Beidou positioning data processing method and system based on artificial intelligence

Abstract

The present application provides a Beidou positioning data processing method and system based on artificial intelligence. First, by collecting the prior position deviation and instant position deviation of each monitoring point in different Beidou positioning stages, the first abnormal positioning stage is screened out by using the prior position deviation and the position deviation parameter in the basic abnormal positioning observation model. By further combining the abnormal positioning continuous parameter, the key abnormal positioning stage is determined. At the same time, the second abnormal positioning stage is screened out according to the instant position deviation. Then, according to the signal coverage area and the key abnormal positioning stage in a specific Beidou positioning partition, the performance deviation between the prior positioning performance and the instant positioning performance is compared, the basic abnormal positioning observation model is updated, and an optimized target abnormal positioning observation model is generated, so that it can dynamically adapt to changes in the Beidou positioning partition, and timely correct and optimize the abnormal positioning observation mechanism, so as to improve the reliability of Beidou positioning in a specific area in the future.

Description

Technical Field

[0001] The present application relates to the field of Beidou positioning technology, and more specifically, to a Beidou positioning data processing method and system based on artificial intelligence. Background Art

[0002] In the current Beidou positioning system, the positioning accuracy may be affected to varying degrees due to the influence of various external factors (such as signal interference, building obstruction, weather changes, etc.). In order to ensure the stability and accuracy of the Beidou positioning system, it is necessary to monitor the Beidou positioning system and handle abnormal positioning. Traditional abnormal positioning methods may not be able to fully utilize historical prior data to predict and identify potential abnormal stages, and the response to immediate position deviations may not be timely or accurate enough. In addition, the existing technology may not have an effective mechanism to automatically update the abnormal positioning observation mechanism to adapt to environmental changes. Summary of the invention

[0003] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a Beidou positioning data processing method and system based on artificial intelligence.

[0004] In a first aspect, the present application provides a Beidou positioning data processing method based on artificial intelligence, which is applied to a Beidou positioning cloud service system, and the method includes:

[0005] Collect the prior position deviation and instantaneous position deviation associated with each monitoring point in a specific Beidou positioning partition in multiple Beidou positioning stages;

[0006] For each of the monitoring points, based on the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, a first abnormal positioning stage is screened out from each Beidou positioning stage, and based on the abnormal positioning persistence parameter included in the basic abnormal positioning observation model, a key abnormal positioning stage is determined from each first abnormal positioning stage;

[0007] For each of the monitoring points, according to the instant position deviation, a second abnormal positioning stage is selected from the various Beidou positioning stages;

[0008] According to the signal coverage area and the key abnormal positioning stage corresponding to the monitoring points in the specific Beidou positioning partition where there is a key abnormal positioning stage, determine the priori positioning performance corresponding to the specific Beidou positioning partition; according to the signal coverage area and the second abnormal positioning stage corresponding to the monitoring points in the specific Beidou positioning partition where there is a second abnormal positioning stage, determine the real-time positioning performance corresponding to the specific Beidou positioning partition;

[0009] According to the performance deviation between the prior positioning performance and the real-time positioning performance, the basic abnormal positioning observation model is updated, and when the performance deviation meets the set standard, an optimized target abnormal positioning observation model is generated; the optimized target abnormal positioning observation model is used to estimate the monitoring points in the key abnormal positioning stage in the specific Beidou positioning partition based on the real-time position deviation.

[0010] In a possible implementation of the first aspect, the collecting of the priori position deviations and the immediate position deviations associated with each monitoring point in a specific Beidou positioning partition in multiple Beidou positioning stages includes:

[0011] Each monitoring point in a specific Beidou positioning zone is used as a target monitoring point;

[0012] Obtain multiple priori positioning accuracies associated with the target monitoring point in multiple Beidou positioning stages; multiple priori positioning accuracies corresponding to the same Beidou positioning stage are the positioning accuracies associated with multiple priori data recording intervals in the same Beidou positioning stage;

[0013] For each Beidou positioning stage, determine the positioning accuracy label associated with each prior positioning accuracy, and determine the prior position deviation corresponding to the target monitoring point in the Beidou positioning stage according to the weight of the accuracy statistics of the prior positioning accuracy of the positioning accuracy label as the target accuracy evaluation label in the global accuracy statistics;

[0014] The real-time positioning accuracy associated with the target monitoring point in each Beidou positioning stage is obtained as the real-time position deviation associated with the target monitoring point in each Beidou positioning stage; the real-time positioning accuracy is the positioning accuracy corresponding to the real-time data recording interval.

[0015] In a possible implementation of the first aspect, for each of the monitoring points, based on the priori position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, a first abnormal positioning stage is screened out from each Beidou positioning stage, and based on the abnormal positioning persistence parameter included in the basic abnormal positioning observation model, a key abnormal positioning stage is determined from each first abnormal positioning stage, including:

[0016] For the real-time monitoring point, each Beidou positioning stage is divided into a first abnormal positioning stage and a first non-abnormal positioning stage according to the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model; the prior position deviation corresponding to the first abnormal positioning stage is not less than the position deviation parameter;

[0017] Arrange the first abnormal positioning phase and the first non-abnormal positioning phase corresponding to the instant monitoring point according to the phase order to generate a basic Beidou positioning phase cluster;

[0018] From the basic Beidou positioning phase cluster corresponding to the instant monitoring point, acquiring each first abnormal positioning phase that progresses in sequence to construct a first Beidou positioning phase cluster, and determining the global phase parameter of the first Beidou positioning phase cluster as the first cumulative abnormal phase parameter;

[0019] From the first Beidou positioning stage clusters corresponding to the instant monitoring point, the first Beidou positioning stage cluster whose first cumulative abnormal stage parameter is not less than the abnormal positioning continuous parameter contained in the basic abnormal positioning observation model is taken as the first target Beidou positioning stage cluster, and each first abnormal positioning stage in the first target Beidou positioning stage cluster is taken as the key abnormal positioning stage corresponding to the instant monitoring point.

[0020] In a possible implementation of the first aspect, the method further includes:

[0021] From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each first non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the first normal stage parameter, and when the first normal stage parameter is not greater than the non-abnormal positioning duration parameter included in the basic abnormal positioning observation model, convert each first non-abnormal positioning stage corresponding to the first normal stage parameter into the first abnormal positioning stage, and generate a first optimized Beidou positioning stage set;

[0022] In the first optimized Beidou positioning stage set corresponding to the instant monitoring point, each first abnormal positioning stage that progresses in sequence is obtained to construct a second Beidou positioning stage cluster, and a global stage parameter of the second Beidou positioning stage cluster is determined as a second accumulated abnormal stage parameter;

[0023] From the second Beidou positioning stage clusters corresponding to the instant monitoring point, the second Beidou positioning stage cluster whose second cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter is taken as the second target Beidou positioning stage cluster, and the first abnormal positioning stages in the second target Beidou positioning stage cluster are taken as the key abnormal positioning stages corresponding to the instant monitoring point.

[0024] In a possible implementation of the first aspect, the method further includes:

[0025] From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, the first non-abnormal positioning stage in which the prior position deviation is not less than the adjusted offset parameter is used as a candidate non-abnormal positioning stage; the adjusted offset parameter is obtained by reducing the position deviation parameter according to the abnormal positioning update parameter in the basic abnormal positioning observation model;

[0026] From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each candidate non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the second normal stage parameter, and when the second normal stage parameter is not greater than the non-abnormal positioning duration parameter included in the basic abnormal positioning observation model, convert each candidate non-abnormal positioning stage corresponding to the second normal stage parameter into the first abnormal positioning stage, and generate a second optimized Beidou positioning stage set;

[0027] In the second optimized Beidou positioning stage set corresponding to the instant monitoring point, each first abnormal positioning stage that progresses in sequence is obtained to construct a third Beidou positioning stage cluster, and a global stage parameter of the third Beidou positioning stage cluster is determined as a third accumulated abnormal stage parameter;

[0028] From the third Beidou positioning stage clusters corresponding to the immediate monitoring point, the third Beidou positioning stage cluster whose third cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter is taken as the third target Beidou positioning stage cluster, and each first abnormal positioning stage in the third target Beidou positioning stage cluster is taken as the key abnormal positioning stage corresponding to the immediate monitoring point.

[0029] In a possible implementation of the first aspect, for each of the monitoring points, screening out the second abnormal positioning stage from the various Beidou positioning stages according to the real-time position deviation includes:

[0030] For the real-time monitoring point, determine the positioning accuracy label associated with each real-time position deviation, generate the real-time positioning accuracy label associated with each Beidou positioning stage, and use the Beidou positioning stage with the real-time positioning accuracy label as the target accuracy evaluation label as the second abnormal positioning stage corresponding to the real-time monitoring point.

[0031] In a possible implementation of the first aspect, determining the priori positioning efficiency corresponding to the specific Beidou positioning partition according to the signal coverage area and the key abnormal positioning stage corresponding to the monitoring point in the key abnormal positioning stage in the specific Beidou positioning partition includes:

[0032] For the monitoring points in the specific Beidou positioning partition where there are key abnormal positioning stages, the global stage parameters of each key abnormal positioning stage corresponding to the monitoring point are determined as the target abnormal positioning stage parameters corresponding to the monitoring point, and the signal coverage area corresponding to the monitoring point and the target abnormal positioning stage parameters are integrated to generate the prior positioning performance corresponding to the monitoring point;

[0033] According to the prior positioning efficiencies associated with the monitoring points in the specific Beidou positioning partition where there is a key abnormal positioning phase, the prior positioning efficiencies corresponding to the specific Beidou positioning partition are generated.

