Data detection method and system based on open-pit mine 5g network optimization

Abstract

The embodiment of the application relates to the technical field of data processing, in particular to a data detection method and system based on open-pit mine 5G network optimization, which generates comprehensive and accurate network environment optimization suggestions by real-time acquisition of operation log streams of a target open-pit mine area and analysis combined with historical data and current data. Through this method, not only the efficiency and accuracy of optimization work can be improved, but also strong guarantee for safe and efficient operation of the open-pit mine area can be provided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, more particularly, to a data detection method based on open-pit mine 5G network optimization, a data detection system and a computer readable storage medium. BACKGROUND

[0002] With the continuous development and expansion of open-pit mine areas, the requirements for network environment during operation are also increasing. Especially in the 5G network coverage area, the amount of operation log data of open-pit mine areas increases dramatically, and how to effectively process and analyze these data to optimize the network environment has become a problem to be solved.

[0003] Traditional network environment optimization methods usually rely on manual inspection and experience judgment, which is not only inefficient, but also difficult to ensure the accuracy and comprehensiveness of optimization suggestions. In addition, due to the lack of comprehensive analysis of historical data and real-time data, traditional optimization methods often cannot timely discover and solve potential problems in the network environment.

[0004] In recent years, with the continuous development of big data and artificial intelligence technology, data-driven network environment optimization methods have gradually attracted attention. However, existing data detection methods still have some shortcomings when processing open-pit mine operation logs. For example, they may not be able to effectively extract key information from massive log data, or accurately assess the trend of network performance changes. In addition, existing methods usually ignore the relevance between historical data and current data, resulting in a lack of continuity and consistency in optimization suggestions. SUMMARY

[0005] To improve the technical problems in the related art, the present application provides a data detection method based on open-pit mine 5G network optimization, a data detection system and a computer readable storage medium.

[0006] In a first aspect, the embodiments of the present application provide a data detection method based on open-pit mine 5G network optimization, applied to a data detection system, the method comprising:

[0007] acquiring target open-pit mine area operation logs and past open-pit mine area operation logs in a target open-pit mine area operation log stream; the target open-pit mine area operation log stream is obtained by converting the target 5G network coverage area based on a target data text conversion period, and then collecting and converting open-pit mine area operation data; the past open-pit mine area operation log refers to the previous open-pit mine area operation log of the target open-pit mine area operation log in the target open-pit mine area operation log stream;

[0008] obtain a target operation log linkage data state vector corresponding to the target open-pit mine operation log, and a past operation log linkage data state vector corresponding to the past open-pit mine operation log;

[0009] generate a first network quality evaluation vector about the target open-pit mine operation log based on the target operation log linkage data state vector, generate a second network quality evaluation vector about the past open-pit mine operation log based on the target operation log linkage data state vector and the past operation log linkage data state vector, and perform knowledge superposition on the target open-pit mine operation log and the past open-pit mine operation log according to the first network quality evaluation vector and the second network quality evaluation vector to obtain target superimposed description knowledge corresponding to the target open-pit mine operation log;

[0010] determine a final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the target operation log linkage data state vector, the target superimposed description knowledge and the past open-pit mine operation log.

[0011] With reference to the first aspect, in a possible implementation manner of the first aspect, the target operation log linkage data state vector includes a first device state attention vector and a first environment monitoring attention vector corresponding to the target open-pit mine operation log.

[0012] The generating the first network quality evaluation vector about the target open-pit mine operation log based on the target operation log linkage data state vector includes:

[0013] inputting the first device state attention vector and the first environment monitoring attention vector into a time domain superimposed processing network;

[0014] performing residual connection processing on the first device state attention vector and the first environment monitoring attention vector through a first residual connection branch of the time domain superimposed processing network to obtain a first operation log residual semantic vector corresponding to the target open-pit mine operation log;

[0015] performing residual connection processing on the first device state attention vector and the first environment monitoring attention vector through a second residual connection branch of the time domain superimposed processing network to obtain a second operation log residual semantic vector corresponding to the target open-pit mine operation log;

[0016] performing semantic unit feature point multiplication on the first operation log residual semantic vector and the second operation log residual semantic vector to obtain the first network quality evaluation vector about the target open-pit mine operation log.

[0017] In a possible implementation manner of the first aspect, the target running log linkage data state vector comprises a first equipment state attention vector and a first environment monitoring attention vector corresponding to the target strip mine running log, and the past running log linkage data state vector comprises a second equipment state attention vector and a second environment monitoring attention vector corresponding to the past strip mine running log.

[0018] The generating, based on the target running log linkage data state vector and the past running log linkage data state vector, of a second network quality evaluation vector about the past strip mine running log comprises:

[0019] The first equipment state attention vector and the first environment monitoring attention vector are respectively subjected to feature migration operations to obtain an equipment state migration vector corresponding to the second equipment state attention vector and an environment monitoring migration vector corresponding to the second environment monitoring attention vector.

[0020] The first equipment state attention vector, the first environment monitoring attention vector, the equipment state migration vector, and the environment monitoring migration vector are input into a time domain superposition processing network.

[0021] The first equipment state attention vector and the first environment monitoring attention vector are subjected to residual connection processing through a first residual connection branch of the time domain superposition processing network to obtain a target running log residual semantic vector corresponding to the target strip mine running log.

[0022] The equipment state migration vector and the environment monitoring migration vector are subjected to residual connection processing through a second residual connection branch of the time domain superposition processing network to obtain a past running log residual semantic vector corresponding to the past strip mine running log.

[0023] The target running log residual semantic vector and the past running log residual semantic vector are subjected to semantic unit feature point multiplication to obtain a second network quality evaluation vector about the past strip mine running log.

[0024] In a possible implementation manner of the first aspect, the knowledge superposition, according to the first network quality evaluation vector and the second network quality evaluation vector, of the target strip mine running log and the past strip mine running log to obtain a target superposition description knowledge corresponding to the target strip mine running log comprises:

[0025] A naive Bayes classifier is acquired, and a first knowledge vector integrated weight about the target strip mine running log is determined through the naive Bayes classifier and the first network quality evaluation vector.

[0026] determine a second knowledge vector integration weight about the past open-pit mine area operation log through the Naive Bayes classifier and the second network quality evaluation vector;

[0027] based on the first knowledge vector integration weight and the second knowledge vector integration weight, knowledge superposition is performed on the target open-pit mine area operation log and the past open-pit mine area operation log, to obtain target superposition description knowledge corresponding to the target open-pit mine area operation log.

[0028] In combination with the first aspect, in a possible implementation manner of the first aspect, based on the first knowledge vector integration weight and the second knowledge vector integration weight, the knowledge superposition is performed on the target open-pit mine area operation log and the past open-pit mine area operation log, to obtain the target superposition description knowledge corresponding to the target open-pit mine area operation log, including:

[0029] obtaining a target network state disturbance linear variable, a target transmission packet loss quantization linear variable and a target data delay quantization linear variable corresponding to the target open-pit mine area operation log, and obtaining a past superposition network state disturbance linear variable, a past superposition transmission packet loss quantization linear variable and a past superposition data delay quantization linear variable corresponding to the past open-pit mine area operation log;

[0030] based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target transmission packet loss quantization linear variable is superimposed on the past superposition transmission packet loss quantization linear variable, to obtain a target superposition transmission packet loss quantization linear variable corresponding to the target open-pit mine area operation log;

[0031] based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target network state disturbance linear variable is superimposed on the past superposition network state disturbance linear variable, to obtain a target superposition network state disturbance linear variable corresponding to the target open-pit mine area operation log;

[0032] based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target data delay quantization linear variable is superimposed on the past superposition data delay quantization linear variable, to obtain a target superposition data delay quantization linear variable corresponding to the target open-pit mine area operation log;

[0033] the target superposition transmission packet loss quantization linear variable, the target superposition network state disturbance linear variable and the target superposition data delay quantization linear variable are determined as the target superposition description knowledge corresponding to the target open-pit mine area operation log.

[0034] In a possible implementation manner of the first aspect, the target running log linkage data state vector comprises a first device state attention vector and a first environment monitoring attention vector; the past running log linkage data state vector comprises a second device state attention vector and a second environment monitoring attention vector corresponding to the past open-pit mine running log;

[0035] The target integrated interactive knowledge vector corresponding to the target open-pit mine running log is determined based on the target running log linkage data state vector, the target superimposed description knowledge and the past open-pit mine running log.

[0036] The target integrated interactive knowledge vector is input into a target network environment optimization detection network, and the final network environment optimization suggestion corresponding to the target open-pit mine running log is output in the target network environment optimization detection network based on the target integrated interactive knowledge vector.

[0037] In a possible implementation manner of the first aspect, the target running log linkage data state vector comprises a first device state attention vector and a first environment monitoring attention vector; the past running log linkage data state vector comprises a second device state attention vector and a second environment monitoring attention vector corresponding to the past open-pit mine running log;

[0038] The target integrated interactive knowledge vector corresponding to the target open-pit mine running log is determined based on the target running log linkage data state vector, the target superimposed description knowledge and the past open-pit mine running log.

[0039] The reference knowledge vector corresponding to the target open-pit mine running log is obtained; the reference knowledge vector comprises the first device state attention vector and the first environment monitoring attention vector.

[0040] The attention vectors in the reference knowledge vector, except the first device state attention vector and the first environment monitoring attention vector, are determined as residual attention vectors.

[0041] The target superimposed description knowledge, the first device state attention vector, the first environment monitoring attention vector and the residual attention vectors are integrated to obtain a running log integrated vector corresponding to the target open-pit mine running log.

[0042] The second device state attention vector and the second environment monitoring attention vector are respectively subjected to feature migration operations to obtain a device state migration vector corresponding to the second device state attention vector and an environment monitoring migration vector corresponding to the second environment monitoring attention vector.

