A Status Monitoring Method and System for 5G Base Station Migration in Open-Pit Mines

Abstract

This application relates to the field of data processing technology, specifically to a method and system for monitoring the migration status of 5G base stations in open-pit mines. It provides a method for the layout and signal monitoring of 5G base stations in open-pit mines. By combining spatiotemporal state migration vectors and signal state monitoring vectors, it achieves comprehensive and dynamic monitoring of the migration status of target open-pit mine 5G base stations. This method has advantages such as real-time performance, accuracy, flexibility, and high visualization, and is expected to solve the problems and challenges of traditional methods in open-pit mine environments.

Description

Technical Field

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

[0002] As open-pit mines continue to expand in scale and increase in automation, the application of 5G base stations in these mines has become particularly important. 5G base stations not only provide mines with high-speed, stable communication networks but also support intelligent applications such as driverless mining trucks and remote monitoring. However, the complex and ever-changing environment of open-pit mines, including undulating terrain and frequent equipment movement, presents significant challenges to the deployment and signal coverage of 5G base stations.

[0003] Traditional 5G base station deployment and signal monitoring methods are often based on static models and datasets, which cannot reflect the real-time changes in the status and signal performance of base stations during migration. This leads to blind spots or overlapping areas in the signal coverage of base stations in dynamic environments such as open-pit mines, seriously affecting communication quality and the operational efficiency of the mine. Summary of the Invention

[0004] To address the technical problems existing in related technologies, this application provides a status monitoring method and system for the migration of 5G base stations in open-pit mines.

[0005] In a first aspect, embodiments of this application provide a status monitoring method based on the migration of 5G base stations in open-pit mines, applied to a status monitoring system, the method comprising:

[0006] The spatiotemporal state transition vector and signal state monitoring vector of the target open-pit mine 5G base station are obtained. The spatiotemporal state transition vector of the target open-pit mine 5G base station is generated based on the base station layout model dataset corresponding to the target open-pit mine 5G base station.

[0007] Based on the spatiotemporal state transition vector, the signal state monitoring vector is dynamically adapted to obtain the signal adaptation representation vector.

[0008] Knowledge integration is performed on the signal adaptation representation vector and the spatiotemporal state transition vector to obtain the first linkage state integrated transition knowledge;

[0009] The signal status monitoring vector of the target open-pit mine 5G base station is mapped to the base station layout model relationship network corresponding to the spatiotemporal state transition vector to obtain the status monitoring layout mapping vector.

[0010] The state monitoring layout mapping vector is integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector.

[0011] In conjunction with the first aspect, in one possible implementation of the first aspect, dynamic adaptation processing is performed on the signal state monitoring vector based on the spatiotemporal state transition vector to obtain a signal adaptation representation vector, including:

[0012] The spatiotemporal state migration vector of the target open-pit mine 5G base station is mapped to the signal state relationship network corresponding to the signal state monitoring vector to obtain the spatiotemporal state mapping vector.

[0013] Determine the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector from the signal state monitoring vector;

[0014] Based on the local signal state monitoring vector, several error features of the spatiotemporal state mapping vector relative to the local signal state monitoring vector are identified;

[0015] The signal adaptation representation vector is obtained based on the aforementioned error features and the spatiotemporal state mapping vector.

[0016] In conjunction with the first aspect, in one possible implementation of the first aspect, obtaining the signal adaptation representation vector based on the plurality of error features and the spatiotemporal state mapping vector includes:

[0017] The aforementioned error features are aggregated into the spatiotemporal state mapping vector to obtain several spatiotemporal state mapping perturbation vectors;

[0018] The spatiotemporal state mapping perturbation vectors are fused according to the feature description level to obtain the signal adaptation representation vector corresponding to the spatiotemporal state mapping vector.

[0019] In conjunction with the first aspect, in one possible implementation of the first aspect, determining the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector in the signal state monitoring vector includes:

[0020] The signal state monitoring vector is subjected to pyramid state vector pooling to obtain several state pooling vector relationship spectra;

[0021] State vector derivation is performed on the plurality of state pooling vector relation spectra respectively to obtain a plurality of first state derived vector relation spectra, wherein the derivative parameters of the plurality of first state derived vector relation spectra are the same relative to the signal state monitoring vector;

[0022] The plurality of first state derived vector relation spectra are integrated by state vector integration to obtain a second state derived vector relation spectrum;

[0023] The local signal state monitoring vector corresponding to the spatiotemporal state mapping vector is determined in the second state-derived vector relation spectrum.

[0024] In conjunction with the first aspect, in one possible implementation of the first aspect, the state monitoring method for 5G base station migration in open-pit mines is implemented by a state monitoring processing algorithm; wherein the method further includes:

[0025] Based on the migration knowledge integrated from the first linkage state, base station migration label identification is performed to obtain the first base station migration label identification result.

[0026] Obtain the first base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station;

[0027] Based on the first base station migration tag identification result and the first base station migration tag identification annotation, a first algorithm debugging evaluation variable is determined, and the status monitoring processing algorithm is debugged based on the first algorithm debugging evaluation variable.

[0028] In conjunction with the first aspect, in one possible implementation of the first aspect, the signal status monitoring vector of the target open-pit mine 5G base station is mapped to the base station layout model relationship network corresponding to the spatiotemporal state transition vector to obtain the status monitoring layout mapping vector, including:

[0029] The signal state monitoring vector is subjected to pyramid state vector pooling to obtain several state pooling vector relationship spectra;

[0030] The plurality of state pooling vector relationship spectra are respectively mapped to the base station layout model relationship network to obtain a plurality of state monitoring layout mapping vectors. The plurality of state monitoring layout mapping vectors are then integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector.

[0031] In conjunction with the first aspect, in one possible implementation of the first aspect, the plurality of state pooling vector relationship spectra include a third state derived vector relationship spectrum, and the plurality of state monitoring layout mapping vectors include a first state monitoring layout mapping vector, wherein the first state monitoring layout mapping vector is obtained by mapping the third state derived vector relationship spectrum; wherein mapping the plurality of state pooling vector relationship spectra to the base station layout model relationship network respectively to obtain the plurality of state monitoring layout mapping vectors includes:

[0032] Knowledge vector mining is performed on the integrated transfer knowledge of the first linkage state to obtain the integrated transfer knowledge of the second linkage state.

[0033] The second linkage state integration transfer knowledge is mapped to the signal state relationship network corresponding to the signal state monitoring vector to obtain the first linkage signal state monitoring vector;

[0034] The first linkage signal state monitoring vector and the third state derived vector relationship spectrum are integrated to obtain the signal state monitoring vector of the first integrated spatiotemporal data.

[0035] The signal state monitoring vector of the first integrated spatiotemporal data is mapped to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the first state monitoring layout mapping vector.

[0036] In conjunction with the first aspect, in one possible implementation of the first aspect, the plurality of state pooling vector relationship spectra include a fourth state derived vector relationship spectrum, wherein the fourth state derived vector relationship spectrum has different feature recognition degrees from the third state derived vector relationship spectrum; the plurality of state monitoring layout mapping vectors include a second state monitoring layout mapping vector, wherein the second state monitoring layout mapping vector is obtained by mapping the fourth state derived vector relationship spectrum; wherein, mapping the plurality of state pooling vector relationship spectra to the base station layout model relationship network respectively to obtain the plurality of state monitoring layout mapping vectors further includes:

[0037] Knowledge embedding is performed on the second linkage state integration transfer knowledge to obtain the third linkage state integration transfer knowledge;

[0038] The second state monitoring layout mapping vector is mapped onto the signal state relationship network to obtain the second linkage signal state monitoring vector;

[0039] The second linkage signal state monitoring vector is integrated with the fourth state derived vector relationship spectrum to obtain the signal state monitoring vector of the second integrated spatiotemporal data.

[0040] The signal state monitoring vector of the second integrated spatiotemporal data is mapped to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the second state monitoring layout mapping vector.

[0041] In conjunction with the first aspect, in one possible implementation of the first aspect, the state monitoring layout mapping vector is integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector, including:

[0042] The third linkage state integration transfer knowledge is embedded to obtain the fourth linkage state integration transfer knowledge;

[0043] The first state monitoring layout mapping vector, the second state monitoring layout mapping vector, and the fourth linkage state integration migration knowledge are integrated to obtain the target 5G base station migration state monitoring vector.

[0044] In conjunction with the first aspect, in one possible implementation of the first aspect, the third state-derived vector relation spectrum includes target signal state monitoring vector elements; wherein, mapping the signal state monitoring vector of the first integrated spatiotemporal data to the base station layout model relation network corresponding to the spatiotemporal state transition vector to obtain the first state monitoring layout mapping vector includes:

[0045] A first feature focusing operation is performed on the signal state monitoring vector of the first integrated spatiotemporal data to obtain a first signal state monitoring focus vector.

[0046] A second feature focusing operation is performed on the signal state monitoring vector of the first integrated spatiotemporal data to obtain a second signal state monitoring focus vector.

[0047] Determine the knowledge mapping path that maps the target signal status monitoring vector elements to the base station layout model relationship network;

[0048] Feature labeling is performed on the knowledge mapping path to obtain several mapping path labeling results;

[0049] Based on the second signal state monitoring focus vector, the signal state mapping thermodynamic features corresponding to the third state derived vector relationship spectrum are identified;

[0050] Based on the first signal state monitoring focus vector, the trend mapping thermal features corresponding to the third state derived vector relationship spectrum are identified;

[0051] Based on the signal state mapping thermal characteristics and the trend mapping thermal characteristics, the mapping results corresponding to the several mapping path marking results are determined;

[0052] The mapping result corresponding to the mapping path marking result is mapped to the base station layout model relationship network to obtain the mapping path marking variable. Based on the mapping path marking variable, the monitoring layout mapping is performed to obtain the first state monitoring layout mapping vector.

