Digital data governance method and system

Through digital data governance methods, the status of the UAV flight data and the appropriate processing method are analyzed, which solves the problem of poor quality of the UAV model training data and improves the accuracy and applicability of the model construction.

CN118503642BActive Publication Date: 2024-11-19GUANGDONG DONGLIAN XINCHUANG INFORMATION TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410958694.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-19
Estimated Expiration
2044-07-17

AI Technical Summary

Technical Problem

In the construction of drone flight models, poor quality of training data leads to low model construction accuracy, and it is difficult for existing technology to effectively screen and supplement data, resulting in poor validity of model flight data.

Method used

Provide a digital data governance method, determine the processing method through data state analysis, including data record processing and simulation supplement, perform mean interpolation, simulation interpolation or deletion of missing data, and select route reference or parameter reference data based on the data rich loss state Simulation supplement.

Benefits of technology

It improves the efficiency of data processing and model construction accuracy, avoids the accuracy poor caused by single-mode data simulation, and enhances the applicability of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118503642B_ABST
    Figure CN118503642B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing, and in particular to a digital data management method and system, the method comprising performing data status analysis on target data to obtain the data status of the target data and determining a data processing method according to the data status of the target data; executing the data processing method, performing data record processing on the target data, or performing data simulation supplement on the target data; in the data record processing on the target data, detecting the data neighborhood status of missing data records, and determining the data record processing method according to the data neighborhood status; in the data simulation supplement on the target data, determining the data simulation supplement method according to the data richness loss status of the target data; in the parameter benchmark data simulation supplement, performing parameter simulation according to the highlighted data and the highlighted value; the present invention improves the management efficiency of the training data for model construction, thereby improving the data quality of the training data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a digital data management method and system. Background Art

[0002] In the field of model learning, the quality of training data is crucial to the subsequent learning process, which in turn affects the accuracy of the final model construction, especially the construction of UAV flight models. The construction of UAV flight models is a complex and sophisticated process. In the actual model construction process, the richness and completeness of the UAV flight record data are very critical to the accuracy and applicability of the final model. However, the flight data uploaded by users are often obtained through flight records and flight experiments. The amount and richness of the data are difficult to meet the needs of model construction. Therefore, how to effectively screen supplementary data and process the data actually uploaded by users so that the training data meets the needs of model construction is a problem that needs to be urgently solved by technical personnel in this field.

[0003] Chinese patent publication number CN116755331A discloses a method for constructing a drone model and a computer device, the method comprising: constructing a drone model according to the physical parameters of a physical drone; calculating the optimal control parameters according to the gray wolf algorithm; obtaining the physical flight data of the physical drone; controlling the drone model for simulation according to the physical flight data and the optimal control parameters to obtain the model flight data; and correcting the drone model according to the physical flight data and the model flight data to obtain the target model. It can be seen that in the above technical solution, the optimal control parameters are calculated according to the gray wolf algorithm, but in the actual drone operation process, the parameters corresponding to different flight states are different. For example, for a drone with stable flight, the angular velocity, pitch angle and roll angle will tend to 0, but the angular velocity, pitch angle and roll angle of the drone under the flight posture of multiple transformation actions such as pitch motion or offset motion will be different from that in stable flight and change very quickly. Therefore, the use of the gray wolf algorithm will result in the inability to effectively select the optimal control parameters when the relevant data of the drone is insufficient, and there is a problem that the poor validity of the model flight data leads to poor accuracy of the final drone flight model. Summary of the invention

[0004] To this end, the present invention provides a digital data management method and system to overcome the problem of low model construction accuracy caused by the poor quality of training data of UAV flight models in the prior art and the inability to effectively manage them.

