Communication data classification management method and system based on AI analysis

Abstract

The invention is suitable for the technical field of communication data scheduling and intelligent network management, and provides a communication data classification management method and system based on AI analysis, and the method comprises the steps: obtaining an original node cache sending window value of a communication node located in a target construction region of a target underground tunnel, historical construction and communication data of the target underground tunnel are acquired; acquiring a plurality of sub-regions which are matched with the background information of the target construction region and are constructed and local historical data corresponding to each sub-region from historical construction and communication data, and extracting construction degree values and effective uploading data utilization rates of the sub-regions in different construction stages; according to the method, a characteristic mode recognition mechanism based on historical construction and communication data is introduced, dynamic self-adaptive adjustment of communication parameters (node cache sending window values) between construction stages is achieved, and the method is remarkably different from an existing management mode depending on static configuration or experience setting.

Description

Technical Field

[0001] The present invention belongs to the technical field of communication data scheduling and intelligent network management, and particularly relates to a communication data classification management method and system based on AI analysis. Background Art

[0002] In the existing communication data management technologies, the configuration of communication nodes in the construction environment mostly still relies on static settings or manual experience for parameter adjustment. Especially in scenarios such as underground tunnels where the communication environment is complex and construction interference is significant, this method has obvious deficiencies in terms of adaptability and real-time performance. Traditional methods often make adjustments based on the local network performance after the construction starts, resulting in a lag in response and being unable to effectively resist problems such as changes in channel quality and enhanced reflection interference caused by the evolution of the construction progress, further exacerbating risks such as packet loss, delay, or upload failure during the data transmission process. In addition, most of the existing communication parameter adjustment methods have not formed a systematic historical data-driven model, making it difficult to achieve intelligent parameter prediction and configuration across projects and stages. Especially for the node cache send window value, which is a key communication scheduling parameter, it still generally uses fixed value configuration or empirical settings and lacks the ability to dynamically optimize with the evolution of the environment.

[0003] Especially in projects such as underground tunnels, the physical environment, signal paths, and occlusion conditions of communication nodes in each construction stage are significantly different. This dynamic evolution process directly affects the communication performance, but the existing technologies lack an in-depth modeling and response mechanism for the correlation between "construction degree change - performance evolution trend". Although some studies have attempted to adopt real-time feedback adjustment methods based on network status, they are limited by problems such as long data accumulation cycles and large real-time analysis and calculation amounts, making it difficult to achieve rapid deployment and low-cost implementation. Therefore, how to have the ability to reasonably preset and dynamically correct communication parameters in each stage at the initial stage of project construction has become an important technical problem faced by the current communication management system. Summary of the Invention

[0004] The purpose of the present invention is to provide a communication data classification management method and system based on AI analysis, aiming to solve the problems proposed in the background art.

[0005] The present invention is implemented as follows. A communication data classification management method based on AI analysis, the method includes:

[0006] Obtain the original node cache send window value of the communication nodes in the target construction area of the target underground tunnel, as well as the historical construction and communication data of the target underground tunnel;

[0007] Obtain several sub-regions that match the background information of the target construction area and have been completed from historical construction and communication data, as well as the corresponding local historical data for each sub-region, and extract the construction degree values and effective upload data utilization rates of the sub-regions at different construction stages;

[0008] Analyze whether there is the following abnormal feature pattern: as the construction degree value increases, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold;

[0009] If it is determined that there is an abnormal feature pattern, determine the reference sub-region and reference historical data that are most matched to the construction rhythm of the target construction area, and calculate the decline amplitude of the effective upload data utilization rate of the reference sub-region in different construction stages compared to the initial construction stage;

[0010] Convert all the decline amplitudes into a set of correction factors, apply them to the original node cache sending window values of communication nodes in different construction stages within the target construction area to generate a set of corrected window values, and apply them to the parameter scheduling in communication data classification management.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the step of analyzing whether there is the following abnormal feature pattern: as the construction degree value increases, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold includes:

[0012] Parse each group of local historical data to determine whether there is a trend change relationship that as the construction degree value increases, the effective upload data utilization rate of its communication nodes decreases accordingly during the construction process of the sub-region;

[0013] Extract all the local historical data that meet the above trend change relationship and calculate its proportion in all local historical data;

[0014] When the proportion exceeds the preset threshold, it is determined that there is an abnormal feature pattern in the sub-regions that match the background information of the target construction area.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, if it is determined that there is an abnormal feature pattern, the step of determining the reference sub-region and reference historical data that are most matched to the construction rhythm of the target construction area and calculating the decline amplitude of the effective upload data utilization rate of the reference sub-region in different construction stages compared to the initial construction stage includes:

[0016] Based on the construction timeline, stage division method and construction progress characteristics of the target construction area, determine the reference sub-region that is most matched to the construction rhythm of the target construction area from several sub-regions with abnormal feature patterns, and set the local historical data corresponding to the reference sub-region as the reference historical data;

[0017] Obtain the effective upload data utilization rate of communication nodes in the reference sub-region at different construction stages and the initial construction stage;

[0018] Calculate the decline amplitude of the effective upload data utilization rate in each construction stage compared with the initial construction stage in turn.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the steps of converting all the decline amplitudes into a set of correction factors, applying them to the original node cache transmission window values of communication nodes in different construction stages in the target construction region, generating a set of corrected window values, and applying them to parameter scheduling in communication data classification management include:

[0020] Establish the corresponding relationship between the target construction region and the reference sub-region in terms of construction stages, and associate each construction stage in the target construction region with the closest construction stage in the reference sub-region;

[0021] Convert the decline amplitude of the effective upload data utilization rate corresponding to each construction stage in the reference sub-region into a correction factor for correcting the original node cache transmission window value of the communication node in the corresponding construction stage of the target construction region;

[0022] Arrange the correction factors in sequence according to the order of each construction stage in the target construction region to form a set of correction factors;

[0023] Call a preset window value correction function, and based on the set of correction factors, adjust the original node cache transmission window values of communication nodes in each construction stage in the target construction region one by one to generate a set of corrected node cache transmission window values, and use this set of window values for parameter scheduling in the process of communication data classification management.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the window value correction function is: ;

[0025] Wherein, refers to the corrected node cache transmission window value at the th construction stage of the target construction region, refers to the initial node cache transmission window value, refers to the effective upload data utilization rate of the construction stage corresponding to the th construction stage of the reference sub-region and the target construction region, refers to the effective upload data utilization rate of the initial construction stage of the reference sub-region, refers to the correction factor at the th construction stage of the target construction region, refers to the adjustment coefficient of the correction factor, and Greater than 0.

[0026] A communication data classification and management system based on AI analysis, the system includes: a data acquisition module, a data parsing module, an abnormal pattern determination module, a descent amplitude calculation module, and a window value correction module, where:

[0027] The data acquisition module is used to obtain the original node cache transmission window value of the communication node in the target construction area of the target underground tunnel, and the historical construction and communication data of the target underground tunnel;

[0028] The data parsing module is used to obtain several sub-regions that match the background information of the target construction area and have been completed from the historical construction and communication data, and the corresponding local historical data of each sub-region, and extract the construction degree value and the effective upload data utilization rate of the sub-region at different construction stages;

[0029] The abnormal pattern determination module is used to analyze whether there is the following abnormal feature pattern: as the construction degree value rises, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold;

[0030] The descent amplitude calculation module is used to, if it is determined that there is an abnormal feature pattern, determine the reference sub-region and reference historical data that are most matched with the construction rhythm of the target construction area, and calculate the descent amplitude of the effective upload data utilization rate of the reference sub-region at different construction stages compared with the initial construction stage;

[0031] The window value correction module is used to convert all descent amplitudes into a set of correction factors, apply them to the original node cache transmission window values of the communication nodes in the target construction area at different construction stages, generate a set of corrected window values, and apply them to the parameter scheduling in the communication data classification and management.

[0032] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal pattern determination module specifically includes:

[0033] The trend change relationship analysis unit is used to parse each group of local historical data to determine whether there is a trend change relationship that as the construction degree value rises, the effective upload data utilization rate of its communication node decreases accordingly during the construction process of the sub-region;

[0034] The proportion calculation unit is used to extract all local historical data that meet the above trend change relationship and calculate its proportion in all local historical data;

[0035] The abnormal feature pattern determination unit is used to determine that there is an abnormal feature pattern in the sub-region that matches the background information of the target construction area when the proportion exceeds the preset threshold.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the descending amplitude calculation module specifically includes:

[0037] A reference data determination unit, configured to determine, based on the construction time axis, stage division method, and construction progress characteristics of the target construction area, a reference sub-area that best matches the construction rhythm of the target construction area from several sub-areas with abnormal feature patterns, and set the local historical data corresponding to the reference sub-area as reference historical data;

[0038] An utilization rate extraction unit, configured to obtain the effective upload data utilization rates of communication nodes in the reference sub-area at different construction stages and the initial construction stage;

[0039] A descending amplitude calculation unit, configured to sequentially calculate the descending amplitudes of the effective upload data utilization rates in each construction stage compared to the initial construction stage.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, the window value correction module specifically includes:

[0041] A construction stage corresponding unit, configured to establish a corresponding relationship between the target construction area and the reference sub-area in terms of construction stages, and associate each construction stage in the target construction area with the closest construction stage in the reference sub-area;

[0042] A correction factor conversion unit, configured to convert the descending amplitudes of the effective upload data utilization rates corresponding to each construction stage in the reference sub-area into correction factors for correcting the original node cache transmission window values of communication nodes at the corresponding construction stages in the target construction area;

[0043] A set generation unit, configured to arrange the correction factors in sequence according to the order of each construction stage in the target construction area to form a correction factor set;

[0044] A window value correction unit, configured to call a preset window value correction function, and based on the correction factor set, adjust the original node cache transmission window values of communication nodes in each construction stage in the target construction area one by one to generate a set of corrected node cache transmission window values, and use this window value set for parameter scheduling in the communication data classification management process.