[0034] In a possible implementation of the first aspect, determining the instant positioning performance corresponding to the specific Beidou positioning partition according to the signal coverage area corresponding to the monitoring point in the second abnormal positioning stage in the specific Beidou positioning partition and the second abnormal positioning stage includes:

[0035] For the monitoring points in the specific Beidou positioning partition where both the key abnormal positioning stage and the second abnormal positioning stage exist, the shared abnormal positioning stage is determined from each key abnormal positioning stage and the second abnormal positioning stage corresponding to the monitoring point, the global stage parameters of each shared abnormal positioning stage corresponding to the monitoring point are determined as the shared abnormal positioning stage parameters corresponding to the monitoring point, the signal coverage area corresponding to the monitoring point and the shared abnormal positioning stage parameters are integrated to generate the real-time positioning performance corresponding to the monitoring point;

[0036] Generate the real-time positioning performance corresponding to the specific Beidou positioning partition according to the real-time positioning performance associated with each monitoring point in the specific Beidou positioning partition that simultaneously exists in the key abnormal positioning stage and the second abnormal positioning stage;

[0037] The updating of the basic abnormal positioning observation model according to the performance deviation between the prior positioning performance and the instant positioning performance, and generating an optimized target abnormal positioning observation model when the performance deviation meets the set standard, includes:

[0038] For monitoring points with real-time positioning performance in the specific Beidou positioning partition, the performance deviation corresponding to each monitoring point is obtained according to the performance deviation between the real-time positioning performance and the prior positioning performance corresponding to the same monitoring point;

[0039] For monitoring points with real-time positioning performance in the specific Beidou positioning partition, generating a performance deviation corresponding to the specific Beidou positioning partition according to an average deviation of performance deviations associated with each monitoring point;

[0040] According to the performance deviation corresponding to the specific Beidou positioning partition, the basic abnormal positioning observation model is updated until the performance deviation corresponding to the specific Beidou positioning partition is less than the set deviation value, thereby generating an optimized target abnormal positioning observation model.

[0041] In a possible implementation of the first aspect, the method further includes:

[0042] Determine the target position deviation associated with each monitoring point in each Beidou positioning stage according to the real-time position deviation associated with each monitoring point in each Beidou positioning stage;

[0043] For each of the monitoring points, when a key abnormal positioning stage is estimated from the various Beidou positioning stages based on the target position deviation and the optimized target abnormal positioning observation model, the monitoring point is determined to be a target abnormal positioning monitoring point;

[0044] According to the target abnormal positioning monitoring point and the key abnormal positioning stage corresponding to the target abnormal positioning monitoring point, abnormal positioning prompt information corresponding to the specific Beidou positioning partition is generated.

[0045] In a second aspect, an embodiment of the present application also provides a Beidou positioning cloud service system, which includes a processor and a machine-readable storage medium, in which a computer program is stored. The computer program is loaded and executed in conjunction with the processor to implement the Beidou positioning data processing method based on artificial intelligence of the first aspect above.

[0046] According to the technical scheme of any aspect above, the abnormal positioning stage in a specific Beidou positioning partition can be estimated and processed more accurately. First, by collecting the prior position deviation and the immediate position deviation of each monitoring point in different Beidou positioning stages, the long-term and short-term positioning data can be comprehensively considered. Subsequently, the first abnormal positioning stage is screened out using the prior position deviation and the position deviation parameter in the basic abnormal positioning observation model. By further combining the abnormal positioning continuous parameter, the key abnormal positioning stage is determined. At the same time, the second abnormal positioning stage is screened out according to the immediate position deviation. Then, according to the signal coverage area and the key abnormal positioning stage in the specific Beidou positioning partition, the prior positioning efficiency of the area is determined; similarly, according to the signal coverage area and stage of the monitoring point in the second abnormal positioning stage, the immediate positioning efficiency is determined. Finally, by comparing the efficiency deviation between the prior positioning efficiency and the immediate positioning efficiency, the present invention can update the basic abnormal positioning observation model. When the efficiency deviation meets the set standard, an optimized target abnormal positioning observation model is generated, which can be used to more accurately estimate the monitoring points in the key abnormal positioning stage, thereby improving the response reliability and accuracy of the overall positioning system. In this way, it is possible to dynamically adapt to changes within the Beidou positioning zone and promptly correct and optimize the abnormal positioning observation mechanism, so as to subsequently improve the positioning efficiency and Beidou positioning reliability in specific areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained by combining these drawings without paying creative work.

[0048] Figure 1 A flowchart of a Beidou positioning data processing method based on artificial intelligence provided in an embodiment of the present application;

[0049] Figure 2 A block diagram showing the functional structure of a Beidou positioning cloud service system for implementing the above-mentioned Beidou positioning data processing method based on artificial intelligence provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following description is intended to enable one of ordinary skill in the art to implement and combine the present application, and the description is provided in the context of a specific application scenario and its requirements. It will be apparent to one of ordinary skill in the art that various changes may be made to the disclosed embodiments, and that the general principles defined in the present application may be applied to other embodiments and application scenarios without departing from the principles and scope of the present application. Therefore, the present application is not limited to the described embodiments, but should be given the broadest scope consistent with the claims.

[0051] See also Figure 1 As shown, the present application provides a Beidou positioning data processing method based on artificial intelligence, comprising the following steps.

[0052] Step S110, collecting the priori position deviations and real-time position deviations associated with each monitoring point in a specific Beidou positioning partition in multiple Beidou positioning stages.

[0053] For example, this step requires data collection for all monitoring points within a specific BeiDou positioning zone, which is a pre-determined geographic area with multiple monitoring points for receiving BeiDou system signals.

[0054] In this embodiment, the Beidou positioning stage can refer to different slices in time, such as different hours or minutes in a day. For each monitoring point, two types of data need to be recorded: one is the prior position deviation, which may be estimated based on past observed data trends, geographical environmental factors, expected system errors, etc.; the other is the immediate position deviation, which is obtained by comparing the difference between the position calculated by the Beidou signal currently received by the monitoring point and the actual position in real time. These prior position deviations and immediate position deviations will be used for subsequent analysis.

[0055] Step S120, for each of the monitoring points, based on the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, the first abnormal positioning stage is screened out from the various Beidou positioning stages, and based on the abnormal positioning duration parameter included in the basic abnormal positioning observation model, the key abnormal positioning stage is determined from the various first abnormal positioning stages.

[0056] For example, in this step, a defined basic abnormal positioning observation model is first used, which is a pre-set framework that contains parameters that can be used to identify position deviations. Using this basic abnormal positioning observation model, the prior position deviation of each monitoring point and the position deviation parameters defined in the model are first analyzed to determine those Beidou positioning stages where potential abnormalities occur (i.e., the first abnormal positioning stage). Then, the abnormal positioning persistence parameters in the basic abnormal positioning observation model are further used to determine which deviations in the first abnormal positioning stage are temporary and which are persistent problems. The ultimate goal is to screen out abnormal positioning stages with significant persistence, which are called key abnormal positioning stages.

[0057] Step S130: for each of the monitoring points, based on the real-time position deviation, select the second abnormal positioning stage from the various Beidou positioning stages.

[0058] For example, this step focuses on analyzing the real-time position deviation data. For each monitoring point in the partition, its real-time position deviation in different Beidou positioning stages is checked. This process involves the processing of real-time data, and it may be necessary to consider deviations caused by sudden signal interference, hardware failure, or other unexpected factors. Based on the real-time position deviation, those stages where the positioning accuracy is significantly reduced will be identified, and these stages will be marked as the second abnormal positioning stage.

[0059] Step S140, based on the signal coverage area and the key abnormal positioning stage corresponding to the monitoring points in the key abnormal positioning stage in the specific Beidou positioning partition, determine the prior positioning performance corresponding to the specific Beidou positioning partition, and based on the signal coverage area and the second abnormal positioning stage corresponding to the monitoring points in the second abnormal positioning stage in the specific Beidou positioning partition, determine the real-time positioning performance corresponding to the specific Beidou positioning partition.

[0060] For example, this step involves evaluating the positioning performance of the entire Beidou positioning partition based on the analysis results. The evaluation of the priori positioning performance relies on the data of the key abnormal positioning stage and the signal coverage of the monitoring points. The evaluation of the immediate positioning performance is based on the real-time data of the second abnormal positioning stage and the signal coverage of the monitoring points. This step may involve complex geographic information system (GIS) analysis to accurately define the signal coverage area of ​​each monitoring point, and combine the data of the abnormal positioning stage to evaluate the overall Beidou positioning service quality.

[0061] Step S150, based on the performance deviation between the prior positioning performance and the real-time positioning performance, the basic abnormal positioning observation model is updated, and when the performance deviation meets the set standard, an optimized target abnormal positioning observation model is generated. The optimized target abnormal positioning observation model is used to estimate the monitoring points in the key abnormal positioning stage in the specific Beidou positioning partition based on the real-time position deviation.