[0005] To achieve the above object, the present invention provides a digital data management method, comprising:

[0006] The user uploads the target data;

[0007] Performing data status analysis on target data to obtain the data status of the target data and determining a data processing method according to the data status of the target data;

[0008] Execute a data processing method, perform data recording processing on the target data, or perform data simulation supplement on the target data;

[0009] In data record processing for target data, the data neighborhood status of missing data records is detected, and the data record processing method is determined according to the data neighborhood status;

[0010] In data simulation supplementation for target data, the data simulation supplementation method is determined according to the data enrichment loss status of the target data;

[0011] In the parameter benchmark data simulation supplement, parameter simulation is performed based on the highlighted data and highlighted values.

[0012] Furthermore, a data status analysis is performed on the target data, wherein the data status of the target data is determined based on the data completeness and data richness of the target data, the data status including the data completeness being within a first preset data completeness range and the data richness being within a second preset data richness range, or the data completeness being within the second preset data completeness range and the data richness being within the first preset data richness range.

[0013] Furthermore, a data processing method is determined according to the data state of the target data, including performing data recording processing on the target data, or performing data simulation supplement on the target data.

[0014] Furthermore, data record processing is performed on the target data, the data neighborhood status of the missing data records is detected, and the data record processing method is determined according to the data neighborhood status, including mean interpolation, simulation interpolation or deletion for the missing data.

[0015] Furthermore, the data neighborhood status is determined based on the coherence of the neighborhood type I data and the proportion of the neighborhood type II data.

[0016] Furthermore, in data simulation supplementation for the target data, the data simulation supplementation method is determined according to the data enrichment loss status of the target data, including performing route baseline data simulation supplementation for the target data, or performing parameter baseline data simulation supplementation for the target data.

[0017] Furthermore, the data enrichment loss state of the target data is determined according to the route uniformity and parameter difference.

[0018] Furthermore, in the simulation supplement of the route reference data for the target data, several flight trajectory route simulations are performed and the data obtained by the simulation are supplemented to the target data;

[0019] The number of the flight trajectory routes is negatively correlated with the route uniformity.

[0020] Furthermore, in the parameter reference data simulation supplement for the target data, the highlighted data in the target data and the highlighted value of the highlighted data are detected, and the parameter simulation is performed several times for the highlighted data;

[0021] The number of parameter simulations of the highlighted data is positively correlated with the highlighted value of the highlighted data.

[0022] The present invention also provides a system for applying the digital data governance method, comprising:

[0023] A data analysis unit connected to the user end, used to determine the data state of the target data according to the data completeness and data richness of the target data, and determine the data processing method according to the data state of the target data;

[0024] A data processing unit connected to the data analysis unit, configured to perform data record processing on target data, detect a data neighborhood state of missing data records, and determine a data record processing method according to the data neighborhood state;

[0025] A simulation supplement unit is connected to the data processing unit and is used to perform data simulation supplement on the target data. The data simulation supplement method is determined according to the data richness loss state of the target data, including performing route baseline data simulation supplement on the target data, or performing parameter baseline data simulation supplement on the target data.

[0026] Compared with the prior art, the beneficial effect of the present invention lies in that, in the technical solution of the present invention, the data status of the target data is determined according to the data completeness and data richness of the target data, and the data completeness and data richness of the flight data are reflected by the data status, and then different data processing methods are selected according to actual conditions, so that the selection of data processing methods is more in line with actual working scenarios, thereby improving the practicability of the present invention and further improving the data processing efficiency of the present invention.

[0027] Furthermore, the present invention analyzes the data neighborhood status and performs different data processing accordingly, thereby avoiding the problem of poor accuracy of supplementary data obtained when using mean interpolation due to abnormalities in neighborhood data, thereby ensuring the accuracy of model construction of the present invention.