[0045] As a further limitation of the technical solution of the embodiment of the present invention, the window value correction function is: ;

[0046] Wherein, refers to the corrected node cache transmission window value of the th construction stage in the target construction area, refers to the initial node cache transmission window value, Refers to the effective upload data utilization rate of the construction stage corresponding to the th construction stage of the reference sub-region and the target construction region, refers to the effective upload data utilization rate of the initial construction stage of the reference sub-region, refers to the correction factor of the th construction stage of the target construction region, refers to the adjustment coefficient of the correction factor, and is greater than 0.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] By introducing a feature pattern recognition mechanism based on historical construction and communication data, the present invention realizes the dynamic adaptive adjustment of communication parameters (node cache send window value) between construction stages, which is significantly different from the existing management methods that rely on static configuration or empirical setting. In particular, for the scenario where there is a trend of "increasing construction degree - decreasing communication performance", the present invention innovatively constructs a quantitative mapping relationship between the decreasing amplitude of the reference sub-region and the window value of the target construction region, and adjusts the cache send window configuration stage by stage through the correction factor, effectively improving the scheduling flexibility and stability of data upload. At the same time, since the correction factor set can be generated in advance based on historical data before the construction starts, the system can realize the pre-parameter planning for the construction process, reduce the later operation and maintenance intervention, and enhance the forward-looking and adaptability of the scheduling strategy. This mechanism not only has good engineering feasibility, but also can significantly enhance the intelligent management ability of communication nodes in complex construction environments such as underground tunnels, and has outstanding practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flowchart of the method provided by the embodiment of the present invention;

[0050] Figure 2 is a flowchart of judging whether there is an abnormal feature pattern in the sub-region in the method provided by the embodiment of the present invention;

[0051] Figure 3 is a flowchart of calculating the decreasing amplitude of the effective upload data utilization rate in the method provided by the embodiment of the present invention;

[0052] Figure 4 is a flowchart of correcting the original node cache send window value in the method provided by the embodiment of the present invention;

[0053] Figure 5 is an application architecture diagram of the system provided by the embodiment of the present invention;

[0054] Figure 6 is a structural block diagram of the abnormal mode determination module in the system provided by the embodiment of the present invention;

[0055] Figure 7 This is the structural block diagram of the descending amplitude calculation module in the system provided by the embodiment of the present invention;

[0056] Figure 8 This is the structural block diagram of the window value correction module in the system provided by the embodiment of the present invention. Detailed implementation manners

[0057] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0058] Figure 1 The flowchart of the method provided by the embodiment of the present invention is shown.

[0059] Specifically, a communication data classification and management method based on AI analysis, the method specifically includes the following steps:

[0060] Step S100, obtaining the original node cache sending window value of the communication node in the target construction area of the target underground tunnel, and the historical construction and communication data of the target underground tunnel.

[0061] In the embodiment of the present invention, step S100 is used to obtain the initial input basis for communication data classification and management, and clarify the basic communication parameters and historical environment evolution information strongly associated with the target scenario. The object "target underground tunnel" mentioned in this step specifically refers to a closed or semi-closed communication environment in a construction scenario, which widely exists in underground construction projects such as urban subway tunnels, underground utility tunnels, and mines. Compared with the conventional ground communication scenario, the underground tunnel has obvious characteristics such as structural evolution, strong communication reflection, and complex construction interference factors. Therefore, the present invention preferably takes the underground tunnel as a representative scenario, and on this basis, constructs a more general and correction-necessary communication data classification and management method.

[0062] The "target construction area" refers to the area in the target underground tunnel that has not been completed and is about to enter the construction stage. Different from the completed construction area, this area does not yet have complete communication deployment conditions, and its communication behavior will be directly affected by the construction progress. Therefore, in the actual communication parameter setting of this area, preset templates or empirical initial values are usually used, and it is difficult to dynamically adapt to the upcoming environmental changes.

[0063] A communication node refers to various network terminal devices deployed in the target construction area for collecting, uploading, or relaying communication data, including but not limited to Mesh relay devices, LoRa base stations, wireless collection terminals, etc. The communication node can be a key control point or a group of multiple nodes within a coverage area, which can be specifically determined according to the communication network design logic without quantity limitation.

[0064] The original node cache transmission window value is a key parameter preset by the communication node in the initial state to control its data cache transmission strategy. This value is usually used to limit the maximum data cache volume that the node is allowed to release per unit time and is one of the important scheduling parameters in the wireless communication protocol to control the load release rhythm and avoid instantaneous congestion. In the existing communication system, this parameter can be configured through network configuration, device firmware initialization, or automatically generated by the communication scheduling module according to a standard template, which belongs to the configuration content of mature applications in the prior art. However, since this value is mostly based on static settings and does not fully consider the long-term impact of subsequent construction processes on communication stability, link quality, and retransmission mechanisms, it is prone to resource allocation lag or classification result distortion. Therefore, the present invention proposes to introduce a historical data-driven correction mechanism to achieve dynamic optimization and adaptive update of this value.

[0065] The historical construction and communication data of the target underground tunnel refer to the structural evolution records and communication behavior data collected from the completed construction areas in the tunnel that are comparable to the current target construction area in terms of background conditions. This type of data can be obtained by extracting from the construction monitoring system, environmental sensing network, historical communication logs, or device operation records. The historical construction and communication data at least include the following types of data: physical information such as construction stages and time series markers, construction completion indicators, structural density, or material reflection coefficients; and at the same time, it should also include communication behavior performance values such as communication stability indicators, data upload success rates, retransmission times, channel quality feedback, and effective upload ratios of data packets of the communication node at the corresponding stages.

[0066] Furthermore, the communication data classification and management method based on AI analysis further includes the following steps:

[0067] Step S200, obtain several sub-regions that match the background information of the target construction area and have been completed and the corresponding local historical data from the historical construction and communication data, and extract the construction degree values and effective upload data utilization rates of the sub-regions at different construction stages.

