Data detection method and data detection system for 5G base stations in open-pit mines

Abstract

This application relates to the field of data processing technology, specifically to a data detection method and system for 5G base stations in open-pit mines. It aims to solve the problems existing in traditional base station performance evaluation methods. By proposing a performance identification and evaluation method for 5G base stations in open-pit mines based on a data detection system, it provides strong support for communication stability and data transmission efficiency in open-pit mines.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and more specifically, to a data detection method, data detection system, and computer-readable storage medium for 5G base stations in open-pit mines. Background Technology

[0002] With the rapid development and widespread application of 5G technology, open-pit mines, as important industrial production sites, are facing increasingly stringent performance requirements for 5G base stations. To ensure stable communication and efficient data transmission in open-pit mines, performance identification and evaluation of 5G base stations are crucial. However, traditional base station performance evaluation methods often limit themselves to the performance analysis of a single base station, neglecting the mutual influence between base stations and the performance trends over time, resulting in incomplete and inaccurate evaluation results. Summary of the Invention

[0003] To address the technical problems existing in related technologies, this application provides a data detection method, a data detection system, and a computer-readable storage medium for 5G base stations in open-pit mines.

[0004] In a first aspect, embodiments of this application provide a data detection method for 5G base stations in open-pit mines, applied to a data detection system, the method comprising:

[0005] Obtain the performance dataset of 5G base stations in open-pit mines to be identified; the performance dataset of 5G base stations in open-pit mines contains X 5G base station operation performance data, where X is a positive integer;

[0006] Performance element mining is performed on each of the X 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data.

[0007] A 5G base station operation performance vector chain is generated based on the base station operation performance element vector of each 5G base station operation performance data, and the 5G base station operation performance vector chain is passed into the performance inference element mining algorithm; the 5G base station operation performance vector chain contains X base station operation performance element vectors concatenated from the X 5G base station operation performance data, the X base station operation performance element vectors correspond to X processing cycles of the performance inference element mining algorithm, and the u-th base station operation performance element vector in the X base station operation performance element vectors corresponds to the u-th processing cycle in the X processing cycles, where u is a positive integer and u is not greater than X;

[0008] Using the performance extrapolation element mining algorithm in the u-th processing cycle, the performance heat vector of the u-th processing cycle is integrated based on the performance heat vector of the u-1-th processing cycle, the u-1-th base station operation performance element vector in the 5G base station operation performance vector chain, and the u-th base station operation performance element vector in the 5G base station operation performance vector chain; the performance heat vector of the u-1-th processing cycle is obtained by integrating the performance extrapolation element mining algorithm in the u-1-th processing cycle.

[0009] When u = X, the performance heat vector of the integrated Xth processing cycle is determined as the global operating performance vector of the open-pit mine 5G base station performance dataset, and the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is determined based on the global operating performance vector.

[0010] In conjunction with the first aspect, in one possible implementation of the first aspect, the step of performing performance element mining on each of the X 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data includes:

[0011] The operational performance data of the X 5G base stations are input into the base station operational performance data mining model;

[0012] The base station operation performance data mining model is used to mine performance elements of each of the input 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data.

[0013] In conjunction with the first aspect, in one possible implementation of the first aspect, the step of using the base station operation performance data mining model to perform performance element mining on each of the input 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data includes:

[0014] The base station operation performance data mining model is used to mine performance elements of each of the input 5G base station operation performance data to obtain the basic performance element linear variables of each 5G base station operation performance data.

[0015] Based on the linear variables of the basic performance elements of the X 5G base station operation performance data, knowledge vector reinforcement is performed on the linear variables of the basic performance elements of any 5G base station operation performance data to obtain the base station operation performance element vector of any 5G base station operation performance data.

[0016] In conjunction with the first aspect, in one possible implementation of the first aspect, the step of using the performance extrapolation element mining algorithm in the u-th processing cycle to integrate the performance heat vector of the u-th processing cycle based on the performance heat vector of the (u-1)-th processing cycle, the (u-1)-th base station operation performance element vector in the 5G base station operation performance vector chain, and the u-th base station operation performance element vector in the 5G base station operation performance vector chain, includes:

[0017] Obtain the preceding and following sequence correlation vector for the (u-1)th processing cycle; the preceding and following sequence correlation vector is generated by the performance inference element mining algorithm in the (u-1)th processing cycle based on the (u-1)th base station operation performance element vector, and the preceding and following sequence correlation vector includes the element vector cached by the performance inference element mining algorithm for the (u-1)th base station operation performance element vector.

[0018] Based on the preceding and following sequence correlation vector, the performance heat vector of the (u-1)th processing cycle, and the operating performance element vector of the uth base station, the performance heat vector of the uth processing cycle is integrated to obtain the performance heat vector of the uth processing cycle.

[0019] In conjunction with the first aspect, in one possible implementation of the first aspect, determining the performance quality detection viewpoint to which the 5G base station operation performance data in the open-pit mine 5G base station performance dataset belongs based on the global operation performance vector includes:

[0020] The global operating performance vector is input into the quality inspection viewpoint discrimination model, and the quality inspection viewpoint discrimination model is used to determine the possibility that the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is the target performance quality detection viewpoint based on the global operating performance vector.

[0021] If the discriminant probability is not less than the probability threshold, then the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is determined to be the target performance quality detection viewpoint.

[0022] If the discriminant probability is less than the probability threshold, then it is determined that the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is not the target performance quality detection viewpoint.

[0023] In conjunction with the first aspect, in one possible implementation of the first aspect, the X 5G base station operation performance data are 5G base station operation performance data collected within the coverage area of ​​the target open-pit mine base station; the target performance quality detection viewpoint is a performance quality detection viewpoint associated with the target interference source range;

[0024] The method further includes:

[0025] If the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is the target performance quality detection viewpoint, then the interference source range of the target open-pit mine base station coverage area is determined to be the target interference source range.

[0026] If the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is not the target performance quality detection viewpoint, then the interference source range of the target open-pit mine base station coverage area is determined to be not the target interference source range.

[0027] In conjunction with the first aspect, in one possible implementation of the first aspect, the method further includes:

[0028] Obtain the base station operation performance quality inspection algorithm to be debugged; the base station operation performance quality inspection algorithm includes the base station operation performance data mining model to be debugged, the performance inference element mining algorithm to be debugged, and the quality inspection opinion discrimination model to be debugged.

[0029] Obtain a sample of 5G base station performance data set in an open-pit mine; the sample of 5G base station performance data set in an open-pit mine contains multiple 5G base station operation performance data samples; the sample of 5G base station performance data set in an open-pit mine has prior learning annotations, the prior learning annotations of the sample of 5G base station performance data set in an open-pit mine are used to indicate whether the performance quality detection viewpoint to which the sample of 5G base station performance data set in an open-pit mine belongs is the target performance quality detection viewpoint or not the target performance quality detection viewpoint;

[0030] Using the base station operation performance data mining model to be debugged, performance element mining is performed on each 5G base station operation performance data sample in the open-pit mine 5G base station performance dataset sample to obtain a base station operation performance element vector sample for each 5G base station operation performance data sample.

[0031] Based on the base station operation performance element vector sample of each 5G base station operation performance data sample, a 5G base station operation performance vector chain sample is generated. Then, using the performance inference element mining algorithm to be debugged, a global operation performance vector sample of the open-pit mine 5G base station performance dataset sample is obtained by integrating the 5G base station operation performance vector chain sample. The integration is used to extract the interrelation features between each base station operation performance element vector sample in the 5G base station operation performance vector chain sample.

[0032] Using the quality inspection viewpoint discrimination model to be debugged, based on the global operating performance vector sample, it is determined whether the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset sample belongs is a discrimination probability sample of the target performance quality detection viewpoint;

[0033] The algorithm parameters of the base station operation performance quality inspection algorithm are improved based on the discriminative probability examples and the prior learning annotations to obtain a debugged base station operation performance quality inspection algorithm. The debugged base station operation performance quality inspection algorithm includes a base station operation performance data mining model, the performance inference element mining algorithm, and a quality inspection opinion discrimination model.

[0034] In conjunction with the first aspect, in one possible implementation of the first aspect, the step of improving the algorithm parameters of the base station operation performance quality inspection algorithm based on the discriminative probability examples and the prior learning annotations to obtain the debugged base station operation performance quality inspection algorithm includes:

[0035] Based on the discriminative probability examples and the prior learning annotations, the quality inspection discriminative loss of the base station operation performance quality inspection algorithm for the open-pit mine 5G base station performance dataset examples is generated;

[0036] Based on the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for the open-pit mine 5G base station performance dataset sample, the algorithm parameters of the base station operation performance quality inspection algorithm are improved to obtain the base station operation performance quality inspection algorithm that has been debugged.

[0037] In conjunction with the first aspect, in one possible implementation of the first aspect, there are multiple open-pit mine 5G base station performance dataset samples. These multiple open-pit mine 5G base station performance dataset samples include positive 5G base station performance dataset samples and negative 5G base station performance dataset samples. The prior learning annotation of the positive 5G base station performance dataset samples is used to indicate that the performance quality detection viewpoint of the 5G base station operation performance data samples in the positive 5G base station performance dataset samples is the target performance quality detection viewpoint. The prior learning annotation of the negative 5G base station performance dataset samples is used to indicate that the performance quality detection viewpoint of the 5G base station operation performance data samples in the negative 5G base station performance dataset samples is not the target performance quality detection viewpoint.