[0028] Furthermore, the present invention determines the data simulation supplement method according to the data enrichment loss state of the target data, reflects the route uniformity and parameter difference of the target data through the data enrichment loss state, thereby reflecting the flight usage habits of the drone in the flight data, and selectively selects different data simulation supplement methods, so that the selection of data simulation method is more in line with the user's usage needs, thereby avoiding the problems of poor data accuracy and poor practicality caused by single-mode data simulation in the prior art, and further improving the accuracy of the model components and the applicability of the model of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a digital data management method according to an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of determining a data processing method according to a data state of target data according to an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of determining a data record processing method according to a data neighborhood state according to an embodiment of the present invention;

[0032] Figure 4 A schematic diagram of determining a data simulation supplement method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0034] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0035] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0036] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0037] See also Figures 1 to 4 As shown, the present invention provides a digital data governance method, comprising:

[0038] The user uploads the target data;

[0039] Performing data status analysis on target data to obtain the data status of the target data and determining a data processing method according to the data status of the target data;

[0040] Execute a data processing method, perform data recording processing on the target data, or perform data simulation supplement on the target data;

[0041] In data record processing for target data, the data neighborhood status of missing data records is detected, and the data record processing method is determined according to the data neighborhood status;

[0042] In data simulation supplementation for target data, the data simulation supplementation method is determined according to the data enrichment loss status of the target data;

[0043] In the parameter benchmark data simulation supplement, parameter simulation is performed based on the highlighted data and highlighted values.

[0044] Specifically, the target data includes several flight records of the UAV. A single flight record includes the flight duration of the UAV and all monitoring parameters at different time points in the flight record. The monitoring parameters are the UAV throttle, propeller speed, propeller torque, UAV linear speed, UAV angular velocity, UAV position and UAV flight trajectory. The time point is set by the user. A time point setting is provided, in which the UAV take-off moment is recorded as a time point. In chronological order, every 5 seconds is recorded as a time point, that is, the monitoring parameters are recorded every 5 seconds, and the UAV throttle is represented by the size of the voltage signal.

[0045] Specifically, a data status analysis is performed on the target data, wherein the data status of the target data is determined according to the data completeness and data richness of the target data;

[0046] If the data integrity is within a first preset data integrity range and the data richness is within a second preset data richness range, determining that the data state is within the first preset data state;

[0047] If the data integrity is within the second preset data integrity range and the data richness is within the first preset data richness range, it is determined that the data state is within the second preset data state.

[0048] Data completeness = (total number of flight records - total number of missing flight records) / total number of flight records. Missing flight records refer to the missing of monitoring parameters corresponding to a time point in the flight records. The total number of flight records is recorded as data richness. Data richness = (total number of flight records - total number of similar flight records) / total number of flight records. Similar flight records are confirmed by detecting the similarity of two flight records. If the similarity is greater than the preset similarity, the two flight records are recorded as similar flight records. If the similarity is less than or equal to the preset similarity, the two flight records are not recorded as similar flight records. The value of the preset similarity can be set by the user according to the demand for data richness. The greater the user's demand for data richness, the greater the value of the preset similarity. A value of the preset similarity is provided. The preset similarity is 0.4. The calculation formula of the similarity S of two flight records is:

[0049] S=(△T / T1)×α1+(△C / C1)×α2+(△V / V1)×α3;

[0050] Among them, △T is the absolute value of the difference in flight time between the two flight records, △C is the absolute value of the difference in maximum UAV throttle corresponding to the two flight records, △V is the absolute value of the difference in maximum UAV linear speed corresponding to the two flight records, the flight time of any one of the flight records is denoted as T1, the maximum UAV throttle is denoted as C1, the maximum UAV linear speed is denoted as V1, α1 is the first weight coefficient, α2 is the second weight coefficient, and α3 is the third weight coefficient. A value of a weight coefficient is provided, α1=0.3, α2=0.3, α3=0.3.

[0051] Among them, the values ​​within the first preset data completeness range are all smaller than the second preset data completeness range, and the maximum value of the values ​​within the first preset data completeness range is the preset data completeness, the values ​​within the first preset data richness range are all smaller than the second preset data richness range, and the maximum value of the values ​​within the first preset data richness range is the preset data richness. The user can set the values ​​of the preset data completeness and the preset data richness according to the actual application scenario. The greater the user's demand for the completeness and richness of the flight data, the greater the values ​​of the preset data completeness and the preset data richness. A value of a preset data richness and a preset data completeness is provided, and the preset data completeness is 95%, and the data richness is 90%.