[0068] In an embodiment of the present invention, step S200 is used to construct a historical sample set that has reference value for the target construction area, so as to provide data support for the subsequent identification of the evolution trend of communication performance and the construction of correction factors. In this step, several sub-areas that match the background information of the target construction area are first screened from the historical construction and communication data of the target underground tunnel. Background information matching means that among multiple candidate sub-areas, sub-areas with high similarity or the same engineering parameters as the target construction area in terms of structural layout, construction process, materials used, layout plan, design width, construction time period, construction team configuration, or communication deployment strategy are preferentially selected.

[0069] To implement the above matching process, a feature vector set for matching can be constructed based on information such as the structural construction BIM model, phased working condition records, material entry and exit logs, construction schedule, and communication equipment deployment drawings in tunnel engineering. For example, several dimensions (such as structural section size, typical construction process, type of waterproof lining structure used, initial number of communication nodes, etc.) are set, the parameter quantification is performed on the target construction area and each historical sub-area respectively, and the matching degree is calculated by means of Euclidean distance, weighted matching score, cosine similarity, etc. Finally, several sub-areas with a matching score higher than the preset threshold are selected as reference objects. The selected sub-areas must have completed construction and have conditions for accumulating stable communication data to ensure that the corresponding communication behavior samples have credible evolution characteristics.

[0070] After the reference sub-areas are selected, the local historical data of each sub-area at different construction stages is further extracted. Among them, the construction stage can be divided based on time series or key construction nodes, such as tunnel excavation stage, primary support completion stage, waterproof layer laying stage, secondary lining completion stage, power and communication pipeline installation stage, etc. For each stage, information such as the structural completion ratio, structural occupancy volume, and steel cage closure rate within the time period it is in is extracted, and these indicators are standardized and used as the "construction degree value". This construction degree value can be calculated from the construction data in the project progress management system or BIM model, which is a parameter already defined in the project management system and is directly applied in the present invention to describe the evolution process of spatial structure closure and interference density.

[0071] At the same time, the "effective upload data utilization rate" of communication nodes is extracted for each stage, that is, the ratio of the total amount of effective data packets successfully uploaded to the target communication control node within a unit time to the total amount of planned data packets to be sent. This indicator reflects the upload ability performance of nodes in the construction interference environment and is commonly used in communication network operation monitoring and equipment operation logs, and is also a common quality evaluation parameter in existing communication systems. In the present invention, this utilization rate can be extracted from the logs generated by communication equipment, protocol layer ACK / NAK feedback records, and statistical data of the upper control platform.

[0072] Furthermore, the communication data classification and management method based on AI analysis further includes the following steps:

[0073] Step S300: Analyze whether there is the following abnormal feature pattern: as the construction degree value increases, the utilization rate of effectively uploaded data shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold.

[0074] Specifically, Figure 2 shows a flowchart for judging whether there is an abnormal feature pattern in a sub-region.

[0075] Among them, analyzing whether there is the following abnormal feature pattern: as the construction degree value increases, the utilization rate of effectively uploaded data shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold specifically includes the following steps:

[0076] Step S301: Parse each group of local historical data to judge whether there is a trend change relationship that as the construction degree value increases, the utilization rate of effectively uploaded data of its communication nodes decreases correspondingly during the construction process of the sub-region;

[0077] Step S302: Extract all local historical data that meet the above trend change relationship, and calculate its proportion in all local historical data;

[0078] Step S303: When the proportion exceeds the preset threshold, determine that there is an abnormal feature pattern in the sub-region that matches the background information of the target construction area.

[0079] In the embodiment of the present invention, steps S301 to S303 constitute an analysis mechanism for the potential correlation trend between communication performance and structural evolution. The core lies in identifying whether there is a statistically significant abnormal feature pattern, that is, the trend relationship of "as the construction degree value increases, the utilization rate of effectively uploaded data decreases correspondingly". This feature pattern does not exist generally in all construction areas, but tends to appear in sub-regions with specific structural characteristics or construction rhythms, especially those areas where the structural airtightness increases rapidly, the number of reflecting surfaces increases significantly, or the construction interference fluctuates violently. During the construction evolution process of these areas, the complexity of the communication signal propagation path increases sharply, resulting in a decline in link quality and an increase in interference frequency, thereby causing a significant reduction in the upload efficiency of communication nodes.

[0080] Once this abnormal feature pattern appears in a large number of historical sub-regions that highly match the background information of the target construction area, it indicates that in the subsequent construction evolution process of the target area, there is also a high probability of a similar trend of communication performance degradation. In other words, this feature pattern is an "evolutionary precursor manifestation" of the vulnerable points of communication performance under specific environmental categories, and has the significance of prior risk identification. Therefore, before implementing the present invention, it is necessary to first determine whether this feature pattern widely exists in similar regions, so as to decide whether to enable the correction mechanism. Blindly correcting all regions will not only introduce redundant calculations, but may also damage the configuration of regions with originally stable communication.

[0081] To ensure the objectivity and statistical significance of the judgment, the "proportion in all local historical data" is introduced as a quantitative judgment criterion in step S302. This proportion indicates how many regions among all the analyzed historical sub-regions actually have this abnormal trend change relationship, forming reliable data support. The "preset threshold" mentioned in step S303 is the boundary condition for determining whether there is a significant abnormality.

[0082] This preset threshold can be set in various ways. For example, based on experience, it is found that when the proportion of abnormal trend sub-regions exceeds 60%, the risk of communication performance decline increases significantly; it can also be based on historical project data, and the optimal balance point of misjudgment and missed judgment is selected as the threshold through statistical learning methods; in addition, the minimum proportion value that causes communication instability can be determined by simulating the data evolution process under different construction conditions.