[0062] For example, after the positioning performance evaluation in the previous steps, a comparison result between the prior positioning performance and the real-time positioning performance will be obtained. The performance deviation generated by this comparison is a quantification of the state of the Beidou positioning system, which can be used to guide how to adjust and optimize the basic abnormal positioning observation model. If this performance deviation is within the tolerance range set in advance, it means that the Beidou positioning system performs at an acceptable level, then an optimized target abnormal positioning observation model will be generated. This new target abnormal positioning observation model will more accurately reflect the actual operating status of the Beidou positioning system, and can be used to predict and evaluate the real-time position deviation of the monitoring point during the critical abnormal positioning stage, so as to take corrective measures in time to ensure the stability and accuracy of the Beidou positioning service.

[0063] Based on the above steps, firstly, by collecting the prior position deviation and the immediate position deviation of each monitoring point in different Beidou positioning stages, the long-term and short-term positioning data can be comprehensively considered. Subsequently, the first abnormal positioning stage is screened out using the prior position deviation and the position deviation parameter in the basic abnormal positioning observation model. By further combining the abnormal positioning continuous parameter, the key abnormal positioning stage is determined. At the same time, the second abnormal positioning stage is screened out according to the immediate position deviation. Then, according to the signal coverage area and the key abnormal positioning stage in the specific Beidou positioning partition, the prior positioning performance of the area is determined; similarly, according to the signal coverage area and stage of the monitoring point in the second abnormal positioning stage, the immediate positioning performance is determined. Finally, by comparing the performance deviation between the prior positioning performance and the immediate positioning performance, the present invention can update the basic abnormal positioning observation model. When the performance deviation meets the set standard, an optimized target abnormal positioning observation model is generated, which can be used to more accurately estimate the monitoring points in the key abnormal positioning stage, thereby improving the response reliability and accuracy of the overall positioning system. In this way, it is possible to dynamically adapt to changes within the Beidou positioning zone and promptly correct and optimize the abnormal positioning observation mechanism, so as to subsequently improve the positioning efficiency and Beidou positioning reliability in specific areas.

[0064] In a possible implementation, step S110 may include:

[0065] Step S111, taking each monitoring point in a specific Beidou positioning area as a target monitoring point.

[0066] For example, in the logistics park scenario, the monitoring points can be cargo warehouses equipped with Beidou positioning equipment, loading and unloading areas, or fixed location monitoring stations, etc. These monitoring points are used to track the location information of transportation vehicles, goods, or personnel within the logistics park to ensure efficient logistics operations.

[0067] For example, in a logistics park, a Beidou positioning receiver is installed at the entrance of each cargo warehouse as a monitoring point. These monitoring points are used to track the location information of logistics vehicles entering and leaving the warehouse. Therefore, the Beidou positioning receiver at the entrance of each warehouse can be determined as a target monitoring point to collect relevant location data.

[0068] Step S112, obtaining multiple priori positioning accuracies associated with the target monitoring point in multiple Beidou positioning stages. The multiple priori positioning accuracies corresponding to the same Beidou positioning stage are the positioning accuracies associated with the same Beidou positioning stage in multiple priori data recording intervals.

[0069] For example, for each target monitoring point in a logistics park (such as the warehouse entrance), multiple prior positioning accuracies associated with each Beidou positioning stage are obtained based on historical data records. These accuracy data may come from records in different time periods or under different weather conditions. The positioning accuracy of the same Beidou positioning stage at different prior data recording intervals can be identified, and these records reflect the positioning accuracy that can usually be expected during that period.

[0070] Step S113, for each Beidou positioning stage in each Beidou positioning stage, determine the positioning accuracy label associated with each prior positioning accuracy, and determine the prior position deviation corresponding to the target monitoring point in the Beidou positioning stage based on the weight of the accuracy statistics of the prior positioning accuracy of the positioning accuracy label as the target accuracy evaluation label in the global accuracy statistics.

[0071] For example, the prior positioning accuracy data collected previously can be used to assign a positioning accuracy label to the prior positioning accuracy of each Beidou positioning stage. This positioning accuracy label can be based on the accuracy range, such as "high accuracy", "medium accuracy" and "low accuracy".

[0072] The weight (such as ratio) of each prior positioning accuracy in the global accuracy statistics can be calculated based on the target accuracy evaluation label of each positioning accuracy label, and the prior position deviation corresponding to the target monitoring point in the Beidou positioning stage can be determined accordingly.

[0073] Step S114, obtaining the real-time positioning accuracy of the target monitoring point in each Beidou positioning stage as the real-time position deviation of the target monitoring point in each Beidou positioning stage. The real-time positioning accuracy is the positioning accuracy corresponding to the real-time data recording interval.

[0074] For example, the dynamics of logistics vehicles in the logistics park can be tracked in real time, and the real-time positioning accuracy of the target monitoring point in each Beidou positioning stage can be collected. For example, when a truck enters or leaves the monitoring point at the warehouse door, the recorded positioning accuracy is the real-time positioning accuracy. In other words, the collected real-time positioning accuracy can be regarded as the real-time position deviation of the target monitoring point in the corresponding Beidou positioning stage. These data reflect the Beidou positioning performance of the monitoring point under current conditions.

[0075] In a possible implementation, step S120 may include:

[0076] Step S121, for the instant monitoring point, according to the a priori position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, each Beidou positioning stage is divided into a first abnormal positioning stage and a first non-abnormal positioning stage. The a priori position deviation corresponding to the first abnormal positioning stage is not less than the position deviation parameter.

[0077] For example, this process can be illustrated by a detailed example.

[0078] Assume that there are multiple warehouses and distribution centers in a large commercial logistics park, each of which is equipped with a Beidou positioning receiver as a monitoring point. These monitoring points are used to track the location information of logistics vehicles, ensure distribution efficiency and handle possible abnormal situations in a timely manner.

[0079] In the logistics park, the BeiDou receiver of warehouse A usually exhibits a priori position deviations relative to surrounding buildings. The basic abnormal positioning observation model sets the maximum allowable position deviation parameter to 5 meters.

[0080] Then, during the operation of a certain day, the real-time position deviation of the monitoring point of warehouse A in each Beidou positioning stage (for example, every minute) is continuously monitored and recorded. If the real-time position deviation recorded in a certain Beidou positioning stage exceeds 5 meters, the stage is marked as the first abnormal positioning stage.

[0081] Step S122, sorting the first abnormal positioning stages and the first non-abnormal positioning stages corresponding to the instant monitoring point according to the stage order to generate a basic Beidou positioning stage cluster.

[0082] For example, over time, a series of Beidou positioning data can be collected, including the first abnormal positioning stage and the first non-abnormal positioning stage, and these data are organized into a list in chronological order to form a basic Beidou positioning stage cluster, which contains the first abnormal positioning stage and the first non-abnormal positioning stage that appear alternately.

[0083] Step S123, from the basic Beidou positioning stage cluster corresponding to the instant monitoring point, obtain each first abnormal positioning stage that progresses in sequence to construct a first Beidou positioning stage cluster, and determine the global stage parameter of the first Beidou positioning stage cluster as the first cumulative abnormal stage parameter.

[0084] For example, for the warehouse A monitoring point, it is noted that there are several consecutive events with position deviations exceeding 5 meters between 10 a.m. and 11 a.m. Then, these consecutive first abnormal positioning stages can be extracted to form a separate first Beidou positioning stage cluster, and the cumulative duration of all abnormal stages in this time period is calculated to obtain the first cumulative abnormal stage parameters of the first Beidou positioning stage cluster (such as a total of 30 minutes of accumulated abnormal state).

[0085] Step S124, from each first Beidou positioning stage cluster corresponding to the instant monitoring point, the first Beidou positioning stage cluster whose first cumulative abnormal stage parameter is not less than the abnormal positioning continuous parameter contained in the basic abnormal positioning observation model is taken as the first target Beidou positioning stage cluster, and each first abnormal positioning stage in the first target Beidou positioning stage cluster is taken as the key abnormal positioning stage corresponding to the instant monitoring point.

[0086] For example, if the first cumulative abnormal phase parameter (e.g., 30 minutes) of the first Beidou positioning phase cluster reaches or exceeds the abnormal positioning duration parameter (assuming 20 minutes) set in the basic abnormal positioning observation model, the first Beidou positioning phase cluster is identified as the first target Beidou positioning phase cluster. All first abnormal positioning phases within the first target Beidou positioning phase cluster are considered critical abnormal positioning phases and need to be reported immediately to the technical team for troubleshooting, which may involve hardware maintenance, software updates, or environmental interference assessments.

[0087] In a possible implementation, the method further includes:

[0088] Step A110, from the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each first non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the first normal stage parameters, when the first normal stage parameters are not greater than the non-abnormal positioning duration parameters contained in the basic abnormal positioning observation model, convert each first non-abnormal positioning stage corresponding to the first normal stage parameters into a first abnormal positioning stage, and generate a first optimized Beidou positioning stage set.

[0089] For example, in the logistics park scenario discussed earlier, monitoring points (such as Beidou receivers at warehouse A) are used to track the location information of logistics vehicles. Now, we will explain in detail how to determine the key anomaly positioning stage by further optimizing data analysis.

[0090] Specific scenario: In the monitored basic Beidou positioning stage cluster, the monitoring point of warehouse A may have a short normal Beidou positioning period between the two first abnormal positioning stages. For example, 10:05 to 10:10 in the morning is an abnormal stage, and 10:15 to 10:20 in the morning is another abnormal stage. The Beidou positioning data between 10:10 and 10:15 is normal.