[0038] The step of generating the quality inspection discriminant loss of the base station operation performance quality inspection algorithm for the 5G base station operation performance data samples in the open-pit mine 5G base station performance dataset, based on the discriminant probability samples and the prior learning annotations, includes:

[0039] Obtain the first discriminant confidence score for positive examples in the 5G base station performance dataset and the second discriminant confidence score for negative examples in the 5G base station performance dataset;

[0040] Based on the first discrimination confidence, the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for the positive samples of the 5G base station performance dataset is updated to obtain the first updated quality inspection discrimination loss;

[0041] Based on the second discrimination confidence, the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for negative samples of the 5G base station performance dataset is updated to obtain the second updated quality inspection discrimination loss;

[0042] The sum of the first updated quality inspection discrimination loss and the second updated quality inspection discrimination loss is determined as the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for the multiple open-pit mine 5G base station performance dataset samples.

[0043] In conjunction with the first aspect, in one possible implementation of the first aspect, there are multiple positive examples in the 5G base station performance dataset, and the first discrimination confidence is a mapping variable of the number of positive examples in the multiple 5G base station performance datasets; there are multiple negative examples in the 5G base station performance dataset, and the second discrimination confidence is a mapping variable of the number of negative examples in the multiple 5G base station performance datasets; wherein, the number of 5G base station operation performance data examples included in each of the multiple open-pit mine 5G base station performance dataset examples is the same or different.

[0044] In conjunction with the first aspect, in one possible implementation of the first aspect, the base station operation performance data mining model to be debugged in the base station operation performance quality inspection algorithm is a network that has completed debugging, and the algorithm parameters of the base station operation performance data mining model to be debugged are locked during the debugging process of the base station operation performance quality inspection algorithm; wherein, the algorithm parameters that the base station operation performance quality inspection algorithm needs to improve include the algorithm parameters of the performance inference element mining algorithm to be debugged and the algorithm parameters of the quality inspection opinion discrimination model to be debugged.

[0045] Secondly, this application also provides a data detection system, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the data detection methods for 5G base stations in open-pit mines.

[0046] Thirdly, this application also provides a computer-readable storage medium, comprising a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute any of the aforementioned data detection methods for 5G base stations in open-pit mines.

[0047] This application proposes a method for performance identification and evaluation of 5G base stations in open-pit mines based on a data detection system. The method first acquires a dataset of 5G base station performance data from multiple open-pit mines, ensuring the comprehensiveness of the evaluation. Then, by mining performance elements from each 5G base station's performance data, a base station performance element vector is obtained, thereby accurately identifying the key factors affecting base station performance.

[0048] Furthermore, this application generates a 5G base station operation performance vector chain based on the base station operation performance element vector of each 5G base station operation performance data, and feeds this chain into a performance extrapolation element mining algorithm. This method not only considers the performance of a single base station, but also the mutual influence between base stations and the performance change trend over time, making the performance evaluation more coherent and dynamic.

[0049] In the performance extrapolation element mining algorithm, this application integrates the performance heatmap of the current processing cycle with the performance heatmap of the previous processing cycle, the performance element vector of the previous base station in the current processing cycle, and the performance element vector of the current base station. This method can efficiently process large amounts of performance data and output a performance heatmap at the end of each processing cycle, making real-time performance evaluation possible.

[0050] Finally, after processing all base station data, this application determines the performance heatmap vector of the last integrated processing cycle as the global operational performance vector, and uses this as the basis for determining the performance quality assessment perspective. This global assessment provides managers with a comprehensive performance overview and targeted optimization suggestions, which helps guide the planning and maintenance of the communication network in the mining area.

[0051] In summary, this application aims to address the problems existing in traditional base station performance evaluation methods by proposing a performance identification and evaluation method for 5G base stations in open-pit mines based on a data detection system, thereby providing strong support for communication stability and data transmission efficiency in open-pit mines. Attached Figure Description

[0052] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0053] Figure 1 A hardware structure block diagram of a mobile terminal for performing a data detection method for an open-pit mine 5G base station is shown in an embodiment of this application.

[0054] Figure 2 A schematic flowchart of a data detection method for a 5G base station in an open-pit mine, according to an embodiment of this application, is shown.

[0055] The above figures include the following reference numerals:

[0056] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0057] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0058] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0059] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0060] As described in the background section, traditional base station performance evaluation methods in the prior art are often limited to the performance analysis of a single base station, ignoring the mutual influence between base stations and the performance change trend over time, resulting in incomplete and inaccurate evaluation results. To solve the above problems, embodiments of this application provide a data detection method, data detection system and computer-readable storage medium for 5G base stations in open-pit mines.

[0061] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0062] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a data detection method for a 5G base station in an open-pit mine, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0063] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0064] This embodiment provides a data detection method for a 5G base station in an open-pit mine, which runs on a mobile terminal, computer terminal or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0065] Based on this, please refer to Figure 2 , Figure 2This is a flowchart illustrating a data detection method for a 5G base station in an open-pit mine, provided in an embodiment of this application. The method is applied to a data detection system and may further include steps 210-250.

[0066] Step 210: Obtain the performance dataset of the open-pit mine 5G base stations to be identified; the above-mentioned open-pit mine 5G base station performance dataset contains X 5G base station operation performance data, where X is a positive integer.

[0067] Step 220: Perform performance element mining on each of the above X 5G base station operation performance data to obtain the base station operation performance element vector for each of the above 5G base station operation performance data.

[0068] Step 230: Generate a 5G base station operation performance vector chain based on the base station operation performance element vector of each 5G base station operation performance data, and input the 5G base station operation performance vector chain into the performance inference element mining algorithm.

[0069] The aforementioned 5G base station operation performance vector chain includes X base station operation performance element vectors cascaded from the aforementioned X 5G base station operation performance data. The aforementioned X base station operation performance element vectors correspond to X processing cycles of the aforementioned performance inference element mining algorithm. The u-th base station operation performance element vector among the aforementioned X base station operation performance element vectors corresponds to the u-th processing cycle among the aforementioned X processing cycles, where u is a positive integer and u is not greater than X.

[0070] Step 240: Using the above-mentioned performance extrapolation element mining algorithm, in the u-1 processing cycle, based on the performance heat vector of the u-1 processing cycle, the u-1 base station operation performance element vector in the above-mentioned 5G base station operation performance vector chain, and the u base station operation performance element vector in the above-mentioned 5G base station operation performance vector chain, the performance heat vector of the u-1 processing cycle is integrated.

[0071] The performance heat vector for the u-1th processing cycle is obtained by integrating the performance deduction element mining algorithm in the u-1th processing cycle.

[0072] Step 250: When u = X, the performance heat vector of the integrated Xth processing cycle is determined as the global operating performance vector of the above-mentioned open-pit mine 5G base station performance dataset, and the performance quality detection viewpoint to which the above-mentioned open-pit mine 5G base station performance dataset belongs is determined based on the above-mentioned global operating performance vector.

[0073] One application scenario of this application involves a large open-pit mine. To ensure smooth communication and safe production within the mine, the mine managers deployed several 5G base stations. To monitor and optimize the performance of these base stations, they used a data monitoring system. The following is the system's workflow.

[0074] First, the data detection system obtained a performance dataset of open-pit mine 5G base stations from the mine's 5G network, containing operational performance data for five 5G base stations (i.e., X=5). This dataset records various operational metrics of the base stations, such as signal strength, data transmission rate, and number of failures.

[0075] Next, the data detection system performs performance element mining on each of the five 5G base station operational performance data. For example, it may use machine learning and data analysis techniques to extract key performance parameters for each base station and represent them as a base station operational performance element vector.

[0076] Then, the data detection system combines these base station operation performance element vectors into a 5G base station operation performance vector chain. This vector chain contains five cascaded base station operation performance element vectors, each corresponding to one processing cycle of the performance extrapolation element mining algorithm. The data detection system then inputs this 5G base station operation performance vector chain into the performance extrapolation element mining algorithm.

[0077] In the first processing cycle of the algorithm (i.e., u=1), since there is no performance heatmap from the previous cycle, the data detection system may use a preset initial value or generate an initial performance heatmap based on the first base station operation performance element vector. Starting from the second processing cycle (i.e., u>1), the data detection system integrates the performance heatmap from the previous cycle, the previous base station operation performance element vector, and the current base station operation performance element vector to form the current cycle's performance heatmap. This process is iteratively performed using the performance extrapolation element mining algorithm until all base station operation performance element vectors have been processed.

[0078] When u = X (i.e., u = 5), the data detection system has completed processing of all base station operational performance data and integrated the performance heat vector of the 5th processing cycle. This integrated performance heat vector is determined as the global operational performance vector of the open-pit mine 5G base station performance dataset, comprehensively reflecting the operational performance of 5G base stations throughout the entire mining area. Finally, based on this global operational performance vector, the data detection system determines the performance quality detection perspective of the open-pit mine 5G base station performance dataset. For example, it can determine whether the current base station performance meets the standards, whether there are potential fault risks, and whether optimization adjustments are needed. This information is highly valuable to mine managers, helping them better manage and maintain 5G base stations, ensuring smooth communication and safe production in the mining area.