[0083] Through the above steps, judging whether there is an abnormal feature pattern before implementing the correction can effectively improve the sensitivity and robustness of the system to abnormal trends, ensure that the correction mechanism is only started when it is truly necessary, and avoid misadjustment interference to non-sensitive regions.

[0084] Furthermore, the communication data classification management method based on AI analysis further includes the following steps:

[0085] Step S400, if it is determined that there is an abnormal feature pattern, determine the reference sub-region and reference historical data that are most matched with the construction rhythm of the target construction area, and calculate the decline amplitude of the effective upload data utilization rate of the reference sub-region in different construction stages compared with the initial construction stage.

[0086] Specifically, Figure 3 The flowchart showing the calculation of the decline amplitude of the effective upload data utilization rate is shown.

[0087] Among them, if it is determined that there is an abnormal feature pattern, determining the reference sub-region and reference historical data that are most matched with the construction rhythm of the target construction area and calculating the decline amplitude of the effective upload data utilization rate of the reference sub-region in different construction stages compared with the initial construction stage specifically includes the following steps:

[0088] Step S401: Based on the construction timeline, stage division method, and construction progress characteristics of the target construction area, determine the reference sub-area that best matches the construction rhythm of the target construction area from several sub-areas with abnormal feature patterns, and set the local historical data corresponding to this reference sub-area as the reference historical data;

[0089] Step S402: Obtain the effective upload data utilization rates of communication nodes in the reference sub-area at different construction stages and the initial construction stage;

[0090] Step S403: Calculate the decline amplitudes of the effective upload data utilization rates in each construction stage compared to the initial construction stage in turn.

[0091] In the embodiment of the present invention, in step S401, by introducing time series matching analysis and rhythm similarity measurement means, integrating information such as the construction timeline, stage division method, and construction progress curve of the target construction area, a target construction rhythm vector is constructed; then, the historical construction rhythm feature vectors of each sub-area with abnormal feature patterns are extracted, and the dynamic time warping (DTW) or similarity scoring function is used to compare them with the target rhythm vector one by one. Finally, the sub-area with the highest similarity score is selected as the reference sub-area, and its local historical data is set as the reference historical data. This method ensures that the reference sub-area is highly consistent with the target area in terms of the construction progress method and the evolution path of node deployment, thereby improving the adaptability and accuracy of subsequent corrections.

[0092] In step S403, based on the effective upload data utilization rates of each construction stage in the reference sub-area, a comparison calculation is made with the utilization rate in the initial construction stage to obtain the decline amplitude of the utilization rate in each stage. This decline amplitude can quantitatively describe the attenuation trend of communication performance due to changes in the construction environment, and reflect the comprehensive influence of factors such as reflection interference and channel quality changes on communication nodes at different stages, providing a real and quantifiable reference basis for correcting the communication parameters in the target construction area corresponding to the reference sub-area.

[0093] Further, the communication data classification management method based on AI analysis further includes the following steps:

[0094] Step S500: Convert all decline amplitudes into a set of correction factors, apply them to the original node cache sending window values of communication nodes in the target construction area at different construction stages to generate a set of corrected window values, and apply them to the parameter scheduling in communication data classification management.

[0095] Specifically, Figure 4 shows a flowchart for correcting the original node cache sending window value.

[0096] Among them, converting all the descending amplitudes into a set of correction factors, applying them to the original node cache transmission window values of communication nodes in different construction stages within the target construction area, generating a set of corrected window values, and applying them to parameter scheduling in communication data classification management specifically includes the following steps:

[0097] Step S501: Establish the corresponding relationship between the target construction area and the reference sub-area in terms of construction stages, and associate each construction stage in the target construction area with the closest construction stage in the reference sub-area;

[0098] Step S502: Convert the descending amplitudes of the effective upload data utilization rates corresponding to each construction stage in the reference sub-area into correction factors for correcting the original node cache transmission window values of communication nodes in the corresponding construction stage of the target construction area;

[0099] Step S503: Arrange the correction factors in sequence according to the order of each construction stage in the target construction area to form a set of correction factors;

[0100] Step S504: Call a preset window value correction function, and based on the set of correction factors, adjust the original node cache transmission window values of communication nodes in each construction stage in the target construction area one by one to generate a set of corrected node cache transmission window values, and use this set of window values for parameter scheduling in the process of communication data classification management.

[0101] The window value correction function is: ;

[0102] Among them, refers to the corrected node cache transmission window value of the th construction stage in the target construction area, refers to the initial node cache transmission window value, refers to the effective upload data utilization rate of the construction stage corresponding to the th construction stage in the reference sub-area and the target construction area, refers to the effective upload data utilization rate of the initial construction stage in the reference sub-area, refers to the correction factor of the th construction stage in the target construction area, refers to the adjustment coefficient of the correction factor, and is greater than 0.

[0103] In the embodiment of the present invention, in step S501, by constructing a mapping relationship in the construction stage, each construction stage to be corrected in the target construction area is respectively matched with the stage that has completed construction and has a communication performance evolution record in the reference sub-area. This matching can be based on dimensions such as the structural completion ratio, the start and end time of the stage, the type of operation process, and the construction density, and the optimal correspondence between stages can be achieved by using weighted similarity analysis or time alignment algorithms (such as dynamic time warping), ensuring that each target construction stage can find a reference stage in the historical data with the closest structural conditions and communication characteristics, and constructing a set of mapping relationships between structure-communication behaviors.