[0091] That is, the global phase parameters of these first non-abnormal positioning phases, i.e., their cumulative duration, can be evaluated. If the first normal phase parameter (e.g., 5 minutes of normal Beidou positioning time) is not greater than the non-abnormal positioning duration parameter (e.g., 10 minutes) set in the basic abnormal positioning observation model, then the first normal phase will be reclassified as the first abnormal positioning phase. After this operation, a first optimized Beidou positioning phase set containing more continuous abnormal data is generated.

[0092] Step A120, in the first optimized Beidou positioning stage set corresponding to the instant monitoring point, obtain each first abnormal positioning stage that progresses in sequence to construct a second Beidou positioning stage cluster, and determine the global stage parameters of the second Beidou positioning stage cluster as the second cumulative abnormal stage parameters.

[0093] For example, after the first round of optimization, the first optimized Beidou positioning stage set of the monitoring point of warehouse A has eliminated those normal stages that may actually be abnormal but have a shorter duration. That is, the various first abnormal positioning stages that progress in sequence can be obtained again, and the second Beidou positioning stage cluster can be constructed. For this new stage cluster, its second cumulative abnormal stage parameter is calculated, that is, the cumulative duration of these first abnormal positioning stages.

[0094] Step A130, from each second Beidou positioning stage cluster corresponding to the instant monitoring point, take the second Beidou positioning stage cluster whose second cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter as the second target Beidou positioning stage cluster, and take each first abnormal positioning stage in the second target Beidou positioning stage cluster as the key abnormal positioning stage corresponding to the instant monitoring point.

[0095] For example, it is now necessary to confirm which continuous abnormal positioning data represent real Beidou positioning problems and require further investigation and intervention. : If the second cumulative abnormal phase parameter of a second Beidou positioning phase cluster (such as the accumulated abnormal state for 30 minutes) is not less than the abnormal positioning duration parameter (assuming 20 minutes), then this phase cluster is considered the second target Beidou positioning phase cluster. All first abnormal positioning phases in this phase cluster are identified as critical abnormal positioning phases because they indicate that there are persistent Beidou positioning problems at the monitoring point, which requires management to take action to investigate and repair.

[0096] Through the above steps, the key abnormal positioning stage of the monitoring point A in warehouse can be determined more accurately, so as to respond to potential Beidou positioning problems in a timely manner and ensure the efficient operation of logistics vehicles and the correct delivery of goods.

[0097] In a possible implementation, the method further includes:

[0098] Step B110, from the basic Beidou positioning stage cluster corresponding to the instant monitoring point, the first non-abnormal positioning stage whose prior position deviation is not less than the adjusted offset parameter is used as a candidate non-abnormal positioning stage. The adjusted offset parameter is obtained by reducing the position deviation parameter according to the abnormal positioning update parameter in the basic abnormal positioning observation model.

[0099] For example, all Beidou positioning data of a certain instant monitoring point (such as a cargo loading and unloading area) within a working cycle can be collected and organized into a basic Beidou positioning stage cluster in chronological order. Then, the first non-abnormal positioning stage whose prior position deviation is not less than the adjusted offset parameter can be screened out from this basic Beidou positioning stage cluster. The adjusted offset parameter is obtained by reducing the original position deviation parameter based on the abnormal positioning update parameter in the basic abnormal positioning observation model.

[0100] Step B120, from the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each candidate non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the second normal stage parameters, when the second normal stage parameters are not greater than the non-abnormal positioning duration parameters contained in the basic abnormal positioning observation model, convert each candidate non-abnormal positioning stage corresponding to the second normal stage parameters into the first abnormal positioning stage, and generate a second optimized Beidou positioning stage set.

[0101] For example, in the basic Beidou positioning phase cluster of the cargo loading and unloading area, there are multiple candidate non-abnormal positioning phases that occur between two known first abnormal positioning phases. The global phase parameters of these candidate non-abnormal positioning phases, i.e., the second normal phase parameters, can be calculated. If the second normal phase parameters are not greater than the non-abnormal positioning persistence parameters in the basic abnormal positioning observation model, these candidate non-abnormal positioning phases are converted to the first abnormal positioning phase, and a second optimized Beidou positioning phase set is generated.

[0102] Step B130, in the second optimized Beidou positioning stage set corresponding to the instant monitoring point, obtain the first abnormal positioning stages that progress in sequence to construct a third Beidou positioning stage cluster, and determine the global stage parameters of the third Beidou positioning stage cluster as the third cumulative abnormal stage parameters.

[0103] For example, the second optimized Beidou positioning stage set of the cargo loading and unloading area is further analyzed, with particular attention paid to the first abnormal positioning stages that occur continuously therein. These continuous first abnormal positioning stages can be extracted and organized from the second optimized Beidou positioning stage set to form a third Beidou positioning stage cluster, and the global stage parameters of the stage cluster are calculated as the third cumulative abnormal stage parameters.

[0104] Step B140, from each third Beidou positioning stage cluster corresponding to the instant monitoring point, take the third Beidou positioning stage cluster whose third cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter as the third target Beidou positioning stage cluster, and take each first abnormal positioning stage in the third target Beidou positioning stage cluster as the key abnormal positioning stage corresponding to the instant monitoring point.

[0105] For example, it is necessary to identify abnormal positioning stages in cargo loading and unloading areas that may have a serious impact on logistics operations. If the third cumulative abnormal stage parameter of any third Beidou positioning stage cluster is not less than the abnormal positioning duration parameter, then this stage cluster is regarded as the third target Beidou positioning stage cluster. The management system identifies each first abnormal positioning stage in the stage cluster as a critical abnormal positioning stage, and immediate measures need to be taken to check and resolve it.

[0106] For example, assume that the logistics park contains multiple warehouses and loading and unloading areas, each of which is equipped with monitoring points of the Beidou positioning system. These monitoring points can be mobile (such as Beidou positioning equipment loaded on a forklift) or fixed (such as Beidou positioning base stations installed in the corners of the loading and unloading area). Now, focus on the loading and unloading area of ​​warehouse B, which has two fixed monitoring points A1 and A2.

[0107] First, all Beidou positioning data of monitoring point A1 within a week were collected. These data show that the positioning accuracy often changes from 8:00 to 9:00 every morning (peak hours) due to the large amount of goods in and out. Analysis shows that the position deviation of monitoring point A1 is usually small during 8:20 to 8:30, but for some reasons, the prior position deviation of this time period is not stable and reaches the level of the adjusted offset parameters on some days. Based on the adjustment of the abnormal positioning update parameters, this period is screened as a candidate non-abnormal positioning stage.

[0108] Next, after further analysis of the data from monitoring point A1 during the peak hours from 8:00 to 9:00, it was found that although the period from 8:20 to 8:30 was marked as a candidate non-abnormal positioning phase, its duration never exceeded the non-abnormal positioning duration parameter threshold specified in the model. Therefore, the data from 8:20 to 8:30 was reclassified as the first abnormal positioning phase, and together with other known abnormal positioning phases, it constituted the second optimized Beidou positioning phase set.

[0109] When analyzing the second optimized Beidou positioning stage set of monitoring point A1, it was noted that between the abnormal positioning stages from 8:10 to 8:20 and from 8:30 to 8:40, the stage from 8:20 to 8:30, which was originally considered to be non-abnormal, should actually be considered an abnormal state. In this way, 8:10 to 8:40 formed a new, continuous third Beidou positioning stage cluster. The global stage parameter of this stage cluster, that is, the cumulative abnormal duration of 30 minutes, can be calculated as the third cumulative abnormal stage parameter.

[0110] Furthermore, since monitoring point A1 has a long critical abnormal positioning phase during peak hours, it may affect the tracking and logistics efficiency of goods. That is, since the third cumulative abnormal phase parameter (30 minutes) exceeds the preset abnormal positioning duration parameter (such as 20 minutes), the Beidou positioning data of monitoring point A1 from 8:10 to 8:40 is marked as a critical abnormal positioning phase. The manager decided to conduct an in-depth inspection of the signal quality, equipment performance and environmental factors during this time period and take necessary measures to solve the problem. Through the above specific examples, it shows how to use the Beidou positioning system in the logistics park to accurately monitor and analyze Beidou positioning anomalies, and quickly identify and solve key problems that may affect logistics operations.

[0111] In a possible implementation, step S130 may include: for the instant monitoring point, determining the positioning accuracy label associated with each instant position deviation, generating the instant positioning accuracy label associated with each Beidou positioning stage, and using the Beidou positioning stage with the instant positioning accuracy label as the target accuracy evaluation label as the second abnormal positioning stage corresponding to the instant monitoring point.

[0112] For example, in the scenario of a logistics park, monitoring points (such as the Beidou receiver at warehouse A) are used to track the location information of logistics vehicles in real time. Assume that the monitoring point of warehouse A records Beidou positioning data for multiple different time periods in a day, including the instantaneous position deviation of each truck when it enters or leaves the warehouse door. These instantaneous position deviations reflect the Beidou positioning performance of the monitoring point in a specific Beidou positioning stage. For the instantaneous monitoring point, the recorded instantaneous position deviations are evaluated in each Beidou positioning stage, and the associated positioning accuracy tags are determined based on these deviations. These positioning accuracy tags may be classified as "very high accuracy", "high accuracy", "medium accuracy", "low accuracy", etc. based on the size of the deviation.

