Method, device, equipment, storage medium and product for trusted alignment of multi-source data

Abstract

The application discloses a kind of multi-source data's reliable alignment method, device, equipment, storage medium and product.Identify the discontinuous fragment of the measurement data sequence of each sensing device and associate sensing device identification, obtain measurement data variation section set;Determine the data channel of each associated sensing device based on sensing device identification and determine overlapping path section through network diagnosis, generate path network atlas;The target measurement data sequence that flows through each overlapping path section is segmented and processed to obtain target data segment, and different target data segments that flow through each overlapping path section at the same time are subjected to data flow consistency analysis to determine an interference channel list;Each target data segment in the target measurement data sequence via the interference channel is subjected to validity determination, and the effective data segment and the measurement data sequence of the non-interference channel are aligned and combined according to time to obtain multi-source reliable alignment data.It ensures data quality, avoids distortion information mixed into fusion results, and improves the accuracy and reliability of downstream decision-making.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a reliable alignment method, apparatus, device, storage medium, and product for multi-source data. Background Technology

[0002] With the large-scale deployment of various types of sensors such as temperature, humidity, air pressure, and vibration in scenarios such as industrial IoT and environmental monitoring, massive amounts of sensor time-series data are widely used for real-time monitoring and decision support after being transmitted and aggregated through complex networks.

[0003] However, due to the dispersed distribution of sensors and the complexity of network transmission paths, the data received at the aggregation point often suffers from quality issues such as timing misalignment, missing segments, and numerical jumps. Existing methods typically perform time alignment and fusion processing directly on these multi-source data with quality defects, resulting in a large amount of distorted information mixed into the fusion result, which seriously affects the accuracy and reliability of downstream decision-making. Summary of the Invention

[0004] This invention provides a reliable alignment method, apparatus, device, storage medium, and product for multi-source data, to solve the problem that existing methods directly perform time alignment and fusion processing on multi-source sensor data with quality defects, resulting in a large amount of distorted information mixed into the fusion result, which seriously affects the accuracy and reliability of downstream decision-making.

[0005] According to one aspect of the present invention, a reliable alignment method for multi-source data is provided, comprising: Acquire the measurement data sequences of each sensing device within the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments; Based on the sensor device identifiers in the set of measurement data change segments, the data channels of each associated sensor device are determined, network diagnostics are performed on each data channel to determine overlapping path segments, and a path network map is generated. Based on the path network map, the target measurement data sequence flowing through each overlapping path segment is segmented to obtain target data fragments. Then, data flow consistency analysis is performed on different target data fragments that flow through each overlapping path segment at the same time to identify interference channels and obtain a list of interference channels. Based on the interference channel list, the validity of each target data segment in the target measurement data sequence passing through the interference channel is determined, and the determined valid data segments and the measurement data sequence passing through the non-interference channel are combined in time alignment to obtain multi-source reliable aligned data.

[0006] According to another aspect of the present invention, a reliable alignment device for multi-source data is provided, comprising: An abnormal data identification module is used to acquire the measurement data sequences of each sensing device within the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments. The channel diagnostic module is used to determine the data channels of each associated sensor device based on the sensor device identifier in the set of measurement data change segments, perform network diagnostics on each data channel to determine overlapping path segments, and generate a path network map. The interference channel identification module is used to segment the target measurement data sequence flowing through each overlapping path segment based on the path network map to obtain target data segments, and to perform data flow consistency analysis on different target data segments that flow through each overlapping path segment at the same time to determine interference channels and obtain a list of interference channels. The data alignment module is used to determine the validity of each target data segment in the target measurement data sequence passing through the interference channel based on the interference channel list, and to combine the determined valid data segments and the measurement data sequence passing through the non-interference channel in time alignment to obtain multi-source reliable aligned data.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the trusted alignment method for multi-source data according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the trusted alignment method for multi-source data as described in any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the trusted alignment method for multi-source data as described in any embodiment of the present invention.