[0104] In step S502, for each reference construction stage, the amplitude of the decrease in the effective upload data utilization rate compared to the initial stage is extracted, and this amplitude of decrease is converted into a correction factor for the communication node cache transmission window value in the corresponding construction stage in the target construction area. The correction logic adopted in the present invention is based on the "performance result degradation amplitude" of the reference sub-area to perform a feedforward boost on the "parameter input intensity" of the target area. In other words, when the upload performance of the reference sub-area decreases more significantly in a certain stage, it indicates that the communication environment is more complex under such structural conditions. Therefore, it is necessary to appropriately tighten the cache transmission window configuration of the nodes in the corresponding stage of the target area to reduce the risk of link congestion and improve communication stability, thereby offsetting potential interference risks. This mechanism constructs a correction mode of "inferring input enhancement from result deviation", and realizes the active optimization of communication resource allocation based on historical response effects without the need for real-time monitoring of communication performance, which is one of the key technical innovations of the present invention.

[0105] In step S503, all the calculated correction factors are arranged in the stage order of the target construction area to construct a set of correction factors for subsequent stages to use in sequence. In step S504, the system calls the preset window value correction function, combines this set of correction factors, and corrects the original node cache transmission window values of each stage one by one, finally forming a set of corrected window values, and uses it in the parameter scheduling link of actual communication data classification management to improve the scheduling accuracy and system stability.

[0106] The correction method adopted by the present invention has significant novelty and beneficial effects. On the one hand, the existing technologies mostly rely on real-time monitoring of the operating status of communication equipment or static configuration templates, and lack feedforward perception of potential communication risks brought about by structural evolution; on the other hand, conventional optimization strategies are often only based on network-side load balancing or signal feedback for responsive adjustments, and it is difficult to actively configure in advance. The present invention, by constructing a performance-parameter mapping relationship driven by historical data, realizes the advance optimization of key communication scheduling parameters before the evolution of structural interference is fully manifested, effectively improving the robustness and adaptability of the system, and is particularly suitable for construction scenarios such as underground tunnels where communication conditions evolve drastically.

[0107] In the window value correction logic adopted by the present invention, the correction factor is based on the decrease in the effective upload data utilization rate of the reference sub-area in each construction stage compared with the initial stage. The more obvious the decrease, the smaller the algebraic value of the correction factor (tending to a negative value), and the larger the corresponding window value adjustment range, ensuring that the sending rate is actively reduced when the communication performance deteriorates to improve the link stability and communication reliability. An adjustable weight coefficient is provided in the function to flexibly control the correction range to adapt to the scheduling requirements of different engineering scenarios or communication strategies.

[0108] In particular, when the effective upload data utilization rate of a certain construction phase is lower than the initial stage level of the reference sub-area, that is, when the communication performance is reduced, the system will automatically tighten the node cache sending window configuration in the target area at that stage. By reducing the window value, the system can reduce the pressure of data transmission and the risk of network congestion, thereby improving the communication stability and transmission reliability during the classification scheduling process.

[0109] Furthermore, Figure 5 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0110] Among them, in another preferred embodiment provided by the present invention, a communication data classification management system based on AI analysis includes:

[0111] The data acquisition module 100 is used to acquire the original node cache sending window value of the communication node in the target construction area of the target underground tunnel, and the historical construction and communication data of the target underground tunnel.

[0112] Furthermore, the communication data classification management system based on AI analysis also includes:

[0113] The data analysis module 200 is used to obtain several sub-areas that match the background information of the target construction area and have completed construction and the local historical data corresponding to each sub-area from the historical construction and communication data, and extract the construction degree value and effective uploaded data utilization rate of the sub-area at different construction stages.

[0114] Furthermore, the communication data classification and management system based on AI analysis further includes:

[0115] An abnormal pattern determination module 300, configured to analyze whether there is the following abnormal feature pattern: as the construction degree value increases, the utilization rate of effective uploaded data shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold.

[0116] Specifically, Figure 6 FIG. shows a structural block diagram of the abnormal pattern determination module 300 in the system provided by an embodiment of the present invention.

[0117] Among them, in the preferred embodiment provided by the present invention, the abnormal pattern determination module 300 specifically includes:

[0118] A trend change relationship analysis unit 301, configured to parse each group of local historical data, and determine whether there is a trend change relationship that as the construction degree value increases, the utilization rate of effective uploaded data of its communication nodes decreases accordingly during the construction process of the sub-region;

[0119] A proportion calculation unit 302, configured to extract all local historical data that meet the above trend change relationship, and calculate its proportion in all local historical data;

[0120] An abnormal feature pattern determination unit 303, configured to determine that there is an abnormal feature pattern in the sub-region matching the background information of the target construction region when the proportion exceeds the preset threshold.

[0121] Furthermore, the communication data classification and management system based on AI analysis further includes:

[0122] A decline amplitude calculation module 400, configured to, if it is determined that there is an abnormal feature pattern, determine a reference sub-region and reference historical data that are most matched with the construction rhythm of the target construction region, and calculate the decline amplitude of the utilization rate of effective uploaded data in the reference sub-region in different construction stages compared with the initial construction stage.

[0123] Specifically, Figure 7 FIG. shows a structural block diagram of the decline amplitude calculation module 400 in the system provided by an embodiment of the present invention.