[0053] In conjunction with the first aspect, in one possible implementation of the first aspect, the state monitoring method for 5G base station migration in open-pit mines is implemented by a state monitoring processing algorithm; wherein, the method further includes:

[0054] Determine the thermal index corresponding to the several mapping path marking results;

[0055] The ideal thermal characteristics of the signal state mapping are determined based on the thermal characteristics of the signal state mapping and the thermal indices corresponding to the several mapping path marking results.

[0056] Determine the spatiotemporal state transition vector corresponding to the target signal state monitoring vector element;

[0057] Determine the heat index after mapping the spatiotemporal state transition vector corresponding to the target signal state monitoring vector element to the signal state relationship network;

[0058] Based on the thermal index of the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element after mapping to the signal state relationship network and the ideal thermal characteristics of the signal state mapping, a second algorithm debugging and evaluation variable is determined, and the state monitoring processing algorithm is debugged based on the second algorithm debugging and evaluation variable.

[0059] In conjunction with the first aspect, in one possible implementation of the first aspect, the state monitoring layout mapping vector is integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector, including: performing adjustable monitoring layout mapping on the state monitoring layout mapping vector to obtain an adjustable spatiotemporal state migration vector; and integrating the adjustable spatiotemporal state migration vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector.

[0060] The state monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a state monitoring processing algorithm. The method further includes: performing base station migration label identification on the migration state monitoring vector of the target 5G base station to obtain a second base station migration label identification result; obtaining the second base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station; determining a third algorithm debugging and evaluation variable based on the second base station migration label identification result and the second base station migration label identification annotation, and debugging the state monitoring processing algorithm based on the third algorithm debugging and evaluation variable.

[0061] Secondly, this application also provides a status monitoring system, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the aforementioned status monitoring methods based on the migration of 5G base stations in open-pit mines.

[0062] Thirdly, this application also provides a computer storage medium containing instructions that, when executed on a processor, implement the above-described method.

[0063] This application proposes a method for monitoring the migration status of 5G base stations based on spatiotemporal state migration vectors and signal state monitoring vectors. First, by acquiring the spatiotemporal state migration vector of the target open-pit mine 5G base station, the location changes of the base station in time and space can be accurately tracked. This step utilizes a base station layout model dataset to ensure the accuracy and reliability of the migration vectors.

[0064] Secondly, traditional signal status monitoring methods often cannot adapt to changes in base station location, leading to distorted or ineffective monitoring results. To overcome this deficiency, this application dynamically adapts the signal status monitoring vector based on spatiotemporal state transition vectors, reflecting real-time changes in the signal status of the base station during migration. This dynamic adaptation method can adaptively adjust signal monitoring parameters according to changes in the base station's location, thereby improving the flexibility and accuracy of signal status monitoring.

[0065] However, relying solely on spatiotemporal state transition vectors and signal state monitoring vectors is insufficient to comprehensively describe the overall state and changing trends of a base station during migration. Therefore, this application further integrates these two vectors to obtain first-linkage state integrated transition knowledge. This knowledge integration method can fuse information from two different sources to form a more comprehensive description of the base station state, providing strong data support for subsequent state monitoring and decision support.

[0066] Furthermore, to more intuitively display the signal status and migration trajectory of the base station, this application also maps the signal status monitoring vector to the base station layout model relationship network corresponding to the spatiotemporal state migration vector, obtaining the status monitoring layout mapping vector. This mapping method can intuitively display the signal status and migration process of the base station in three-dimensional space, improving the visualization of status monitoring.

[0067] Finally, to form a more complete and accurate description of the migration state, this application integrates the state monitoring layout mapping vector with the migration knowledge of the first linkage state to obtain the target 5G base station migration state monitoring vector. This integration method can fuse the location information and signal status information of the base station during the migration process with other relevant information during the migration process, providing mine managers with real-time migration status and signal status information, as well as predictive data to support decision-making.

[0068] In summary, this application relates to a method for the layout and signal monitoring of 5G base stations in open-pit mines. By combining spatiotemporal state migration vectors and signal state monitoring vectors, it achieves comprehensive and dynamic monitoring of the migration status of target open-pit mine 5G base stations. This method has advantages such as real-time performance, accuracy, flexibility, and high visualization, and is expected to solve the problems and challenges of traditional methods in open-pit mine environments. Attached Figure Description

[0069] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0070] Figure 1A hardware structure block diagram of a mobile terminal for performing a state monitoring method based on the migration of a 5G base station in an open-pit mine, according to an embodiment of this application, is shown.

[0071] Figure 2 This is a flowchart illustrating a status monitoring method for 5G base station migration in an open-pit mine, as provided in an embodiment of this application.

[0072] The above figures include the following reference numerals:

[0073] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0074] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0075] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0076] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0077] As described in the background section, existing traditional 5G base station deployment and signal monitoring methods are often based on static models and datasets, which cannot reflect the status changes and signal performance of base stations during migration in real time. This leads to blind spots or overlapping areas in the signal coverage of base stations in dynamic environments such as open-pit mines, seriously affecting communication quality and mine operation efficiency. To solve the above problems, embodiments of this application provide a status monitoring method and system for 5G base station migration in open-pit mines.

[0078] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0079] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a status monitoring method for 5G base station migration in an open-pit mine, according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0080] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0081] This embodiment provides a status monitoring method for the migration of 5G base stations in open-pit mines, which runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0082] Based on this, please refer to Figure 2 , Figure 2 This is a flowchart illustrating a status monitoring method for 5G base station migration in an open-pit mine, provided in an embodiment of this application. The method is applied to a status monitoring system and may further include steps 210-250.

[0083] Step 210: Obtain the spatiotemporal state transition vector and signal state monitoring vector of the target open-pit mine 5G base station. The spatiotemporal state transition vector of the target open-pit mine 5G base station is generated based on the base station layout model dataset corresponding to the target open-pit mine 5G base station.

[0084] Step 220: Based on the above spatiotemporal state transition vector, perform dynamic adaptation processing on the above signal state monitoring vector to obtain the signal adaptation representation vector.

[0085] Step 230: Integrate the above signal adaptation representation vector and the above spatiotemporal state transition vector to obtain the first linkage state integrated transition knowledge.

[0086] Step 240: Map the signal status monitoring vector of the target open-pit mine 5G base station to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the status monitoring layout mapping vector.

[0087] Step 250: Integrate the above-mentioned status monitoring layout mapping vector with the above-mentioned first linkage status integration migration knowledge to obtain the target 5G base station migration status monitoring vector.

[0088] One application scenario covered in this application is in a large open-pit mine. As mining progresses and the work area expands, the existing 5G base stations need to be relocated to maintain good signal coverage. To ensure the stability and signal continuity of the base stations during the relocation process, a status monitoring system is deployed to monitor the entire process.

[0089] The status monitoring system first acquired the spatiotemporal state migration vector and signal status monitoring vector of the target open-pit mine 5G base station. These vectors were obtained by analyzing a base station layout model dataset, which records in detail the base station's location, altitude, orientation, and relative relationship with other base stations. The spatiotemporal state migration vector describes the base station's movement trajectory in time and space, while the signal status monitoring vector reflects changes in the base station's signal strength.

[0090] Based on the acquired spatiotemporal state transition vector, the state monitoring system performs dynamic adaptation processing on the signal state monitoring vector. This means that when the base station location changes, the system adjusts the parameters of the signal monitoring vector according to the new location information to ensure accurate measurement of signal strength. After this processing, the system obtains a signal adaptation representation vector, which more accurately reflects the signal state of the base station at different locations.

[0091] Next, the state monitoring system integrates the signal adaptation representation vector and the spatiotemporal state transition vector. The purpose of this step is to fuse information from two different sources to form a more comprehensive description of the base station's state. Through this integration process, the system obtains the first linked state integrated transition knowledge, which includes the base station's location changes, signal strength changes, and the correlation information between them during the migration process.

[0092] To more intuitively display the migration status and signal changes of base stations, the status monitoring system maps the signal status monitoring vectors of the target open-pit mine 5G base stations onto a base station layout model network. This network is a three-dimensional model that simulates the actual environment of the open-pit mine and marks the location and signal coverage of each base station. By mapping the signal status monitoring vectors onto this model, the system obtains a status monitoring layout mapping vector, which can intuitively display the signal strength and coverage of the base stations in the model space.

[0093] Finally, the status monitoring system integrates the status monitoring layout mapping vector with the first linkage status integration migration knowledge. The purpose of this step is to fuse the base station's location and signal status information in the model space with other relevant information during the migration process (such as migration speed and direction) to form a more complete migration status monitoring vector. This vector not only contains the base station's current status information but also predicts the base station's status change trend over a future period, providing strong support for open-pit mine operational decisions.

[0094] Another application scenario covered in this application is in a vast open-pit mine where heavy machinery is operating, and one of the keys to ensuring smooth operation is stable 5G signal coverage. As the work area moves, the 5G base stations also need to be relocated. To ensure uninterrupted signal and consistent service quality during the relocation process, an advanced status monitoring system is implemented. The following is a detailed workflow of this system.

[0095] The status monitoring system first connects to the mine's central database to obtain the spatiotemporal state migration vector and signal status monitoring vector of the target open-pit 5G base station. This data has been carefully calibrated and verified by mine engineers to ensure it accurately reflects the actual status of the base station. The spatiotemporal state migration vector includes migration information such as the base station's location, speed, and direction, while the signal status monitoring vector records key indicators such as the base station's signal strength and stability. After acquiring this data, the system preprocesses it, including data cleaning and format conversion, to ensure it meets the requirements for subsequent analysis.

[0096] Next, the state monitoring system dynamically adapts the signal state monitoring vector based on the spatiotemporal state transition vector. This means that when a base station moves, the system adjusts the parameters of the signal monitoring vector in real time to reflect the signal state at the new location. This step is crucial because changes in the base station's location directly affect signal propagation and reception. To achieve dynamic adaptation, the system employs an advanced algorithm model that predicts changes in signal strength based on changes in the base station's location and adjusts the parameters of the signal monitoring vector accordingly. Thus, even when the base station is in motion, the system can accurately measure and monitor its signal state.