[0010] The technical solution of this invention involves acquiring measurement data sequences from various sensing devices within a monitoring area, identifying and extracting discontinuous segments from each measurement data sequence, associating each discontinuous segment with the sensor device identifier corresponding to its respective measurement data sequence to obtain a set of measurement data change segments; based on the sensor device identifiers in the set of measurement data change segments, determining the data channels of each associated sensing device, performing network diagnostics on each data channel to determine overlapping path segments, and generating a path network graph; based on the path network graph, segmenting the target measurement data sequences flowing through each overlapping path segment to obtain target data segments, and performing data flow consistency analysis on different target data segments flowing through each overlapping path segment simultaneously to determine interference channels and obtain an interference channel list; based on the interference channel list, determining the validity of each target data segment in the target measurement data sequence passing through the interference channels, and combining the determined valid data segments and the measurement data sequences passing through non-interference channels by time alignment to obtain multi-source reliable aligned data. By extracting discontinuous segments from the measurement data sequences of each sensor device, abnormal data is identified. Based on the sensor device identifiers associated with these discontinuous segments, data channels are determined and the network topology is diagnosed, locating overlapping path segments. The consistency of data flow across different target data segments on overlapping path segments is compared to identify anomalies and determine interfering channels. Then, valid data segments that have passed validity checks and measurement data sequences via non-interfering channels are time-aligned and combined. This approach enables anomaly identification and processing before data alignment, ensuring that only high-quality data participates in the alignment, avoiding the inclusion of distorted information in the fusion results, and significantly improving the accuracy and reliability of downstream decision-making.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart of a reliable alignment method for multi-source data provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of a trusted alignment device for multi-source data provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a trusted alignment method for multi-source data provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving quality diagnosis and time alignment of multi-source sensor data transmitted over complex networks. The method can be executed by a trusted alignment device for multi-source data, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes: S110. Obtain the measurement data sequence of each sensing device within the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments.

[0017] In this embodiment, the sensing device is a device deployed within the monitoring area for collecting environmental or equipment physical parameters, including but not limited to temperature and humidity sensors, air pressure sensors, and vibration sensors. The sensing device identifier is used to uniquely identify the sensing device and is embedded in the measurement data sequence during data reporting (such as the device ID field in the data frame header or payload). The measurement data sequence is a collection of raw measurement data from a single sensing device arranged in sampling order within a preset time window, containing the physical quantity values ​​at each sampling time and the corresponding sampling timestamp. Discontinuous segments are identified and segmented after performing temporal continuity analysis on the measurement data sequence; these segments are used to characterize data quality defects in the measurement data sequence, such as numerical jumps, missing sampling data, or temporal interval discontinuities.

[0018] Specifically, the process involves acquiring measurement data sequences reported by each sensor within the monitoring area, performing continuity analysis on each data sequence, identifying and extracting segments whose data continuity does not meet preset requirements, and designating these as discontinuous segments. Simultaneously, each discontinuous segment is associated with the sensor identifier of its corresponding measurement data sequence. Furthermore, by summarizing all discontinuous segments and their associated sensor identifiers, a set of measurement data variation segments is obtained. This allows for the preliminary identification of potential data anomalies and their sources.

[0019] S120. Based on the sensor device identifiers in the set of measurement data change segments, determine the data channels of each associated sensor device, perform network diagnosis on each data channel to determine overlapping path segments, and generate a path network map.

[0020] In this embodiment, the data channel is the communication link established between the sensing device and the transmission node, used to carry the transmission of measurement data sequences. Network diagnostics involves analyzing the transmission paths and topology of each data channel, identifying overlapping path segments between different data channels, and evaluating the transmission performance of each overlapping path segment, providing a basis for generating a path network map. Overlapping path segments are the same or shared transmission path intervals traversed by different data channels during transmission, and are key areas where potential interference or congestion of the data flow may occur.

[0021] Specifically, based on the sensor device identifiers in the set of measurement data change segments, the data channels corresponding to each sensor device are determined; network diagnostics are performed on each data channel to analyze the transmission path and topology of each data channel, identify overlapping path segments between different data channels, and evaluate the transmission performance status of each overlapping path segment; a network connection diagram of each data channel is constructed, and the transmission performance status of each overlapping path segment and corresponding transmission node is recorded on the network connection diagram to obtain the path network map.

[0022] S130. Based on the path network map, the target measurement data sequence flowing through each overlapping path segment is segmented to obtain target data fragments. Data flow consistency analysis is performed on different target data fragments flowing through each overlapping path segment simultaneously to determine interference channels and obtain a list of interference channels.

[0023] In this embodiment, the target measurement data sequence is the measurement data sequence flowing through overlapping path segments. The target data segment is a data segment obtained within the same time window after segmenting the target measurement data sequence. Each data segment is used for lateral comparison along the overlapping path segment dimension to verify whether the change patterns of multiple data streams are consistent. Data flow consistency refers to the degree of consistency in the flow patterns of different target data segments flowing through the same overlapping path segment simultaneously within the same time window; the flow pattern reflects the comprehensive performance of each data segment in terms of numerical changes, sampling patterns, and transmission characteristics. If there are significant differences in the flow patterns of multiple target data segments, it is determined that the data flow is inconsistent, indicating that there may be transmission interference in the overlapping path segment. The interference channel is an overlapping path segment identified after data flow consistency analysis that does not meet the preset transmission conditions. This path segment is used to characterize network congestion, signal conflicts, or other transmission anomalies during multi-source data transmission.