[0079] Another application scenario of this application involves the performance monitoring and optimization of 5G base stations in open-pit mines. The stable operation of 5G base stations is crucial for communication and safe production in the mine. In order to monitor and optimize the performance of these base stations in real time, mine managers have introduced an advanced data detection system.

[0080] The data monitoring system first connects to the 5G network in the mining area and automatically acquires a dataset of open-pit mine 5G base station performance data, containing operational performance data from five 5G base stations (X=5). This dataset details key operational indicators for each base station at different time periods, including signal strength, data transmission rate, number of failures, and equipment temperature.

[0081] Next, the data detection system utilizes advanced data mining techniques to conduct in-depth analysis of the operational performance data of each 5G base station. Through machine learning algorithms and statistical models, the system extracts key performance elements for each base station, such as signal coverage, data transmission stability, and equipment failure rate, and represents these elements as a multi-dimensional base station operational performance element vector.

[0082] The data detection system concatenates these base station operational performance element vectors in chronological order to generate a 5G base station operational performance vector chain. This vector chain not only contains the performance element information of each base station but also preserves their temporal correlation and mutual influence. Subsequently, this vector chain is input into the performance extrapolation element mining algorithm, providing basic data for subsequent performance analysis and extrapolation.

[0083] In the processing of the performance projection element mining algorithm, the data detection system iteratively integrates performance heatmap vectors. In each processing cycle (u from 1 to 5), the system performs a comprehensive analysis based on the performance heatmap vector of the previous cycle (for the first cycle, a preset initial value can be used, or it can be generated based on the first base station's operational performance element vector), the previous base station's operational performance element vector, and the current base station's operational performance element vector. Through complex mathematical calculations and model reasoning, the system generates the performance heatmap vector for the current cycle. This vector graphically displays the heatmap distribution of base station performance across different dimensions, helping managers intuitively understand the changing trends and potential problems of base station performance.

[0084] Once all base station performance data has been processed (i.e., u=5), the data detection system integrates the performance heatmap vector from the last processing cycle and determines it as the global performance vector of the open-pit mine 5G base station performance dataset. This global vector comprehensively reflects the performance of the entire mining area's 5G base stations across different time periods and dimensions.

[0085] Finally, the data monitoring system determines the performance quality monitoring perspectives associated with the open-pit mine 5G base station performance dataset based on the global operational performance vector. These perspectives may include base station performance compliance status, potential fault risk points, and performance optimization suggestions. Through this information, mine managers can gain a more comprehensive understanding of the 5G base station's operational status, promptly identify and resolve problems, and ensure smooth communication and safe production in the mine. Simultaneously, this data can also provide valuable reference for future base station planning and optimization.

[0086] The following is a glossary of the technical terms used in steps 210-250 above.

[0087] Performance Dataset of 5G Base Stations in Open-Pit Mines to be Identified: This is a specific dataset containing various performance data of 5G base stations in open-pit mines. This data may be collected from the daily operation of the base stations for further analysis and identification. The dataset may contain data from multiple base stations and may cover data changes over a period of time. For example, if an open-pit mine has 10 5G base stations, to evaluate their performance, operational data from these 10 base stations over the past week was collected, including signal strength, data transmission rate, equipment temperature, and number of failures. This data, combined, forms a "Performance Dataset of 5G Base Stations in Open-Pit Mines to be Identified."

[0088] 5G base station operational performance data: This refers to the various performance metrics generated by a single 5G base station during operation. This data reflects the base station's working status, efficiency, and potential problems. For example, a specific 5G base station might generate the following operational performance data: average signal strength -80dBm, data transmission rate 1Gbps, equipment temperature 45℃, and two failures occurring in the past 24 hours. This data can be recorded and analyzed to evaluate the base station's performance.

[0089] Performance factor mining: This is a data analysis process designed to extract key performance factors from raw 5G base station operational performance data. These factors are typically core indicators affecting base station performance and can be used for further performance evaluation, problem diagnosis, or optimization decisions. For example, during performance factor mining, it might be discovered that a base station experiences significant signal strength fluctuations, a key factor impacting user communication experience. In-depth analysis reveals that this fluctuation is caused by improper antenna orientation settings. This process constitutes performance factor mining and analysis.

[0090] Base Station Operation Performance Element Vector: This is a vector composed of multiple performance elements used to comprehensively describe the operational performance of a 5G base station. Each element represents an aspect of the base station's performance, and the vector integrates these elements to form a multi-dimensional performance description. For example, three key performance elements might be extracted from the operational data of a 5G base station: signal strength, data transmission rate, and device temperature. These three elements can form a three-dimensional vector, for example (signal strength: -75dBm, data transmission rate: 1.2Gbps, device temperature: 40℃). This vector is the "operation performance element vector" of that base station, which can be used for comparison with other base stations or for performance evaluation.

[0091] 5G Base Station Operation Performance Vector Chain: A 5G base station operation performance vector chain is a chain formed by connecting the operation performance element vectors of multiple 5G base stations according to time sequence or other logical relationships. Each base station's performance element vector is a node in the chain, and the entire chain reflects the comprehensive performance changes of multiple base stations over a period of time or in a specific scenario. For example, if there are three 5G base stations A, B, and C, and their operation performance data is collected hourly for three consecutive hours, forming performance element vectors, then the data from these three hours can constitute a 5G base station operation performance vector chain, in the form of: A1->B1->C1->A2->B2->C2->A3->B3->C3, where A1, B1, and C1 represent the performance element vectors of base stations A, B, and C in the first hour, and so on.

[0092] Performance extrapolation factor mining algorithm: This algorithm is used to analyze and predict changes in 5G base station performance. It extracts key factors affecting base station performance by mining and learning from historical performance data, and then builds a model to predict future performance trends. This algorithm typically includes steps such as data preprocessing, feature extraction, model training, and prediction. For example, one performance extrapolation factor mining algorithm first cleans and formats the collected 5G base station operating performance data, then extracts key performance indicators as features, such as signal strength and data transmission rate. Next, the algorithm uses these features to train a predictive model that can predict the performance trend of the base station over a future period based on current and historical performance data. In this way, managers can identify potential performance problems in advance and take corresponding optimization measures.

[0093] Processing Cycle: The processing cycle is a concept in performance extrapolation factor mining algorithms, referring to the time unit or number of iterations used by the algorithm when processing 5G base station operational performance data. Within each processing cycle, the algorithm analyzes and calculates the input data and outputs corresponding results or status updates. For example, in the above example, if 5G base station operational performance data is collected and processed on an hourly basis, then each hour can be considered a processing cycle. Within each processing cycle, the performance extrapolation factor mining algorithm analyzes and mines the data collected within that hour, extracting key performance factors and predicting future performance trends. In this way, the performance status of the base station can be monitored and evaluated in real time.

[0094] Performance Heatmap: A performance heatmap is a result representation output by a performance projection factor mining algorithm. It typically displays the distribution of base station performance across different dimensions in a graphical way. This vector contains information about base station performance in various aspects, helping managers intuitively understand performance trends and potential problems. Each element of the performance heatmap represents the popularity or importance of a performance indicator. For example, the performance projection factor mining algorithm outputs a two-dimensional performance heatmap, where the horizontal axis represents signal strength and the vertical axis represents data transmission rate. Each point in the vector corresponds to a specific combination of signal strength and data transmission rate, and the color or numerical value indicates the popularity or importance of this combination in performance evaluation. Through this heatmap, it is clear which areas have good signal strength and data transmission rate performance, and which areas have performance bottlenecks or need optimization.

[0095] Global Operational Performance Vector (GOVPS): A GVPS is a vector describing the overall performance of all base stations in a 5G base station network or a specific area. It integrates the operational performance element vectors of each base station, forming a multi-dimensional set of indicators that comprehensively reflects the overall network performance status. The GVPS can be used to evaluate the overall network performance, identify potential problems, and formulate optimization strategies. For example, a mining area might have 10 main 5G base stations. To evaluate the overall performance of these base stations, operational performance data for each of the 10 base stations over a period of time is collected, and individual performance element vectors are formed. These performance element vectors are then integrated and summarized to form a global operational performance vector. This vector contains comprehensive information on all base stations in terms of signal coverage, data transmission rate, equipment failure rate, and other aspects, and can be used to evaluate the performance status of the entire 5G network in the mining area.

[0096] Performance quality assessment perspectives: These perspectives are evaluations or judgments of 5G base station performance quality based on the analysis and mining of operational performance data. These perspectives may include whether the base station meets performance standards, potential fault risks, and performance optimization suggestions, aiming to help managers better understand and improve the base station's performance status. For example, through in-depth analysis and mining of the operational performance data of a specific 5G base station, the following performance quality assessment perspectives were formed: First, the base station's signal coverage is generally up to standard, but weak coverage exists in some areas; second, the overall data transmission rate is good, but some congestion occurs during peak hours; finally, the equipment failure rate is slightly high, requiring strengthened maintenance and repair work. These perspectives provide managers with targeted optimization suggestions and improvement directions.

[0097] The data detection system and method proposed in this application have shown significant beneficial effects in the performance identification and evaluation of 5G base stations in open-pit mines:

[0098] Comprehensiveness: By acquiring a dataset of 5G base station performance data from multiple open-pit mines, this application ensures the comprehensiveness of the assessment, covering all key communication nodes within the mining area. This comprehensive assessment helps managers to more accurately grasp the communication status of the entire mining area.