[0113] Next, we hope to identify which Beidou positioning stages have not achieved the expected performance, such as reduced positioning accuracy due to equipment failure, signal interference, or environmental changes. An instant positioning accuracy label can be generated for each Beidou positioning stage. Then, based on the target accuracy evaluation label (such as "low accuracy"), those Beidou positioning stages whose instant positioning accuracy labels meet this condition are divided into the second abnormal positioning stage corresponding to the instant monitoring point. Such a screening process helps to promptly discover and resolve potential problems that affect operational efficiency and safety.

[0114] For example, take Warehouse A in a logistics park as an example. A Beidou positioning receiver is installed at the entrance of the warehouse to track the location information of vehicles entering and leaving. On a specific working day, from 8 am to 5 pm, the monitoring point of Warehouse A records the location data of each vehicle entering and leaving at different time periods. These data include the deviation value between the actual position of the vehicle and the position calculated by the Beidou system, that is, the real-time position deviation. For each recorded Beidou positioning stage (for example, once a minute), the management system of Warehouse A automatically calculates the real-time position deviation and classifies it according to the size of the deviation. For example, if the deviation is less than 1 meter, a "very high precision" label is assigned; 1-2 meters are assigned a "high precision" label; 2-5 meters are assigned a "medium precision" label; greater than 5 meters are assigned a "low precision" label.

[0115] Warehouse A needs to determine which time periods of Beidou positioning data may indicate equipment failure or other problems that affect Beidou positioning accuracy. To do this, it pays special attention to those Beidou positioning stages marked as "low accuracy". Then, all Beidou positioning stages marked with the "low accuracy" label can be screened out because the instant position deviation of these stages exceeds the acceptable range for normal operation. These stages will be considered as the second abnormal positioning stage. For example, if five consecutive Beidou positioning stages from 8:15AM to 8:20AM are all marked as "low accuracy", then these five minutes will be classified as the second abnormal positioning stage. Through such a detailed screening process, the logistics park can accurately identify those second abnormal positioning stages that may require further investigation and repair. For example, if the "low accuracy" Beidou positioning stage occurs frequently, it may indicate that there is a fault in the receiver or a new interference source has appeared in the environment. Based on this information, managers can take corresponding maintenance and repair measures to ensure that the Beidou positioning system of the entire logistics park is stable and reliable.

[0116] Through the above technical steps, it is possible to effectively screen out critical time periods with problems from a large amount of real-time Beidou positioning data, thereby ensuring the accuracy and reliability of the monitoring system and maintaining the efficiency of logistics operations.

[0117] In a possible implementation, step S140 may include:

[0118] Step S141, for the monitoring points in the specific Beidou positioning partition where there are key abnormal positioning stages, determine the global stage parameters of each key abnormal positioning stage corresponding to the monitoring point as the target abnormal positioning stage parameters corresponding to the monitoring point, integrate the signal coverage area and the target abnormal positioning stage parameters corresponding to the monitoring point, and generate the prior positioning performance corresponding to the monitoring point.

[0119] For example, suppose there are two Beidou positioning system monitoring points, A1 and A2, in the loading and unloading area B in the logistics park. These monitoring points are used to track the precise location of the loaded and unloaded goods. After a period of monitoring, in certain specific time periods, the Beidou positioning data of monitoring points A1 and A2 showed an unusual increase in cumulative duration, and these time periods were identified as key abnormal positioning stages.

[0120] Then, for each monitoring point A1 and A2, all key anomaly location phases can be identified and their cumulative duration values ​​can be calculated. These cumulative duration values ​​are the target anomaly location phase parameters corresponding to the monitoring point.

[0121] It is assumed that the signal coverage area of ​​monitoring point A1 may be affected by the interference of large metal equipment in the surrounding area, resulting in the degradation of Beidou positioning signal quality. Monitoring point A2 may be affected by the obstruction of buildings.

[0122] Then, the prior positioning performance of each monitoring point can be evaluated based on the signal coverage area characteristics of monitoring points A1 and A2 and the recorded target abnormal positioning phase parameters (i.e., cumulative duration values). The prior positioning performance will reflect the monitoring point's ability to process Beidou positioning signals within its signal coverage area.

[0123] Exemplarily, a specific calculation example can be used to illustrate how to combine the signal coverage area of ​​the monitoring point and the target abnormality positioning phase parameters to generate the prior positioning effectiveness. Assume that in the container storage area of ​​the logistics park, there is a monitoring point A1 with a specific signal coverage area and records the key abnormality positioning phase data for a period of time.

[0124] Assume that the signal coverage area of ​​monitoring point A1 is 1000 square meters (area parameter). In the past month, monitoring point A1 recorded several key anomaly positioning stages, and the cumulative duration values ​​of these key anomaly positioning stages are as follows:

[0125] The first critical anomaly location phase: cumulative duration is 10 minutes

[0126] The second critical anomaly location phase: cumulative duration is 15 minutes

[0127] The third critical anomaly location phase: cumulative duration is 20 minutes

[0128] First, the cumulative duration of each key abnormality positioning stage of monitoring point A1 is summarized to obtain a total cumulative abnormality duration. Total cumulative abnormality duration = 10 + 15 + 20 = 45 minutes

[0129] Now it is necessary to evaluate the prior positioning performance by combining the area parameters of the signal coverage area of ​​monitoring point A1 and the cumulative duration value of the key anomaly positioning stage.

[0130] Suppose a simple priori positioning performance scoring system is defined, in which the positioning performance score is inversely proportional to the cumulative duration of the key anomaly positioning phase, and the influence of the signal coverage area is taken into account. To this end, the following formula can be used to calculate the priori positioning performance of monitoring point A1:

[0131] [A priori positioning effectiveness score = frac{signal coverage area}{total cumulative abnormal duration}times a constant coefficient]

[0132] If we set the constant coefficient to 10 (to simplify the calculation), we have:

[0133] [Prior positioning effectiveness score = frac{1000}{45}times10approx222.22]

[0134] Through the above calculation, the prior positioning performance score of monitoring point A1 within a specific time range is given. In actual situations, this calculation may be more complicated, involving more variables and weight factors, such as signal quality, number of interferences, specific time of anomaly occurrence, etc., to provide a more accurate positioning performance evaluation. However, this example shows how to combine the two factors of signal coverage area and the cumulative duration of the key anomaly positioning phase to generate the prior positioning performance of the monitoring point, which is a key step to help managers understand and improve the Beidou positioning performance of the monitoring point.

[0135] Step S142, generating a priori positioning performance corresponding to the specific Beidou positioning partition according to the a priori positioning performance associated with each monitoring point in the specific Beidou positioning partition where there is a key abnormal positioning stage.

[0136] For example, this step may be to conduct a comprehensive assessment of the positioning performance of the entire loading and unloading area B in order to better optimize the operation process and improve the overall work efficiency.

[0137] Then, the prior positioning performance information of all monitoring points (A1, A2, etc.) in loading and unloading area B can be aggregated, and the prior positioning performance corresponding to the entire specific Beidou positioning partition can be generated based on the sum of the prior positioning performance associated with the key abnormal positioning order of each monitoring point. This comprehensive evaluation takes into account the data of all relevant monitoring points and provides an overall view of the Beidou positioning service quality in loading and unloading area B.

[0138] Through the above steps, the key issues that affect the positioning performance of a specific Beidou positioning partition can be identified and corresponding improvement measures can be taken. For example, if the cumulative duration of the key abnormal positioning phase of monitoring point A1 is abnormally high, it may be necessary to check whether there is an interference source in the area or whether the equipment needs to be adjusted or replaced, so as to ensure that the Beidou positioning system in loading and unloading area B can operate accurately and stably.

[0139] In a possible implementation, step S140 may include:

[0140] Step S141, for the monitoring points in the specific Beidou positioning partition where both the key abnormal positioning stage and the second abnormal positioning stage exist, the shared abnormal positioning stage is determined from the key abnormal positioning stages and the second abnormal positioning stages corresponding to the monitoring points, the global stage parameters of the shared abnormal positioning stages corresponding to the monitoring points are determined as the shared abnormal positioning stage parameters corresponding to the monitoring points, the signal coverage area corresponding to the monitoring points and the shared abnormal positioning stage parameters are integrated to generate the real-time positioning performance corresponding to the monitoring points.

[0141] For example, in a logistics park, there is a specific Beidou positioning zone, called the container dispatching zone. This zone is equipped with multiple monitoring points (such as P1, P2, P3, etc.) to track the location of containers in real time and assist in dispatching operations.

[0142] First, monitoring point P1 covers a corner of the container dispatching area. After data analysis, it was found that the Beidou positioning data recorded by P1 in certain periods showed unexpected fluctuations, and these periods were defined as key abnormal positioning stages. At the same time, smaller Beidou positioning errors also occurred in other different time periods, which were defined as the second abnormal positioning stage. Those time periods that belong to both the key abnormal positioning stage and the second abnormal positioning stage can be screened out and defined as shared abnormal positioning stages. For monitoring point P1, the cumulative duration value of each shared abnormal positioning stage is calculated as a global stage parameter, that is, a shared abnormal positioning stage parameter.

[0143] Among them, the signal coverage area corresponding to the monitoring point and the shared abnormal positioning stage parameters are integrated to generate the real-time positioning performance corresponding to the monitoring point. Please refer to the aforementioned calculation example.

[0144] Step S142, generating the real-time positioning performance corresponding to the specific Beidou positioning partition according to the real-time positioning performance associated with each monitoring point in the specific Beidou positioning partition that simultaneously exists in the key abnormal positioning stage and the second abnormal positioning stage.