[0043] The operation log set integration vector, the device state migration vector, and the environment monitoring migration vector are interacted to obtain a target integration interaction knowledge vector corresponding to the target open-pit mine operation log.

[0044] In combination with the first aspect, in a possible implementation manner of the first aspect, the outputting, in the target network environment optimization detection network, of a final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the target integration interaction knowledge vector comprises:

[0045] The target integration interaction knowledge vector is determined by the target network environment optimization detection network to correspond to a first operation log optimization simulation result, a second operation log optimization simulation result, a first network environment optimization decision feature, and a second network environment optimization decision feature; the first operation log optimization simulation result does not contain error text, and the feature recognition degree of the first operation log optimization simulation result is greater than the feature recognition degree of the second operation log optimization simulation result.

[0046] In the target network environment optimization detection network, the first operation log optimization simulation result and the second operation log optimization simulation result are subjected to network environment optimization detection by the first network environment optimization decision feature to obtain an initial network environment optimization suggestion corresponding to the target open-pit mine operation log.

[0047] The past network environment optimization suggestion corresponding to the past open-pit mine operation log is obtained, and the initial network environment optimization suggestion and the past network environment optimization suggestion are subjected to joint updating by the second network environment optimization decision feature to obtain the final network environment optimization suggestion corresponding to the target open-pit mine operation log.

[0048] In a second aspect, the present application further 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 comprise a program for executing any one of the data detection methods based on open-pit mine 5G network optimization.

[0049] In a third aspect, the present application further provides a computer-readable storage medium comprising a stored program, wherein when the program is running, the device where the computer-readable storage medium is located executes any one of the data detection methods based on open-pit mine 5G network optimization.

[0050] The application provides an open-pit mine network environment optimization method based on a data detection system. The method obtains the running log stream of the target open-pit mine in real time, analyzes the historical data and current data, and generates comprehensive and accurate network environment optimization suggestions. This method not only improves the efficiency and accuracy of optimization work, but also provides strong protection for the safe and efficient operation of the open-pit mine. BRIEF DESCRIPTION OF DRAWINGS

[0051] The drawings accompanying the specification of the present application are used to provide a further understanding of the present application, the illustrative embodiments of the present application and the description thereof serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0052] Figure 1 A hardware structure block diagram of a mobile terminal for performing a data detection method based on open-pit mine 5G network optimization is shown according to an embodiment of the present application;

[0053] Figure 2 A flowchart of a data detection method based on open-pit mine 5G network optimization provided by an embodiment of the present application.

[0054] Among them, the above drawings include the following reference signs:

[0055] 102, processor; 104, memory; 106, transmission device; 108, input and output device. DETAILED DESCRIPTION

[0056] It should be noted that the embodiments and features in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0057] In order 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 described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0059] As introduced in the background, the correlation between historical data and current data is generally ignored in the prior art, resulting in a lack of continuity and consistency in optimization recommendations. To solve the above problems, the embodiments of the present application provide a data detection method based on open-pit mine 5G network optimization, a data detection system and a computer readable storage medium.

[0060] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application.

[0061] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking the case of running on a mobile terminal, Figure 1 is a hardware structure block diagram of a mobile terminal of a data detection method based on open-pit mine 5G network optimization according to an embodiment of the present application. As shown in Figure 1 , the mobile terminal can include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 can include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned mobile terminal can further include a transmission device 106 for communication function and an input and output device 108. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal can include more or less components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0062] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the device information display method of the embodiments of the present application. The processor 102 executes various functional applications and data processing, i.e., implements the above method, by running the computer programs stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories remotely arranged with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The specific examples of the above network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet in a wireless manner.

[0063] In the embodiments, a data detection method based on open-pit mine 5G network optimization running on a mobile terminal, a computer terminal or the like is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that herein.

[0064] Based on this, please refer to Figure 2 , Figure 2 is a flowchart of a data detection method based on open-pit mine 5G network optimization provided by the embodiments of the present application. The method is applied to a data detection system and can further include steps 210-240.

[0065] In step 210, target open-pit mine operation logs and past open-pit mine operation logs are obtained in a target open-pit mine operation log stream. The target open-pit mine operation log stream is obtained by collecting and converting open-pit mine operation data in a target 5G network coverage area based on a target data text conversion period. The past open-pit mine operation log refers to a previous open-pit mine operation log of the target open-pit mine operation log in the target open-pit mine operation log stream.

[0066] Step 220, obtaining a target operation log linkage data state vector corresponding to the target open-pit mine operation log, and a past operation log linkage data state vector corresponding to the past open-pit mine operation log.

[0067] Step 230, generating a first network quality evaluation vector about the target open-pit mine operation log based on the target operation log linkage data state vector, generating a second network quality evaluation vector about the past open-pit mine operation log based on the target operation log linkage data state vector and the past operation log linkage data state vector, and performing knowledge superposition on the target open-pit mine operation log and the past open-pit mine operation log according to the first network quality evaluation vector and the second network quality evaluation vector to obtain target superimposed description knowledge corresponding to the target open-pit mine operation log.

[0068] Step 240, determining a final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the target operation log linkage data state vector, the target superimposed description knowledge, and the past open-pit mine operation log.

[0069] In order to facilitate understanding of the above technical solutions, seven adaptability combined embodiments are further given below.

[0070] In embodiment 1, the target operation log linkage data state vector includes a first device state attention vector and a first environment monitoring attention vector corresponding to the target open-pit mine operation log; the first network quality evaluation vector about the target open-pit mine operation log is generated based on the target operation log linkage data state vector, including: inputting the first device state attention vector and the first environment monitoring attention vector into a time domain superposition processing network; performing residual connection processing on the first device state attention vector and the first environment monitoring attention vector through a first residual connection branch of the time domain superposition processing network to obtain a first operation log residual semantic vector corresponding to the target open-pit mine operation log; performing residual connection processing on the first device state attention vector and the first environment monitoring attention vector through a second residual connection branch of the time domain superposition processing network to obtain a second operation log residual semantic vector corresponding to the target open-pit mine operation log; and performing semantic unit feature point multiplication on the first operation log residual semantic vector and the second operation log residual semantic vector to obtain the first network quality evaluation vector about the target open-pit mine operation log.

[0071] In the embodiment 2, the target operation log linkage data state vector includes the first equipment state attention vector and the first environment monitoring attention vector corresponding to the target open-pit mine operation log, and the past operation log linkage data state vector includes the second equipment state attention vector and the second environment monitoring attention vector corresponding to the past open-pit mine operation log; the second network quality evaluation vector about the past open-pit mine operation log is generated based on the target operation log linkage data state vector and the past operation log linkage data state vector, including: performing feature migration operations on the second equipment state attention vector and the second environment monitoring attention vector respectively to obtain an equipment state migration vector corresponding to the second equipment state attention vector and an environment monitoring migration vector corresponding to the second environment monitoring attention vector; inputting the first equipment state attention vector, the first environment monitoring attention vector, the equipment state migration vector and the environment monitoring migration vector into a time domain superposition processing network; performing residual connection processing on the first equipment state attention vector and the first environment monitoring attention vector through a first residual connection branch of the time domain superposition processing network to obtain a target operation log residual semantic vector corresponding to the target open-pit mine operation log; performing residual connection processing on the equipment state migration vector and the environment monitoring migration vector through a second residual connection branch of the time domain superposition processing network to obtain a past operation log residual semantic vector corresponding to the past open-pit mine operation log; performing semantic unit feature point multiplication on the target operation log residual semantic vector and the past operation log residual semantic vector to obtain the second network quality evaluation vector about the past open-pit mine operation log.

[0072] In the embodiment 3, the target open-pit mine operation log and the past open-pit mine operation log are knowledge superimposed according to the first network quality evaluation vector and the second network quality evaluation vector to obtain the target superimposed description knowledge corresponding to the target open-pit mine operation log, including: obtaining a Naive Bayes classifier, determining a first knowledge vector integration weight about the target open-pit mine operation log through the Naive Bayes classifier and the first network quality evaluation vector; determining a second knowledge vector integration weight about the past open-pit mine operation log through the Naive Bayes classifier and the second network quality evaluation vector; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target open-pit mine operation log and the past open-pit mine operation log are knowledge superimposed to obtain the target superimposed description knowledge corresponding to the target open-pit mine operation log.

[0073] In embodiment 4, based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target open-pit mine operation log is knowledge superimposed with the past open-pit mine operation log to obtain the target superimposed description knowledge corresponding to the target open-pit mine operation log, including: obtaining the target network state disturbance linear variable, the target transmission packet loss quantization linear variable and the target data delay quantization linear variable corresponding to the target open-pit mine operation log, obtaining the past superimposed network state disturbance linear variable, the past superimposed transmission packet loss quantization linear variable and the past superimposed data delay quantization linear variable corresponding to the past open-pit mine operation log; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target transmission packet loss quantization linear variable is superimposed with the past superimposed transmission packet loss quantization linear variable to obtain the target superimposed transmission packet loss quantization linear variable corresponding to the target open-pit mine operation log; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target network state disturbance linear variable is superimposed with the past superimposed network state disturbance linear variable to obtain the target superimposed network state disturbance linear variable corresponding to the target open-pit mine operation log; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target data delay quantization linear variable is superimposed with the past superimposed data delay quantization linear variable to obtain the target superimposed data delay quantization linear variable corresponding to the target open-pit mine operation log; the target superimposed transmission packet loss quantization linear variable, the target superimposed network state disturbance linear variable and the target superimposed data delay quantization linear variable are determined as the target superimposed description knowledge corresponding to the target open-pit mine operation log.