[0052] Specifically, the data processing method is determined according to the data status of the target data, including:

[0053] In the first preset data state, a first data processing mode for performing data recording processing on target data, the first data processing mode is performing data recording processing on target data;

[0054] In the second preset data state, a second data processing method is used to perform data simulation and supplement on the target data. The second data processing method is to perform data simulation and supplement on the target data.

[0055] If the data integrity is within the second preset data integrity range and the data richness is within the second preset data richness range, the target data is qualified and no data processing is required;

[0056] If the data completeness is within the first preset data completeness range and the data richness is within the first preset data richness range, the target data quality does not meet the construction requirements, and artificial data supplement information is sent to the user.

[0057] Specifically, data record processing is performed on the target data, the data neighborhood status of the missing data records is detected, and the data record processing method is determined according to the data neighborhood status, including mean interpolation, simulation interpolation or deletion for the missing data.

[0058] When the data neighborhood state is in the first preset data neighborhood state, determining whether to perform mean interpolation or deletion for the missing data according to the neighborhood data volume and the neighborhood data uniformity;

[0059] When the data neighborhood state is in the second preset data neighborhood state, performing simulation interpolation for the missing data;

[0060] When the amount of neighborhood data is greater than or equal to the preset amount of neighborhood data and the uniformity of neighborhood data is greater than or equal to the preset uniformity of neighborhood data, mean interpolation is performed for the missing data;

[0061] If the amount of neighborhood data is less than the preset amount of neighborhood data or the uniformity of neighborhood data is less than the preset uniformity of neighborhood data, the missing data is deleted;

[0062] The first preset data neighborhood state is that the proportion of the second category of neighborhood data is less than or equal to the preset proportion, and the second preset data neighborhood state is that the proportion of the second category of neighborhood data is greater than the preset proportion. The proportion of the second category of neighborhood data is 0, which is the number of monitoring parameters with a value of 0 in the associated time point corresponding to the missing monitoring parameter / the number of monitoring parameters with a value not equal to 0. It is known to those skilled in the art that when the drone is in steady-state operation, the angular velocity, pitch angle and roll angle will approach 0. Therefore, the proportion of the second category of neighborhood data reflects the operating stability of the drone in the corresponding time period, and further reflects whether the credibility of the neighborhood data can meet the means of mean interpolation. The value of the preset proportion can be set by the user for the model construction accuracy requirement. The greater the user's demand for model construction accuracy, the smaller the value of the preset proportion. A value of the preset proportion is provided, and the preset proportion is 30%.

[0063] Among them, the missing data record is a flight record in which the monitoring parameters corresponding to at least one time point are missing, the defective data is the missing monitoring parameter, the neighborhood data volume is the number of the same monitoring parameters in the associated time points of the time point corresponding to the missing monitoring parameter, the same monitoring parameters represent monitoring parameters of the same category and not 0, the neighborhood data uniformity is the value obtained by subtracting the maximum value from the minimum value of the same monitoring parameters in the associated time points of the time point corresponding to the missing monitoring parameter, the 10 adjacent time points between the time points corresponding to the missing monitoring parameter in chronological order and the 10 adjacent time points after the time point in chronological order are all recorded as associated time points, the preset neighborhood data volume is 6, and the preset neighborhood data uniformity is the number of the missing monitoring parameter corresponding to the missing monitoring parameter. 20% of the average value of the same monitoring parameter in the associated time point of the time point, mean interpolation is to record the average value of the same monitoring parameter in the associated time point corresponding to the missing monitoring parameter as mean supplementary data to supplement the missing data, simulation interpolation is to use the same monitoring parameters as the flight record to simulate the UAV model, and use the simulation data of the time point corresponding to the missing data in the simulation process to supplement the missing data. If the number of data deletions reaches 5 times, it is determined that the data is seriously missing and an alarm message is sent to the user. It is known to those skilled in the art that controlling the UAV model for simulation according to the flight data and control parameters of the entity to obtain model flight data, thereby supplementing the missing data, is a content of understanding and implementation, which will not be elaborated here.