[0099] Accuracy: By mining performance elements from the operational performance data of each 5G base station, this application can accurately identify the key factors affecting base station performance, thereby forming a base station operational performance element vector. This precise performance element mining helps to understand the root causes of base station performance problems more deeply;

[0100] Continuity and dynamism: By generating a 5G base station operational performance vector chain and feeding this chain into a performance extrapolation element mining algorithm, this application considers not only the performance of individual base stations but also the mutual influence between base stations and the changes in performance over time. This continuous and dynamic analysis method makes performance evaluation more closely aligned with actual operating conditions.

[0101] High efficiency: By utilizing a performance extrapolation element mining algorithm to integrate performance heatmaps within a processing cycle, this application can efficiently process large amounts of performance data and output a performance heatmap at the end of each processing cycle. This efficient processing method enables real-time performance evaluation, providing timely feedback to managers;

[0102] Global and Guiding: After processing data from all base stations, this application determines the performance heatmap vector of the last integrated processing cycle as the global operational performance vector, and uses this as the basis for performance quality assessment. This global assessment provides managers with a comprehensive performance overview and targeted optimization suggestions, which helps guide the planning and maintenance of the communication network in the mining area.

[0103] In summary, this application provides a novel and effective solution for the performance identification and evaluation of 5G base stations in open-pit mines through its comprehensive, accurate, coherent, dynamic, efficient, and holistic evaluation method.

[0104] In some preferred embodiments, step 220, which describes the above-mentioned performance element mining of each of the X 5G base station operation performance data to obtain a base station operation performance element vector for each of the 5G base station operation performance data, includes: inputting the X 5G base station operation performance data into a base station operation performance data mining model; and using the base station operation performance data mining model to perform performance element mining on each of the input 5G base station operation performance data to obtain a base station operation performance element vector for each of the 5G base station operation performance data.

[0105] In some preferred embodiments, the process described in step 220 of mining performance elements for each of the X 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data can be implemented in the following ways.

[0106] First, the data detection system inputs the acquired 5G base station operation performance data from X base stations into a pre-built base station operation performance data mining model. This model is built based on machine learning or deep learning techniques, and after learning from a large amount of training data, it has the ability to extract key performance elements from the raw operation performance data.

[0107] Next, using this base station operation performance data mining model, the data detection system processes the incoming 5G base station operation performance data. During the processing, the model analyzes and mines various performance indicators in each dataset, such as signal strength, data transmission rate, latency, and packet loss rate. These performance indicators are important parameters reflecting the base station's operation performance.

[0108] Through model processing, the operational performance data of each 5G base station is transformed into a base station operational performance element vector. This vector contains key performance elements extracted from the original data, representing the base station's operational performance status in a more abstract and concise form. For example, a base station's operational performance element vector might include values ​​for key performance indicators such as the base station's average signal strength, maximum data transmission rate, average latency, and packet loss rate.

[0109] Thus, through the processing in step 220, the data detection system obtains the base station operation performance element vectors for each 5G base station's operation performance data. These vectors not only contain the key information from the original data but are also represented in a form more suitable for subsequent processing and analysis, facilitating subsequent performance evaluation and optimization.

[0110] It's important to note that the base station operation performance data mining model here is a crucial technical component. Its construction requires extensive training data and advanced machine learning or deep learning algorithms. During model training, the model's parameters and structure need continuous adjustment to better extract key performance elements from the raw data. Furthermore, as technology advances and data accumulates, this model also requires ongoing updates and optimization to adapt to new application scenarios and demands.

[0111] In the following steps, the aforementioned base station operation performance data mining model is used to mine performance elements for each of the input 5G base station operation performance data to obtain a base station operation performance element vector for each of the 5G base station operation performance data. This includes: using the aforementioned base station operation performance data mining model to mine performance elements for each of the input 5G base station operation performance data to obtain basic performance element linear variables for each of the 5G base station operation performance data; and performing knowledge vector reinforcement on the basic performance element linear variables of any 5G base station operation performance data based on the basic performance element linear variables of the X 5G base station operation performance data to obtain a base station operation performance element vector for any of the 5G base station operation performance data.

[0112] In the next step, the system utilizes a base station operation performance data mining model to perform in-depth performance element mining on the input 5G base station operation performance data. This process includes two main parts: First, the system uses the model to process the operation performance data of each 5G base station and extracts basic performance element linear variables; second, based on the basic performance element linear variables of all 5G base stations, the system performs knowledge vector reinforcement on these variables of any given base station to generate the operation performance element vector of that base station.

[0113] Specifically, once the system receives a dataset containing operational performance data from X 5G base stations, it inputs this data one by one into a base station operational performance data mining model. This model, through complex algorithms and calculations, extracts key performance indicators from the raw operational performance data. These indicators are represented as linear variables of basic performance elements. These linear variables may include base station signal strength, data transmission rate, network latency, packet loss rate, etc., which together constitute the basic data framework reflecting base station operational performance.

[0114] After extracting the linear variables of the basic performance elements of each 5G base station, the system is not satisfied with these independent data points. To more comprehensively evaluate the operational performance of the base stations and take into account the potential mutual influence and correlation between different base stations, the system performs a knowledge vector enhancement step. The purpose of this step is to place the data of a single base station into a broader network environment for consideration, and to enhance and enrich the understanding of the performance of any specific base station by comparing and analyzing the data of all X base stations.

[0115] The knowledge vector enhancement process can be viewed as a data fusion and enhancement technique. The system compares the linear variables of the basic performance elements of any 5G base station with the data of all other base stations, looking for commonalities, differences, and potential connections among them. Then, based on these comparison results, the system adjusts and optimizes the linear variables of the basic performance elements of that base station, generating a more comprehensive and accurate base station operation performance element vector. This vector not only includes the base station's own performance indicators but also reflects its performance and status within the entire 5G network.

[0116] Through this processing flow, the system can achieve in-depth analysis and comprehensive evaluation of the operational performance of each 5G base station. This not only provides managers with more detailed and accurate performance data support, but also provides a strong data foundation for subsequent performance optimization and network upgrades. Furthermore, this evaluation method based on data mining and knowledge reinforcement has excellent scalability and adaptability, allowing for continuous optimization and improvement as 5G networks evolve and change.

[0117] Under some optional design approaches, step 240, which describes the above-mentioned use of the performance extrapolation element mining algorithm in the u-th processing cycle, integrates the performance heat vector of the u-th processing cycle based on the performance heat vector of the u-1th processing cycle, the u-1th base station operation performance element vector in the 5G base station operation performance vector chain, and the u-th base station operation performance element vector in the 5G base station operation performance vector chain. This includes: obtaining the pre- and post-order correlation vectors of the u-1th processing cycle; the pre- and post-order correlation vectors are generated by the performance extrapolation element mining algorithm in the u-1th processing cycle based on the u-1th base station operation performance element vector, and the pre- and post-order correlation vectors include the element vectors cached by the performance extrapolation element mining algorithm for the u-1th base station operation performance element vector; and integrating the performance heat vector of the u-th processing cycle based on the pre- and post-order correlation vectors, the performance heat vector of the u-1th processing cycle, and the u-th base station operation performance element vector.

[0118] Under some optional design approaches, the operational process of the performance extrapolation element mining algorithm described in step 240 can be further refined. This process involves several key steps and components, including the use of pre- and post-order correlation vectors, performance heatmap vectors, and base station operational performance element vectors.

[0119] First, the system obtains the preceding and following sequence correlation vectors for the (u-1)th processing cycle. This correlation vector is generated in the previous processing cycle by the performance prediction element mining algorithm based on the (u-1)th base station operational performance element vector. It contains the algorithm's processing results on the previous base station operational performance element vector and the cached element vectors. These cached element vectors can be seen as a "memory" of performance elements from the previous processing cycle, and they have significant reference value for performance prediction in the current processing cycle.

[0120] Specifically, the preceding and following sequence correlation vectors may contain the changing trends and interrelationships of key performance indicators of the base station in the previous cycle, such as signal strength, data transmission rate, and latency. This information reflects the continuity and changing patterns of base station performance over time, and is of significant guiding importance for predicting the performance status in the current cycle.

[0121] Next, the system will use this sequential correlation vector, the performance heat vector of the (u-1)th processing cycle, and the base station operation performance element vector of the uth processing cycle to integrate and obtain the performance heat vector of the uth processing cycle. This process can be viewed as an information fusion and deduction process.

[0122] In this process, the system first fuses the preceding and following correlation vectors with the performance heatmap vector of the (u-1)th processing cycle. This fusion process may involve some complex mathematical operations and data processing techniques, such as weighted averaging, convolution operations, and neural network models. Through these operations and processing, the system can effectively combine the performance information of the previous cycle with the performance elements of the current cycle to form a more comprehensive and accurate performance description.

[0123] The system then further integrates this fused result with the performance element vector of the u-th base station. This integration process may involve performance extrapolation algorithms and models, such as time series analysis, regression analysis, and machine learning models. Through the processing of these algorithms and models, the system can extrapolate and predict the performance status of the current period based on the performance elements of the current period and the performance information of the previous period.

[0124] Finally, after this series of processing and deductions, the system obtains the performance heatmap for the u-th processing cycle. This performance heatmap is a vector representation containing rich performance information, reflecting the overall performance status of the base station and the correlation between various performance indicators in the current cycle. Through this performance heatmap, managers can gain a more intuitive and comprehensive understanding of the base station's performance in the current cycle, providing strong data support for subsequent performance optimization and network upgrades.