[0124] Among them, in the preferred embodiment provided by the present invention, the decline amplitude calculation module 400 specifically includes:

[0125] A reference data determination unit 401, configured to determine, based on the construction timeline, stage division method, and construction progress characteristics of the target construction area, a reference sub-area that best matches the construction rhythm of the target construction area from several sub-areas with abnormal feature patterns, and set the local historical data corresponding to the reference sub-area as reference historical data;

[0126] A utilization rate extraction unit 402, configured to obtain the effective upload data utilization rates of communication nodes in the reference sub-area at different construction stages and the initial construction stage;

[0127] A decline amplitude calculation unit 403, configured to sequentially calculate the decline amplitudes of the effective upload data utilization rates in each construction stage compared to the initial construction stage.

[0128] Furthermore, the communication data classification and management system based on AI analysis further includes:

[0129] A window value correction module 500, configured to convert all decline amplitudes into a set of correction factors, apply them to the original node cache transmission window values of communication nodes in the target construction area at different construction stages, generate a set of corrected window values, and apply them to parameter scheduling in communication data classification and management.

[0130] Specifically, Figure 8 FIG. shows the structural block diagram of the window value correction module 500 in the system provided by the embodiment of the present invention.

[0131] Among them, in the preferred embodiment provided by the present invention, the window value correction module 500 specifically includes:

[0132] A construction stage corresponding unit 501, configured to establish a corresponding relationship between the target construction area and the reference sub-area in terms of construction stages, and respectively associate each construction stage in the target construction area with the closest construction stage in the reference sub-area;

[0133] A correction factor conversion unit 502, configured to respectively convert the decline amplitudes of the effective upload data utilization rates corresponding to each construction stage in the reference sub-area into correction factors for correcting the original node cache transmission window values of communication nodes at the corresponding construction stages in the target construction area;

[0134] A set generation unit 503, configured to arrange the correction factors in sequence according to the order of each construction stage in the target construction area to form a set of correction factors;

[0135] The window value correction unit 504 is configured to call a preset window value correction function, and based on a set of correction factors, adjust the original node cache transmission window values of communication nodes in the target construction area at each construction stage one by one, generate a set of corrected node cache transmission window values, and use this set of window values for parameter scheduling in the process of communication data classification management.

[0136] The window value correction function is as follows: ;

[0137] Wherein, refers to the corrected node cache transmission window value at the th construction stage of the target construction area, refers to the initial node cache transmission window value, refers to the effective upload data utilization rate at the construction stage corresponding to the th construction stage of the reference sub-area and the target construction area, refers to the effective upload data utilization rate at the initial construction stage of the reference sub-area, refers to the correction factor at the th construction stage of the target construction area, refers to the adjustment coefficient of the correction factor, and is greater than 0.

[0138] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily need to be executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0139] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0140] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0141] The above embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention should be subject to the appended claims.

[0142] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A communication data classification and management method based on AI analysis, characterized in that, The method includes: Obtaining the original node cache sending window value of the communication nodes in the target construction area of the target underground tunnel, as well as the historical construction and communication data of the target underground tunnel; Obtaining several sub-areas that match the background information of the target construction area and have been completed and the corresponding local historical data from the historical construction and communication data, and extracting the construction degree value and the effective upload data utilization rate of the sub-areas at different construction stages; Analyzing whether there is the following abnormal feature pattern: as the construction degree value increases, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold; If it is determined that there is an abnormal feature pattern, determining the reference sub-area and reference historical data that are most matched with the construction rhythm of the target construction area, and calculating the decrease amplitude of the effective upload data utilization rate of the reference sub-area at different construction stages compared with the initial construction stage; Converting all the decrease amplitudes into a set of correction factors, applying them to the original node cache sending window values of the communication nodes in the target construction area at different construction stages, generating a set of corrected window values, and applying them to the parameter scheduling in the classification management of communication data.

2. The communication data classification management method based on AI analysis according to claim 1, wherein The step of analyzing whether there is the following abnormal feature pattern: as the construction degree value increases, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold includes: Parsing each group of local historical data to determine whether there is a trend change relationship that as the construction degree value increases, the effective upload data utilization rate of the communication nodes in the sub-area decreases accordingly during the construction process of the sub-area; Extracting all the local historical data that meet the above trend change relationship and calculating their proportion in all local historical data; When the proportion exceeds the preset threshold, it is determined that there is an abnormal feature pattern in the sub-areas that match the background information of the target construction area.

3. The communication data classification management method based on AI analysis according to claim 2, characterized in that The step of, if it is determined that there is an abnormal feature pattern, determining the reference sub-area and reference historical data that are most matched with the construction rhythm of the target construction area, and calculating the decrease amplitude of the effective upload data utilization rate of the reference sub-area at different construction stages compared with the initial construction stage includes: Based on the construction timeline, stage division method and construction progress characteristics of the target construction area, determining the reference sub-area that is most matched with the construction rhythm of the target construction area from several sub-areas with abnormal feature patterns, and setting the local historical data corresponding to the reference sub-area as the reference historical data; Obtaining the effective upload data utilization rates of the communication nodes in the reference sub-area at different construction stages and the initial construction stage; Sequentially calculating the decrease amplitude of the effective upload data utilization rate of each construction stage compared with the initial construction stage.