[0074] In embodiment 5, based on the target operation log linkage data state vector, the target superimposed description knowledge and the past open-pit mine operation log, the final network environment optimization suggestion corresponding to the target open-pit mine operation log is determined, including: based on the target operation log linkage data state vector, the target superimposed description knowledge and the past open-pit mine operation log, the target integrated interactive knowledge vector corresponding to the target open-pit mine operation log is determined; the target integrated interactive knowledge vector is entered into the target network environment optimization detection network, and in the target network environment optimization detection network, based on the target integrated interactive knowledge vector, the final network environment optimization suggestion corresponding to the target open-pit mine operation log is output.

[0075] In the embodiment 6, the target operation log linkage data state vector includes a first equipment state attention vector and a first environment monitoring attention vector; the past operation log linkage data state vector includes a second equipment state attention vector and a second environment monitoring attention vector corresponding to the past open-pit mine operation log; and the target integrated interaction knowledge vector corresponding to the target open-pit mine operation log is determined based on the target operation log linkage data state vector, the target superimposed description knowledge and the past open-pit mine operation log, including: obtaining a reference knowledge vector corresponding to the target open-pit mine operation log; the reference knowledge vector includes the first equipment state attention vector and the first environment monitoring attention vector; determining, as a remaining attention vector, an attention vector in the reference knowledge vector except the first equipment state attention vector and the first environment monitoring attention vector; performing vector integration on the target superimposed description knowledge, the first equipment state attention vector, the first environment monitoring attention vector and the remaining attention vector to obtain an operation log integrated vector corresponding to the target open-pit mine operation log; performing feature migration operations on the second equipment state attention vector and the second environment monitoring attention vector respectively to obtain an equipment state migration vector corresponding to the second equipment state attention vector and an environment monitoring migration vector corresponding to the second environment monitoring attention vector; and performing feature interaction on the operation log integrated vector, the equipment state migration vector and the environment monitoring migration vector to obtain the target integrated interaction knowledge vector corresponding to the target open-pit mine operation log.

[0076] In embodiment 7, the above target network environment optimization detection network is used to output the final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the above target integrated interactive knowledge vector, which includes: determining the first operation log optimization simulation result, the second operation log optimization simulation result, the first network environment optimization decision feature, and the second network environment optimization decision feature corresponding to the target integrated interactive knowledge vector through the target network environment optimization detection network; the first operation log optimization simulation result does not contain error text, and the feature recognition degree of the first operation log optimization simulation result is greater than that of the second operation log optimization simulation result; in the target network environment optimization detection network, the first operation log optimization simulation result and the second operation log optimization simulation result are detected for network environment optimization through the first network environment optimization decision feature, to obtain the initial network environment optimization suggestion corresponding to the target open-pit mine operation log; the past network environment optimization suggestion corresponding to the past open-pit mine operation log is obtained, and the initial network environment optimization suggestion and the past network environment optimization suggestion are jointly updated through the second network environment optimization decision feature, to obtain the final network environment optimization suggestion corresponding to the target open-pit mine operation log.

[0077] To further understand the above technical solutions and embodiments, the following will be introduced through specific examples.

[0078] The following is a specific application scenario example, which details how steps 210-240 are implemented by the data detection system: In a certain large open-pit mine, in order to ensure safe and efficient production, the mine introduces 5G network coverage, and through the data detection system, the operation data of the mine is collected and analyzed in real time. The system collects and converts the operation data of the open-pit mine in the target 5G network coverage area according to the preset target data text conversion period, forming a target open-pit mine operation log stream.

[0079] The data detection system first performs step 210 to obtain the current target open-pit mine operation log and its previous past open-pit mine operation log from the target open-pit mine operation log stream. These logs contain various operation data of the mine, such as device status, production, environmental conditions, etc.

[0080] Next, the data detection system performs step 220 to extract the corresponding linkage data state vectors for the obtained target open-pit mine operation log and past open-pit mine operation log. These vectors are obtained by feature extraction and coding of key data in the logs, reflecting the state information of multiple aspects of the mine operation.

[0081] Then, the data detection system enters step 230, based on the extracted target operational log linkage data state vector, generates a first network quality evaluation vector about the target open-pit mine operational log. This vector is a quantitative assessment of the current mine network environment quality. At the same time, the system also generates a second network quality evaluation vector about the past open-pit mine operational log, combining the target operational log linkage data state vector and the past operational log linkage data state vector. This is an evaluation of the mine network environment quality in the past period of time.

[0082] On this basis, the data detection system uses the first network quality evaluation vector and the second network quality evaluation vector to perform knowledge superposition on the target open-pit mine operational log and the past open-pit mine operational log. This process is achieved by comparing and analyzing the network quality evaluation vectors of the two periods to find their differences and connections, thereby obtaining the target superposition description knowledge corresponding to the target open-pit mine operational log. These knowledge reflects the dynamic change law and potential problems of the mine network environment.

[0083] Finally, the data detection system performs step 240 to determine the final network environment optimization suggestions corresponding to the target open-pit mine operational log based on the target operational log linkage data state vector, the target superposition description knowledge, and the past open-pit mine operational log. These suggestions are improvement measures proposed for the problems and deficiencies existing in the current mine network environment, aiming to improve the network quality and production efficiency of the mine. For example, the suggestions may include optimizing 5G network layout, upgrading network equipment, adjusting data transmission protocols, etc.

[0084] The following is another specific application scenario example, which details how the above steps 210-240 are implemented by the data detection system: A large open-pit mine has fully covered 5G network to improve production efficiency and ensure job safety. To continuously optimize network performance, the mine introduces an advanced data detection system that can collect and analyze operational data in real time and provide network environment optimization suggestions.

[0085] 1. Data collection and preparation

[0086] Step 210 details: The data detection system first captures the operational log stream of the target open-pit mine in real time through the pre-set 5G network data interface. These log streams contain the working status, communication quality, environmental parameters, and other key information of various devices within the mine. The system converts the raw data stream into structured operational logs according to the pre-set text conversion period (such as every minute, every hour, etc.), facilitating subsequent analysis and processing. At the same time, the system retains the past operational logs as historical data for comparative analysis.

[0087] 2. Data state vector extraction

[0088] Step 220: In-depth Analysis of Operational Logs The data detection system uses advanced machine learning algorithms and natural language processing techniques to deeply analyze the collected operational logs. The system extracts key features from the logs, such as signal strength, data transmission rate, and device failure rate, and encodes these features into a state vector of network performance. These vectors not only reflect the current network performance in the mine area but also contain information about various factors that may affect network performance.

[0089] 3. Network Quality Evaluation and Knowledge Superposition

[0090] Step 230: Network Quality Evaluation and Knowledge Superposition Based on the extracted state vector of network performance, the data detection system uses a pre-trained network quality evaluation model to evaluate the current and past operational logs. The evaluation results are represented in the form of vectors, quantifying the network's performance in various aspects such as stability, throughput, and latency. Then, the system performs knowledge superposition on the current and past network quality evaluation vectors. This process identifies the network performance trends and potential problem points by comparing the network performance in two periods, providing data support for subsequent optimization recommendations.

[0091] 4. Optimization Recommendation Generation

[0092] Step 240: Optimization Recommendation Generation After completing the knowledge superposition, the data detection system combines the current network state, historical network performance trends, and known mine operation requirements to generate a series of targeted network environment optimization recommendations using optimization algorithms. These recommendations may include adjusting the 5G base station layout to improve signal coverage, optimizing data transmission protocols to reduce communication latency, upgrading network devices to improve processing capacity, etc. The system also prioritizes these recommendations to help mine managers quickly identify and solve network performance bottleneck problems.

[0093] Summary: Through the above detailed steps, the data detection system can effectively utilize real-time and historical operational log data to comprehensively evaluate and generate optimization recommendations for the 5G network environment in the open-pit mine. This not only improves the overall performance of the mine network but also provides strong support for the safety production and efficiency improvement of the mine.

[0094] Next, the steps 210-240 are explained in detail and further refined.

[0095] In step 210, the relevant terms are explained as follows.

[0096] Target Open Pit Mine Operational Log Stream: The target open pit mine operational log stream refers to a continuous collection and transmission of a series of operational log data from the target open pit mine within a specific time period. These data streams usually contain real-time operational status, performance parameters, fault records, and other information of various equipment, systems, and networks in the mine. These data are transmitted in real-time in the form of streams for real-time monitoring and analysis. For example, a certain open pit mine has deployed dozens of excavators, transport vehicles, and monitoring equipment, each equipped with sensors and data acquisition systems. These devices send log data containing their own operational status, work efficiency, fault codes, and other information to the central server every minute. The continuous data stream received by the central server constitutes the operational log stream of the target open pit mine.

[0097] Target Open Pit Mine Operational Log: The target open pit mine operational log refers to detailed records collected from the target open pit mine at a specific time point or time period, covering equipment operation, production activities, environmental conditions, and other aspects. These logs usually contain timestamps, device identifiers, operational status, performance parameters, fault information, and other key data for subsequent analysis and processing. For example, at 10 am on a certain day, a mining excavator in the mine area broke down. At this time, the data acquisition system of the excavator sent a log record containing the fault code to the central server. This record is one of the operational logs of the target open pit mine at 10 am.

[0098] Past Open Pit Mine Operational Log: The past open pit mine operational log refers to historical log data before the target open pit mine operational log. These data record the operational status of the mine in the past period, including device performance, production efficiency, fault history, and other information. By analyzing past logs, we can understand the operational trends and potential problems of the mine. For example, to investigate the cause of the above-mentioned excavator failure, engineers reviewed the operational logs of the excavator in the past week. These logs recorded the working hours, operational efficiency, maintenance records, and other information of the excavator in the past week. These historical data are examples of past open pit mine operational logs.