[0125] Under some alternative design approaches, step 250, which describes determining the performance quality detection viewpoint of the 5G base station operation performance data in the open-pit mine 5G base station performance dataset based on the global operation performance vector, includes: inputting the global operation performance vector into the quality detection viewpoint discrimination model, and using the quality detection viewpoint discrimination model based on the global operation performance vector to determine the discrimination probability that the performance quality detection viewpoint of the open-pit mine 5G base station performance dataset is the target performance quality detection viewpoint; if the discrimination probability is not less than the probability threshold, then the performance quality detection viewpoint of the open-pit mine 5G base station performance dataset is determined to be the target performance quality detection viewpoint; if the discrimination probability is less than the probability threshold, then the performance quality detection viewpoint of the open-pit mine 5G base station performance dataset is determined not to be the target performance quality detection viewpoint.

[0126] Under some alternative design approaches, the process described in step 250 involves the use of a global operational performance vector and the application of a quality inspection perspective discrimination model. This process is a key step in determining the performance quality inspection perspective to which the 5G base station operational performance data in the open-pit mine 5G base station performance dataset belongs.

[0127] First, the system acquires a global operational performance vector, which is obtained through comprehensive analysis and processing of the operational performance data of all 5G base stations within the open-pit mine area. This global operational performance vector contains key indicators and information reflecting the operational performance of the 5G network throughout the entire open-pit mine area, serving as an important basis for assessing network performance status.

[0128] Next, the system will input the global runtime performance vector into the quality inspection opinion discrimination model. This model is a pre-trained machine learning model capable of discriminating performance quality inspection opinions based on the input global runtime performance vector. This model may be built using algorithms such as deep learning, support vector machines, and decision trees. Through learning and training on a large amount of historical data, it has already been able to accurately identify different performance quality inspection opinions.

[0129] In the quality inspection perspective discrimination model, the global operational performance vector undergoes a series of mathematical operations and data processing steps. These processes may include vector normalization, feature extraction, and classifier discrimination. Through these processes, the model can extract key features from the global operational performance vector and, based on these features, determine the performance quality inspection perspective to which the current open-pit mine 5G base station performance dataset belongs.

[0130] After the discrimination is completed, the system will obtain a discrimination probability value. This value represents the likelihood that the current open-pit mine 5G base station performance dataset belongs to the target performance quality detection viewpoint. If this discrimination probability value is not less than a preset probability threshold, the system will determine that the performance quality detection viewpoint to which the current open-pit mine 5G base station performance dataset belongs is the target performance quality detection viewpoint. Conversely, if the discrimination probability value is less than the probability threshold, the system will determine that the performance quality detection viewpoint to which the current open-pit mine 5G base station performance dataset belongs is not the target performance quality detection viewpoint.

[0131] Through this processing flow, the system can accurately identify the performance quality detection perspectives associated with the 5G base station operation performance data in the open-pit mine 5G base station performance dataset. This provides important reference for subsequent performance optimization and network upgrades, helping to improve the operational performance and service quality of the 5G network in the open-pit mine area.

[0132] In the following steps, the aforementioned X 5G base station operation performance data are 5G base station operation performance data collected within the coverage area of ​​the target open-pit mine base station; the aforementioned target performance quality detection viewpoint is a performance quality detection viewpoint associated with the target interference source range; the aforementioned method further includes: if the performance quality detection viewpoint to which the aforementioned open-pit mine 5G base station performance dataset belongs is the aforementioned target performance quality detection viewpoint, then the interference source range within the coverage area of ​​the aforementioned target open-pit mine base station is determined to be the aforementioned target interference source range; if the performance quality detection viewpoint to which the aforementioned open-pit mine 5G base station performance dataset belongs is not the aforementioned target performance quality detection viewpoint, then the interference source range within the coverage area of ​​the aforementioned target open-pit mine base station is determined to be not the aforementioned target interference source range.

[0133] In the next step, the system will process the operational performance data of X 5G base stations collected within the coverage area of ​​the target open-pit mine base station. This data reflects the operational status and performance of the 5G base stations in the area. The purpose of processing this data is to determine whether the interference source range in this area is related to the preset target interference source range.

[0134] First, the system defines the target performance quality detection perspective, specifically the performance quality detection perspective associated with the target interference source range. This perspective is pre-defined and used to assess whether 5G base station performance data is related to a specific interference source range. If the performance of a 5G base station degrades or becomes abnormal, it may be related to interference sources within that area. Therefore, determining the interference source range is crucial for optimizing network performance and improving service quality.

[0135] Next, the system will use a quality inspection perspective discrimination model to process the global operational performance vector. This global operational performance vector is generated based on the operational performance data of X 5G base stations, comprehensively reflecting the network performance status within the coverage area of ​​the target open-pit mine base station. The quality inspection perspective discrimination model will use this vector to determine whether the performance quality inspection perspective of the current performance dataset is consistent with the target performance quality inspection perspective.

[0136] If the output of the quality inspection viewpoint discrimination model shows that the performance quality inspection viewpoint of the open-pit mine 5G base station performance dataset is the target performance quality inspection viewpoint, then the system will determine that the interference source range within the coverage area of ​​the target open-pit mine base station is the preset target interference source range. This means that the performance of the 5G base stations in this area has been affected by the target interference source, and corresponding measures need to be taken to optimize network performance and eliminate interference.

[0137] Conversely, if the output of the quality inspection viewpoint discrimination model shows that the performance quality inspection viewpoint to which the open-pit mine 5G base station performance dataset belongs is not the target performance quality inspection viewpoint, then the system will determine that the interference source range within the coverage area of ​​the target open-pit mine base station is not the preset target interference source range. This indicates that the performance degradation or anomaly of the 5G base stations in this area may be related to other factors, rather than the target interference source. In this case, the system may need to further analyze other causes and take corresponding measures to solve the problem.

[0138] Through this processing flow, the system can accurately identify whether the range of interference sources within the coverage area of ​​the target open-pit mine base station is related to the preset target interference source range, thus providing important reference for network optimization and interference elimination. This helps improve the operational performance and service quality of the 5G network in the open-pit mine area, ensuring smooth and reliable communication.

[0139] In some alternative technical solutions, the above method also includes steps 310-360.

[0140] Step 310: Obtain the base station operation performance quality inspection algorithm to be debugged; the base station operation performance quality inspection algorithm includes the base station operation performance data mining model to be debugged, the performance inference element mining algorithm to be debugged, and the quality inspection opinion discrimination model to be debugged.

[0141] Step 320: Obtain a sample of the performance dataset of 5G base stations in open-pit mines; the sample of the performance dataset of 5G base stations in open-pit mines contains multiple samples of 5G base station operation performance data; the sample of the performance dataset of 5G base stations in open-pit mines has prior learning annotations, which are used to indicate whether the performance quality detection viewpoint to which the sample of the performance dataset of 5G base stations in open-pit mines belongs is the target performance quality detection viewpoint or not the target performance quality detection viewpoint.

[0142] Step 330: Using the base station operation performance data mining model to be debugged, perform performance element mining on each 5G base station operation performance data sample in the above-mentioned open-pit mine 5G base station performance dataset sample to obtain the base station operation performance element vector sample of each 5G base station operation performance data sample.

[0143] Step 340: Generate a 5G base station operation performance vector chain sample based on the base station operation performance element vector sample of each 5G base station operation performance data sample, and use the above-mentioned performance inference element mining algorithm to be debugged to integrate the global operation performance vector sample of the above-mentioned open-pit mine 5G base station performance dataset sample based on the above-mentioned 5G base station operation performance vector chain sample; integrate to extract the interrelation features between each base station operation performance element vector sample in the above-mentioned 5G base station operation performance vector chain sample.

[0144] Step 350: Using the quality inspection viewpoint discrimination model to be debugged, based on the global operating performance vector sample, determine whether the performance quality detection viewpoint to which the above-mentioned open-pit mine 5G base station performance dataset sample belongs is a discrimination probability sample of the above-mentioned target performance quality detection viewpoint.

[0145] Step 360: Based on the above-mentioned probability discrimination examples and the above-mentioned prior learning annotations, improve the algorithm parameters of the above-mentioned base station operation performance quality inspection algorithm to obtain the debugged base station operation performance quality inspection algorithm; the debugged base station operation performance quality inspection algorithm includes the base station operation performance data mining model, the above-mentioned performance inference element mining algorithm and the quality inspection viewpoint discrimination model.

[0146] In some alternative technical solutions, the above method also includes a detailed debugging process, namely steps 310 to 360, for debugging and optimizing the base station operation performance quality inspection algorithm.

[0147] First, the system will acquire the base station operation performance quality inspection algorithm to be debugged. This algorithm is a composite algorithm, comprising three parts: the base station operation performance data mining model to be debugged, the performance inference element mining algorithm to be debugged, and the quality inspection opinion discrimination model to be debugged. These models and algorithms may have certain errors or deficiencies before debugging, and need to be debugged and optimized through subsequent steps.

[0148] Next, the system acquires a sample dataset of 5G base station performance in an open-pit mine. This dataset contains multiple samples of 5G base station operational performance data, all of which have prior learning annotations. These annotations indicate whether the performance quality detection viewpoint to which the data sample belongs is the target performance quality detection viewpoint. The existence of these prior learning annotations allows the system to perform supervised learning and optimization of the algorithm in subsequent steps.