[0024] Specifically, based on the path network map, target measurement data sequences flowing through each overlapping path segment are located and extracted. Each target measurement data sequence is then segmented according to a unified time window to obtain target data fragments, ensuring comparability of these fragments in the temporal dimension. Furthermore, a horizontal comparison is conducted between multiple target data fragments flowing simultaneously along the same overlapping path segment to analyze data flow consistency. Based on this analysis, overlapping path segments exhibiting transmission anomalies are identified as interference channels by judging the differences in flow patterns between the target data fragments. Finally, all interference channels are summarized to obtain a list of interference channels, which is used for subsequent validity determination of data fragments within the interference channels.

[0025] S140. Based on the interference channel list, the validity of each target data segment in the target measurement data sequence passing through the interference channel is determined, and the determined valid data segments and the measurement data sequence passing through the non-interference channel are combined in time alignment to obtain multi-source reliable aligned data.

[0026] Specifically, based on the list of interference channels, target measurement data sequences transmitted through each interference channel are selected. The validity of each target data segment in each target measurement data sequence is determined, and the data integrity and timestamp continuity of each target data segment are checked to identify and eliminate data missing or time-series disordered segments caused by transmission anomalies, retaining only the data segments determined to be valid. For measurement data sequences transmitted through non-interference channels, since they are not affected by transmission anomalies, they are considered as valid data as a whole. To maintain a uniform alignment granularity with the valid data segments, the data segments are processed according to a uniform time window. After obtaining the data segments, they are time-aligned and combined with the determined valid data segments according to a uniform time series benchmark, ultimately forming multi-source trusted aligned data with regular time series and reliable data quality, completing the cleaning, screening, and trusted fusion of multi-source data.

[0027] The technical solution provided in Embodiment 1 of this invention involves acquiring measurement data sequences from various sensing devices within a monitoring area, identifying and extracting discontinuous segments from each measurement data sequence, associating each discontinuous segment with the sensor device identifier corresponding to its respective measurement data sequence to obtain a set of measurement data change segments; based on the sensor device identifiers in the set of measurement data change segments, determining the data channels of each associated sensing device, performing network diagnostics on each data channel to determine overlapping path segments, and generating a path network graph; based on the path network graph, segmenting the target measurement data sequences flowing through each overlapping path segment to obtain target data segments, and performing data flow consistency analysis on different target data segments flowing through each overlapping path segment simultaneously to determine interference channels and obtain a list of interference channels; based on the list of interference channels, determining the validity of each target data segment in the target measurement data sequence passing through the interference channels, and combining the determined valid data segments and the measurement data sequences passing through non-interference channels by time alignment to obtain multi-source reliable aligned data. By extracting discontinuous segments from the measurement data sequences of each sensor device, abnormal data is identified. Based on the sensor device identifiers associated with these discontinuous segments, data channels are determined and the network topology is diagnosed, locating overlapping path segments. The consistency of data flow across different target data segments on overlapping path segments is compared to identify anomalies and determine interfering channels. Then, valid data segments that have passed validity checks and measurement data sequences via non-interfering channels are time-aligned and combined. This approach enables anomaly identification and processing before data alignment, ensuring that only high-quality data participates in the alignment, avoiding the inclusion of distorted information in the fusion results, and significantly improving the accuracy and reliability of downstream decision-making.

[0028] In some embodiments, the step of identifying and extracting discontinuous segments from each of the measurement data sequences, and associating each discontinuous segment with a sensor device identifier corresponding to its respective measurement data sequence to obtain a set of measurement data change segments includes: determining the change characteristics of each measurement data sequence; for each measurement data sequence, performing time segmentation on the current measurement data sequence based on the change characteristics of the current measurement data sequence to obtain multiple continuous data segments; comparing adjacent data segments to identify the discontinuous positions of the current measurement data sequence, extracting discontinuous segments based on the discontinuous positions; associating each discontinuous segment with a sensor device identifier corresponding to its respective measurement data sequence; and obtaining a set of measurement data change segments based on the discontinuous segments of each measurement data sequence and the sensor device identifier associated with the discontinuous segments.

[0029] In this embodiment, the variation characteristics can be understood as the statistical attributes obtained after performing time-series analysis on the measurement data sequence of a single sensing device, used to describe the numerical variation patterns and laws. These include, but are not limited to: the linear trend of data values, fluctuation amplitude, uniformity of sampling time intervals, and the degree of numerical difference between adjacent data points. Discontinuity locations are the boundary points where data continuity is interrupted, identified by comparing adjacent data segments after segmenting the same measurement data sequence over time. Discontinuity locations are manifested as numerical jumps between adjacent segments exceeding a preset threshold, missing sampled data, or abnormally increased sampling time intervals; they serve as the start and end markers for extracting discontinuous segments.