[0099] Target Data Text Conversion Period: The target data text conversion period refers to the fixed time interval for converting raw data (such as sensor readings, device status, etc.) into structured text format (such as CSV, JSON, etc.). Within this period, the data detection system will clean, format, and encode the collected raw data for subsequent analysis and processing. For example, in the above-mentioned mine area, the data acquisition system converts the collected raw data into JSON format operational logs every 5 minutes and sends them to the central server. This 5-minute time interval is an example of the target data text conversion period.

[0100] Target 5G network coverage area: The target 5G network coverage area refers to the area within an open-pit mine where 5G base stations and network equipment are deployed, providing stable and high-speed 5G communication services. In this area, various mine equipment can perform real-time data transmission, remote monitoring and control, and other operations through the 5G network. For example, a certain open-pit mine deploys multiple 5G base stations in the main operating area to improve automation and intelligence levels. The network coverage area formed by these base stations is the target 5G network coverage area. In this area, mobile equipment such as excavators and transport vehicles can upload real-time operation data through the 5G network and receive remote instructions for operation.

[0101] Conducting open-pit mine operation data collection and conversion: Conducting open-pit mine operation data collection and conversion refers to the process of using specialized data collection systems and conversion tools to collect raw operation data from various equipment and systems in the open-pit mine and convert them into structured data in a unified format. This process includes data collection, cleaning, formatting, encoding, and transmission steps. For example, in the above-mentioned mine, in order to monitor the running status and production efficiency of the equipment in real time, the mine manager deploys a set of data collection system. This system collects raw operation data in real time through sensors and data interfaces connected to each device. Then, using predefined conversion rules and algorithms, the raw data is converted into JSON operation logs in a unified format and sent to the central server for analysis and processing through the 5G network. This process is an example of conducting open-pit mine operation data collection and conversion.

[0102] Further expansion of step 210 is as follows.

[0103] Before detailing how the data detection system obtains target open-pit mine operation logs and past open-pit mine operation logs, it is necessary to understand the sources of these logs and their role in the overall operation of the mine.

[0104] As a complex industrial environment, the daily operation of an open-pit mine involves a large number of equipment, personnel, and work processes. In order to ensure the safe and efficient operation of the mine, it is essential to monitor and analyze these equipment and processes in real time. The data detection system is a key tool to achieve this goal.

[0105] Firstly, the system collects real-time operation data of various equipment in the mine through sensors and data collection devices deployed in the target 5G network coverage area. These data include device status information, working parameters, production statistics, etc., which exist in raw form and need to be processed before being used for subsequent analysis and decision-making.

[0106] This is where the target data text conversion cycle comes into play. This cycle defines the frequency and rules of data conversion from raw form to structured text format. According to this cycle, the data detection system regularly cleans, organizes, and converts the collected raw data into a unified text format (such as JSON, XML, etc.), forming a continuous running log stream. This log stream is the target open-pit mine running log stream, which reflects the overall running status of the mine in real time.

[0107] In this log stream, each running log records the running information of the mine at a specific time point. The data detection system can extract the running log at any time point from the log stream as the target open-pit mine running log as needed. At the same time, since the log stream is continuous, the system can also easily obtain the running log before the target log, i.e., the past open-pit mine running log.

[0108] The past open-pit mine running log is of great significance to the operation and management of the mine. By comparing the current log and the past log, the management personnel can understand the changing trend of the mine running, find potential problems and hidden dangers, and thus take timely measures for intervention and adjustment. This data-based decision-making approach not only improves the operation efficiency of the mine, but also greatly enhances the safety of the mine.

[0109] In summary, the data detection system provides strong support for the safe and efficient operation of the mine by collecting, converting, and analyzing the running data of the open-pit mine in real time. The acquisition and application of the target open-pit mine running log and the past open-pit mine running log are indispensable important links in this process.

[0110] In step 220, the relevant noun explanations are as follows.

[0111] Target operation log linkage data state vector: The target operation log linkage data state vector refers to the multi-dimensional vector formed by extracting key data features from the real-time operation logs of the target open-pit mine area and encoding them. This vector not only contains the operation state information of a single device, but also integrates linkage data related to other devices, environmental parameters, etc., to reflect the comprehensive state of the entire mine area system. Each dimension represents a specific data feature, such as the working efficiency, failure rate, communication quality, etc. of a device. For example, in the target open-pit mine area, there is a key excavator in operation. Its operation log contains real-time working parameters of the excavator, such as engine speed, oil temperature, digging depth, etc. At the same time, these data are closely related to the working state of other devices (such as transport vehicles, loaders, etc.) in the mine area, the weather conditions of the mine area, and the signal strength of the 5G communication network, etc. The data detection system will extract key features such as the average working efficiency of the excavator, the number of failures, and the coordination efficiency with other devices from these logs and encode them into a multi-dimensional linkage data state vector. This vector can reflect the comprehensive operation state of the excavator and the entire mine area system associated with it in real time.

[0112] Past operation log linkage data state vector: The past operation log linkage data state vector refers to the multi-dimensional vector reflecting the past state of the mine area system extracted and encoded from historical operation logs. Similar to the target operation log linkage data state vector, it also contains key information such as device working state, environmental parameters, etc., but reflects the mine area system state at a certain time in the past. For example, to analyze the production efficiency trend of the target open-pit mine area in the past week, the data detection system will extract key data features from the operation logs of the past week, such as daily total output, average device working time, number of failures, etc. Then, encode these features into daily linkage data state vectors. By comparing these vectors, management personnel can clearly see the trend of production efficiency and possible influencing factors. For example, if the output of a certain day is significantly lower than other days, further check the device working state, environmental parameters, etc. of that day can be made to find out the specific reasons for the output decline.

[0113] Further development of step 220 is as follows.

[0114] In the complex environment of an open-pit mine area, the data detection system plays a crucial role in extracting valuable information from massive operation logs to provide data support for the safe and efficient operation of the mine area. Among them, the acquisition of target operation log linkage data state vector and past operation log linkage data state vector is two core functions of the data detection system.

[0115] First, let's understand the meaning of these two vectors. Simply put, they are both multi-dimensional vectors formed by encoding key data features extracted from the operation logs. These vectors contain critical information such as the working status of the equipment, environmental parameters, and other key information that can reflect the comprehensive operation status of the mining area system. The difference is that the target operation log linkage data state vector reflects the current operation status, while the past operation log linkage data state vector reflects the past operation status.

[0116] The process of obtaining these two vectors by the data detection system is actually a process of deep analysis and feature extraction of operation logs. The system will first read the real-time operation logs and past operation logs of the target open-pit mine, and then use advanced algorithms and techniques to clean, organize and format the logs to eliminate noise and redundant information in the original data.

[0117] Next, the system will use machine learning, natural language processing and other technologies to deeply analyze the cleaned logs. In this process, the system will identify and extract key data features from the logs, such as the working efficiency of the equipment, the failure rate, the communication quality, etc. These features not only reflect the operation status of a single device, but also integrate the linkage information related to other devices, environmental parameters, etc.

[0118] After extracting the key data features, the system will encode these features to form multi-dimensional linkage data state vectors. These vectors represent the comprehensive operation status of the mining area system in numerical form, making the originally complex and difficult-to-understand operation logs intuitive and easy to analyze.

[0119] In this way, the data detection system can obtain linkage data state vectors reflecting the current and past operation status of the mining area in real time. These vectors not only provide strong support for real-time monitoring of the mining area, but also provide important data basis for historical data analysis, trend prediction, fault diagnosis, etc. of the mining area. Management personnel can compare and analyze these vectors to timely discover problems and hidden dangers in the operation of the mining area, and develop effective intervention and adjustment measures to ensure the safe and efficient operation of the mining area.

[0120] In step 230, the relevant noun explanations are as follows.

[0121] First network quality evaluation vector: The first network quality evaluation vector refers to a multidimensional numerical vector formed by measuring and evaluating various key performance indicators (KPIs) of the network in a specific network environment or application scenario. This vector can comprehensively reflect the service quality, transmission efficiency, stability, and coverage range of the network. Specifically, this vector may include network delay, packet loss rate, throughput, signal strength, interference level, and other indicators. For example, in the data collection and transmission scenario of an open-pit mine area, the first network quality evaluation vector can be used to evaluate the performance of the 5G network in the mine area. For example, one dimension of the vector can be network delay to measure the speed of data transmission, and another dimension can be packet loss rate to reflect the reliability of data transmission. By analyzing the specific values of these dimensions, the actual performance of the network in the mine area can be understood, thereby providing a basis for optimizing network configuration or adjusting data transmission strategies.

[0122] Second network quality evaluation vector: The second network quality evaluation vector is similar to the first network quality evaluation vector, which is also a multidimensional numerical vector for evaluating network performance. The difference is that the second network quality evaluation vector may focus on different evaluation indicators or be applied to different network environments. It can be a supplement to the first vector, or it can be designed to compare or verify the results of the first vector. For example, in addition to the 5G network, other types of wireless networks (such as WiFi) are also deployed in the open-pit mine area. At this time, the second network quality evaluation vector can be used to specifically evaluate the performance of these other networks. This vector may include the same indicators as the first vector (such as delay, packet loss rate, etc.), but may also include some additional indicators specific to the network type (such as WiFi signal coverage or the number of interference sources, etc.).

[0123] Knowledge superposition: Knowledge superposition refers to the process of integrating and fusing knowledge or data from different sources and types in information processing or decision support systems. This process aims to create a more comprehensive and accurate information set to improve decision accuracy or system performance. Knowledge superposition may involve data cleaning, data fusion, feature extraction, model training, and other steps, and requires the use of various algorithms and technologies to achieve. For example, in the operation and management of an open-pit mine area, knowledge superposition can be used to improve the overall operational efficiency of the mine area. For example, information from device operation logs, environmental monitoring data, personnel activity records, and other sources can be superimposed and integrated. In this way, a more comprehensive view of the mine area operation can be obtained, including the working status of the equipment, the real-time changes of the environment, the activity trajectory of the personnel, etc. Based on this view, the maintenance needs of the equipment, the optimization of production plans, or the improvement of safety management levels can be more accurately predicted.