[0149] After acquiring the dataset samples and algorithms, the system will use the base station operation performance data mining model to be debugged to perform performance element mining on each 5G base station operation performance data sample in the dataset. This process involves extracting the key performance elements in each data sample using data mining techniques and transforming them into base station operation performance element vector samples.

[0150] Then, the system generates a 5G base station operation performance vector chain sample based on the base station operation performance element vector samples of each 5G base station operation performance data sample. This vector chain sample is a sequence containing multiple base station operation performance element vectors. Next, the system processes this vector chain sample using a performance extrapolation element mining algorithm to obtain a global operation performance vector sample of the open-pit mine 5G base station performance dataset samples. This process comprehensively evaluates the 5G base station operation performance status of the entire open-pit mine area by extracting the interrelationship features between each base station operation performance element vector sample in the vector chain sample.

[0151] After obtaining the global runtime performance vector sample, the system uses the quality inspection viewpoint discrimination model to be debugged to discriminate this vector sample. The purpose of the discrimination is to determine whether the performance quality inspection viewpoint to which the open-pit mine 5G base station performance dataset sample belongs is the target performance quality inspection viewpoint. This process will output a discrimination probability sample, indicating the likelihood that the dataset sample belongs to the target performance quality inspection viewpoint.

[0152] Finally, the system improves the algorithm parameters of the base station operation performance quality inspection algorithm based on the discriminant probability samples and prior learning annotations. This process involves comparing the discriminant results with the prior learning annotations to adjust the algorithm's parameters and model structure, enabling the algorithm to more accurately discriminate performance quality inspection viewpoints in subsequent runs. After this series of debugging and optimization steps, the system obtains a fully debugged base station operation performance quality inspection algorithm, which includes an optimized base station operation performance data mining model, a performance inference element mining algorithm, and a quality inspection viewpoint discrimination model.

[0153] In another possible application scenario, the system first acquires a base station operation performance quality inspection algorithm to be debugged. This algorithm is a complex system consisting of three parts: a base station operation performance data mining model, a performance inference element mining algorithm, and a quality inspection viewpoint discrimination model. These components may not be perfect in their initial state and need to be optimized for performance and accuracy through debugging. To debug this algorithm, the system acquires a sample dataset of 5G base station performance from an open-pit mine. This dataset contains operation performance data from multiple 5G base stations, and all of these data have been annotated with prior learning annotations. These annotations are crucial because they tell the system whether each data sample belongs to the target performance quality inspection viewpoint, thus providing a foundation for subsequent supervised learning. In this step, the system uses the base station operation performance data mining model to be debugged to process each 5G base station operation performance data in the dataset sample. This process is like using a sieve to filter out the key performance elements in the data, and then converting these elements into a vector form, called a base station operation performance element vector sample. This vector sample contains the key information of the 5G base station's operation performance. Next, the system generates a 5G base station operation performance vector chain example based on the operation performance element vector examples of each 5G base station obtained in the previous step. This vector chain is like a string of pearls, with each pearl representing the operation performance status of a base station. Then, the system uses a performance extrapolation element mining algorithm to process this vector chain, extracting the implicit global operation performance features, and finally obtaining a global operation performance vector example. This global vector example comprehensively reflects the operation performance status of 5G base stations in the entire open-pit mine area. With the global operation performance vector example, the system can use a quality inspection viewpoint discrimination model for discrimination. This process is like using a ruler to measure the degree of matching between this global vector example and the target performance quality detection viewpoint. The output is a discrimination probability example, which tells the system how likely this dataset example is to belong to the target performance quality detection viewpoint. The final step is to improve the algorithm based on the discrimination result and prior learning annotations. The system compares the differences between the discrimination probability example and the prior learning annotations, and then adjusts the algorithm parameters and model structure based on these differences. This process is akin to a craftsman polishing a work of art. Through continuous adjustments and optimizations, the algorithm can more accurately identify performance quality issues during subsequent runs. Ultimately, the system will obtain a debugged and optimized base station operation performance quality inspection algorithm, which will be better able to serve the performance testing of 5G base stations in open-pit mines.

[0154] In the following steps, the algorithm parameters of the base station operation performance quality inspection algorithm described in step 360, which are improved based on the discriminant probability samples and the prior learning annotations, to obtain the debugged base station operation performance quality inspection algorithm, include: generating a quality inspection discriminant loss for the base station operation performance quality inspection algorithm for the open-pit mine 5G base station performance dataset samples based on the discriminant probability samples and the prior learning annotations; and improving the algorithm parameters of the base station operation performance quality inspection algorithm based on the quality inspection discriminant loss for the open-pit mine 5G base station performance dataset samples to obtain the debugged base station operation performance quality inspection algorithm.

[0155] In the following steps, the system will improve the algorithm parameters of the base station operation performance quality inspection algorithm based on the discriminative probability samples and prior learning annotations, ultimately obtaining a debugged base station operation performance quality inspection algorithm. This process mainly includes two steps: generating the quality inspection discriminative loss and improving the algorithm parameters.

[0156] First, the system generates a quality control loss for the base station performance quality inspection algorithm based on the possible samples and prior learning annotations, targeting the open-pit mine 5G base station performance dataset samples. This quality control loss is an indicator that measures the difference between the algorithm's judgment result and the actual result. Specifically, the system compares the difference between the possible samples and the prior learning annotations to calculate a loss value. This loss value reflects the degree of inaccuracy of the algorithm in judging the open-pit mine 5G base station performance dataset samples.

[0157] In calculating the loss for quality inspection discrimination, the system may employ various loss functions, such as cross-entropy loss and mean squared error loss. The most suitable loss function is selected based on the specific application scenario and algorithm characteristics. These loss functions can quantify the gap between the algorithm's discrimination result and the actual result, providing guidance for subsequent algorithm parameter improvements.

[0158] Next, the system will improve the algorithm's parameters based on the quality inspection loss of the open-pit mine 5G base station performance dataset samples. This process is typically achieved through algorithm optimization, such as gradient descent or stochastic gradient descent. The system will adjust the algorithm's parameters according to the magnitude and direction of the quality inspection loss, enabling the algorithm to more accurately determine the performance quality inspection perspective of the open-pit mine 5G base station performance dataset samples in subsequent judgments.

[0159] During the process of improving the algorithm parameters, the system may undergo multiple iterations. In each iteration, the algorithm parameters are adjusted based on the current quality inspection and discrimination loss, and the quality inspection and discrimination loss is recalculated. Through continuous iterative optimization, the algorithm parameters will gradually converge to the optimal value, thus obtaining a fully debugged base station operation performance quality inspection algorithm.

[0160] Ultimately, the successfully debugged base station performance quality inspection algorithm will be able to more accurately determine the performance quality inspection perspective of the open-pit mine 5G base station performance dataset, providing strong support for subsequent base station performance optimization. At the same time, this debugging process also provides valuable reference and guidance for the debugging and optimization of other similar algorithms.

[0161] Furthermore, there are multiple open-pit mine 5G base station performance dataset examples. These multiple open-pit mine 5G base station performance dataset examples include positive examples and negative examples. The prior learning annotations of the positive examples are used to indicate that the performance quality detection viewpoint of the 5G base station operation performance data examples in the positive examples is the aforementioned target performance quality detection viewpoint. The prior learning annotations of the negative examples are used to indicate that the performance quality detection viewpoint of the 5G base station operation performance data examples in the negative examples is not the aforementioned target performance quality detection viewpoint.

[0162] The above-mentioned method, based on the discriminant probability samples and prior learning annotations, generates the quality inspection discriminant loss of the base station operation performance quality inspection algorithm for the 5G base station operation performance data samples in the above-mentioned open-pit mine 5G base station performance dataset. This includes: obtaining a first discriminant confidence for positive samples in the above-mentioned 5G base station performance dataset and a second discriminant confidence for negative samples in the above-mentioned 5G base station performance dataset; updating the quality inspection discriminant loss of the base station operation performance quality inspection algorithm for positive samples in the above-mentioned 5G base station performance dataset based on the first discriminant confidence to obtain a first updated quality inspection discriminant loss; updating the quality inspection discriminant loss of the base station operation performance quality inspection algorithm for negative samples in the above-mentioned 5G base station performance dataset based on the second discriminant confidence to obtain a second updated quality inspection discriminant loss; and determining the sum of the first updated quality inspection discriminant loss and the second updated quality inspection discriminant loss as the quality inspection discriminant loss of the base station operation performance quality inspection algorithm for the above-mentioned multiple open-pit mine 5G base station performance dataset samples.

[0163] Furthermore, considering the diversity of the 5G base station performance dataset samples in open-pit mines, these samples are divided into two categories: positive samples and negative samples. The prior learning annotations for these two categories are used to indicate whether the 5G base station performance data samples belong to the target performance quality detection perspective.

[0164] When generating the base station operation performance quality inspection algorithm to determine the loss for these samples, the system will take the following steps.

[0165] First, the system obtains the first discriminant confidence score for positive examples in the 5G base station performance dataset and the second discriminant confidence score for negative examples in the same dataset. These discriminant confidence scores reflect the algorithm's confidence level in whether each example belongs to the target performance quality detection viewpoint. Generally, the higher the discriminant confidence score, the more confident the algorithm is in its judgment of the example.