[0030] Specifically, the variation characteristics of each measurement data sequence are determined one by one to characterize the numerical variation patterns and temporal evolution attributes of the data. For each measurement data sequence, time segmentation is performed based on its own variation characteristics, dividing the entire measurement data sequence into multiple data segments arranged continuously in time. By comparing the state and values ​​of adjacent data segments one by one, anomalies in the connection between segments are screened to identify discontinuous positions in the measurement data sequence. Then, using the identified discontinuous positions as boundaries, the corresponding discontinuous segments are extracted. Subsequently, each discontinuous segment is bound and associated with the sensor device identifier corresponding to its measurement data sequence. Finally, all discontinuous segments of the measurement data sequences and their associated sensor device identifiers are integrated and summarized to form a set of measurement data variation segments.

[0031] For example, a vibration sensor collects amplitude data 100 times per second, and under normal circumstances, the amplitude fluctuates smoothly within the range of 0.1g to 0.3g. Analysis of the sensor's measurement data sequence reveals that within a 1-second timeframe, the amplitude at 100 sampling points suddenly jumps to over 2.5g, creating a significant discontinuity compared to the smooth trend in adjacent timeframes. By comparing adjacent data segments, this timeframe is identified as a discontinuous location, extracted as a discontinuous segment, associated with the vibration sensor's device identifier, and included in the set of measurement data variation segments.

[0032] This embodiment extracts discontinuous segments and associates them with sensor device identifiers to accurately identify data quality abnormalities and establish device attribution mappings before data alignment and fusion, providing a basis for subsequent transmission path diagnosis and effective data screening.

[0033] In some embodiments, the step of performing network diagnostics on each of the data channels to determine overlapping path segments and generate a path network map includes: determining overlapping path segments between different data channels based on the transmission line routing of each data channel; selecting target transmission nodes that meet preset load conditions from each overlapping path segment and evaluating the transmission direction stability of each overlapping path segment; constructing a network connection diagram for each data channel, and recording each overlapping path segment, the transmission direction stability of each overlapping path segment, and the load status of each target transmission node on the network connection diagram to obtain a path network map.

[0034] In this embodiment, the transmission line route refers to the specific routing trajectory followed by each data channel in the network topology, including the transmission nodes traversed sequentially and the link connections between nodes. The link connections include the routing links and interface connection methods between adjacent transmission nodes in the data channel. The data channel is the communication link between the sensing device and the transmission node, and the transmission line route characterizes the spatial extension path of this link in the network and the order in which nodes are traversed. By comparing the transmission line routes of different data channels, it is possible to identify whether there are shared transmission intervals between channels, thereby determining overlapping path segments. The preset load condition is a criterion used to evaluate the processing capacity of transmission nodes, and this criterion is set based on at least one performance indicator among bandwidth utilization, data throughput, and transmission delay. The transmission direction stability is the ability of the data channel to maintain a stable data transmission flow on the overlapping path segment; if the data channel frequently experiences route switching or flow changes during transmission, the transmission direction stability is low, indicating transmission instability in the overlapping path segment; conversely, the transmission flow remains stable, and the stability is high. A network connection graph is a network topology representation structure constructed with each transmission node as a connection point and each data channel as a link. It is used to describe the connection relationships between data channels and the link distribution between transmission nodes. After recording each overlapping path segment, the stability of the transmission direction of each overlapping path segment, and the load status of each transmission node on the network connection graph, a path network map is formed.

[0035] Specifically, based on the transmission route of each data channel, the transmission nodes and link connections traversed by each data channel are compared. This comparison identifies whether multiple data channels pass through the same transmission nodes and share links, thereby determining the shared transmission intervals as overlapping path segments. Then, for each overlapping path segment, the load status of the corresponding transmission node is obtained. The load status includes at least one performance indicator among bandwidth utilization, data throughput, and transmission delay during data communication. It is determined whether the load status meets preset load conditions, and transmission nodes that meet the conditions are identified as target transmission nodes. Simultaneously, the changes in the transmission direction of the data channels on each overlapping path segment are monitored. Changes in the transmission direction refer to changes in the data flow direction or routing path during data transmission, thereby assessing the stability of the transmission direction of each overlapping path segment. Subsequently, a network connection graph is constructed using each transmission node as a connection point and each data channel as a link. The network connection graph records each overlapping path segment, the stability of the transmission direction of each overlapping path segment, and the load status of each target transmission node, resulting in a path network map.

[0036] For example, two sensing devices upload data through different data channels, and the transmission lines of both channels pass through the same network switch. By comparing the transmission nodes traversed by the two channels, the switch is identified as a shared transmission range, thus forming an overlapping path segment. The load status of the switch is then obtained, and if it meets preset load conditions, it is determined as the target transmission node. Simultaneously, the changes in the direction of data transmission through the switch are monitored to assess the stability of the transmission direction. The location of the overlapping path segment, the load status of the target transmission node, and the stability of the transmission direction are recorded in the network connection diagram, forming a path network graph.

[0037] By identifying overlapping path segments based on the transmission line routes of each data channel and assessing the stability of the transmission direction to construct a path network map, the correlation mapping between data quality anomalies and network transmission topology is realized. This accurately locates bottleneck areas in the shared transmission path of multi-source data, providing network topology basis for subsequent identification of transmission anomalies and determination of data validity, thereby improving the traceability of multi-source data transmission paths and the reliability of network resource optimization.