[0124] Target overlay description knowledge: Target overlay description knowledge refers to the comprehensive descriptive information about the target object (such as equipment, system or scene) formed or extracted during the process of knowledge overlay. These information are usually the comprehensive reflection of the characteristics and attributes of the target object in multiple aspects and multiple levels, which can provide comprehensive and in-depth support for decision-making or analysis. For example, taking an open-pit mine as an example, the target overlay description knowledge may include the detailed working parameters of various equipment in the mine, historical maintenance records, coordination relationship with other equipment, etc.; it may also include environmental information such as topography, climate conditions, resource distribution in the mine; and management information such as production process, safety management strategy, personnel allocation in the mine. After these information are integrated together, a comprehensive descriptive knowledge base about the operation of the open-pit mine is formed. Management personnel can make various complex analyses and decisions based on this knowledge base, such as optimizing equipment layout, adjusting production plan or developing emergency plan, etc.

[0125] Further expansion of step 230 is as follows.

[0126] In the daily operation of the open-pit mine, the data detection system plays a core role, and through in-depth analysis of the running log, it provides important support for network quality evaluation and knowledge overlay of the mine. In this process, the target running log linkage data state vector and the past running log linkage data state vector are key elements, which together constitute the basis for evaluating network quality and forming overlay description knowledge.

[0127] Firstly, the data detection system will generate a first network quality evaluation vector about the target open-pit mine running log according to the target running log linkage data state vector. This vector integrates multiple dimensional indicators of network performance under the current running state of the mine, such as delay, throughput, packet loss rate, etc., providing a real-time and comprehensive network quality evaluation tool for management personnel. Through this vector, management personnel can intuitively understand the performance of the current network in supporting the mine operation, and timely discover and solve potential network problems.

[0128] Then, the system not only considers the current network state, but also combines the past running log linkage data state vector to generate a second network quality evaluation vector about the past open-pit mine running log. This vector reflects the network performance trend in the past period of time, which helps management personnel analyze the stability, reliability and improvement space of network performance. By comparing the current and past network quality evaluation vectors, management personnel can identify the change pattern of network performance, providing data support for future network planning and optimization.

[0129] Finally, the data detection system superimposes the target open-pit mine operation log with the past open-pit mine operation log based on the first network quality evaluation vector and the second network quality evaluation vector. This process essentially combines current and past network performance data with the operational knowledge, experience rules, etc. of the mine, forming a more comprehensive and in-depth target superposition description knowledge. These knowledge not only contains direct indicators of network performance, but also integrates various indirect information related to mine operation and expert judgment, providing strong data support for the decision support system of the mine.

[0130] In this way, the data detection system not only improves the accuracy and comprehensiveness of the open-pit mine network quality evaluation, but also provides a powerful tool for knowledge management and decision optimization of the mine. Management personnel can more accurately grasp the network performance status of the mine and develop more scientific and reasonable operation strategies and maintenance plans, thereby ensuring the safety, efficiency and sustainable development of the mine.

[0131] In step 240, the relevant explanations are as follows.

[0132] Final network environment optimization recommendations (output by the data detection system): The final network environment optimization recommendations refer to the specific improvement recommendations for network configuration, performance, security, etc. output by the data detection system after the system conducts comprehensive data collection, analysis and evaluation on the network environment. These recommendations are based on the real-time monitoring of the network status and the deep mining of historical data by the system, aiming to help network administrators or operators improve the network environment and improve the overall performance and stability of the network. For example, in a certain open-pit mine, the data detection system continuously collects and analyzes the network environment data of the mine, including device status, network traffic, communication quality, etc. After a period of data accumulation and analysis, the system finds that the network environment of the mine has the following problems: high network latency, unstable communication between devices, insufficient network coverage in some areas, etc.

[0133] In view of these problems, the data detection system outputs the following final network environment optimization recommendations:

[0134] Optimize network layout: According to the actual work area and device distribution of the mine, adjust the position and number of wireless base stations to ensure that the network signal can fully cover the mine and reduce signal blind areas;

[0135] Upgrade network equipment: For network equipment with insufficient performance or aging, it is recommended to upgrade or replace to improve data transmission speed and stability;

[0136] Implement traffic management strategies: According to the monitoring results of network traffic, develop reasonable traffic management strategies, such as limiting the bandwidth occupation of non-critical applications to ensure the transmission priority of critical business data;

[0137] Strengthen network security protection: Suggest increasing network security devices such as firewalls, intrusion detection systems, etc. to improve network security and prevent unauthorized access and data leakage;

[0138] These optimization suggestions are based on the in-depth analysis and evaluation of the network environment by the data detection system, and have high pertinence and practicality. The mine administrator can make corresponding adjustments and optimizations to the network environment according to these suggestions, so as to improve the overall operational efficiency and safety of the mine.

[0139] Further expansion of step 240 is as follows.

[0140] The data detection system comprehensively uses the target running log linkage data state vector, target superposition description knowledge, and past open-pit mine running logs when determining the final network environment optimization suggestions corresponding to the target open-pit mine running log.

[0141] Firstly, the system deeply analyzes the target running log linkage data state vector, which reflects the current network environment running state and performance parameters of the mine in real time. By monitoring key indicators such as network delay, packet loss rate, and bandwidth utilization, the system can accurately identify problem areas such as network bottlenecks, communication failures, or performance degradation.

[0142] Secondly, the system combines target superposition description knowledge, which integrates historical experience of mine operation, expert rules, and trend analysis of network performance changes. This allows the system not only to understand the immediate state of the current network environment, but also to grasp its long-term evolution law and potential risks. By comparing the current state with historical data, the system can predict possible future network problems and develop corresponding optimization strategies in advance.

[0143] In addition, past open-pit mine running logs provide the system with rich historical data resources. These data record the performance and stability of the mine network under different time periods and different working conditions. The system can discover seasonal changes in network performance, periodic fluctuations, and network pressure patterns related to specific work activities by mining and analyzing these historical data.

[0144] Based on the above information, the data detection system uses advanced algorithms and models to comprehensively evaluate and optimize the network environment of the mine. It considers the rationality of network architecture, the appropriateness of device configuration, the efficiency of traffic management, and the tightness of security protection, etc. to generate a series of targeted optimization suggestions. These suggestions aim to improve the overall performance of the network, enhance the reliability and security of data transmission, and ensure the efficient and smooth operation of the mine.

[0145] Finally, the network environment optimization recommendations output by the data detection system are a comprehensive solution that combines real-time status monitoring, historical trend analysis, and forward-looking prediction, providing network administrators in the mining area with comprehensive, accurate, and practical guidance to help them create a more stable, efficient, and secure network environment.

[0146] As can be seen, the beneficial effects of the present application based on steps 210-240 mainly manifest in the following aspects:

[0147] By obtaining the target open-pit mine operation log stream in real time, the data detection system can ensure that the processed open-pit mine operation log data is up-to-date, thereby reflecting the current operating conditions of the target open-pit mine in a timely manner. This helps to improve the real-time and accuracy of network environment optimization recommendations;

[0148] By analyzing the target open-pit mine operation log in combination with the past open-pit mine operation log, the present application realizes the knowledge superposition of the open-pit mine operation log. This process not only considers the current network performance status, but also incorporates the knowledge of historical operation data, making the network environment optimization recommendations more comprehensive and in-depth;

[0149] By using the target operation log linkage data state vector and the past operation log linkage data state vector to generate the first network quality evaluation vector and the second network quality evaluation vector, the present application can quantify and evaluate the network performance trend of the target open-pit mine. This vector-based evaluation method helps to more accurately identify problem areas in the network environment, and thus propose more targeted optimization recommendations;

[0150] By comprehensively considering the target operation log linkage data state vector, the target superposition description knowledge, and the past open-pit mine operation log, the data detection system can determine the final network environment optimization recommendations. These recommendations combine real-time network status, historical network performance, and mining area operation knowledge, providing strong support for network environment optimization in open-pit mines;

[0151] The method provided by the present application realizes automatic generation of network environment optimization recommendations, greatly reducing the need for manual participation and improving the efficiency and accuracy of optimization work. At the same time, this method also has good universality and scalability, and can be applied to network environment optimization tasks in open-pit mines of different scales and types.

[0152] Further, the following will continue to illustrate the embodiments 1-7.

[0153] In embodiment 1, the technical solution of the present application is implemented in detail. First of all, it is necessary to clarify the composition of the target operating log linkage data state vector. This vector includes the first equipment state attention vector and the first environment monitoring attention vector corresponding to the target open-pit mine operating log. The equipment state attention vector mainly focuses on the running state of the mine equipment (such as excavators, transport vehicles, crushers, etc.), including its work efficiency, failure rate, maintenance situation and other information. The environment monitoring attention vector focuses on the environmental conditions of the mine, such as air quality, noise level, temperature and humidity, etc., which may affect the network performance.

[0154] Next, the technical solution enters the stage of generating the first network quality evaluation vector about the target open-pit mine operating log. This process is mainly completed through the time domain superposition processing network. The time domain superposition processing network is a deep learning network specially designed for processing time series data such as mine operating logs. It can capture the changes and correlations of data in the time dimension.

[0155] Specifically, first, the first equipment state attention vector and the first environment monitoring attention vector are entered into the time domain superposition processing network. This network has two residual connection branches, which are used to process these two types of attention vectors. Residual connection is a commonly used technique in deep learning, which can help the network better learn the features of the data, especially when the network has a large number of layers.

[0156] In the first residual connection branch, the first equipment state attention vector is processed by residual connection. This means that the network will learn the changes of the equipment state over time and capture the impact of these changes on network performance. The result after processing is called the first operating log residual semantic vector, which contains the semantic information of the changes of the equipment state on network performance.