[0097] After dynamic adaptation processing, the system obtains the integrated result of the signal adaptation representation vector and the spatiotemporal state transition vector. The purpose of this step is to fuse information from two different sources to form a more comprehensive description of the base station's state. Through this integration process, the system can not only understand the signal state of the base station at different locations but also grasp the overall state and trends of the base station during its migration. To achieve knowledge integration, the system employs a deep learning-based fusion algorithm model. This model can automatically learn and extract key information from the two vectors and then fuse them together to form a new integrated vector. This integrated vector contains information about the base station's location changes, signal strength changes, and their interrelationships during the migration process, providing strong data support for subsequent state monitoring and decision support.

[0098] To more intuitively display the migration status and signal changes of base stations, the status monitoring system maps the signal status monitoring vectors of the target open-pit mine's 5G base stations onto a base station layout model network. This network is a high-precision 3D model that simulates the actual environment of the open-pit mine in detail, and marks the location, altitude, direction, and signal coverage range of each base station. By mapping the signal status monitoring vectors onto this model, the system obtains a status monitoring layout mapping vector, which can intuitively display the changes in signal strength and coverage range of the base stations in the model space. To achieve 3D mapping and visualization, the system employs an advanced graphics rendering technology. Through this technology, the system can present the signal status of the base stations graphically to mine managers, helping them to more intuitively understand the migration status and signal changes of the base stations. This is of great significance for timely detection of potential problems, optimization of migration plans, and improvement of mine operational efficiency.

[0099] Finally, the status monitoring system integrates the status monitoring layout mapping vector with the first linkage status integration migration knowledge for final processing. The purpose of this step is to fuse the base station's location and signal status information in the model space with other relevant information during the migration process (such as migration speed, direction, machine operating status, etc.) to form a more complete migration status monitoring vector. This vector not only contains the base station's current status information but also predicts the base station's status change trend over a future period. The target 5G base station migration status monitoring vector obtained through this final integration process is a comprehensive and accurate status description. It provides mine managers with real-time migration and signal status information, as well as predictive data to support decision-making. Based on this information, managers can promptly adjust migration plans, optimize signal coverage layouts, and take necessary maintenance measures to ensure the stable operation of base stations and continuous signal coverage. This is of great significance for improving the operational efficiency of open-pit mines, ensuring operational safety, and enhancing overall competitiveness.

[0100] To facilitate understanding of the above technical solutions, the technical terms appearing in steps 210-250 are explained below.

[0101] Targeted open-pit mine 5G base stations refer to 5G communication base stations deployed in specific open-pit mine environments. These base stations not only bear the important task of providing stable, high-speed 5G network services to the mine, but also need to adapt to the complex and ever-changing working environment of open-pit mines, such as harsh weather conditions, the movement of large amounts of machinery and equipment, and constantly changing work areas. Therefore, the design, deployment, and maintenance of targeted open-pit mine 5G base stations require consideration of higher durability, flexibility, and security. They are typically equipped with advanced communication equipment and antenna systems to ensure good signal coverage in every corner of the mine, thereby supporting the intelligent and automated operation needs of the mine, such as driverless mining trucks, remote monitoring, and control.

[0102] A spatiotemporal state transition vector is a vector describing the state changes of a target object (such as a 5G base station) in the temporal and spatial dimensions. In the context of an open-pit mine, this vector specifically refers to the set of state information of the 5G base station during its migration process, including its location, speed, direction, and timestamp. This state information is represented in a vectorized manner, facilitating mathematical analysis and calculation. The spatiotemporal state transition vector not only records the historical migration trajectory of the base station but can also be used to predict future migration trends and location changes, providing crucial information for network planning and optimization in the mine.

[0103] The signal status monitoring vector is a set of data metrics used to track and evaluate the signal status of 5G base stations in real time. This vector includes key parameters such as base station signal strength, stability, interference level, and data transmission rate. By continuously monitoring changes in these parameters, signal problems can be detected promptly, and corresponding optimization measures can be taken to ensure that the communication quality of the mining farm remains at its optimal level. The signal status monitoring vector is often used in conjunction with the spatiotemporal state transition vector to achieve dynamic adaptation and optimization of the signal status during base station migration.

[0104] The base station layout model dataset is a dataset containing the layout information of all 5G base stations within a target area. In the open-pit mine scenario, this dataset records detailed information such as the location coordinates, altitude, antenna configuration, power settings, and relative relationships with other base stations for each base station. This data was collected through various methods including on-site surveys, drone aerial photography, and Geographic Information Systems (GIS), and after processing and analysis, a comprehensive and accurate base station layout model was formed. This model not only provides fundamental data support for network planning and optimization in mines, but can also be used to simulate and predict network performance under complex scenarios such as base station migration and signal coverage changes.

[0105] Dynamic adaptation refers to the process of dynamically adjusting and optimizing the relevant parameters or configurations of a target object (such as a 5G base station) based on its real-time state changes to ensure optimal performance or meet specific requirements under different environments. In the scenario of 5G base stations in open-pit mines, dynamic adaptation specifically refers to adjusting the parameters of the signal state monitoring vector in real time based on the spatiotemporal state migration vector of the base station to accurately reflect the signal state changes during the base station's movement. This process is necessary because the location and speed of the base station directly affect the signal propagation and reception quality. Through dynamic adaptation, the system can track and optimize the signal state of the base station in real time, ensuring the continuity and stability of communication services during migration.

[0106] The signal adaptation representation vector, obtained through dynamic adaptation processing, is a set of vectors used to describe the signal performance of a 5G base station in different locations or states. This vector contains optimized and adjusted signal state parameters, such as signal strength, signal-to-noise ratio, and interference level, enabling a more accurate reflection of the base station's signal state in its actual operating environment. As the result of dynamic adaptation processing, the signal adaptation representation vector considers not only the base station's own performance characteristics but also the impact of external environmental factors (such as terrain, buildings, and other electromagnetic interference sources) on signal propagation. Therefore, this vector provides mine managers with more accurate and comprehensive signal state information, helping them better monitor and optimize base station performance.

[0107] Knowledge integration refers to the process of fusing and integrating knowledge or data from different sources, formats, or representations to form a more comprehensive, consistent, and easily understood and used knowledge body. In the scenario of 5G base stations in open-pit mines, knowledge integration specifically refers to the fusion and processing of information from two different sources: signal adaptation representation vectors and spatiotemporal state transition vectors, to form a more complete description of the base station's state. This process requires the use of advanced algorithms and models, such as deep learning and data mining, to automatically learn and extract key information from the two vectors and fuse them together to form a new integrated vector. Through knowledge integration, the system can gain a more comprehensive understanding of the base station's state changes and performance during the migration process, providing strong data support for subsequent state monitoring and decision support.

[0108] The first integrated migration knowledge refers to a comprehensive knowledge system with a linkage effect obtained by integrating the spatiotemporal state migration vector and signal state monitoring vector of the base station during the migration of 5G base stations in open-pit mines. This knowledge system not only includes the state information of the base station at different times and spatial locations (such as position, speed, and direction), but also integrates the changes in the base station's signal state (such as signal strength and stability) and the correlation between them. This integrated knowledge can comprehensively and accurately describe the overall state and performance of the base station during the migration process, while revealing the mutual influence and linkage effects between different state parameters. Through this integrated knowledge, managers can gain a deeper understanding of the base station's operating status and migration patterns, providing strong decision support for optimizing migration plans, improving signal coverage quality, and ensuring the stable operation of the mine's communication network.

[0109] The base station layout model is a complex and sophisticated network model that details the spatial layout and interrelationships of all 5G base stations in an open-pit mine. This network not only includes basic information such as the specific location, altitude, and orientation of each base station, but also deeply illustrates signal coverage overlap areas, potential interference zones, and the possibility of collaborative operation between base stations. Through this model, mine managers can intuitively understand the overall communication coverage of the mine, thereby optimizing the layout and configuration of base stations to ensure signal continuity and stability. Furthermore, the base station layout model provides crucial foundational data support for subsequent migration planning and status monitoring.

[0110] The status monitoring layout mapping vector is a vector representation obtained by mapping the signal status monitoring vector of a 5G base station to the network of relationships in the base station layout model. This vector not only contains the signal status information of the base station at a specific time and spatial location (such as signal strength and stability), but also integrates the spatial relationships and network topology information in the base station layout model. Through this mapping, managers can intuitively see the signal coverage and changing trends of the base station in the model space, thereby more accurately grasping the operating status and performance of the base station. The status monitoring layout mapping vector is one of the key technologies for realizing the visualization and monitoring of the status of 5G base stations in open-pit mines.

[0111] The target 5G base station migration status monitoring vector is a comprehensive vector that integrates the spatiotemporal and signal status information of the target open-pit mine 5G base station during its migration process. This vector not only records migration status parameters such as the base station's location, speed, and direction, but also incorporates key performance indicators such as signal strength and stability. Through this vector, managers can track the base station's status changes and signal performance in real time during the migration process, promptly identifying and resolving potential problems. The target 5G base station migration status monitoring vector is one of the important bases for realizing dynamic management and optimization decisions for 5G base stations in open-pit mines, providing stable and efficient communication service guarantees for the mine.

[0112] This application provides a comprehensive and dynamic method for monitoring the migration status of a 5G base station in a target open-pit mine by combining the spatiotemporal state migration vector and the signal state monitoring vector. Specifically, the beneficial effects of this application are mainly reflected in the following aspects.

[0113] First, by obtaining the spatiotemporal state migration vector of the target open-pit mine 5G base station, this application can accurately track the location changes of the base station in time and space, providing basic data support for subsequent dynamic adaptation processing. This step utilizes a base station layout model dataset to ensure the accuracy and reliability of the migration vector.

[0114] Secondly, this application dynamically adapts the signal state monitoring vector based on the spatiotemporal state transition vector to obtain a signal adaptation representation vector. This step can reflect the signal state changes of the base station during the migration process in real time, ensuring the real-time performance and accuracy of signal state monitoring. Through dynamic adaptation processing, this application can adaptively adjust the signal monitoring parameters to adapt to changes in the base station's location, thereby improving the flexibility and accuracy of signal state monitoring.