[0038] In some embodiments, the step of performing data flow consistency analysis on different target data segments that simultaneously flow through overlapping path segments to determine interference channels includes: for each overlapping path segment, comparing the flow patterns of different target data segments flowing through the current overlapping path segment within the same time window; wherein the flow pattern includes at least one of data change trend, numerical fluctuation amplitude, and sampling time regularity; identifying abnormal flow segments with inconsistent data flow based on the comparison results; counting the occurrence frequency of abnormal flow segments corresponding to each overlapping path segment, and determining overlapping path segments whose occurrence frequency of abnormal flow segments exceeds a preset threshold as interference channels.

[0039] In this embodiment, the same time window refers to a fixed observation period with aligned time axes and a fixed duration, set for each target data segment flowing through the same overlapping path segment during data flow consistency analysis. This serves as a unified time series benchmark for comparing multiple data flow patterns. The flow pattern is a comprehensive representation of the target data segment's numerical changes, sampling patterns, and transmission characteristics within the same time window. The flow pattern includes at least one of data change trends, numerical fluctuation amplitudes, and sampling time regularity, used to characterize the transmission consistency of multiple target data segments on the overlapping path segment. The data change trend is the characteristic of the change in the numerical values ​​of each data point within the target data segment over time, including patterns such as numerical increase, decrease, stable fluctuations, or sudden changes. By comparing the data change trends of multiple target data segments, the transmission consistency of each segment on the overlapping path segment can be determined. The numerical fluctuation amplitude is the degree of deviation of the numerical values ​​of each data point within the target data segment from the benchmark level, used to characterize the dispersion and oscillation intensity of the data within the sampling period. By comparing the numerical fluctuation amplitudes of multiple target data segments, the differences in data stability of each segment on the overlapping path segment can be identified. Sampling time regularity refers to the uniformity of the sampling time interval between adjacent data points within a target data segment. If the sampling time interval is uniform and conforms to the preset sampling period, the sampling time regularity is high; conversely, if the sampling time interval shows jumps, gaps, or abnormal increases, the sampling time regularity is low. By comparing the sampling time regularity of multiple target data segments, temporal consistency differences between segments on overlapping path segments can be identified. Abnormal flow segments are data segments identified in data flow consistency analysis as having significantly different flow patterns from other target data segments on the same overlapping path segment. These differences manifest as inconsistent data change trends, significant numerical fluctuations, or mismatched sampling time regularities. The preset threshold can be set according to actual conditions.

[0040] Specifically, within the same time window, a data flow consistency analysis is conducted on multiple target data segments flowing simultaneously on overlapping path segments. The performance of each target data segment is compared one by one from at least one dimension: data change trend, numerical fluctuation amplitude, and sampling time regularity. Target data segments showing significant deviations in the comparison results are identified as abnormal flow segments with inconsistent data flow. Furthermore, the frequency of occurrence of abnormal flow segments on each overlapping path segment is statistically analyzed. If the frequency of occurrence of abnormal flow segments on a certain overlapping path segment exceeds a preset threshold, that overlapping path segment is identified as an interference channel. Finally, all interference channels are summarized to obtain a list of interference channels.

[0041] For example, three target measurement data sequences flow simultaneously along an overlapping path segment, and after segmentation, corresponding target data segments are obtained. The flow patterns of the three target data segments are compared within the same time window: two of the target data segments show a steady increasing trend with numerical fluctuations within 0.1g and uniform sampling intervals; while the third target data segment exhibits a sudden increase in numerical fluctuations exceeding 2.5g, and its sampling intervals become disordered. The comparison confirms a significant difference in flow pattern between the third and first two segments, identifying it as an abnormal flow segment. If the frequency of such abnormal flow segments on the overlapping path segment exceeds a preset threshold, the overlapping path segment is determined as an interference channel and included in the interference channel list.

[0042] By comparing the flow patterns of multiple target data segments on overlapping path segments, abnormal flow segments with inconsistent data flow are accurately identified and their frequency of occurrence is counted. Overlapping path segments with frequent transmission anomalies are identified as interference channels, enabling precise location and isolation marking of bottlenecks in multi-source data transmission. This provides a channel-level screening basis for subsequent removal of distorted data and ensuring the quality of fused data.

[0043] In some embodiments, the step of determining the validity of each target data segment in the target measurement data sequence via the interference channel based on the interference channel list, and combining the determined valid data segments with the measurement data sequence via the non-interference channel in time alignment to obtain multi-source reliable aligned data, includes: for each interference channel in the interference channel list, determining multiple target measurement data sequences corresponding to the current interference channel; for each target measurement data sequence, verifying the data integrity and timestamp continuity of each target data segment in the current target measurement data sequence to determine valid data segments; and combining each valid data segment with the measurement data sequence via the non-interference channel in time alignment to obtain multi-source reliable aligned data.

