a future set time period; The prediction model is obtained by training a neural network based on high- and low-frequency cycles and environmental variable collaboration through historical failure probability time series data samples and historical environmental variable time series data samples of each component of the second target base station.

Images