[0115] Furthermore, this application integrates knowledge from the signal adaptation representation vector and the spatiotemporal state transition vector to obtain the first linked state integration transition knowledge. This step integrates information from two different sources to form a more comprehensive description of the base station state. Through knowledge integration, this application can reveal the overall state and change trend of the base station during the migration process, providing strong data support for subsequent state monitoring and decision support.

[0116] Furthermore, this application maps the signal status monitoring vector of the target open-pit mine 5G base station to the base station layout model relationship network corresponding to the spatiotemporal state migration vector, obtaining the status monitoring layout mapping vector. This step can intuitively display the signal status and migration trajectory of the base station in the model space, improving the visualization of status monitoring. Through mapping processing, managers can more intuitively understand the operating status and migration process of the base station, thereby promptly identifying potential problems and taking corresponding optimization measures.

[0117] Finally, this application integrates the state monitoring layout mapping vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. This step can fuse the base station's location information and signal status information during the migration process with other relevant information to form a more complete and accurate migration state description. Through final integration processing, this application can provide mine managers with real-time migration and signal status information, as well as predictive data to support decision-making, improving the operational efficiency of open-pit mines, ensuring operational safety, and enhancing overall competitiveness.

[0118] In summary, this application achieves comprehensive and dynamic monitoring of the migration status of 5G base stations in target open-pit mines by combining spatiotemporal state migration vectors and signal state monitoring vectors, and has the advantages of real-time performance, accuracy, flexibility and high degree of visualization.

[0119] In some possible embodiments, step 220 describes the dynamic adaptation processing of the signal state monitoring vector based on the spatiotemporal state transition vector to obtain the signal adaptation representation vector, including steps 221-224.

[0120] Step 221: Map the spatiotemporal state migration vector of the above-mentioned target open-pit mine 5G base station to the signal state relationship network corresponding to the above-mentioned signal state monitoring vector to obtain the spatiotemporal state mapping vector.

[0121] Step 222: Determine the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector in the above signal state monitoring vector.

[0122] Step 223: Based on the above local signal state monitoring vector, identify several error features of the above spatiotemporal state mapping vector relative to the above local signal state monitoring vector.

[0123] Step 224: Based on the above error features and the above spatiotemporal state mapping vector, obtain the above signal adaptation representation vector.

[0124] In some possible embodiments, the process described in step 220 of dynamically adapting the signal state monitoring vector based on the spatiotemporal state transition vector to obtain the signal adaptation representation vector can be further refined into steps 221 to 224. The following are detailed examples and explanations of these steps.

[0125] In step 221, the system first maps the spatiotemporal state migration vector of the target open-pit mine 5G base station (which describes the location changes of the base station in time and space) to the signal state relationship network corresponding to the signal state monitoring vector. The signal state relationship network is a complex network model that reflects the interrelationships and influences between the signal states of base stations. Through the mapping operation, the system can obtain a spatiotemporal state mapping vector that integrates the spatiotemporal state information of the base station and relevant information from the signal state relationship network.

[0126] Next, the system determines the corresponding local signal state monitoring vector from the signal state monitoring vector based on the spatiotemporal state mapping vector. The local signal state monitoring vector refers to the portion of the signal state monitoring vector associated with the spatiotemporal state mapping vector, which reflects the signal state information of the base station at a specific time and spatial location.

[0127] In step 223, the system identifies error characteristics between the spatiotemporal state mapping vector and the local signal state monitoring vector. These error characteristics may include differences in signal strength, fluctuations in signal-to-noise ratio, etc., reflecting the difference between the actual and expected changes in the signal state of the base station during migration. By identifying these error characteristics, the system can more accurately understand the changes in the base station's signal state.

[0128] Finally, the system generates a signal adaptation representation vector based on several identified error features and spatiotemporal state mapping vectors. This signal adaptation representation vector, obtained after dynamic adaptation processing, is a set of vectors used to describe the signal performance of the base station during migration. It integrates the spatiotemporal state information and signal state information of the base station, enabling it to more accurately reflect the signal state of the base station in the actual operating environment. Through the signal adaptation representation vector, the system can provide more accurate and comprehensive data support for subsequent state monitoring and decision support.

[0129] In summary, these steps together constitute a technical solution for dynamically adapting signal state monitoring vectors based on spatiotemporal state transition vectors. Through this solution, the system can track and optimize the signal state of base stations in real time, ensuring the continuity and stability of communication services during migration. This is of great significance for scenarios requiring high-speed, stable communication networks, such as open-pit mines.

[0130] In the following steps, step 224, which obtains the signal adaptation representation vector based on the aforementioned error features and the aforementioned spatiotemporal state mapping vector, includes: aggregating the aforementioned error features into the aforementioned spatiotemporal state mapping vector to obtain a number of spatiotemporal state mapping perturbation vectors; and fusing the aforementioned number of spatiotemporal state mapping perturbation vectors according to the feature description level to obtain the signal adaptation representation vector corresponding to the aforementioned spatiotemporal state mapping vector.

[0131] In the following steps, step 224 specifically describes how to obtain the signal adaptation representation vector based on several error features and spatiotemporal state mapping vectors. This process can be further subdivided into the following two sub-steps.

[0132] First, the system aggregates several error features into a spatiotemporal state mapping vector, obtaining several spatiotemporal state mapping perturbation vectors. In this process, each error feature is considered individually and combined with the original spatiotemporal state mapping vector. This combination is achieved through a specific algorithm or mathematical model; for example, the error feature can be added as a weighting factor or perturbation term to the spatiotemporal state mapping vector to obtain a new vector, namely the spatiotemporal state mapping perturbation vector. Each error feature generates a corresponding spatiotemporal state mapping perturbation vector, and these vectors retain the original spatiotemporal state information while incorporating the influence of the error feature.

[0133] Secondly, the system fuses several spatiotemporal state mapping perturbation vectors according to feature description levels to obtain the signal adaptation representation vector corresponding to the spatiotemporal state mapping vector. Here, "feature description level" refers to the level or perspective of the signal state described by different error features. For example, some error features may describe changes in signal strength, while others may describe fluctuations in signal-to-noise ratio. Based on these different description levels, the system uses appropriate fusion methods (such as weighted averaging, maximum value selection, feature concatenation, etc.) to fuse several spatiotemporal state mapping perturbation vectors into a comprehensive vector, i.e., the signal adaptation representation vector. This vector considers both the spatiotemporal state changes of the base station and the actual changes in signal state, thus more accurately reflecting the signal performance of the base station during migration.

[0134] Through this processing flow, the system can dynamically adapt to and accurately monitor the signal status of 5G base stations in the target open-pit mine. This is of great significance for ensuring the stability and reliability of the open-pit mine's communication network, and also provides strong data support for the intelligent application of the mine.

[0135] In the following steps, step 222, determining the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector from the aforementioned signal state monitoring vector, includes: performing pyramidal state vector pooling on the aforementioned signal state monitoring vector to obtain several state pooling vector relationship spectra; performing state vector derivation on each of the aforementioned several state pooling vector relationship spectra to obtain several first state derived vector relationship spectra, wherein the aforementioned several first state derived vector relationship spectra have the same derivation parameters relative to the aforementioned signal state monitoring vector; performing state vector integration on the aforementioned several first state derived vector relationship spectra to obtain a second state derived vector relationship spectrum; and determining the aforementioned local signal state monitoring vector corresponding to the aforementioned spatiotemporal state mapping vector from the aforementioned second state derived vector relationship spectrum.

[0136] In the following steps, step 222 details how to determine the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector in the signal state monitoring vector. This process can be further subdivided into the following four sub-steps.

[0137] First, the system performs pyramid state vector pooling on the signal state monitoring vector to obtain several state pooling vector relationship spectra. Pyramid state vector pooling is a multi-level, multi-scale feature extraction method that can abstract and aggregate information in the signal state monitoring vector according to different levels and scales, thereby obtaining a series of state pooling vector relationship spectra. These relationship spectra describe the features and relationships of the signal state at different levels and scales.

[0138] Secondly, the system performs state vector derivation on several state pooling vector relation spectra to obtain several first-state derived vector relation spectra. State vector derivation is a transformation or extension method based on the original state vectors, which can generate new, more expressive state vectors. In this process, the system uses the same derivation parameters to process each state pooling vector relation spectrum, ensuring that the generated first-state derived vector relation spectra are compared and integrated in the same feature space.

[0139] Next, the system integrates several first-state derived vector relation spectra to obtain a second-state derived vector relation spectrum. State vector integration is a method that fuses multiple state vectors into a more comprehensive and integrated vector. In this process, the system employs appropriate integration strategies (such as weighted averaging, feature concatenation, etc.) to fuse several first-state derived vector relation spectra into a single second-state derived vector relation spectrum. This relation spectrum integrates signal state information at multiple levels and scales, enabling a more comprehensive description of the base station's signal state.

[0140] Finally, the system determines the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector in the second state-derived vector relation spectrum. This step is achieved by searching for the part associated with the spatiotemporal state mapping vector in the second state-derived vector relation spectrum. The system can find the part that best matches or is most similar to the spatiotemporal state mapping vector in the second state-derived vector relation spectrum according to certain matching criteria or similarity measurement methods, and use it as the local signal state monitoring vector. This local signal state monitoring vector reflects the signal state information of the base station at a specific time and spatial location, and is an important input for subsequent dynamic adaptation processing.

[0141] Through this processing flow, the system can accurately extract the local signal state monitoring vector associated with the spatiotemporal state mapping vector from the signal state monitoring vector, providing an accurate data foundation for the subsequent generation of signal adaptation representation vectors. This helps ensure accurate monitoring and optimization of the signal state of 5G base stations in open-pit mines during migration.

[0142] In some alternative embodiments, the above-mentioned state monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a state monitoring processing algorithm; wherein the above method further includes steps 310-330.

[0143] Step 310: Based on the migration knowledge integrated from the first linkage state mentioned above, perform base station migration tag identification to obtain the first base station migration tag identification result.