[0044] In this embodiment, data integrity refers to the completeness of data fields and the number of data points within the target data segment. If there are missing fields, missing data points, or incomplete sampling records within the target data segment, the data integrity of that segment is deemed unsatisfactory. Timestamp continuity refers to the uniformity of sampling time intervals between adjacent data points within the target data segment. If the time interval between adjacent data points conforms to the preset sampling period and there are no time interval jumps, the timestamp of that segment is deemed continuous; otherwise, there is a time discontinuity and the timestamp continuity is not up to standard. Valid data segments are target data segments from the target measurement data sequence transmitted through interference channels that meet the preset requirements for both data integrity and timestamp continuity. Valid data segments possess complete field information and uniform sampling time sequence, and can participate in subsequent time alignment combinations. Non-interference channels are data channels that were not identified as interference channels in the data flow consistency analysis. Measurement data sequences transmitted through non-interference channels are not affected by transmission anomalies, and their data segments are considered valid as a whole and can directly participate in time alignment combinations.

[0045] Specifically, for each interference channel in the interference channel list, multiple target measurement data sequences corresponding to the current interference channel are identified. For each target measurement data sequence, the data integrity and timestamp continuity of each target data segment in the current target measurement data sequence are checked. This includes verifying whether the data fields within each target data segment are complete, whether there are any missing sampling data points, and whether the time sequence between adjacent data points within each target data segment is consistent and whether the time interval conforms to the preset sampling period. Target data segments that simultaneously meet the data integrity and timestamp continuity requirements are determined as valid data segments. Furthermore, the valid data segments corresponding to each interference channel and the measurement data sequences via non-interference channels are time-aligned and combined according to a unified time reference to form multi-source reliable aligned data with clear origins and consistent time sequence.

[0046] For example, the target measurement data sequence corresponding to a certain interference channel contains 10 target data segments. Upon inspection, 3 of the target data segments have missing sampling data (data integrity not satisfied), and the time interval between adjacent data points in 2 of the target data segments abruptly changes from a preset 5 seconds to 15 seconds (timestamp continuity not satisfied). These 5 segments are discarded; the remaining 5 target data segments that simultaneously satisfy both data integrity and timestamp continuity are determined as valid data segments. Furthermore, these 5 valid data segments are combined with the measurement data sequence via the non-interference channel according to time alignment to obtain multi-source reliable aligned data.

[0047] This embodiment performs integrity and timing continuity checks on data segments from interfering channels, filters valid data segments and removes abnormal segments; then it combines the valid data segments with the data from non-interfering channels in a timing-aligned manner to avoid data distortion and timing disorder caused by channel interference, ensuring the integrity, reliability and timing matching of multi-source data, and improving the accuracy of subsequent data fusion analysis.

[0048] In some embodiments, the step of combining each valid data segment and the measurement data sequence via the non-interference channel in time alignment to obtain multi-source reliable aligned data includes: arranging each valid data segment and the measurement data sequence via the non-interference channel according to a unified time reference, and filling the time positions of missing valid data segments with null values ​​or invalid records to obtain multi-source reliable aligned data.

[0049] This embodiment uses a unified time base to arrange the time series of multi-source data, and fills in the missing time positions with null values ​​or invalid records, so that the time series of each data is regular and the time dimension is strictly aligned; it not only fills in the time series gaps of the data, but also ensures the uniformity of the multi-source data structure and the reliability of the time series matching, which facilitates subsequent unified processing and fusion analysis.

[0050] Optionally, before acquiring the measurement data sequences of each sensor device within the monitoring area, the data transmission status of each sensor device can be monitored to detect the time interval of its transmitted signals. By comparing the transmission intervals at different time intervals, it can be determined whether the signal is continuous and stable. Simultaneously, network access layer link status information can be retrieved to check the connection between the device and the access channel, analyzing the impact of link bandwidth, latency, and packet loss rate on signal stability. Furthermore, the connection process between the device and the access channel can be examined to determine if there are any mismatches in frequency settings, protocol versions, data formats, etc., thus identifying the cause of signal interruption. Through this pre-monitoring, sensor devices with a risk of communication interruption can be preemptively eliminated or marked, ensuring that the subsequently acquired measurement data sequences have basic transmission reliability and providing a data source foundation for the identification and extraction of discontinuous segments.