[0157] Similarly, in the second residual connection branch, the first environment monitoring attention vector is processed by residual connection. This process will focus on the changes of the environmental conditions and evaluate how these changes affect network performance. The result after processing is called the second operating log residual semantic vector, which contains the semantic information of the changes of the environment monitoring on network performance.

[0158] Finally, the first operating log residual semantic vector and the second operating log residual semantic vector are performed semantic unit feature dot product. Dot product operation can measure the similarity of two vectors and fuse their semantic information together. In this way, the first network quality evaluation vector about the target open-pit mine operating log is obtained. This vector integrates the information of equipment state and environment monitoring, and can comprehensively and accurately reflect the network performance status of the mine.

[0159] Overall, the technical solution in Example 1 achieves efficient and accurate evaluation of the network environment in an open-pit mine area through fine data processing and the use of deep learning networks. This provides a solid foundation for subsequent optimization recommendations.

[0160] In Example 2, the technical solution further expands the processing range of the data state vector, covering the target open-pit mine operation log and the past open-pit mine operation log linked data state vector. This includes the first device state attention vector and the first environment monitoring attention vector corresponding to the target operation log, as well as the second device state attention vector and the second environment monitoring attention vector corresponding to the past operation log.

[0161] First, the system processes the past operation log linked data state vector, i.e., the second device state attention vector and the second environment monitoring attention vector. These two vectors reflect the historical information of the past mine area device state and environment monitoring. In order to effectively integrate these historical information with the current state, the system performs feature transfer operation. Feature transfer is a technique that applies knowledge learned from one domain or task to another related domain or task. Here, it is used to transfer the attention vectors of past device state and environment monitoring to the current network quality evaluation process.

[0162] Through the feature transfer operation, the system obtains the device state transfer vector corresponding to the second device state attention vector, and the environment monitoring transfer vector corresponding to the second environment monitoring attention vector. These two transfer vectors contain key information in the past mine area operation log, which have important reference value for the evaluation of current network quality.

[0163] Next, the system enters the first device state attention vector, the first environment monitoring attention vector, the device state transfer vector, and the environment monitoring transfer vector into the time domain superposition processing network. This network structure has been introduced in Example 1, which can process time series data and capture the changes and correlations of data in the time dimension.

[0164] Inside the time domain superposition processing network, the first residual connection branch is responsible for processing the device state and environment monitoring information of the current mine area. By performing residual connection processing on the first device state attention vector and the first environment monitoring attention vector, the network can learn the influence of device state changes and environmental condition changes in the current mine area operation log on network performance. The processing result is the target operation log residual semantic vector, which contains the semantic information of the current mine area network performance.

[0165] Meanwhile, the second residual connection branch processes the past mine site device state and environmental monitoring information that has undergone feature migration. By performing residual connection processing on the device state migration vector and the environmental monitoring migration vector, the network can capture the contribution of key information in the past mine site operation log to the current network performance evaluation. The processing result is a past operation log residual semantic vector, which reflects the semantic influence of the past mine site network performance on the current evaluation.

[0166] Finally, the system performs semantic unit feature point multiplication operation on the target operation log residual semantic vector and the past operation log residual semantic vector. This step effectively integrates the network performance information of the current mine site with the network performance information of the past mine site, generating a second network quality evaluation vector for the past open-pit mine site operation log. This vector not only considers the actual running state of the current mine site, but also incorporates the knowledge of historical operation data, making the network quality evaluation more comprehensive and in-depth.

[0167] In summary, the technical solution in Example 2 realizes efficient and accurate evaluation of the open-pit mine site network environment by introducing feature migration and time domain superposition processing network. This not only helps to timely discover and solve network problems, but also provides a strong guarantee for the safe and efficient operation of the mine site.

[0168] In Example 3, the core of the technical solution is to use a Naive Bayes classifier to determine the knowledge vector integration weight of different network quality evaluation vectors, and then realize the knowledge superposition of the target open-pit mine site operation log and the past open-pit mine site operation log. This process aims to generate more comprehensive and accurate knowledge description of the target open-pit mine site operation log to support subsequent network environment optimization work.

[0169] First, the system obtains a Naive Bayes classifier. Naive Bayes classifier is a classification method based on Bayes theorem and feature conditional independence, which is simple and efficient and has wide application in classification problems. Here, the Naive Bayes classifier is used to determine the knowledge vector integration weight corresponding to the network quality evaluation vector.

[0170] Next, the system determines the first knowledge vector integration weight for the target open-pit mine site operation log through the interaction of the Naive Bayes classifier and the first network quality evaluation vector (about the target open-pit mine site operation log). This weight reflects the importance of the current mine site network quality evaluation information in the knowledge superposition process. Specifically, the system will calculate the class probability corresponding to each feature value of the first network quality evaluation vector through the Naive Bayes classifier, and then obtain the first knowledge vector integration weight.

[0171] Likewise, the system also determines the second knowledge vector integration weight about the past open-pit mine operation log through the interaction of the second network quality evaluation vector (about the past open-pit mine operation log) with the naive Bayes classifier. This weight reflects the contribution degree of the past mine network quality evaluation information to the current knowledge superposition. The system will analyze the eigenvalues of the second network quality evaluation vector, and use the naive Bayes classifier to calculate the corresponding class probability, so as to obtain the second knowledge vector integration weight.

[0172] Finally, the system performs knowledge superposition on the target open-pit mine operation log and the past open-pit mine operation log based on the first knowledge vector integration weight and the second knowledge vector integration weight. This process is essentially an effective fusion of network quality evaluation information at two different time points. Through weighted superposition, the system can generate a more comprehensive and accurate target superposition description knowledge corresponding to the target open-pit mine operation log. This target superposition description knowledge not only contains the network performance information of the current mine, but also integrates the knowledge of historical operation data, providing strong data support for subsequent network environment optimization.

[0173] In summary, the technical solution in embodiment 3 realizes effective knowledge superposition of the target open-pit mine operation log and the past open-pit mine operation log by introducing the naive Bayes classifier to determine the knowledge vector integration weight. This method not only improves the accuracy of network quality evaluation, but also provides more reliable data support for the safe and efficient operation of the mine.

[0174] In embodiment 4, the technical solution further refines the knowledge superposition process to the quantized linear variables of network state, transmission packet loss and data delay. These quantized linear variables are key indicators for evaluating network performance, and by superimposing them, a more comprehensive and accurate network quality evaluation can be obtained.

[0175] First, the system obtains the target network state disturbance linear variable, the target transmission packet loss quantized linear variable and the target data delay quantized linear variable corresponding to the target open-pit mine operation log. These variables respectively reflect the stability of the mine network in the current state, the integrity of data transmission and the timeliness of data transmission. At the same time, the system also obtains the past superimposed network state disturbance linear variable, the past superimposed transmission packet loss quantized linear variable and the past superimposed data delay quantized linear variable corresponding to the past open-pit mine operation log. These past variables represent the performance of the mine network in the past period of time.

[0176] Next, the system superimposes the target transmission packet loss quantization linear variable and the past superimposed transmission packet loss quantization linear variable based on the first knowledge vector integration weight and the second knowledge vector integration weight. During the superimposition process, the size of the weight determines the contribution degree of the current state and the past state in the final superimposition result. Through superimposition, the system obtains the target superimposed transmission packet loss quantization linear variable corresponding to the target open-pit mine operation log, which comprehensively considers the current and past transmission packet loss conditions and provides more comprehensive data support for evaluating network performance.

[0177] Similarly, the system also superimposes the target network state disturbance linear variable and the past superimposed network state disturbance linear variable based on the weight to obtain the target superimposed network state disturbance linear variable corresponding to the target open-pit mine operation log. This variable reflects the overall performance of the mine network in terms of stability and disturbance, which helps to discover potential problems in the network in a timely manner.

[0178] In addition, the system also superimposes the target data delay quantization linear variable and the past superimposed data delay quantization linear variable to obtain the target superimposed data delay quantization linear variable corresponding to the target open-pit mine operation log. This variable measures the timeliness performance of data transmission, which is particularly important for application scenarios that require real-time response.

[0179] Finally, the system determines the target superimposed transmission packet loss quantization linear variable, the target superimposed network state disturbance linear variable, and the target superimposed data delay quantization linear variable as the target superimposed description knowledge corresponding to the target open-pit mine operation log. These knowledge not only contains the current network performance information, but also integrates the influence of historical data, providing strong data support and decision basis for network optimization of the mine.

[0180] In summary, the technical solution in embodiment 4 realizes more comprehensive and accurate evaluation of network performance by refining the superimposition process of knowledge. This method helps to improve the stability and transmission efficiency of the mine network, providing strong guarantee for safe production and efficient operation of the mine.

[0181] In embodiment 5, the technical solution mainly focuses on how to use the target operation log linkage data state vector, the target superimposed description knowledge, and the past open-pit mine operation log to determine the final network environment optimization suggestion for the target open-pit mine operation log. This process involves data integration, interaction, and output of optimization suggestions through a specific network.

[0182] Firstly, the system determines the target integrated interaction knowledge vector corresponding to the target open-pit mine operation log based on the target operation log linkage data state vector, the target superposition description knowledge, and the past open-pit mine operation log. This step is a data integration and interaction process, in which the target operation log linkage data state vector reflects the current mine equipment state and environmental monitoring situation, the target superposition description knowledge integrates the current and past network performance information, and the past open-pit mine operation log provides a reference for historical operation data. By effectively integrating and interacting these information, the system can generate a more comprehensive and targeted target integrated interaction knowledge vector, which contains key information for network environment optimization.