[0144] Step 320: Obtain the first base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the above-mentioned target open-pit mine 5G base station.

[0145] Step 330: Based on the above-mentioned first base station migration tag identification results and the above-mentioned first base station migration tag identification annotations, determine the first algorithm debugging evaluation variables, and debug the above-mentioned status monitoring and processing algorithm based on the above-mentioned first algorithm debugging evaluation variables.

[0146] In some alternative embodiments, the status monitoring method for 5G base station migration in open-pit mines is implemented through a status monitoring processing algorithm. This method not only includes the steps described above, but also adds steps 310 to 330 for further optimization and debugging of the status monitoring processing algorithm.

[0147] In step 310, the system integrates migration knowledge based on the first linkage state to identify base station migration tags, obtaining the first base station migration tag identification result. Here, "integrated migration knowledge based on the first linkage state" likely refers to knowledge and experience accumulated in similar scenarios or experiments, which is integrated and used to guide the current base station migration tag identification process. By applying this knowledge, the system can more accurately identify tags related to base station migration, which may include the type of migration, the stage of migration, key events during the migration process, etc. The first base station migration tag identification result is a concretization and quantification of these tags, reflecting the system's understanding and judgment of the current base station migration state.

[0148] In step 320, the system obtains the first base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station. These annotations may be manually marked or interpreted by experts or experienced operators based on the actual migration situation of the base station and related data. They provide reference standards or true values ​​for the base station migration label identification results, which are used for comparison and verification in the subsequent algorithm debugging and evaluation process.

[0149] In step 330, the system determines the first algorithm debugging and evaluation variable based on the first base station migration tag identification result and the first base station migration tag identification annotation. This variable may be the difference between the identification result and the annotation, the accuracy, recall, or F1 score of the identification result, etc., reflecting the performance of the state monitoring processing algorithm on the base station migration tag identification task. By determining this evaluation variable, the system can quantify the algorithm's performance and perform subsequent debugging and optimization work accordingly. The debugging process may include adjusting the algorithm's parameters, improving the algorithm's structure, or introducing new features, aiming to improve the accuracy and stability of the algorithm on the base station migration tag identification task.

[0150] In summary, these additional steps enable the condition monitoring processing algorithm to better adapt to the specific scenarios and needs of 5G base station migration in open-pit mines, improving the accuracy and effectiveness of condition monitoring. Simultaneously, through continuous debugging and optimization, the algorithm's performance will be continuously improved, providing stronger support for intelligent applications in open-pit mines.

[0151] In some preferred embodiments, mapping the signal state monitoring vector of the target open-pit mine 5G base station to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the state monitoring layout mapping vector includes: performing pyramid state vector pooling on the signal state monitoring vector to obtain several state pooling vector relationship spectra; mapping the several state pooling vector relationship spectra to the base station layout model relationship network to obtain several state monitoring layout mapping vectors, and integrating the several state monitoring layout mapping vectors with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector.

[0152] In some preferred embodiments, the system performs a process of mapping the signal status monitoring vector of the target open-pit mine 5G base station to the base station layout model relationship network corresponding to the spatiotemporal state transition vector, in order to obtain the status monitoring layout mapping vector. This process can be further subdivided into the following steps.

[0153] First, the system performs pyramid state vector pooling on the signal state monitoring vector. Pyramid state vector pooling is a multi-level, multi-scale feature extraction method, similar to a pyramid structure in image processing. In this process, the system abstracts and aggregates the information of the signal state monitoring vector according to different levels and scales, resulting in several state pooling vector relation spectra. Each relation spectrum contains feature information of the original signal state monitoring vector at different levels and scales.

[0154] Next, the system maps these state pooling vector relationship spectra to the base station layout model relationship network. The base station layout model relationship network is a network model describing the layout and interrelationships of base stations, reflecting their spatial distribution and connectivity. By mapping the state pooling vector relationship spectra to this network, the system can combine the characteristics of the signal state monitoring vectors with the base station layout and interrelationships to obtain several state monitoring layout mapping vectors. These mapping vectors not only contain signal state information but also incorporate the characteristics of the base station layout and interrelationships.

[0155] Finally, the system integrates these status monitoring layout mapping vectors with the first linked state integrated migration knowledge. This first linked state integrated migration knowledge comprises knowledge and experience accumulated during previous migration processes, containing valuable information about the base station migration status. By integrating this knowledge, the system can combine the current status monitoring layout mapping vector with previous migration knowledge, thereby obtaining a more comprehensive and accurate target 5G base station migration status monitoring vector. This vector not only reflects the current signal status and base station layout but also incorporates previous migration experience and knowledge, providing strong support for subsequent migration decisions and status monitoring.

[0156] Through this processing flow, the system can effectively combine the characteristics of the signal status monitoring vector with the layout and interrelationships of the base stations, and optimize and improve it using prior migration knowledge, thereby obtaining a more accurate and reliable target 5G base station migration status monitoring vector. This is of great significance for ensuring the stability and reliability of 5G base stations in open-pit mines during the migration process, and also provides strong data support for the intelligent application of mining operations.

[0157] In the following steps, the aforementioned plurality of state pooling vector relation spectra include a third state derived vector relation spectrum, and the aforementioned plurality of state monitoring layout mapping vectors include a first state monitoring layout mapping vector, wherein the first state monitoring layout mapping vector is obtained by mapping the aforementioned third state derived vector relation spectrum; wherein, mapping the aforementioned plurality of state pooling vector relation spectra to the aforementioned base station layout model relation network to obtain a plurality of state monitoring layout mapping vectors includes: performing knowledge vector mining on the aforementioned first linkage state integration migration knowledge to obtain second linkage state integration migration knowledge; mapping the aforementioned second linkage state integration migration knowledge to the signal state relation network corresponding to the aforementioned signal state monitoring vector to obtain a first linkage signal state monitoring vector; integrating the aforementioned first linkage signal state monitoring vector with the aforementioned third state derived vector relation spectrum to obtain a signal state monitoring vector of the first integrated spatiotemporal data; and mapping the aforementioned signal state monitoring vector of the first integrated spatiotemporal data to the base station layout model relation network corresponding to the aforementioned spatiotemporal state migration vector to obtain the aforementioned first state monitoring layout mapping vector.

[0158] In the following steps, the system processes several state pooling vector relation spectra to generate state monitoring layout mapping vectors. These relation spectra include a third-state derived vector relation spectrum, which is a set of features extracted from the original signal data using a specific algorithm, reflecting the changes in signal state at different dimensions and levels.

[0159] First, the system performs knowledge vector mining on the integrated transfer knowledge of the first linkage state. This is a process of transforming transfer knowledge into a computationally usable form. Through mining, the system obtains the integrated transfer knowledge of the second linkage state. This knowledge is a refinement and expansion of the original transfer knowledge, containing more regular information about the changes in signal state during base station migration.

[0160] Next, the system integrates the transfer knowledge of the second linkage state and maps it to the signal state relation network corresponding to the signal state monitoring vector. The signal state relation network is a network model describing the relationships between signal states, reflecting the correlation of signal states in different times and spaces. Through mapping, the system obtains the first linkage signal state monitoring vector, which integrates the information from the transfer knowledge and the signal state relation network, and can more accurately reflect the changes in the signal state during the transfer process.

[0161] Then, the system integrates the first linkage signal state monitoring vector with the third state derived vector relationship spectrum. The integration process fuses information from two sources to generate a more comprehensive and accurate signal state description. Through integration, the system obtains the first integrated spatiotemporal data signal state monitoring vector, which simultaneously contains the signal state change patterns and spatiotemporal characteristics.

[0162] Finally, the system maps the signal state monitoring vector of the first integrated spatiotemporal data to the base station layout model relationship network corresponding to the spatiotemporal state migration vector. The base station layout model relationship network is a network model describing the relationship between base station layout and signal propagation, reflecting the spatial distribution of base stations and signal propagation paths. Through mapping, the system obtains the first state monitoring layout mapping vector, which closely integrates changes in signal state with the layout and signal propagation relationship of base stations, providing strong support for subsequent migration decisions and state monitoring.

[0163] This processing flow fully leverages information from migration knowledge, signal state relationship networks, and base station layout model relationship networks. Through multi-level mapping and integration operations, it generates a state monitoring layout mapping vector that accurately reflects changes in signal state during the migration process. This is crucial for ensuring the signal stability and continuity of 5G base stations in open-pit mines during migration, and also provides a reliable data foundation for intelligent applications in mines.

[0164] In a further step, the aforementioned plurality of state pooling vector relation spectra include a fourth state derived vector relation spectrum, the fourth state derived vector relation spectrum having different feature recognition degrees from the third state derived vector relation spectrum, and the aforementioned plurality of state monitoring layout mapping vectors include a second state monitoring layout mapping vector, wherein the second state monitoring layout mapping vector is obtained by mapping the aforementioned fourth state derived vector relation spectrum; wherein, mapping the aforementioned plurality of state pooling vector relation spectra to the aforementioned base station layout model relation network to obtain a plurality of state monitoring layout mapping vectors further includes: embedding the aforementioned second linkage state integration migration knowledge to obtain third linkage state integration migration knowledge; mapping the aforementioned second state monitoring layout mapping vector to the aforementioned signal state relation network to obtain a second linkage signal state monitoring vector; integrating the aforementioned second linkage signal state monitoring vector with the aforementioned fourth state derived vector relation spectrum to obtain a signal state monitoring vector of the second integrated spatiotemporal data; and mapping the aforementioned signal state monitoring vector of the second integrated spatiotemporal data to the base station layout model relation network corresponding to the aforementioned spatiotemporal state migration vector to obtain the aforementioned second state monitoring layout mapping vector.

[0165] In a further step, the system processes several state pooling vector relation spectra to generate more state monitoring layout mapping vectors. These relation spectra include a fourth state-derived vector relation spectrum, which differs from the previously mentioned third state-derived vector relation spectrum in feature recognition, meaning that the signal state features they focus on or extract are different.