[0166] Next, the system updates the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for positive examples in the 5G base station performance dataset based on the first discrimination confidence level, resulting in the first updated quality inspection discrimination loss. This update process essentially adjusts the loss value based on the difference between the algorithm's discrimination result for positive examples and the actual result. If the algorithm has a high discrimination confidence level for positive examples but the actual result does not match the target performance quality inspection viewpoint, the loss value will increase accordingly; conversely, if the discrimination result matches the actual result, the loss value will decrease.

[0167] Similarly, the system also updates the quality inspection loss of the base station operation performance quality inspection algorithm for negative samples in the 5G base station performance dataset based on the second discrimination confidence level, resulting in a second updated quality inspection discrimination loss. This update process is similar to that for positive samples, adjusting the loss value based on the difference between the algorithm's discrimination result for negative samples and the actual result.

[0168] Finally, the system determines the sum of the first and second updated quality inspection discrimination losses as the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for multiple open-pit mine 5G base station performance dataset samples. This total loss value reflects the overall inaccuracy of the algorithm in judging all samples, providing an important reference for subsequent algorithm parameter improvements.

[0169] In this way, the system can more comprehensively evaluate the performance of the base station operation performance quality inspection algorithm when judging the performance dataset samples of 5G base stations in open-pit mines, and make targeted optimizations and improvements to the algorithm based on the actual results.

[0170] Let (L) denote the quality inspection discrimination loss, (L^+) denote the quality inspection discrimination loss for positive examples in the 5G base station performance dataset, and (L^-) denote the quality inspection discrimination loss for negative examples in the 5G base station performance dataset. Simultaneously, let (p^+) denote the first discrimination confidence, i.e., the probability that the algorithm judges a positive example as a positive example (target performance quality detection perspective); and let (p^-) denote the second discrimination confidence, i.e., the probability that the algorithm judges a negative example as a negative example (non-target performance quality detection perspective).

[0171] Typically, the loss function can be in the form of cross-entropy loss, which measures the difference between the actual probability distribution and the predicted probability distribution. For binary classification problems, cross-entropy loss can be expressed as:

[0172] [L=-frac{1}{N}sum_{i=1}^{N}left[y_ilog(p_i)+(1-y_i)log(1-p_i)right]];

[0173] Where (N) is the number of samples, (y_i) is the true label (0 or 1) of sample (i), and (p_i) is the probability that the model predicts sample (i) to be a positive example.

[0174] In the exemplary scenario, the losses for positive and negative examples can be calculated separately, and then summed to obtain the total loss:

[0175] [L^+=-frac{1}{N^+}sum_{iin text{positive sample}}log(p_i^+)];

[0176] [L^-=-frac{1}{N^-}sum_{iin text{negative example}}log(1-p_i^-)];

[0177] [L=L^++L^-].

[0178] Here, (N^+) and (N^-) are the number of positive and negative examples, respectively. Note that in positive examples, the true label is always 1 (positive example), so we only need to consider the (log(p_i^+)) part; in negative examples, the true label is always 0 (negative example), so we only need to consider the (log(1-p_i^-)) part.

[0179] Ultimately, the system attempts to minimize this total loss (L) by optimizing the parameters of the base station performance quality inspection algorithm. This optimizes the algorithm so that the decision confidence (p+) for positive examples is as close to 1 as possible, while the decision confidence (p-) for negative examples is as close to 0 as possible. In this way, the algorithm can more accurately determine whether the examples in the open-pit mine 5G base station performance dataset belong to the target performance quality inspection criteria.

[0180] In some examples, there are multiple positive examples in the aforementioned 5G base station performance dataset, and the first discrimination confidence level is a mapping variable of the number of positive examples in the multiple 5G base station performance datasets; there are multiple negative examples in the aforementioned 5G base station performance dataset, and the second discrimination confidence level is a mapping variable of the number of negative examples in the multiple 5G base station performance datasets; wherein, the number of 5G base station operation performance data examples contained in each of the aforementioned multiple open-pit mine 5G base station performance dataset examples is the same or different.

[0181] In some examples, when processing open-pit mine 5G base station performance dataset samples, the system will encounter multiple positive 5G base station performance dataset samples and multiple negative 5G base station performance dataset samples. Each of these samples may contain the same or different number of 5G base station operation performance data samples.

[0182] For positive samples in the 5G base station performance dataset, the system generates a first discrimination confidence level based on the algorithm's judgment result for each sample. This first discrimination confidence level is actually a mapping variable of the number of positive samples in multiple 5G base station performance datasets, meaning it dynamically changes based on the number of positive samples and the algorithm's judgment result for each sample. If the number of positive samples increases, or if the algorithm becomes more confident in the judgment results of one or more positive samples (i.e., the discrimination confidence level increases), then the first discrimination confidence level will be adjusted accordingly.

[0183] Similarly, for negative samples in the 5G base station performance dataset, the system generates a second discrimination confidence level. This second discrimination confidence level is a mapping variable between the number of negative samples in multiple 5G base station performance datasets, and it changes based on the number of negative samples and the algorithm's discrimination result for each sample. If the number of negative samples increases, or if the algorithm becomes more confident in its discrimination results for one or more negative samples, the second discrimination confidence level will be adjusted accordingly.

[0184] It's important to note that the "mapping variable" here can be understood as a functional relationship, establishing a correspondence between the number of samples in the 5G base station performance dataset and the discrimination confidence level. This correspondence can be linear or non-linear, depending on the algorithm's design and implementation.

[0185] In practice, the system calculates a first and second discrimination confidence score based on the number of 5G base station performance data samples included in each open-pit mine 5G base station performance dataset sample and the algorithm's discrimination result for each sample. These discrimination confidence scores are then used to update the quality inspection discrimination loss, thereby guiding the improvement and optimization of algorithm parameters.

[0186] In this way, the system can more comprehensively evaluate the algorithm's performance in judging multiple open-pit mine 5G base station performance datasets, and make targeted adjustments and optimizations to the algorithm based on the actual results. This helps improve the accuracy and reliability of the algorithm, thus better serving the performance testing of open-pit mine 5G base stations.

[0187] In other application examples, the base station operation performance data mining model to be debugged in the above-mentioned base station operation performance quality inspection algorithm is a network that has been debugged. The algorithm parameters of the base station operation performance data mining model to be debugged are locked during the debugging process of the base station operation performance quality inspection algorithm. Among them, the algorithm parameters that need to be improved by the base station operation performance quality inspection algorithm include the algorithm parameters of the performance inference element mining algorithm to be debugged and the algorithm parameters of the quality inspection opinion discrimination model to be debugged.

[0188] In other application examples, the base station performance quality inspection algorithm includes a network that has already been debugged; this network is referred to as the base station performance data mining model to be debugged. In this specific scenario, the algorithm parameters of this data mining model are locked throughout the debugging process of the base station performance quality inspection algorithm, meaning they will not change during debugging. The purpose of locking these parameters is to maintain the stability of the data mining model, allowing focus to be placed on optimizing other parts of the algorithm.

[0189] In this process, the algorithm parameters that need improvement for the base station operation performance quality inspection algorithm mainly include two parts: first, the algorithm parameters of the performance extrapolation element mining algorithm to be debugged; and second, the algorithm parameters of the quality inspection viewpoint discrimination model to be debugged. These two parts of parameters will be key factors affecting the algorithm's performance and accuracy.

[0190] First, the performance projection element mining algorithm is responsible for extracting key performance indicators and features from base station operation data. These indicators and features will serve as input to the quality inspection opinion discrimination model. Improving the parameters of this part of the algorithm can enhance its ability to process performance data and the accuracy of extracting effective information.

[0191] Secondly, the quality inspection judgment model is responsible for determining whether the base station's operational performance meets the preset quality standards based on the input performance indicators and characteristics. Improving the parameters of this part of the model can enhance its accuracy and generalization ability in judging base station operational performance.

[0192] To optimize the algorithm parameters of these two parts, the system may employ optimization algorithms such as gradient descent, stochastic gradient descent, and Adam, combined with techniques such as cross-validation and regularization, to prevent overfitting and improve the generalization performance of the algorithm.

[0193] Through these improvements and optimizations, the system can gradually enhance the overall performance of the base station operation performance quality inspection algorithm, enabling it to more accurately assess base station operation performance and thus provide strong support for base station maintenance and management.

[0194] This solution also provides a data detection system, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any of the above-described data detection methods for 5G base stations in open-pit mines.

[0195] Furthermore, a computer-readable storage medium is also provided, comprising a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to execute any of the aforementioned data detection methods for 5G base stations in open-pit mines.

[0196] This invention provides a processor for running a program, wherein the program executes the data detection method for 5G base stations in open-pit mines.

[0197] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the data detection method steps for an open-pit mine 5G base station.

[0198] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0199] A computer program product includes a non-volatile computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps of the data detection method for an open-pit mine 5G base station described in various embodiments of this application.