[0183] Next, the system inputs the target integrated interaction knowledge vector into the target network environment optimization detection network. This network is a neural network model specifically designed for analyzing and optimizing mine network environment, which can predict and optimize future network environment by learning historical data and current state. Here, the target integrated interaction knowledge vector is used as input data to train and optimize the network environment optimization detection network.

[0184] In the target network environment optimization detection network, the system outputs the final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the target integrated interaction knowledge vector. This process involves forward propagation and decision output of the neural network. Specifically, the network environment optimization detection network will perform a series of complex calculations and processing based on the input target integrated interaction knowledge vector, and finally output an optimization suggestion for the current mine network environment. This suggestion may include adjusting device configuration, optimizing network topology, improving environmental monitoring conditions, etc., aiming to improve the stability and transmission efficiency of the mine network.

[0185] In summary, the technical solution in embodiment 5 realizes precise optimization suggestion output for open-pit mine network environment by integrating and interacting information from multiple data sources and using neural network model for analysis and optimization. This method not only improves the pertinence and effectiveness of optimization suggestions, but also provides strong technical support for safe production and efficient operation of mines.

[0186] In embodiment 6, the technical solution details how to determine the target integrated interaction knowledge vector corresponding to the target open-pit mine operation log by combining the target operation log linkage data state vector, the target superposition description knowledge, and the past open-pit mine operation log. This process involves processing and integration of multiple vectors and features.

[0187] Firstly, the scheme mentions that the target operation log linkage data state vector contains the first device state attention vector and the first environment monitoring attention vector, while the past operation log linkage data state vector contains the second device state attention vector and the second environment monitoring attention vector. These vectors respectively represent the important features of the mine equipment and environment monitoring at the current and past time points.

[0188] Next, the system obtains the reference knowledge vector corresponding to the target open-pit mine operation log, which contains the first device state attention vector and the first environment monitoring attention vector. The reference knowledge vector may also contain other types of attention vectors, which together constitute a comprehensive description of the current mine operation state.

[0189] Subsequently, the system removes the first device state attention vector and the first environment monitoring attention vector from the reference knowledge vector to obtain the remaining attention vectors. These remaining vectors may contain other key information in addition to equipment and environment monitoring, such as personnel operation, process flow, etc.

[0190] Next, the system performs vector integration on the target superposition description knowledge, the first device state attention vector, the first environment monitoring attention vector, and the remaining attention vectors. This process is to fuse these vectors into an operation log integrated vector through some integration method (such as weighted average, splicing, etc.). The integrated vector integrates the multi-faceted information of the current mine, providing rich input for subsequent feature interaction.

[0191] Then, the system performs feature migration operations on the second device state attention vector and the second environment monitoring attention vector respectively. Feature migration is a machine learning technique that aims to apply knowledge learned from one domain to another related but different domain. Here, through feature migration, the system migrates the past device state and environment monitoring features to the current scenario, generating a device state migration vector and an environment monitoring migration vector.

[0192] Finally, the system performs feature interaction on the operation log integrated vector, the device state migration vector, and the environment monitoring migration vector. Feature interaction is to combine and interact the features in these vectors through some interaction mechanism (such as neural networks, decision trees, etc.) to capture their complex relationships and nonlinear dependencies. Through this interaction, the system can generate a target integrated interaction knowledge vector corresponding to the target open-pit mine operation log. This vector integrates the current and past information, as well as the deep knowledge obtained through feature migration and interaction, providing strong support for subsequent network environment optimization.

[0193] In embodiment 7, the technical solution elaborates on how to output the final network environment optimization suggestion corresponding to the target open-pit mine operation log based on the target integrated interactive knowledge vector in the target network environment optimization detection network. This process involves the generation of multiple simulation results, feature extraction, optimization decision-making, and suggestion updating.

[0194] Firstly, the system processes the target integrated interactive knowledge vector through the target network environment optimization detection network, generates the first operation log optimization simulation result and the second operation log optimization simulation result. These two simulation results are based on different optimization strategies and algorithms, representing different possibilities of network environment optimization schemes. At the same time, the system also extracts the first network environment optimization decision feature and the second network environment optimization decision feature related to these two simulation results. These features are key information extracted after in-depth analysis of the simulation results, used to guide subsequent optimization decisions.

[0195] Then, the system evaluates the two operation log optimization simulation results. The evaluation criteria include whether the simulation results contain error text and the feature recognition degree of the simulation results. Feature recognition degree refers to the matching degree of feature information in the simulation results with the actual state of the network environment. In this evaluation process, the first operation log optimization simulation result is determined to not contain error text, and its feature recognition degree is greater than that of the second operation log optimization simulation result. Therefore, the system selects the first operation log optimization simulation result as the basis for subsequent network environment optimization detection.

[0196] Then, the system uses the first network environment optimization decision feature to perform network environment optimization detection on the first operation log optimization simulation result and the second operation log optimization simulation result in the target network environment optimization detection network. This process is a verification and screening process of the simulation results, aiming to find the most optimized network environment configuration scheme. Through this detection process, the system generates the initial network environment optimization suggestion corresponding to the target open-pit mine operation log.

[0197] Finally, the system obtains the past network environment optimization suggestions corresponding to the past open-pit mine operation logs. These past suggestions are generated in the past network environment optimization process and contain valuable experience information. Then, the system uses the second network environment optimization decision feature to jointly update the initial network environment optimization suggestion and the past network environment optimization suggestion. This process is a knowledge fusion process, aiming to combine current and past knowledge to generate more comprehensive and accurate network environment optimization suggestions. Through this joint updating process, the system finally outputs the final network environment optimization suggestion corresponding to the target open-pit mine operation log.

[0198] Additionally, to further understand the above technical solutions, the conceptual role of various vectors in the above process can be illustrated by example numerical values.

[0199] Consider an open-pit mine site that contains various equipment (such as excavators, transport vehicles, etc.) and environmental monitoring stations (for monitoring temperature, humidity, wind speed, etc.). The system needs to optimize the mine site network environment based on the current equipment status and environmental monitoring data to ensure the stability and efficiency of data transmission.

[0200] Numerical example:

[0201] Target operation log linkage data state vector:

[0202] First equipment status attention vector (e.g., the status of an excavator): [0.8, 0.2] (where 0.8 represents the equipment is working, and 0.2 represents the equipment is in idle state);

[0203] First environmental monitoring attention vector (e.g., temperature monitoring): [0.6, 0.4] (where 0.6 represents normal temperature, and 0.4 represents high temperature);

[0204] Past operation log linkage data state vector:

[0205] Second equipment status attention vector (e.g., the status of an excavator in historical records): [0.5, 0.5];

[0206] Second environmental monitoring attention vector (e.g., temperature monitoring in historical records): [0.7, 0.3];

[0207] Reference knowledge vector:

[0208] This vector can be a higher-dimensional vector containing more information, such as the current status of other equipment in the mine site, staff activities, weather conditions, etc. However, for simplicity, only the above two aspects of information are considered, so the reference knowledge vector can be a combination of the two: [0.8, 0.2, 0.6, 0.4,...] (where... represents other unlisted attention vectors);

[0209] Remaining attention vector:

[0210] If the equipment status and environmental monitoring attention vectors are removed from the reference knowledge vector, the remaining part is the remaining attention vector. In this simplified example, no specific value of the remaining attention vector is given.

[0211] Operation log integrated vector:

[0212] By vector integration (e.g., by weighted average or concatenation, etc.) of the target overlay description knowledge (which can be a vector describing current network performance or historical network performance), the first device state attention vector, the first environment monitoring attention vector, and the remaining attention vectors, an integrated operational log vector that integrates multiple aspects of information can be obtained. The specific values will depend on the choice of integration method and the specific values of the input vectors.

[0213] Device state migration vector and environment monitoring migration vector:

[0214] By feature migration operations (e.g., using a certain transformation function or model to learn the relationship between historical data and current data) on the second device state attention vector and the second environment monitoring attention vector, corresponding device state migration vectors and environment monitoring migration vectors can be obtained. The specific values of these vectors will depend on the migration method and the characteristics of the historical data.

[0215] Target integrated interaction knowledge vector:

[0216] Finally, by feature interaction (e.g., using a neural network or other machine learning model to capture the complex relationships between them) of the integrated operational log vector, the device state migration vector, and the environment monitoring migration vector, a target integrated interaction knowledge vector can be obtained. The specific values of this vector will depend on the structure and parameters of the interaction model and the specific values of the input vectors.

[0217] It should be noted that the above numerical examples are only used to illustrate the concept and do not represent the specific values in actual applications. In actual applications, the dimensions and specific values of these vectors will be determined according to the specific data set and algorithm model. At the same time, the processing and conversion process of the vectors will be more complex and diverse.

[0218] The present application 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 a program for executing any of the above data detection methods based on open-pit mine 5G network optimization.

[0219] Further, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is running, it controls the device where the computer-readable storage medium is located to execute any of the above data detection methods based on open-pit mine 5G network optimization.

[0220] The embodiments of the present application provide a processor for running a program, wherein the program executes the above data detection method based on open-pit mine 5G network optimization when running.

[0221] The device provided by the embodiment of the present application comprises a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the steps of the data detection method based on the open-pit mine 5G network optimization when executing the program.

[0222] The device herein can be a server, a PC, a PAD, a mobile phone, etc.

[0223] A computer program product comprises a non-volatile computer readable storage medium, which stores a computer program, and the computer program implements the steps of the data detection method based on the open-pit mine 5G network optimization in the embodiments of the present application when executed by a processor.

[0224] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be realized by general computing devices, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, and can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, and in some cases, the steps shown or described can be executed in different orders, or they can be manufactured into individual integrated circuit modules or a single integrated circuit module. Therefore, the present application is not limited to any particular combination of hardware and software.