[0166] First, the system embeds the integrated transfer knowledge of the second linkage state. Knowledge embedding is a method that transforms knowledge into vector representation, embedding discrete knowledge elements into a continuous vector space while preserving the correlation between knowledge elements. Through knowledge embedding, the system obtains the integrated transfer knowledge of the third linkage state, which is a further refinement and abstraction of the integrated transfer knowledge of the second linkage state, containing richer and deeper transfer knowledge information.

[0167] Next, the system maps the previously obtained second state monitoring layout mapping vector to the signal state relationship network. This mapping process involves corresponding and matching the state monitoring layout mapping vector with the relationships between signal states to obtain the second linkage signal state monitoring vector. This vector not only contains information about the state monitoring layout but also incorporates the relationships between signal states, enabling a more comprehensive reflection of the changes in signal states during the migration process.

[0168] Then, the system integrates the second linkage signal state monitoring vector with the fourth state-derived vector relationship spectrum. The integration process fuses and integrates information from both sources to generate a more comprehensive and accurate description of the signal state. Through integration, the system obtains a second integrated spatiotemporal data signal state monitoring vector, which simultaneously contains the signal state change patterns and spatiotemporal characteristics, as well as information on the state monitoring layout.

[0169] Finally, the system maps the signal state monitoring vector of the second integrated spatiotemporal data to the base station layout model relationship network corresponding to the spatiotemporal state migration vector. This mapping process involves corresponding and matching the signal state monitoring vector with the base station layout model to obtain the second state monitoring layout mapping vector. This vector closely integrates the changes in signal state with the layout and interrelationships of base stations, providing more accurate and comprehensive data support for subsequent migration decisions and state monitoring.

[0170] This processing flow, through multi-level and multi-angle information extraction and fusion, fully utilizes information from migration knowledge, signal state relationship networks, and base station layout model relationship networks to generate a more comprehensive and accurate state monitoring layout mapping vector. This is of great significance for ensuring the signal stability and continuity of 5G base stations in open-pit mines during migration, and also provides a more reliable and accurate data foundation for intelligent applications in mines.

[0171] Under other design approaches, the aforementioned state monitoring layout mapping vector is integrated with the aforementioned first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. This includes: embedding the aforementioned third linkage state integration migration knowledge to obtain fourth linkage state integration migration knowledge; and integrating the aforementioned first state monitoring layout mapping vector, the aforementioned second state monitoring layout mapping vector, and the aforementioned fourth linkage state integration migration knowledge to obtain the aforementioned target 5G base station migration state monitoring vector.

[0172] In other design approaches, the system employs a different method to integrate the state monitoring layout mapping vector with the first linkage state integration migration knowledge to generate the target 5G base station migration state monitoring vector. This process can be divided into the following steps.

[0173] First, the system performs knowledge embedding on the integrated transfer knowledge of the third linkage state. Knowledge embedding is a technique that transforms knowledge into vector representations, embedding discrete knowledge elements into a continuous vector space while preserving the relationships between knowledge elements. Through knowledge embedding, the system obtains the integrated transfer knowledge of the fourth linkage state, which is a further refinement and abstraction of the integrated transfer knowledge of the third linkage state, containing richer and deeper levels of transfer knowledge information.

[0174] Next, the system prepares to perform an integration operation. In this step, the system needs to integrate the first-state monitoring layout mapping vector, the second-state monitoring layout mapping vector, and the newly acquired fourth-state linkage migration knowledge. These vectors and knowledge all contain important information about the migration status of 5G base stations. By integrating them together, the system can obtain a more comprehensive and accurate migration status monitoring vector.

[0175] The integration process is achieved through a specific algorithm that effectively fuses and integrates information from different sources. During this process, the system needs to ensure that information from each source is fully utilized and that information from different sources complements each other, thereby generating a more accurate and reliable migration state monitoring vector.

[0176] Finally, through integrated operations, the system obtained the target 5G base station migration status monitoring vector. This vector not only contains information from the first and second state monitoring layout mapping vectors, but also incorporates the content of the fourth linkage state integrated migration knowledge. Therefore, it can more comprehensively and accurately reflect the state changes of the 5G base station during the migration process, providing strong support for subsequent migration decisions and status monitoring.

[0177] This design approach fully leverages existing state monitoring layout mapping vectors and migration knowledge, generating more accurate and reliable target 5G base station migration state monitoring vectors through effective integration operations. This is crucial for ensuring the stability and reliability of 5G base stations during migration, and also provides strong data support for the intelligent management and maintenance of base stations.

[0178] In some examples, the aforementioned third-state derived vector relation spectrum includes target signal state monitoring vector elements; wherein, mapping the signal state monitoring vector of the aforementioned first integrated spatiotemporal data to the base station layout model relation network corresponding to the aforementioned spatiotemporal state transition vector to obtain the aforementioned first state monitoring layout mapping vector includes: performing a first feature focusing operation on the signal state monitoring vector of the aforementioned first integrated spatiotemporal data to obtain a first signal state monitoring focus vector; performing a second feature focusing operation on the signal state monitoring vector of the aforementioned first integrated spatiotemporal data to obtain a second signal state monitoring focus vector; determining the knowledge mapping path for mapping the aforementioned target signal state monitoring vector elements to the aforementioned base station layout model relation network; and in the aforementioned knowledge mapping... Feature marking is performed on the transmission path to obtain several mapping path marking results; based on the second signal state monitoring focus vector, the signal state mapping thermal features corresponding to the third state derived vector relationship spectrum are identified; based on the first signal state monitoring focus vector, the trend mapping thermal features corresponding to the third state derived vector relationship spectrum are identified; based on the signal state mapping thermal features and the trend mapping thermal features, the mapping results corresponding to the several mapping path marking results are determined; the mapping results corresponding to the mapping path marking results are mapped to the base station layout model relationship network to obtain mapping path marking variables, and monitoring layout mapping is performed based on the mapping path marking variables to obtain the first state monitoring layout mapping vector.

[0179] In some examples, the third-state derived vector relation spectrum specifically includes target signal state monitoring vector elements. These elements are key parts of the relation spectrum and are crucial for subsequent mapping and monitoring processes. To obtain the first-state monitoring layout mapping vector, the system needs to perform a series of detailed steps involving the processing and analysis of signal state monitoring vectors from integrated spatiotemporal data.

[0180] First, the system performs a first feature-focusing operation on the signal state monitoring vector of the first integrated spatiotemporal data. Feature focusing is a method that emphasizes specific features in a vector. Through this operation, the system can obtain a first signal state monitoring focus vector. This vector highlights certain key features in the original data, making these features more significant in subsequent processing.

[0181] Next, the system performs a second feature-focusing operation on the signal state monitoring vector of the same integrated spatiotemporal data. Unlike the first feature-focusing operation, this operation may emphasize different feature sets or use different focusing methods to obtain a second signal state monitoring focus vector. This vector provides another perspective on the original data, increasing the diversity of information.

[0182] Then, the system determines the knowledge mapping path that maps the target signal state monitoring vector elements to the base station layout model network. The knowledge mapping path is the bridge connecting the signal state monitoring vector elements and the base station layout model network; it specifies how to map the monitoring vector information onto the layout model. Determining the mapping path may involve a deep understanding of the base station layout and signal propagation characteristics.

[0183] After determining the knowledge mapping paths, the system performs feature labeling on these paths. Feature labeling adds extra information or tags to the mapping paths to indicate specific attributes or features of the paths. Through feature labeling, the system obtains several mapping path labeling results, which enrich the information content of the original mapping paths.

[0184] Next, the system identifies the signal state mapping thermal features corresponding to the third state derived vector relationship spectrum based on the second signal state monitoring focus vector. Thermal features are a visualization method used to display hotspots or high-value areas in the data. By identifying the signal state mapping thermal features, the system can understand which regions or states have higher signal strength or quality.

[0185] Simultaneously, the system also identifies the trend mapping thermal features corresponding to the third-state derived vector relationship spectrum based on the first signal state monitoring focus vector. Unlike signal state mapping thermal features, trend mapping thermal features focus on the trend of signal state changes over time or space. By identifying these trends, the system can predict possible changes in future signal states.

[0186] Finally, the system combines the signal state mapping thermal characteristics and trend mapping thermal characteristics to determine the mapping results corresponding to the previously obtained mapping path marking results. This process may involve complex mathematical calculations or pattern matching algorithms to ensure the accuracy and reliability of the mapping results. Once the mapping results are determined, the system maps these results to the base station layout model relationship network to obtain mapping path marking variables. These variables can be used in subsequent monitoring layout mapping processes, ultimately generating the first-state monitoring layout mapping vector. This vector not only reflects the current signal state distribution but also contains trend information on future signal state changes, providing strong data support for the intelligent management and maintenance of base stations.

[0187] In another possible embodiment, the above-mentioned state monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a state monitoring processing algorithm; wherein, the method further includes: determining the heat index corresponding to the above-mentioned plurality of mapping path marking results; determining the ideal heat feature of signal state mapping based on the above-mentioned signal state mapping heat feature and the heat index corresponding to the above-mentioned plurality of mapping path marking results; determining the spatiotemporal state migration vector corresponding to the above-mentioned target signal state monitoring vector element; determining the heat index after the spatiotemporal state migration vector corresponding to the above-mentioned target signal state monitoring vector element is mapped to the above-mentioned signal state relationship network; determining the second algorithm debugging evaluation variable based on the heat index after the spatiotemporal state migration vector corresponding to the above-mentioned target signal state monitoring vector element is mapped to the above-mentioned signal state relationship network and the above-mentioned ideal heat feature of signal state mapping, and debugging the above-mentioned state monitoring processing algorithm based on the above-mentioned second algorithm debugging evaluation variable.

[0188] In another possible embodiment, the state monitoring method for the migration of 5G base stations in open-pit mines is implemented through a state monitoring processing algorithm. This method includes a series of complex and sophisticated steps to ensure accurate and comprehensive monitoring of state changes during the base station migration process.