[0051] Example 2 Figure 2 This is a schematic diagram of a trusted alignment device for multi-source data provided in Embodiment 2 of the present invention. Figure 2 As shown, the device includes: The abnormal data identification module 21 is used to acquire the measurement data sequence of each sensing device in the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments. Channel diagnostic module 22 is used to determine the data channels of each associated sensor device based on the sensor device identifier in the set of measurement data change segments, perform network diagnostics on each data channel to determine overlapping path segments, and generate a path network map; The interference channel identification module 23 is used to segment the target measurement data sequence flowing through each overlapping path segment based on the path network map to obtain target data segments, and to perform data flow consistency analysis on different target data segments that flow through each overlapping path segment at the same time to determine interference channels and obtain a list of interference channels. The data alignment module 24 is used to determine the validity of each target data segment in the target measurement data sequence via the interference channel based on the interference channel list, and to combine the determined valid data segments and the measurement data sequence via the non-interference channel in time alignment to obtain multi-source reliable aligned data.

[0052] The technical solution provided in Embodiment 2 of this invention identifies abnormal data by extracting discontinuous segments from the measurement data sequences of each sensing device; determines data channels and diagnoses network topology based on the sensor device identifiers associated with the discontinuous segments, locating overlapping path segments; compares the data flow consistency of different target data segments on the overlapping path segments to identify anomalies and determine interference channels; and then, aligns and combines the valid data segments that have passed the validity determination with the measurement data sequences that pass through non-interference channels according to time. This achieves anomaly identification and processing before data alignment, ensuring that only high-quality data participates in the alignment, avoiding distorted information from being mixed into the fusion result, and significantly improving the accuracy and reliability of downstream decision-making.

[0053] Optionally, the abnormal data identification module 21 includes: The change characteristic determination unit is used to determine the change characteristics of each measurement data sequence; The segmentation processing unit is used to segment the current measurement data sequence into multiple continuous data segments based on the changing characteristics of the current measurement data sequence. The discontinuous segment extraction unit is used to compare adjacent data segments, identify the discontinuous positions of the current measurement data sequence, and extract discontinuous segments based on the discontinuous positions; An identification association unit is used to associate each of the discontinuous segments with the sensor device identifier corresponding to the measurement data sequence to which they belong; The variation segment set generation unit is used to obtain a measurement data variation segment set based on the discontinuous segments of each measurement data sequence and the sensor device identifier associated with the discontinuous segments.

[0054] Optionally, the channel diagnostic module 22 includes: The overlapping path segment determination unit is used to determine the overlapping path segments between different data channels based on the transmission line routing of each data channel. The transmission performance evaluation unit is used to select target transmission nodes that meet preset load conditions from each overlapping path segment and evaluate the transmission direction stability of each overlapping path segment. The graph construction unit is used to construct the network connection graph of each data channel, and record each overlapping path segment, the stability of the transmission direction of each overlapping path segment, and the load status of each target transmission node on the network connection graph to obtain the path network graph.

[0055] Optionally, the interference channel identification module 23 includes: The pattern comparison unit is used to compare the flow patterns of different target data segments flowing through the current overlapping path segments within the same time window for each overlapping path segment; wherein the flow pattern includes at least one of data change trend, numerical fluctuation amplitude and sampling time regularity. The abnormal segment identification unit is used to identify abnormal flow segments with inconsistent data flow based on the comparison results. The interference channel determination unit is used to count the frequency of occurrence of abnormal flow segments corresponding to each overlapping path segment, and to determine the overlapping path segments whose frequency of occurrence of abnormal flow segments exceeds a preset threshold as interference channels.

[0056] Optionally, the data alignment module 24 includes: The target sequence determination unit is used to determine multiple target measurement data sequences corresponding to the current interference channel for each interference channel in the interference channel list. The valid fragment verification unit is used to verify the data integrity and timestamp continuity of each target data fragment in the current target measurement data sequence for each target measurement data sequence in order to determine the valid data fragments; The data alignment unit is used to align and combine each valid data segment and the measurement data sequence via the non-interference channel according to time to obtain multi-source reliable aligned data.

[0057] Optionally, the data alignment module 24 is specifically used to arrange each valid data segment and the measurement data sequence via the non-interference channel according to a unified time reference, and fill the time position of the missing valid data segment with null values ​​or invalid records to obtain multi-source reliable aligned data.

[0058] The trusted alignment device for multi-source data provided in the embodiments of the present invention can execute the trusted alignment method for multi-source data provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0059] Example 3 Figure 3 This is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0060] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0061] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0062] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a trusted alignment method for multi-source data.

[0063] In some embodiments, the trusted alignment method for multi-source data may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the trusted alignment method for multi-source data described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the trusted alignment method for multi-source data by any other suitable means (e.g., by means of firmware).

[0064] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0065] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0066] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0067] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0068] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0069] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0070] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0071] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0072] This invention also provides a computer program product, including a computer program and / or instructions, which, when executed by a processor, implements the trusted alignment method for multi-source data as provided in any embodiment of this application.