[0225] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0226] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks, can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions described in the flowcharts and / or block diagrams. Figure 1 Each flow or multiple flows and / or blocks Figure 1an apparatus to perform each function

[0227] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a Figure 1 one or more processes and / or blocks Figure 1 an apparatus to perform each function

[0228] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing processes Figure 1 one or more processes and / or blocks Figure 1 an apparatus to perform each function

[0229] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0230] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, about which the processor can execute instructions. The memory is an example of computer readable media.

[0231] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules 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 technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0232] It should also be noted that the terms "comprising," "including," or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0233] The preferred embodiments of the application are described above in detail. The application can be modified and changed in various ways by those skilled in the art without departing from the spirit and principles of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the application should be included in the protection scope of the application.

Claims

1. A data detection method based on 5G network optimization in open-pit mines, characterized in that, The method, applied to a data inspection system, includes: The target open-pit mine operation log and past open-pit mine operation logs are obtained from the target open-pit mine operation log stream. The target open-pit mine operation log stream is obtained by collecting and converting open-pit mine operation data in the target 5G network coverage area based on the target data text conversion cycle. The past open-pit mine operation log refers to the previous open-pit mine operation log in the target open-pit mine operation log stream. Obtain the target operation log linkage data status vector corresponding to the target open-pit mine operation log, and the past operation log linkage data status vector corresponding to the past open-pit mine operation log; Based on the target operation log linkage data state vector, a first network quality evaluation vector for the target open-pit mine operation log is generated. Based on the target operation log linkage data state vector and the past operation log linkage data state vector, a second network quality evaluation vector for the past open-pit mine operation log is generated. Based on the first network quality evaluation vector and the second network quality evaluation vector, the target open-pit mine operation log and the past open-pit mine operation log are overlaid to obtain the target overlay description knowledge corresponding to the target open-pit mine operation log. Based on the target operation log linkage data state vector, the target overlay description knowledge, and the past open-pit mine operation logs, the final network environment optimization suggestions corresponding to the target open-pit mine operation logs are determined. The step of superimposing the target open-pit mine operation log with the past open-pit mine operation logs based on the first network quality evaluation vector and the second network quality evaluation vector to obtain the target superimposed descriptive knowledge corresponding to the target open-pit mine operation log includes: obtaining a Naive Bayes classifier; determining a first knowledge vector integration weight for the target open-pit mine operation log using the Naive Bayes classifier and the first network quality evaluation vector; determining a second knowledge vector integration weight for the past open-pit mine operation logs using the Naive Bayes classifier and the second network quality evaluation vector; and superimposing the target open-pit mine operation log with the past open-pit mine operation logs based on the first knowledge vector integration weight and the second knowledge vector integration weight to obtain the target superimposed descriptive knowledge corresponding to the target open-pit mine operation log. The step of superimposing the target open-pit mine operation log with the past open-pit mine operation log based on the first knowledge vector integration weight and the second knowledge vector integration weight to obtain the target superimposed description knowledge corresponding to the target open-pit mine operation log includes: obtaining the target network state disturbance linear variable, the target transmission packet loss quantization linear variable, and the target data delay quantization linear variable corresponding to the target open-pit mine operation log; obtaining the past superimposed network state disturbance linear variable, the past superimposed transmission packet loss quantization linear variable, and the past superimposed data delay quantization linear variable corresponding to the past open-pit mine operation log; and superimposing the target transmission packet loss quantization linear variable with the past superimposed transmission packet loss quantization linear variable based on the first knowledge vector integration weight and the second knowledge vector integration weight to obtain the target open-pit mine operation log. The target superimposed transmission packet loss quantization linear variable is obtained; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target network state disturbance linear variable is superimposed with the past superimposed network state disturbance linear variable to obtain the target superimposed network state disturbance linear variable corresponding to the target open-pit mine operation log; based on the first knowledge vector integration weight and the second knowledge vector integration weight, the target data delay quantization linear variable is superimposed with the past superimposed data delay quantization linear variable to obtain the target superimposed data delay quantization linear variable corresponding to the target open-pit mine operation log; the target superimposed transmission packet loss quantization linear variable, the target superimposed network state disturbance linear variable, and the target superimposed data delay quantization linear variable are determined as the target superimposed descriptive knowledge corresponding to the target open-pit mine operation log.

2. The method according to claim 1, characterized in that, The target operation log linkage data status vector includes the first equipment status attention vector and the first environmental monitoring attention vector corresponding to the target open-pit mine operation log; The process of generating a first network quality evaluation vector for the target open-pit mine operation log based on the target operation log linkage data status vector includes: The first device state attention vector and the first environmental monitoring attention vector are entered into the time-domain overlay processing network; Through the first residual connection branch of the time-domain overlay processing network, the first device state attention vector and the first environmental monitoring attention vector are subjected to residual connection processing to obtain the first operation log residual semantic vector corresponding to the target open-pit mine operation log. Through the second residual connection branch of the time-domain overlay processing network, the first device state attention vector and the first environmental monitoring attention vector are subjected to residual connection processing to obtain the second operation log residual semantic vector corresponding to the target open-pit mine operation log. Perform a semantic unit feature dot product between the first operation log residual semantic vector and the second operation log residual semantic vector to obtain a first network quality evaluation vector for the operation log of the target open-pit mine.

3. The method according to claim 1, characterized in that, The target operation log linkage data status vector includes the first equipment status attention vector and the first environmental monitoring attention vector corresponding to the target open-pit mine operation log; the past operation log linkage data status vector includes the second equipment status attention vector and the second environmental monitoring attention vector corresponding to the past open-pit mine operation log. The step of generating a second network quality evaluation vector based on the target operation log linked data state vector and the past operation log linked data state vector includes: The second device state attention vector and the second environmental monitoring attention vector are subjected to feature transfer operations respectively to obtain the device state transfer vector corresponding to the second device state attention vector and the environmental monitoring transfer vector corresponding to the second environmental monitoring attention vector. The first device state attention vector, the first environmental monitoring attention vector, the device state transition vector, and the environmental monitoring transition vector are entered into the time-domain overlay processing network; Through the first residual connection branch of the time-domain overlay processing network, the first device state attention vector and the first environmental monitoring attention vector are subjected to residual connection processing to obtain the target operation log residual semantic vector corresponding to the target open-pit mine operation log. Through the second residual connection branch of the time-domain overlay processing network, the device state transition vector and the environmental monitoring transition vector are subjected to residual connection processing to obtain the past operation log residual semantic vector corresponding to the past open-pit mine operation log. The semantic unit feature dot product is performed between the target operation log residual semantic vector and the past operation log residual semantic vector to obtain the second network quality evaluation vector for the past open-pit mine operation log.

4. The method according to claim 1, characterized in that, The process of determining the final network environment optimization suggestions corresponding to the target open-pit mine's operation log based on the target operation log linkage data state vector, the target overlay description knowledge, and the past open-pit mine operation logs includes: Based on the target operation log linkage data status vector, the target superimposed description knowledge, and the past open-pit mine operation logs, determine the target integrated interactive knowledge vector corresponding to the target open-pit mine operation logs; The target integrated interactive knowledge vector is entered into the target network environment optimization detection network. In the target network environment optimization detection network, the final network environment optimization suggestions corresponding to the target open-pit mine operation log are output based on the target integrated interactive knowledge vector.

5. The method according to claim 4, characterized in that, The target operation log linkage data state vector includes a first device state attention vector and a first environmental monitoring attention vector; the past operation log linkage data state vector includes a second device state attention vector and a second environmental monitoring attention vector corresponding to the past open-pit mine operation logs; The process of determining the target integrated interactive knowledge vector corresponding to the target open-pit mine operation log based on the target operation log linkage data state vector, the target overlay description knowledge, and the past open-pit mine operation logs includes: Obtain the reference knowledge vector corresponding to the operation log of the target open-pit mine area; the reference knowledge vector includes the first equipment status attention vector and the first environmental monitoring attention vector. The attention vectors other than the first device state attention vector and the first environmental monitoring attention vector in the reference knowledge vector are determined as the remaining attention vectors; The target superimposed description knowledge, the first equipment state attention vector, the first environmental monitoring attention vector, and the remaining attention vector are vector integrated to obtain the operation log integration vector corresponding to the target open-pit mine operation log. The second device state attention vector and the second environmental monitoring attention vector are subjected to feature transfer operations respectively to obtain the device state transfer vector corresponding to the second device state attention vector and the environmental monitoring transfer vector corresponding to the second environmental monitoring attention vector. By performing feature interaction on the operation log integration vector, the device state transition vector, and the environmental monitoring transition vector, a target integrated interaction knowledge vector corresponding to the target open-pit mine operation log is obtained.

6. The method according to claim 4, characterized in that, In the target network environment optimization detection network, based on the target integrated interactive knowledge vector, the final network environment optimization suggestions corresponding to the target open-pit mine operation log are output, including: The target network environment optimization detection network is used to determine the first operation log optimization simulation result, the second operation log optimization simulation result, the first network environment optimization decision feature, and the second network environment optimization decision feature corresponding to the target integrated interaction knowledge vector; the first operation log optimization simulation result does not contain erroneous text, and the feature recognition degree of the first operation log optimization simulation result is greater than that of the second operation log optimization simulation result. In the target network environment optimization detection network, the first operation log optimization simulation result and the second operation log optimization simulation result are used to perform network environment optimization detection through the first network environment optimization decision feature to obtain the initial network environment optimization suggestion corresponding to the target open-pit mine operation log; Obtain past network environment optimization suggestions corresponding to the past open-pit mine operation logs, and jointly update the initial network environment optimization suggestions and the past network environment optimization suggestions through the second network environment optimization decision features to obtain the final network environment optimization suggestions corresponding to the target open-pit mine operation logs.

7. 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 based on an open-pit mine 5G network optimization as described in any one of claims 1 to 6.

8. 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 based on open-pit mine 5G network optimization as described in any one of claims 1 to 6.

Images