[0145] For example, the signal coverage area of ​​monitoring point P1 may be partially blocked by temporarily stacked containers, affecting the signal quality and Beidou positioning accuracy. Therefore, the real-time positioning performance of P1 can be evaluated by combining the signal coverage area characteristics of P1 and the shared anomaly positioning phase parameters obtained from the shared anomaly positioning phase. Real-time positioning performance refers to the Beidou positioning performance of monitoring point P1 under the current environment and conditions.

[0146] In order to comprehensively understand the performance of the Beidou positioning system in the entire container dispatching area, it is necessary to evaluate the positioning performance of all monitoring points in the area. The real-time positioning performance information of all monitoring points (P1, P2, P3, etc.) can be summarized, which includes the shared abnormal positioning phase parameters of each monitoring point and its signal coverage area. Based on this information, the real-time positioning performance of the entire container dispatching area is generated, providing an instant view of the quality of Beidou positioning services in the area.

[0147] Through these steps, it is possible to identify which areas in the container dispatching area have Beidou positioning problems, when these problems are most serious, and formulate corresponding countermeasures accordingly. For example, if monitoring point P1 frequently enters the shared abnormal positioning stage during the afternoon hours on weekdays, it may be necessary to re-evaluate the signal interference source during this time period, or consider adding additional monitoring points to improve signal coverage and positioning performance. Such an instant feedback mechanism is crucial to ensure the efficient and safe operation of the logistics park.

[0148] In a possible implementation, step S150 may include:

[0149] Step S151, for monitoring points with real-time positioning performance in the specific Beidou positioning partition, the performance deviation corresponding to each monitoring point is obtained according to the performance deviation between the real-time positioning performance and the priori positioning performance corresponding to the same monitoring point.

[0150] For example, suppose that in a logistics park, there is a specific area covered by the BeiDou system, called the cargo sorting area. Multiple monitoring points (such as S1, S2, and S3) are deployed in this area to track and manage the accuracy and efficiency of cargo sorting.

[0151] Assume that monitoring point S1 is responsible for tracking the movement of goods on the west side of the goods sorting area. One day, its real-time positioning performance (the positioning performance measured on that day) deviates from the previously calculated prior positioning performance (the positioning performance estimated based on historical data). The performance deviation of S1 can be calculated, and the same calculation is performed for S2 and S3. This deviation may be caused by temporary signal interference, equipment aging, or other unexpected factors.

[0152] Step S152: for monitoring points with real-time positioning performance in the specific Beidou positioning partition, generate a performance deviation corresponding to the specific Beidou positioning partition according to an average deviation of performance deviations associated with each monitoring point.

[0153] For example, in order to evaluate whether the positioning performance of the entire cargo sorting area meets the standard, it is necessary to calculate and analyze the performance deviation of all monitoring points. The average of the performance deviations of S1, S2, and S3 can be taken as the overall performance deviation of the cargo sorting area. For example, if the performance deviation of S1 is -5%, S2 is +3%, and S3 is -2%, then the average deviation is (-5%+3%-2%) / 3=-1.33%.

[0154] Step S153, according to the performance deviation corresponding to the specific Beidou positioning partition, update the basic abnormal positioning observation model until the performance deviation corresponding to the specific Beidou positioning partition is less than the set deviation value, and generate an optimized target abnormal positioning observation model.

[0155] For example, we want to ensure that the Beidou positioning system in the cargo sorting area is always in the best condition, so we need to continuously adjust and optimize the abnormal positioning observation model. Then, we can use the calculated performance deviation to update the basic abnormal positioning observation model. If the overall performance deviation of the cargo sorting area exceeds the preset deviation threshold (such as ±1%), adjustments are made. Depending on the size and direction of the deviation, it may be necessary to adjust the configuration of the monitoring point, improve the signal quality, or upgrade the software algorithm. After the adjustment, the system recalculates the performance deviation until the deviation is less than the set deviation threshold. At this point, an optimized target abnormal positioning observation model is obtained, thereby ensuring the positioning accuracy and operating efficiency of the cargo sorting area.

[0156] For example, in order to update the basic anomaly location observation model and generate an optimized target anomaly location observation model, an iterative method can be used to adjust the model parameters until the preset standard of performance deviation is reached. The following is a simplified calculation process and steps:

[0157] Continuing to use the "cargo sorting area" of the logistics park as the scenario, multiple Beidou positioning system monitoring points (such as S1, S2 and S3) are deployed in this area.

[0158] Assumptions:

[0159] -The set performance deviation threshold is ±1%.

[0160] -The basic anomaly positioning observation model includes a parameter set P = {p1, p2, ..., pn}, where each parameter has an impact on the positioning performance.

[0161] - Preliminary estimates of these parameters have been derived using historical data and prior knowledge.

[0162] Iteration process:

[0163] 1. Calculate the initial performance deviation:

[0164] For each monitoring point Si, calculate the deviation between its real-time positioning efficiency (Ei_actual) and the prior positioning efficiency (Ei_prior):

[0165] [ΔE_i=frac{Ei_actual-Ei_prior}{Ei_prior}times100%]

[0166] The deviations of all monitoring points are averaged to obtain the overall performance deviation of the cargo sorting area:

[0167] [ΔE_{avg}=frac{sumΔE_i}{n}]

[0168] 2. Determine whether the deviation threshold is met:

[0169] If |ΔE_avg|≤1%, the current model is considered to meet the requirements and the iteration is stopped.

[0170] If |ΔE_avg|>1%, the model parameters need to be adjusted.

[0171] 3. Adjust model parameters:

[0172] According to the direction and size of the performance deviation, the model parameters are adjusted. For example, if ΔE_avg>0, it means that the real-time positioning performance is generally higher than the prior positioning performance, and some sensitive parameter values ​​may need to be reduced; otherwise, they should be increased.

[0173] The adjusted parameter set P'={p1', p2', ..., pn'} will be used to update the model.

[0174] 4. Apply the new model and recalculate the performance deviation:

[0175] The real-time positioning performance is re-evaluated using the adjusted parameter P'.

[0176] Repeat steps 1 and 2 to calculate a new performance deviation ΔE_avg'.

[0177] 5. Iterative optimization:

[0178] Repeat steps 3 and 4 until |ΔE_avg'|≤1%.

[0179] 6. Generate optimized model:

[0180] When the performance deviation meets the preset conditions, the current parameter set P' is used as the optimized target anomaly location observation model.

[0181] The above steps provide a basic framework that shows how to gradually approach a more accurate anomaly location observation model. In practice, factors such as the frequency of model updates, the mutual influence between monitoring points, and environmental changes need to be considered to ensure the stability and accuracy of the model.

[0182] In a possible implementation, the method further includes:

[0183] Step S160, determining the target position deviation associated with each monitoring point in each Beidou positioning stage according to the real-time position deviation associated with each monitoring point in each Beidou positioning stage.

[0184] For example, in the container dispatching area of ​​the logistics park, the following technical steps are specifically described using monitoring point P1 as an example:

[0185] Monitoring point P1 is responsible for tracking the real-time location of containers in the area. The real-time position deviation data of P1 is recorded in different Beidou positioning stages (such as daytime working hours, nighttime non-working hours, etc.). Based on the real-time position deviation associated with P1 in each Beidou positioning stage, the target position deviation of P1 in these stages can be calculated and determined. The target position deviation can be regarded as an expected value or benchmark for the positioning accuracy of P1, which may be an average deviation or other statistical indicators based on historical data statistics.

[0186] For example, in the container dispatching area of ​​the logistics park, in order to determine the target position deviation associated with the monitoring point in each Beidou positioning stage, the following steps need to be performed:

[0187] Monitoring point P1 continuously collects data in different Beidou positioning phases (such as morning shift, evening shift and night shift), recording the instantaneous position deviation between the actual Beidou positioning result and the expected target. Next, the historical position deviation data recorded by monitoring point P1 in the same Beidou positioning phase over a period of time can be accessed. This may include extracting data from historical log files or querying historical Beidou positioning records saved in the database.

[0188] Then, statistical methods are used, such as calculating the mean, median, or using more complex statistical models (such as a prediction model based on time series) to determine the target position deviation that the monitoring point P1 should have in each Beidou positioning stage.

[0189] First, for each BeiDou positioning phase, the average instantaneous position deviation of P1 is calculated, which may be based on data from the past few weeks or months.

[0190] External factors such as seasonality, weather conditions, and workload fluctuations may then be considered to adjust these averages to ensure that the target position deviations reflect the true BeiDou positioning performance expectations.

[0191] Finally, the target position deviation is set as the corrected average instantaneous position deviation, or the predicted value obtained through other statistical models, which will serve as the expected level of positioning accuracy of the monitoring point in the future Beidou positioning stage.

[0192] Once the target position deviations are determined, they will be stored in the management system and used as a benchmark for subsequent monitoring and evaluation of the positioning performance of the monitoring point. In future Beidou positioning phases, the real-time position deviation of monitoring point P1 will be continuously monitored and compared with the stored target position deviations. Any deviation beyond expectations will trigger further analysis and necessary adjustment measures.

[0193] More specifically, in order to determine the target position deviations associated with each monitoring point in each Beidou positioning phase, firstly, for each monitoring point (such as S1, S2, and S3) in the logistics park, its recorded real-time position data are collected in different Beidou positioning phases (e.g., morning, noon, and evening).