[0189] First, the system determines the heat index corresponding to several mapping path marking results. A heat index is an indicator used to measure the degree of clustering of hotspots or high-value areas in a data distribution. In this context, the heat index may be used to reflect the clustering or intensity of signal states on different mapping paths. By calculating the heat index for each mapping path marking result, the system can obtain a quantitative description of the signal state distribution.

[0190] Next, the system determines the ideal thermal characteristics of the signal state mapping based on the thermal characteristics of the signal state mapping and the thermal indices corresponding to several mapping path labeling results. The thermal characteristics of the signal state mapping describe the thermal distribution of the signal state during the mapping process, while the ideal thermal characteristics are an idealized standard or target used to evaluate the quality of the current thermal distribution. By combining actual thermal indices and thermal characteristics, the system can formulate a more specific and operable standard for ideal thermal characteristics.

[0191] Then, the system determines the spatiotemporal state transition vector corresponding to the target signal state monitoring vector element. The spatiotemporal state transition vector is a vector describing the changes in signal state over time and space. By determining the transition vector corresponding to the target signal state monitoring vector element, the system can track and record the specific changes in signal state during the transition process.

[0192] Next, the system determines the heat index of the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element after mapping it to the signal state relationship network. This step maps the migration vector to the signal state relationship network and calculates the mapped heat index. The signal state relationship network is a network model describing the relationships between signal states. By mapping the migration vector to this network, the system can further analyze the mutual influence and correlation of signal states during the migration process.

[0193] Finally, the system determines the second algorithm debugging and evaluation variable based on the thermal index and ideal thermal characteristics of the signal state mapping after mapping the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element to the signal state relationship network. This evaluation variable is an indicator used to measure the algorithm's performance or effectiveness; it integrates the actual thermal index and idealized thermal characteristic standards to evaluate the algorithm's accuracy and effectiveness. By continuously adjusting and optimizing the algorithm parameters or structure, the system can gradually improve the algorithm's performance, making it more adaptable to the actual needs of 5G base station migration state monitoring in open-pit mines.

[0194] In summary, the status monitoring method in this embodiment achieves comprehensive monitoring and accurate assessment of the signal status during the migration of 5G base stations in open-pit mines by comprehensively utilizing technologies and methods such as thermal index, signal status mapping thermal characteristics, and spatiotemporal state migration vectors. This not only helps improve the reliability and stability of base station migration but also provides strong data support and technical assurance for subsequent base station management and maintenance.

[0195] In some alternative embodiments, the state monitoring layout mapping vector is integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. This includes: performing adjustable monitoring layout mapping on the state monitoring layout mapping vector to obtain an adjustable spatiotemporal state migration vector; and integrating the adjustable spatiotemporal state migration vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. Based on this, the state monitoring method for open-pit mine 5G base station migration is implemented by a state monitoring processing algorithm. The method further includes: performing base station migration tag identification on the target 5G base station migration state monitoring vector to obtain a second base station migration tag identification result; obtaining the second base station migration tag identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station; and determining a third algorithm debugging evaluation variable based on the second base station migration tag identification result and the second base station migration tag identification annotation, and debugging the state monitoring processing algorithm based on the third algorithm debugging evaluation variable.

[0196] In some alternative embodiments, the system employs different methods to integrate the state monitoring layout mapping vector with the first linkage state integration migration knowledge to generate the target 5G base station migration state monitoring vector. This process can be divided into several key steps.

[0197] First, the system performs adjustable monitoring layout mapping on the state monitoring layout mapping vector. Adjustable monitoring layout mapping is a flexible mapping method that allows the system to adjust the mapping parameters and rules according to actual needs. Through this mapping, the system obtains an adjustable spatiotemporal state transition vector. This vector not only contains information from the original state monitoring layout mapping vector but also incorporates the adjustability of the mapping process, enabling it to better adapt to different transition scenarios and requirements.

[0198] Next, the system integrates the adjustable spatiotemporal state transition vector with the first linked state integrated transition knowledge. This integration process is achieved through a specific algorithm that effectively fuses and integrates information from different sources. In this process, the adjustable spatiotemporal state transition vector and the first linked state integrated transition knowledge complement each other, jointly forming the target 5G base station migration state monitoring vector. This vector contains comprehensive information about the 5G base station migration state, providing strong support for subsequent migration decisions and state monitoring.

[0199] Based on the above embodiments, the status monitoring method for 5G base station migration in open-pit mines is implemented through a status monitoring processing algorithm. This method also includes additional steps to further improve the accuracy and reliability of the monitoring.

[0200] Specifically, the system performs base station migration label identification on the target 5G base station migration status monitoring vector. Base station migration label identification is a method for classifying and labeling monitoring vectors, which helps the system better understand the meaning and characteristics of the vectors. Through identification, the system obtains a second base station migration label identification result. This result is a detailed description and classification of the target 5G base station migration status monitoring vector.

[0201] Simultaneously, the system acquires the second base station migration tag identification annotations corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station. These annotations explain and illustrate the second base station migration tag identification results, providing more background information and details about the identification results.

[0202] Finally, the system determines the third algorithm debugging and evaluation variable based on the second base station migration tag identification results and annotations. This evaluation variable is an indicator used to measure the algorithm's performance or effectiveness; it integrates the information from the identification results and annotations to evaluate the algorithm's accuracy and reliability. By continuously adjusting and optimizing the algorithm parameters or structure, the system can gradually improve the algorithm's performance, making it more adaptable to the actual needs of 5G base station migration status monitoring in open-pit mines.

[0203] In summary, these alternative embodiments provide a more flexible and comprehensive status monitoring method, which can be adaptively adjusted and optimized according to different migration scenarios and needs, thereby improving the accuracy and reliability of 5G base station migration status monitoring in open-pit mines.

[0204] In some standalone embodiments, several spatiotemporal state mapping perturbation vectors are fused according to feature description levels to obtain signal adaptation representation vectors corresponding to spatiotemporal state mapping vectors, including feature level partitioning, feature level aggregation, inter-level correlation analysis, dynamic weight allocation, level fusion, and post-processing optimization.

[0205] in,

[0206] Feature-level partitioning involves dividing several spatiotemporal state mapping perturbation vectors into feature-level components. This typically involves grouping different parts or elements of the vectors, with each group representing a specific feature description level, such as time rate of change, spatial distribution characteristics, signal strength fluctuations, etc.

[0207] Intra-feature aggregation includes aggregating the perturbation vector elements belonging to each feature description level. The aggregation method can be selected according to specific needs; for example, statistical measures such as mean, median, maximum, minimum, and weighted average can be used to represent the overall characteristics of that level.

[0208] Inter-layer correlation analysis includes analyzing the correlation between different feature description layers. This can be achieved by calculating statistical measures such as inter-layer correlation coefficients, mutual information, and covariance. Understanding the inter-layer correlations helps in the rational allocation of weights during subsequent fusion processes.

[0209] Dynamic weight allocation involves dynamically assigning weights to each feature description layer based on the results of inter-layer correlation analysis. The weight allocation should consider the contribution of different layers to the final signal adaptation representation vector, as well as any potential redundancy or complementarity between layers.

[0210] Layer fusion involves combining the aggregation results from different feature description layers using assigned weights. This can be achieved through weighted summation, multiplication, or more complex fusion functions (such as neural networks). The fused result is the signal adaptation representation vector corresponding to the spatiotemporal state mapping vector.

[0211] Post-processing optimization includes performing post-processing on the fused signal adaptation representation vector, such as normalization and denoising, to further optimize the vector representation. Furthermore, the fusion method can be iteratively optimized according to actual application requirements to improve the accuracy of signal adaptation.

[0212] These sub-steps effectively fuse several spatiotemporal state mapping perturbation vectors according to feature description levels, thereby obtaining a comprehensive and accurate signal adaptation representation vector. This method not only considers the characteristics of different levels but also optimizes the fusion result through dynamic weight allocation and correlation analysis, improving the accuracy and reliability of state monitoring.

[0213] In another independent embodiment, several state pooling vector relationship spectra are mapped to the base station layout model relationship network respectively, and several state monitoring layout mapping vectors are obtained. These vectors are then integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector, including the following sub-steps.

[0214] (1) Constructing the base station layout model relationship network:

[0215] First, based on the base station layout model dataset of the target open-pit mine 5G base stations, a base station layout model relationship network is constructed. This relationship network should be able to represent the spatial layout, signal coverage, and potential signal interference relationships between base stations.

[0216] (2) State pooling vector relation spectrum mapping:

[0217] For each state-pooled vector relation spectrum, an appropriate mapping function or algorithm is used to map its elements to the corresponding nodes or connections in the base station layout model relation network. The mapping process can be based on the similarity, distance, or other correlation measures between the vector elements and the relation network nodes or connections.

[0218] (3) Generate the status monitoring layout mapping vector:

[0219] After mapping is completed, each state pooling vector relation spectrum will form a specific mapping pattern in the base station layout model relation network. This mapping pattern is converted into a state monitoring layout mapping vector, which can capture the spatial distribution and variation characteristics of the original signal state monitoring vector in the base station layout.

[0220] (4) Integrating mapping vectors and linkage state knowledge:

[0221] The generated state monitoring layout mapping vector is integrated with the transfer knowledge of the first linkage state. Integration can be achieved through weighted averaging, serial connection, parallel connection, or other complex fusion algorithms. The goal is to combine the state monitoring layout information with the transfer knowledge to form a more comprehensive state monitoring vector.

[0222] (5) Optimization and iteration:

[0223] Based on practical application requirements and performance evaluation results, the above mapping and integration process is optimized. Optimization may include improving the mapping function, adjusting the weight parameters in the integration algorithm, and introducing new features or information sources. Through iterative optimization, the accuracy and reliability of the state monitoring vector are gradually improved.

[0224] (6) Obtain the target 5G base station migration status monitoring vector:

[0225] After the above steps, the obtained state monitoring layout mapping vectors are integrated with the first linkage state integrated migration knowledge to finally generate the target 5G base station migration state monitoring vector. This vector integrates information from multiple aspects such as signal state, spatiotemporal migration, and base station layout, and can provide strong support for the migration decision of 5G base stations in open-pit mines.