[0200] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0201] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0202] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0203] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0204] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0205] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0206] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0207] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media 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 memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0208] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0209] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A data detection method for 5G base stations in open-pit mines, characterized in that, The method, applied to a data inspection system, includes: Obtain the performance dataset of 5G base stations in open-pit mines to be identified; the performance dataset of 5G base stations in open-pit mines contains X 5G base station operation performance data, where X is a positive integer; Performance element mining is performed on each of the X 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data. A 5G base station operation performance vector chain is generated based on the base station operation performance element vector of each 5G base station operation performance data, and the 5G base station operation performance vector chain is passed into the performance inference element mining algorithm; the 5G base station operation performance vector chain contains X base station operation performance element vectors concatenated from the X 5G base station operation performance data, the X base station operation performance element vectors correspond to X processing cycles of the performance inference element mining algorithm, and the u-th base station operation performance element vector in the X base station operation performance element vectors corresponds to the u-th processing cycle in the X processing cycles, where u is a positive integer and u is not greater than X; Using the performance extrapolation element mining algorithm in the u-th processing cycle, the performance heat vector of the u-th processing cycle is integrated based on the performance heat vector of the u-1-th processing cycle, the u-1-th base station operation performance element vector in the 5G base station operation performance vector chain, and the u-th base station operation performance element vector in the 5G base station operation performance vector chain; the performance heat vector of the u-1-th processing cycle is obtained by integrating the performance extrapolation element mining algorithm in the u-1-th processing cycle. When u = X, the performance heat vector of the integrated Xth processing cycle is determined as the global operating performance vector of the open-pit mine 5G base station performance dataset, and the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is determined based on the global operating performance vector.

2. The method according to claim 1, characterized in that, The step of mining performance elements for each 5G base station operation performance data in the X 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data includes: The operational performance data of the X 5G base stations are input into the base station operational performance data mining model; The base station operation performance data mining model is used to mine performance elements of each of the input 5G base station operation performance data to obtain a base station operation performance element vector for each 5G base station operation performance data.

3. The method according to claim 2, characterized in that, The step involves using the base station operation performance data mining model to mine performance elements for each incoming 5G base station operation performance data, obtaining a base station operation performance element vector for each 5G base station operation performance data, including: The base station operation performance data mining model is used to mine performance elements of each of the input 5G base station operation performance data to obtain the basic performance element linear variables of each 5G base station operation performance data. Based on the linear variables of the basic performance elements of the X 5G base station operation performance data, knowledge vector reinforcement is performed on the linear variables of the basic performance elements of any 5G base station operation performance data to obtain the base station operation performance element vector of any 5G base station operation performance data.

4. The method according to claim 1, characterized in that, The process of integrating the performance heat vector of the u-th processing cycle using the performance extrapolation element mining algorithm, based on the performance heat vector of the (u-1)-th processing cycle, the (u-1)-th base station operation performance element vector in the 5G base station operation performance vector chain, and the u-th base station operation performance element vector in the 5G base station operation performance vector chain, includes: Obtain the preceding and following sequence correlation vector for the (u-1)th processing cycle; the preceding and following sequence correlation vector is generated by the performance inference element mining algorithm in the (u-1)th processing cycle based on the (u-1)th base station operation performance element vector, and the preceding and following sequence correlation vector includes the element vector cached by the performance inference element mining algorithm for the (u-1)th base station operation performance element vector. Based on the preceding and following sequence correlation vector, the performance heat vector of the (u-1)th processing cycle, and the operating performance element vector of the uth base station, the performance heat vector of the uth processing cycle is integrated to obtain the performance heat vector of the uth processing cycle.

5. The method according to claim 1, characterized in that, The process of determining the performance quality detection perspective to which the 5G base station operation performance data in the open-pit mine 5G base station performance dataset belongs based on the global operation performance vector includes: The global operating performance vector is input into the quality inspection viewpoint discrimination model, and the quality inspection viewpoint discrimination model is used to determine the possibility that the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is the target performance quality detection viewpoint based on the global operating performance vector. If the discriminant probability is not less than the probability threshold, then the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is determined to be the target performance quality detection viewpoint. If the discriminant probability is less than the probability threshold, then it is determined that the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is not the target performance quality detection viewpoint. Wherein, the X 5G base station operation performance data are 5G base station operation performance data collected within the coverage area of ​​the target open-pit mine base station; the target performance quality detection viewpoint is a performance quality detection viewpoint associated with the target interference source range; the method further includes: if the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is the target performance quality detection viewpoint, then the interference source range of the coverage area of ​​the target open-pit mine base station is determined to be the target interference source range; if the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset belongs is not the target performance quality detection viewpoint, then the interference source range of the coverage area of ​​the target open-pit mine base station is determined not to be the target interference source range.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the base station operation performance quality inspection algorithm to be debugged; the base station operation performance quality inspection algorithm includes the base station operation performance data mining model to be debugged, the performance inference element mining algorithm to be debugged, and the quality inspection opinion discrimination model to be debugged. Obtain a sample of 5G base station performance data set in an open-pit mine; the sample of 5G base station performance data set in an open-pit mine contains multiple 5G base station operation performance data samples; the sample of 5G base station performance data set in an open-pit mine has prior learning annotations, the prior learning annotations of the sample of 5G base station performance data set in an open-pit mine are used to indicate whether the performance quality detection viewpoint to which the sample of 5G base station performance data set in an open-pit mine belongs is the target performance quality detection viewpoint or not the target performance quality detection viewpoint; Using the base station operation performance data mining model to be debugged, performance element mining is performed on each 5G base station operation performance data sample in the open-pit mine 5G base station performance dataset sample to obtain a base station operation performance element vector sample for each 5G base station operation performance data sample. Based on the base station operation performance element vector sample of each 5G base station operation performance data sample, a 5G base station operation performance vector chain sample is generated. Then, using the performance inference element mining algorithm to be debugged, a global operation performance vector sample of the open-pit mine 5G base station performance dataset sample is obtained by integrating the 5G base station operation performance vector chain sample. The integration is used to extract the interrelation features between each base station operation performance element vector sample in the 5G base station operation performance vector chain sample. Using the quality inspection viewpoint discrimination model to be debugged, based on the global operating performance vector sample, it is determined whether the performance quality detection viewpoint to which the open-pit mine 5G base station performance dataset sample belongs is a discrimination probability sample of the target performance quality detection viewpoint; The algorithm parameters of the base station operation performance quality inspection algorithm are improved based on the discriminative probability examples and the prior learning annotations to obtain a debugged base station operation performance quality inspection algorithm. The debugged base station operation performance quality inspection algorithm includes a base station operation performance data mining model, the performance inference element mining algorithm, and a quality inspection opinion discrimination model.

7. The method according to claim 6, characterized in that, The algorithm parameters of the base station operation performance quality inspection algorithm are improved based on the discriminative probability samples and the prior learning annotations to obtain the debugged base station operation performance quality inspection algorithm, including: Based on the discriminative probability examples and the prior learning annotations, the quality inspection discriminative loss of the base station operation performance quality inspection algorithm for the open-pit mine 5G base station performance dataset examples is generated; Based on the quality inspection and discrimination loss of the base station operation performance quality inspection algorithm for the open-pit mine 5G base station performance dataset sample, the algorithm parameters of the base station operation performance quality inspection algorithm are improved to obtain the base station operation performance quality inspection algorithm that has been debugged. The open-pit mine 5G base station performance dataset includes multiple samples, comprising both positive and negative samples. The prior learning annotations of the positive samples indicate that the performance quality detection viewpoint of the 5G base station operation performance data samples within the positive samples is the target performance quality detection viewpoint. Conversely, the prior learning annotations of the negative samples indicate that the performance quality detection viewpoint of the 5G base station operation performance data samples within the negative samples is not the target performance quality detection viewpoint. Therefore, the base station operation performance quality inspection algorithm is generated based on the discriminant probability samples and the prior learning annotations, targeting the samples in the open-pit mine 5G base station performance dataset. The quality inspection discrimination loss for 5G base station operation performance data samples includes: obtaining a first discrimination confidence level for positive samples of the 5G base station performance dataset and a second discrimination confidence level for negative samples of the 5G base station performance dataset; updating the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for positive samples of the 5G base station performance dataset based on the first discrimination confidence level to obtain a first updated quality inspection discrimination loss; updating the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for negative samples of the 5G base station performance dataset based on the second discrimination confidence level to obtain a second updated quality inspection discrimination loss; and determining the sum of the first updated quality inspection discrimination loss and the second updated quality inspection discrimination loss as the quality inspection discrimination loss of the base station operation performance quality inspection algorithm for the multiple open-pit mine 5G base station performance dataset samples. The 5G base station performance dataset contains multiple positive samples, and the first discrimination confidence level is a mapping variable of the number of positive samples in the multiple 5G base station performance datasets; the 5G base station performance dataset contains multiple negative samples, and the second discrimination confidence level is a mapping variable of the number of negative samples in the multiple 5G base station performance datasets; the number of 5G base station operation performance data samples included in each of the multiple open-pit mine 5G base station performance dataset samples may be the same or different.

8. The method according to claim 7, characterized in that, The base station operation performance data mining model to be debugged in the base station operation performance quality inspection algorithm is the network that has been debugged. The algorithm parameters of the base station operation performance data mining model to be debugged are locked during the debugging process of the base station operation performance quality inspection algorithm. The algorithm parameters that need to be improved in the base station operation performance quality inspection algorithm include the algorithm parameters of the performance inference element mining algorithm to be debugged and the algorithm parameters of the quality inspection opinion discrimination model to be debugged.

9. A data detection system, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including a data detection method for an open-pit mine 5G base station as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the data detection method for an open-pit mine 5G base station as described in any one of claims 1 to 8.

Images