[0194] Then, the real-time position deviation of each Beidou positioning stage is calculated using the known real position of the monitoring point (which may be the accurate position pre-marked by map or other means). The real-time position deviation can be obtained by the following formula:

[0195] [text{Real-time position deviation}_{i,j}=text{monitoring point}_{i}text{real-time position}_{j}-text{monitoring point}_{i}text{real position}]

[0196] Where (i) represents the index of the monitoring point and (j) represents the index of the Beidou positioning stage.

[0197] Next, analyze the trends and patterns of these instantaneous position deviations to see if the deviations are regular (e.g., larger deviations at certain times), random, or affected by some external factors (e.g., weather conditions, surrounding buildings, etc.).

[0198] Based on the collected data and trend analysis results, determine the target position deviation that each monitoring point should achieve in each Beidou positioning stage. The target position deviation may be based on one of the following methods:

[0199] The average of all instant position deviations is taken as the target position deviation.

[0200] [text{target position deviation}_{i,j}=frac{sumtext{immediate position deviation}_{i,j}}{text{number of samples}}]

[0201] Median deviation: To take into account the impact of outliers, use the median instead of the mean as the target position deviation.

[0202] Rule of thumb: If the data shows that the bias always increases or decreases under certain conditions, adjust the target position bias based on this pattern.

[0203] Predictive Models: Use statistical or machine learning models to predict and set target position deviations.

[0204] Once the target position deviation is determined, it can be used to monitor and improve the performance of the Beidou positioning system. When the instantaneous position deviation of the monitoring point exceeds the target position deviation, it can be regarded as a potential abnormal positioning event, thus triggering corresponding inspection or correction measures.

[0205] In practical applications, the determination of target position deviation may involve more considerations, such as mutual influence between monitoring points, dynamic environmental changes, etc., and needs to be updated regularly to adapt to new data and environmental changes.

[0206] Step S170, for each of the monitoring points, when a key abnormal positioning stage is estimated from the various Beidou positioning stages based on the target position deviation and the optimized target abnormal positioning observation model, the monitoring point is determined to be a target abnormal positioning monitoring point.

[0207] For example, a series of Beidou positioning deviations that occurred at monitoring point P1 in a specific time period exceeded the normal level, which attracted attention. The optimized target abnormal positioning observation model can be used to estimate the key abnormal positioning stage from multiple Beidou positioning stages in combination with the target position deviation. When a monitoring point is frequently identified as having a key abnormal positioning stage under this target abnormal positioning observation model, the monitoring point is determined as a target abnormal positioning monitoring point.

[0208] Step S180, generating abnormal positioning prompt information corresponding to the specific Beidou positioning partition according to the target abnormal positioning monitoring point and the key abnormal positioning stage corresponding to the target abnormal positioning monitoring point.

[0209] For example, monitoring point P1 is used as a target abnormal positioning monitoring point. After model analysis, it is confirmed that there are significant Beidou positioning errors in certain periods. Based on P1 as the target abnormal positioning monitoring point and the key abnormal positioning stage corresponding to P1, abnormal positioning prompt information for the container dispatching area can be generated. These prompt information contains detailed information such as the timestamp, duration, and possible affected areas of the key abnormal positioning stage to assist managers in further analysis and decision-making.

[0210] Through the above technical steps, the Beidou positioning system in the logistics park can be more effectively monitored and managed. When the monitoring point P1 is marked as a target abnormal positioning monitoring point and the relevant abnormal positioning prompt information is generated, the manager can take measures based on this information, such as adjusting the configuration of the monitoring point P1, enhancing the signal strength, or deploying additional monitoring equipment to improve the overall positioning accuracy and efficiency of the container dispatching area. This timely feedback and adjustment is crucial to ensure smooth logistics operations and reduce potential operational risks.

[0211] Figure 2 The Beidou positioning cloud service system 100 which can be used to implement the various embodiments described in this application is schematically shown.

[0212] For one embodiment, Figure 2 A BeiDou positioning cloud service system 100 is shown, which has multiple processors 102, a control module (chip set) 104 coupled to one or more of the (multiple) processors 102, a memory 106 coupled to the control module 104, a non-volatile memory (NVM) / storage device 108 coupled to the control module 104, multiple input / output devices 110 coupled to the control module 104, and a network interface 112 coupled to the control module 104.

[0213] The processor 102 may include multiple single-core or multi-core processors, and the processor 102 may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). In some alternative implementations, the Beidou positioning cloud service system 100 can be used as a server device such as a gateway described in the embodiments of the present application.

[0214] In some alternative embodiments, the Beidou positioning cloud service system 100 may include multiple computer-readable media (e.g., memory 106 or NVM / storage device 108) having instructions 114 and multiple processors 102 combined with the multiple computer-readable media and configured to execute instructions 114 to implement modules to perform the actions described in the present disclosure.

[0215] For one embodiment, the control module 104 may include any suitable interface controller to provide any suitable interface to one or more of the processor(s) 102 and / or any suitable management end or component in communication with the control module 104 .

[0216] The control module 104 may include a memory controller module to provide an interface to the memory 106. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0217] The memory 106 may be used, for example, to load and store data and / or instructions 114 for the Beidou positioning cloud service system 100. For one embodiment, the memory 106 may include any suitable volatile memory, for example, a suitable DRAM. In some alternative implementations, the memory 106 may include a double data rate type four synchronous dynamic random access memory.

[0218] For one embodiment, the control module 104 may include a plurality of input / output controllers to provide interfaces to the NVM / storage device 108 and the input / output device(s) 110 .

[0219] For example, NVM / storage device 108 may be used to store data and / or instructions 114. NVM / storage device 108 may include any suitable non-volatile memory (eg, flash memory) and / or may include any suitable non-volatile storage device(s).

[0220] The NVM / storage device 108 may include a storage resource that is physically part of the management terminal on which the Beidou positioning cloud service system 100 is installed, or it may be accessible to the device and may not be part of the device. For example, the NVM / storage device 108 may be accessed via (multiple) input / output devices 110 in conjunction with a network.

[0221] The (multiple) input / output devices 110 may provide an interface for the Beidou positioning cloud service system 100 to communicate with any other appropriate management end, and the input / output device 110 may include a communication component, a pinyin component, a sensor component, etc. The network interface 112 may provide an interface for the Beidou positioning cloud service system 100 to communicate based on multiple networks. The Beidou positioning cloud service system 100 may wirelessly communicate with multiple components of a wireless network based on any of a plurality of wireless network standards and / or protocols, for example, access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof for wireless communication.

[0222] For one embodiment, one or more of the processor(s) 102 may be packaged together with the logic of multiple controllers (e.g., memory controller modules) of the control module 104. For one embodiment, one or more of the processor(s) 102 may be packaged together with the logic of multiple controllers of the control module 104 to form a system-in-package. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with the logic of multiple controllers of the control module 104. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with the logic of multiple controllers of the control module 104 to form a system-on-chip.

[0223] In various embodiments, the Beidou positioning cloud service system 100 may be, but is not limited to, a terminal device such as a desktop computing device or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the Beidou positioning cloud service system 100 may have more or fewer components and / or different architectures. For example, in some alternative implementations, the Beidou positioning cloud service system 100 includes multiple cameras, a keyboard, a liquid crystal display screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, a dedicated integrated circuit, and a speaker.

[0224] The above is a detailed introduction to the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A Beidou positioning data processing method based on artificial intelligence, characterized in that: Applied to the Beidou positioning cloud service system, the method includes: Collect the prior position deviation and the immediate position deviation associated with each monitoring point in a specific Beidou positioning partition in multiple Beidou positioning stages, wherein the prior position deviation is estimated based on the data trend observed in the past, the geographical environment factors, and the expected system error, and the immediate position deviation is obtained by comparing the difference between the position calculated by the Beidou signal currently received by the monitoring point and the actual position in real time; For each of the monitoring points, based on the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, a first abnormal positioning stage is screened out from each Beidou positioning stage, and based on the abnormal positioning persistence parameter included in the basic abnormal positioning observation model, a key abnormal positioning stage is determined from each first abnormal positioning stage, wherein the key abnormal positioning stage refers to an abnormal positioning stage with significant persistence; For each of the monitoring points, according to the instant position deviation, a second abnormal positioning stage is selected from the various Beidou positioning stages; According to the signal coverage area and the key abnormal positioning stage corresponding to the monitoring points in the specific Beidou positioning partition where there is a key abnormal positioning stage, determine the priori positioning performance corresponding to the specific Beidou positioning partition; according to the signal coverage area and the second abnormal positioning stage corresponding to the monitoring points in the specific Beidou positioning partition where there is a second abnormal positioning stage, determine the real-time positioning performance corresponding to the specific Beidou positioning partition; According to the performance deviation between the prior positioning performance and the real-time positioning performance, the basic abnormal positioning observation model is updated, and when the performance deviation meets the set standard, an optimized target abnormal positioning observation model is generated; the optimized target abnormal positioning observation model is used to estimate the monitoring points in the key abnormal positioning stage in the specific Beidou positioning partition based on the real-time position deviation.