[0226] Through these sub-steps, the state pooling vector relation spectrum can be effectively mapped onto the base station layout model relation network and integrated with the linked state knowledge, thereby obtaining a comprehensive and accurate target 5G base station migration state monitoring vector. This method not only considers the spatial distribution and change characteristics of signal states but also combines base station layout and migration knowledge, improving the accuracy and reliability of state monitoring.

[0227] This application also provides a status monitoring system, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described status monitoring methods based on the migration of 5G base stations in open-pit mines.

[0228] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the status monitoring method for the migration of the open-pit mine 5G base station.

[0229] This invention provides a processor for running a program, wherein the program executes the above-mentioned open-pit mine 5G base station migration status monitoring method.

[0230] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the steps of a status monitoring method based on the migration of a 5G base station in an open-pit mine.

[0231] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0232] A computer program product includes a non-volatile computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the state monitoring method for 5G base station migration based on open-pit mines described in various embodiments of this application.

[0233] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0234] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0235] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0236] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0237] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0238] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0239] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0240] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0241] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0242] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A status monitoring method for 5G base station migration in open-pit mines, characterized in that, Applied to a status monitoring system, the method includes: The spatiotemporal state transition vector and signal state monitoring vector of the target open-pit mine 5G base station are obtained. The spatiotemporal state transition vector of the target open-pit mine 5G base station is generated based on the base station layout model dataset corresponding to the target open-pit mine 5G base station. Based on the spatiotemporal state transition vector, the signal state monitoring vector is dynamically adapted to obtain the signal adaptation representation vector. Knowledge integration is performed on the signal adaptation representation vector and the spatiotemporal state transition vector to obtain the first linkage state integrated transition knowledge; The signal status monitoring vector of the target open-pit mine 5G base station is mapped to the base station layout model relationship network corresponding to the spatiotemporal state transition vector to obtain the status monitoring layout mapping vector. The state monitoring layout mapping vector is integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. Dynamic adaptation processing of the signal state monitoring vector based on the spatiotemporal state transition vector to obtain a signal adaptation representation vector includes: mapping the spatiotemporal state transition vector of the target open-pit mine 5G base station to the signal state relationship network corresponding to the signal state monitoring vector to obtain a spatiotemporal state mapping vector; determining the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector in the signal state monitoring vector; identifying several error features of the spatiotemporal state mapping vector relative to the local signal state monitoring vector based on the local signal state monitoring vector; and obtaining the signal adaptation representation vector based on the several error features and the spatiotemporal state mapping vector.

2. The method according to claim 1, characterized in that, The signal adaptation representation vector is obtained based on the aforementioned error features and the spatiotemporal state mapping vector, including: The aforementioned error features are aggregated into the spatiotemporal state mapping vector to obtain several spatiotemporal state mapping perturbation vectors; The spatiotemporal state mapping perturbation vectors are fused according to the feature description level to obtain the signal adaptation representation vector corresponding to the spatiotemporal state mapping vector.

3. The method according to claim 1, characterized in that, Determining the local signal state monitoring vector corresponding to the spatiotemporal state mapping vector from the signal state monitoring vector includes: The signal state monitoring vector is subjected to pyramid state vector pooling to obtain several state pooling vector relationship spectra; State vector derivation is performed on the plurality of state pooling vector relation spectra respectively to obtain a plurality of first state derived vector relation spectra, wherein the derivative parameters of the plurality of first state derived vector relation spectra are the same relative to the signal state monitoring vector; The plurality of first state derived vector relation spectra are integrated by state vector integration to obtain a second state derived vector relation spectrum; The local signal state monitoring vector corresponding to the spatiotemporal state mapping vector is determined in the second state-derived vector relation spectrum.

4. The method according to claim 1, characterized in that, The status monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a status monitoring processing algorithm; the method also includes: Based on the migration knowledge integrated from the first linkage state, base station migration label identification is performed to obtain the first base station migration label identification result. Obtain the first base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station; Based on the first base station migration tag identification result and the first base station migration tag identification annotation, a first algorithm debugging evaluation variable is determined, and the status monitoring processing algorithm is debugged based on the first algorithm debugging evaluation variable.

5. The method according to claim 1, wherein Mapping the signal status monitoring vector of the target open-pit mine 5G base station to the base station layout model relationship network corresponding to the spatiotemporal state transition vector, to obtain the state monitoring layout mapping vector, including: The signal state monitoring vector is subjected to pyramid state vector pooling to obtain several state pooling vector relationship spectra; The plurality of state pooling vector relationship spectra are respectively mapped to the base station layout model relationship network to obtain a plurality of state monitoring layout mapping vectors. The plurality of state monitoring layout mapping vectors are then integrated with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. The plurality of state pooling vector relationship spectra include a third state derived vector relationship spectrum, and the plurality of state monitoring layout mapping vectors include a first state monitoring layout mapping vector, wherein the first state monitoring layout mapping vector is obtained by mapping the third state derived vector relationship spectrum; wherein, mapping the plurality of state pooling vector relationship spectra to the base station layout model relationship network respectively to obtain a plurality of state monitoring layout mapping vectors includes: Knowledge vector mining is performed on the integrated transfer knowledge of the first linkage state to obtain the integrated transfer knowledge of the second linkage state. The second linkage state integration transfer knowledge is mapped to the signal state relationship network corresponding to the signal state monitoring vector to obtain the first linkage signal state monitoring vector; The first linkage signal state monitoring vector and the third state derived vector relationship spectrum are integrated to obtain the signal state monitoring vector of the first integrated spatiotemporal data. The signal state monitoring vector of the first integrated spatiotemporal data is mapped to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the first state monitoring layout mapping vector.

6. The method according to claim 5, characterized in that, The plurality of state pooling vector relationship spectra include a fourth state derived vector relationship spectrum, wherein the fourth state derived vector relationship spectrum has a different feature recognition degree than the third state derived vector relationship spectrum; the plurality of state monitoring layout mapping vectors include a second state monitoring layout mapping vector, wherein the second state monitoring layout mapping vector is obtained by mapping the fourth state derived vector relationship spectrum; wherein, mapping the plurality of state pooling vector relationship spectra to the base station layout model relationship network to obtain a plurality of state monitoring layout mapping vectors further includes: Knowledge embedding is performed on the second linkage state integration transfer knowledge to obtain the third linkage state integration transfer knowledge; The second state monitoring layout mapping vector is mapped onto the signal state relationship network to obtain the second linkage signal state monitoring vector; The second linkage signal state monitoring vector is integrated with the fourth state derived vector relationship spectrum to obtain the signal state monitoring vector of the second integrated spatiotemporal data. The signal state monitoring vector of the second integrated spatiotemporal data is mapped to the base station layout model relationship network corresponding to the spatiotemporal state migration vector to obtain the second state monitoring layout mapping vector. Specifically, integrating the state monitoring layout mapping vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector includes: embedding the third linkage state integration migration knowledge to obtain the fourth linkage state integration migration knowledge; and integrating the first state monitoring layout mapping vector, the second state monitoring layout mapping vector, and the fourth linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector.

7. The method according to claim 5, characterized in that, The third state-derived vector relation spectrum includes target signal state monitoring vector elements; wherein, mapping the signal state monitoring vector of the first integrated spatiotemporal data to the base station layout model relation network corresponding to the spatiotemporal state transition vector to obtain the first state monitoring layout mapping vector includes: A first feature focusing operation is performed on the signal state monitoring vector of the first integrated spatiotemporal data to obtain a first signal state monitoring focus vector. A second feature focusing operation is performed on the signal state monitoring vector of the first integrated spatiotemporal data to obtain a second signal state monitoring focus vector. Determine the knowledge mapping path that maps the target signal status monitoring vector elements to the base station layout model relationship network; Feature labeling is performed on the knowledge mapping path to obtain several mapping path labeling results; Based on the second signal state monitoring focus vector, the signal state mapping thermodynamic features corresponding to the third state derived vector relationship spectrum are identified; Based on the first signal state monitoring focus vector, the trend mapping thermal features corresponding to the third state derived vector relationship spectrum are identified; Based on the signal state mapping thermal characteristics and the trend mapping thermal characteristics, the mapping results corresponding to the several mapping path marking results are determined; Map the mapping result corresponding to the mapping path marking result to the base station layout model relationship network to obtain the mapping path marking variable, and perform monitoring layout mapping based on the mapping path marking variable to obtain the first state monitoring layout mapping vector. The state monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a state monitoring processing algorithm. The method further includes: determining the heat index corresponding to the several mapping path marking results; determining the ideal heat feature of the signal state mapping based on the signal state mapping heat feature and the heat index corresponding to the several mapping path marking results; determining the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element; determining the heat index after mapping the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element to the signal state relationship network; and determining a second algorithm debugging and evaluation variable based on the heat index after mapping the spatiotemporal state migration vector corresponding to the target signal state monitoring vector element to the signal state relationship network and the ideal heat feature of the signal state mapping, and debugging the state monitoring processing algorithm based on the second algorithm debugging and evaluation variable.

8. The method according to claim 1, characterized in that Integrating the state monitoring layout mapping vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector includes: performing adjustable monitoring layout mapping on the state monitoring layout mapping vector to obtain an adjustable spatiotemporal state migration vector; and integrating the adjustable spatiotemporal state migration vector with the first linkage state integration migration knowledge to obtain the target 5G base station migration state monitoring vector. The state monitoring method based on the migration of 5G base stations in open-pit mines is implemented by a state monitoring processing algorithm. The method further includes: performing base station migration label identification on the migration state monitoring vector of the target 5G base station to obtain a second base station migration label identification result; obtaining the second base station migration label identification annotation corresponding to the spatiotemporal state migration vector of the target open-pit mine 5G base station; determining a third algorithm debugging and evaluation variable based on the second base station migration label identification result and the second base station migration label identification annotation, and debugging the state monitoring processing algorithm based on the third algorithm debugging and evaluation variable.

9. A status monitoring 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 being used to perform the status monitoring method for 5G base station migration based on any one of claims 1 to 8.

Images