4. The communication data classification management method based on AI analysis according to claim 3, characterized in that, The step of converting all the decrease amplitudes into a set of correction factors, applying them to the original node cache sending window values of the communication nodes in the target construction area at different construction stages, generating a set of corrected window values, and applying them to the parameter scheduling in the classification management of communication data includes: Establishing the corresponding relationship between the construction stages of the target construction area and the reference sub-area, and associating each construction stage in the target construction area with the closest construction stage in the reference sub-area; The decreased amplitude values of the effective upload data utilization rates corresponding to each construction stage in the reference sub-region are respectively converted into correction factors for correcting the original node cache transmission window values of the communication nodes in the corresponding construction stage of the target construction region; According to the order of each construction stage in the target construction region, the correction factors are arranged in sequence to form a correction factor set; Call a preset window value correction function, and based on the correction factor set, adjust the original node cache transmission window values of the communication nodes in each construction stage in the target construction region one by one to generate a set of corrected node cache transmission window values, and use this set of window values for parameter scheduling in the communication data classification management process.

5. The communication data classification management method based on AI analysis according to claim 4, characterized in that The window value correction function is: ； Among them, refers to the corrected node cache transmission window value in the th construction stage of the target construction area, refers to the initial node cache transmission window value, refers to the effective upload data utilization rate in the construction stage corresponding to the th construction stage of the reference sub-area and the target construction area, refers to the effective upload data utilization rate in the initial construction stage of the reference sub-area, refers to the correction factor in the th construction stage of the target construction area, refers to the adjustment coefficient of the correction factor, and is greater than 0.

6. A communication data classification and management system based on AI analysis, characterized in that, The system includes: a data acquisition module, a data parsing module, an abnormal mode determination module, a decreased amplitude calculation module, and a window value correction module, where: The data acquisition module is used to acquire the original node cache transmission window values of the communication nodes in the target construction region of the target underground tunnel, and the historical construction and communication data of the target underground tunnel; The data parsing module is used to obtain several sub-regions that match the background information of the target construction region and have completed construction and the corresponding local historical data from the historical construction and communication data, and extract the construction degree values and effective upload data utilization rates of the sub-regions in different construction stages; The abnormal mode determination module is used to analyze whether there is the following abnormal characteristic mode: as the construction degree value increases, the effective upload data utilization rate shows a downward trend, and the proportion of this trend change relationship in all local historical data exceeds a preset threshold; The decreased amplitude calculation module is used to, if it is determined that there is an abnormal characteristic mode, determine the reference sub-region and reference historical data that are most matched with the construction rhythm of the target construction region, and calculate the decreased amplitude of the effective upload data utilization rate of the reference sub-region in different construction stages compared with the initial construction stage; The window value correction module is used to convert all the decreased amplitude values into a correction factor set, apply it to the original node cache transmission window values of the communication nodes in different construction stages in the target construction region, generate a set of corrected window values, and apply it to the parameter scheduling in the communication data classification management.

7. The communication data classification and management system based on AI analysis according to claim 6, characterized in that The abnormal mode determination module specifically includes: The trend change relationship analysis unit is used to parse each group of local historical data to determine whether there is a trend change relationship that as the construction degree value increases, the effective upload data utilization rate of its communication nodes decreases accordingly during the construction process of the sub-region; The proportion calculation unit is used to extract all the local historical data that meet the above trend change relationship and calculate its proportion in all local historical data; The abnormal characteristic mode determination unit is used to determine that there is an abnormal characteristic mode in the sub-region that matches the background information of the target construction region when the proportion exceeds the preset threshold.

8. The communication data classification and management system based on AI analysis according to claim 7, wherein, The decreased amplitude calculation module specifically includes: A reference data determination unit, configured to determine, based on the construction timeline, stage division method, and construction progress characteristics of the target construction area, a reference sub-area that best matches the construction rhythm of the target construction area from several sub-areas with abnormal feature patterns, and set the local historical data corresponding to the reference sub-area as reference historical data; A utilization rate extraction unit, configured to obtain the effective upload data utilization rates of communication nodes in the reference sub-area at different construction stages and the initial construction stage; A decline amplitude calculation unit, configured to sequentially calculate the decline amplitudes of the effective upload data utilization rates in each construction stage compared to the initial construction stage.

9. The communication data classification and management system based on AI analysis according to claim 8, characterized in that, The window value correction module specifically includes: A construction stage corresponding unit, configured to establish a corresponding relationship between the target construction area and the reference sub-area in terms of construction stages, and associate each construction stage in the target construction area with the closest construction stage in the reference sub-area; A correction factor conversion unit, configured to convert the decline amplitudes of the effective upload data utilization rates corresponding to each construction stage in the reference sub-area into correction factors for correcting the original node cache transmission window values of communication nodes at the corresponding construction stages in the target construction area; A set generation unit, configured to arrange the correction factors in sequence according to the order of each construction stage in the target construction area to form a correction factor set; A window value correction unit, configured to call a preset window value correction function, and based on the correction factor set, adjust the original node cache transmission window values of communication nodes in each construction stage in the target construction area one by one to generate a corrected node cache transmission window value set, and use this window value set for parameter scheduling in the communication data classification management process.

10. The communication data classification and management system based on AI analysis according to claim 9, characterized in that, The window value correction function is: ； Among them, refers to the corrected node cache sending window value in the th construction stage of the target construction area, refers to the initial node cache sending window value, refers to the effective upload data utilization rate in the construction stage corresponding to the th construction stage of the reference sub - area and the target construction area, refers to the effective upload data utilization rate in the initial construction stage of the reference sub - area, refers to the correction factor in the th construction stage of the target construction area, refers to the adjustment coefficient of the correction factor, and is greater than 0.

Images