2. The Beidou positioning data processing method based on artificial intelligence according to claim 1 is characterized in that: The collecting of the prior position deviations and the immediate position deviations associated with each monitoring point in a specific Beidou positioning partition in multiple Beidou positioning stages includes: Each monitoring point in a specific Beidou positioning zone is used as a target monitoring point; Obtain multiple priori positioning accuracies associated with the target monitoring point in multiple Beidou positioning stages; multiple priori positioning accuracies corresponding to the same Beidou positioning stage are the positioning accuracies associated with multiple priori data recording intervals in the same Beidou positioning stage; For each Beidou positioning stage, determine the positioning accuracy label associated with each prior positioning accuracy, and determine the prior position deviation corresponding to the target monitoring point in the Beidou positioning stage according to the weight of the accuracy statistics of the prior positioning accuracy of the positioning accuracy label as the target accuracy evaluation label in the global accuracy statistics; The real-time positioning accuracy associated with the target monitoring point in each Beidou positioning stage is obtained as the real-time position deviation associated with the target monitoring point in each Beidou positioning stage; the real-time positioning accuracy is the positioning accuracy corresponding to the real-time data recording interval.

3. The Beidou positioning data processing method based on artificial intelligence according to claim 1 is characterized in that: For each of the monitoring points, according to the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model, a first abnormal positioning stage is selected from each Beidou positioning stage, and according to the abnormal positioning persistence parameter included in the basic abnormal positioning observation model, a key abnormal positioning stage is determined from each first abnormal positioning stage, including: For the real-time monitoring point, each Beidou positioning stage is divided into a first abnormal positioning stage and a first non-abnormal positioning stage according to the prior position deviation and the position deviation parameter belonging to the basic abnormal positioning observation model; the prior position deviation corresponding to the first abnormal positioning stage is not less than the position deviation parameter; Arrange the first abnormal positioning phase and the first non-abnormal positioning phase corresponding to the instant monitoring point according to the phase order to generate a basic Beidou positioning phase cluster; From the basic Beidou positioning phase cluster corresponding to the instant monitoring point, obtain each first abnormal positioning phase that progresses in sequence to construct a first Beidou positioning phase cluster, and determine the global phase parameter of the first Beidou positioning phase cluster as the first cumulative abnormal phase parameter, wherein the global phase parameter is the cumulative duration of all abnormal phases; From the first Beidou positioning stage clusters corresponding to the instant monitoring point, the first Beidou positioning stage cluster whose first cumulative abnormal stage parameter is not less than the abnormal positioning continuous parameter contained in the basic abnormal positioning observation model is taken as the first target Beidou positioning stage cluster, and each first abnormal positioning stage in the first target Beidou positioning stage cluster is taken as the key abnormal positioning stage corresponding to the instant monitoring point.

4. The Beidou positioning data processing method based on artificial intelligence according to claim 3 is characterized in that: The method further comprises: From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each first non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the first normal stage parameter, and when the first normal stage parameter is not greater than the non-abnormal positioning duration parameter included in the basic abnormal positioning observation model, convert each first non-abnormal positioning stage corresponding to the first normal stage parameter into the first abnormal positioning stage, and generate a first optimized Beidou positioning stage set; In the first optimized Beidou positioning stage set corresponding to the instant monitoring point, each first abnormal positioning stage that progresses in sequence is obtained to construct a second Beidou positioning stage cluster, and a global stage parameter of the second Beidou positioning stage cluster is determined as a second accumulated abnormal stage parameter; From the second Beidou positioning stage clusters corresponding to the instant monitoring point, the second Beidou positioning stage cluster whose second cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter is taken as the second target Beidou positioning stage cluster, and the first abnormal positioning stages in the second target Beidou positioning stage cluster are taken as the key abnormal positioning stages corresponding to the instant monitoring point.

5. The Beidou positioning data processing method based on artificial intelligence according to claim 3 is characterized in that: The method further comprises: From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, the first non-abnormal positioning stage in which the prior position deviation is not less than the adjusted offset parameter is used as a candidate non-abnormal positioning stage; the adjusted offset parameter is obtained by reducing the position deviation parameter according to the abnormal positioning update parameter in the basic abnormal positioning observation model; From the basic Beidou positioning stage cluster corresponding to the instant monitoring point, determine the global stage parameters of each candidate non-abnormal positioning stage that progresses in sequence between the two associated first abnormal positioning stages as the second normal stage parameter, and when the second normal stage parameter is not greater than the non-abnormal positioning duration parameter included in the basic abnormal positioning observation model, convert each candidate non-abnormal positioning stage corresponding to the second normal stage parameter into the first abnormal positioning stage, and generate a second optimized Beidou positioning stage set; In the second optimized Beidou positioning stage set corresponding to the instant monitoring point, each first abnormal positioning stage that progresses in sequence is obtained to construct a third Beidou positioning stage cluster, and a global stage parameter of the third Beidou positioning stage cluster is determined as a third accumulated abnormal stage parameter; From the third Beidou positioning stage clusters corresponding to the immediate monitoring point, the third Beidou positioning stage cluster whose third cumulative abnormal stage parameter is not less than the abnormal positioning duration parameter is taken as the third target Beidou positioning stage cluster, and each first abnormal positioning stage in the third target Beidou positioning stage cluster is taken as the key abnormal positioning stage corresponding to the immediate monitoring point.

6. The Beidou positioning data processing method based on artificial intelligence according to claim 1 is characterized in that: For each of the monitoring points, according to the instant position deviation, selecting the second abnormal positioning stage from the various Beidou positioning stages includes: For the real-time monitoring point, determine the positioning accuracy label associated with each real-time position deviation, generate the real-time positioning accuracy label associated with each Beidou positioning stage, and use the Beidou positioning stage with the real-time positioning accuracy label as the target accuracy evaluation label as the second abnormal positioning stage corresponding to the real-time monitoring point.

7. The Beidou positioning data processing method based on artificial intelligence according to claim 1 is characterized in that: The determining, based on the signal coverage area and the key abnormal positioning stage corresponding to the monitoring point in the key abnormal positioning stage in the specific Beidou positioning partition, the priori positioning performance corresponding to the specific Beidou positioning partition includes: For the monitoring points in the specific Beidou positioning partition where there are key abnormal positioning stages, the global stage parameters of each key abnormal positioning stage corresponding to the monitoring point are determined as the target abnormal positioning stage parameters corresponding to the monitoring point, and the signal coverage area and the target abnormal positioning stage parameters corresponding to the monitoring point are integrated to generate the prior positioning performance corresponding to the monitoring point; According to the prior positioning efficiencies associated with the monitoring points in the specific Beidou positioning partition where there is a key abnormal positioning phase, the prior positioning efficiencies corresponding to the specific Beidou positioning partition are generated.

8. The Beidou positioning data processing method based on artificial intelligence according to claim 1 is characterized in that: Determining the instant positioning performance corresponding to the specific Beidou positioning partition according to the signal coverage area corresponding to the monitoring point in the second abnormal positioning phase in the specific Beidou positioning partition and the second abnormal positioning phase includes: For the monitoring points in the specific Beidou positioning partition where both the key abnormal positioning stage and the second abnormal positioning stage exist, the shared abnormal positioning stage is determined from each key abnormal positioning stage and the second abnormal positioning stage corresponding to the monitoring point, the global stage parameters of each shared abnormal positioning stage corresponding to the monitoring point are determined as the shared abnormal positioning stage parameters corresponding to the monitoring point, the signal coverage area corresponding to the monitoring point and the shared abnormal positioning stage parameters are integrated to generate the real-time positioning performance corresponding to the monitoring point; Generate the real-time positioning performance corresponding to the specific Beidou positioning partition according to the real-time positioning performance associated with each monitoring point in the specific Beidou positioning partition that simultaneously exists in the key abnormal positioning stage and the second abnormal positioning stage; The updating of the basic abnormal positioning observation model according to the performance deviation between the prior positioning performance and the instant positioning performance, and generating an optimized target abnormal positioning observation model when the performance deviation meets the set standard, includes: For monitoring points with real-time positioning performance in the specific Beidou positioning partition, the performance deviation corresponding to each monitoring point is obtained according to the performance deviation between the real-time positioning performance and the prior positioning performance corresponding to the same monitoring point; For monitoring points with real-time positioning performance in the specific Beidou positioning partition, generating a performance deviation corresponding to the specific Beidou positioning partition according to an average deviation of performance deviations associated with each monitoring point; According to the performance deviation corresponding to the specific Beidou positioning partition, the basic abnormal positioning observation model is updated until the performance deviation corresponding to the specific Beidou positioning partition is less than the set deviation value, thereby generating an optimized target abnormal positioning observation model.

9. The Beidou positioning data processing method based on artificial intelligence according to any one of claims 1 to 8, characterized in that: The method further comprises: Determine the target position deviation associated with each monitoring point in each Beidou positioning stage according to the real-time position deviation associated with each monitoring point in each Beidou positioning stage; For each of the monitoring points, when a key abnormal positioning stage is estimated from the various Beidou positioning stages based on the target position deviation and the optimized target abnormal positioning observation model, the monitoring point is determined to be a target abnormal positioning monitoring point; According to the target abnormal positioning monitoring point and the key abnormal positioning stage corresponding to the target abnormal positioning monitoring point, abnormal positioning prompt information corresponding to the specific Beidou positioning partition is generated.

10. A Beidou positioning cloud service system, characterized in that: The Beidou positioning cloud service system includes a processor and a machine-readable storage medium, in which machine-executable instructions are stored. The machine-executable instructions are loaded and executed by the processor to implement the Beidou positioning data processing method based on artificial intelligence as described in any one of claims 1-9.

Images