[0073] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0074] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A reliable alignment method for multi-source data, characterized in that, include: Acquire the measurement data sequences of each sensing device within the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments; Based on the sensor device identifiers in the set of measurement data change segments, the data channels of each associated sensor device are determined, network diagnostics are performed on each data channel to determine overlapping path segments, and a path network map is generated. Based on the path network map, the target measurement data sequence flowing through each overlapping path segment is segmented to obtain target data fragments. Then, data flow consistency analysis is performed on different target data fragments that flow through each overlapping path segment at the same time to identify interference channels and obtain a list of interference channels. Based on the interference channel list, the validity of each target data segment in the target measurement data sequence passing through the interference channel is determined, and the determined valid data segments and the measurement data sequence passing through the non-interference channel are combined in time alignment to obtain multi-source reliable aligned data.

2. The method according to claim 1, characterized in that, The process involves identifying and extracting discontinuous segments from each of the measurement data sequences, associating each discontinuous segment with the sensor identifier corresponding to its respective measurement data sequence, and obtaining a set of measurement data variation segments, including: Determine the variation characteristics of each measurement data sequence; For each measurement data sequence, based on the changing characteristics of the current measurement data sequence, the current measurement data sequence is segmented over time to obtain multiple continuous data segments; By comparing adjacent data segments, the discontinuity positions of the current measurement data sequence are identified, and discontinuous segments are extracted based on the discontinuity positions; And associate each of the discontinuous segments with the sensor identifier corresponding to its respective measurement data sequence; Based on the discontinuous segments of each measurement data sequence and the sensor device identifiers associated with the discontinuous segments, a set of measurement data change segments is obtained.

3. The method according to claim 1, characterized in that, The step of performing network diagnostics on each of the data channels to determine overlapping path segments and generate a path network graph includes: Based on the transmission line routing of each data channel, the overlapping path segments between different data channels are determined. Select target transmission nodes that meet the preset load conditions from each overlapping path segment, and evaluate the stability of the transmission direction of each overlapping path segment. Construct a network connection diagram for each data channel, and record each overlapping path segment, the stability of the transmission direction of each overlapping path segment, and the load status of each target transmission node on the network connection diagram to obtain a path network map.

4. The method according to claim 1, characterized in that, The step of performing data flow consistency analysis on different target data segments that simultaneously flow through overlapping path segments to determine interference channels includes: For each overlapping path segment, within the same time window, the flow patterns of different target data segments flowing through the current overlapping path segment are compared; wherein, the flow pattern includes at least one of data change trend, numerical fluctuation amplitude and sampling time regularity; Based on the comparison results, abnormal data flow segments with inconsistent data flow were identified; The frequency of occurrence of abnormal flow segments corresponding to each overlapping path segment is counted, and overlapping path segments whose frequency of occurrence of abnormal flow segments exceeds a preset threshold are identified as interference channels.

5. The method according to claim 1, characterized in that, Based on the interference channel list, the validity of each target data segment in the target measurement data sequence via the interference channel is determined, and the determined valid data segments and the measurement data sequence via the non-interference channel are combined in time alignment to obtain multi-source reliable aligned data, including: For each interference channel in the interference channel list, determine multiple target measurement data sequences corresponding to the current interference channel; For each target measurement data sequence, the data integrity and timestamp continuity of each target data segment in the current target measurement data sequence are checked to determine the valid data segments; By aligning and combining each valid data segment and the measurement data sequence via the non-interference channel according to time, multi-source reliable aligned data is obtained.

6. The method according to claim 5, characterized in that, The step of combining each valid data segment and the measurement data sequence via the non-interference channel in time alignment to obtain multi-source reliable aligned data includes: The valid data segments and the measurement data sequence via the non-interference channel are arranged according to a unified time base. For the time positions of missing valid data segments, null values ​​or invalid records are filled in to obtain multi-source reliable aligned data.

7. A trusted alignment device for multi-source data, characterized in that, include: An abnormal data identification module is used to acquire the measurement data sequences of each sensing device within the monitoring area, identify and extract discontinuous segments of each measurement data sequence, associate each discontinuous segment with the sensing device identifier corresponding to its measurement data sequence, and obtain a set of measurement data change segments. The channel diagnostic module is used to determine the data channels of each associated sensor device based on the sensor device identifier in the set of measurement data change segments, perform network diagnostics on each data channel to determine overlapping path segments, and generate a path network map. The interference channel identification module is used to segment the target measurement data sequence flowing through each overlapping path segment based on the path network map to obtain target data segments, and to perform data flow consistency analysis on different target data segments that flow through each overlapping path segment at the same time to determine interference channels and obtain a list of interference channels. The data alignment module is used to determine the validity of each target data segment in the target measurement data sequence passing through the interference channel based on the interference channel list, and to combine the determined valid data segments and the measurement data sequence passing through the non-interference channel in time alignment to obtain multi-source reliable aligned data.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the trusted alignment method for multi-source data as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the trusted alignment method for multi-source data as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the trusted alignment method for multi-source data as described in any one of claims 1-6.

Images