[0064] Specifically, in the data simulation supplementation for the target data in the second preset data state, the data simulation supplementation method is detected and determined according to the data enrichment loss state of the target data;

[0065] If the data richness loss state is in the first preset data richness loss state, it is determined to perform route reference data simulation supplement for the target data;

[0066] If the data richness loss state is in the second preset data richness loss state, it is determined to perform parameter reference data simulation supplement for the target data.

[0067] Specifically, the data enrichment loss state of the target data is determined according to the route uniformity and parameter difference;

[0068] The first preset data enrichment loss state is that the route uniformity is within a first preset route uniformity range, and the parameter difference is within a second preset parameter difference range;

[0069] The second preset data enrichment loss state is that the route uniformity is within a second preset route uniformity range, and the parameter difference is within a second preset parameter difference range.

[0070] Specifically, route uniformity = (the number of all flight trajectories - the number of different flight trajectories) / the number of all flight trajectories.

[0071] For two flight trajectories, denoted as trajectory A and trajectory B, the Hausdorff distance is used to quantify the difference between the two flight trajectories, including:

[0072] Define the trajectory point set, and regard each flight trajectory as a collection of points. The points can be the positions of the drone recorded in a fixed time interval.

[0073] For each point in trajectory A, find the distance to the nearest point in trajectory B, record it as the reference distance, and count all reference distances;

[0074] The maximum value is selected from the reference distances. This value is the one-way Hausdorff distance from trajectory A to trajectory B, denoted as (d(A, B)).

[0075] Using the above method, calculate the Hausdorff distance in the other direction. Similarly, for each point in trajectory B, find the reference distance of the point closest to it in trajectory A, and select the maximum value from these distances. This value is the one-way Hausdorff distance from trajectory B to trajectory A, denoted as (d(B, A)).

[0076] The final Hausdorff distance is the larger value of (d(A, B)) and (d(B, A)), which is recorded as the difference between the two flight trajectories. The two flight trajectories with a difference greater than the preset difference are recorded as difference flight trajectories. The value of the preset difference can be set by the user according to the actual application scenario. The greater the user's demand for data richness, the greater the preset difference.

[0077] The calculation formula of parameter difference is:

[0078]

[0079] Pi is the difference parameter corresponding to the i-th flight record, P0 is the average value of the sum of the difference parameters corresponding to all flight records, i=1, 2, 3, ..., e.

[0080] Among them, the absolute value of the difference between the maximum and minimum values ​​of each identical monitoring parameter corresponding to each flight record is recorded as the parameter fluctuation value, and Mk / Mkmax is detected. Mk is the absolute value of the difference between the maximum and minimum values ​​of the kth identical monitoring parameter, and Mk is the maximum value of the kth identical monitoring parameter. The kth monitoring parameter corresponding to the largest Mk / Mkmax is recorded as the difference parameter.

[0081] The values ​​within the uniformity range of the first preset route are all greater than the values ​​within the uniformity range of the second preset route, and the maximum value within the uniformity range of the second preset route is the uniformity of the preset route. The values ​​within the first preset parameter difference range are all smaller than the values ​​within the second preset parameter difference range, and the maximum value within the first preset parameter difference range is the preset parameter difference. The values ​​of the uniformity of the preset route and the difference of the preset parameters can be set by the user according to the actual application scenario. The greater the user's demand for data richness, the smaller the uniformity of the preset route and the larger the difference of the preset parameters. A value of the uniformity of the preset route and the difference of the preset parameters are provided. The uniformity of the preset route is 50%, and the value of the difference of the preset parameters is 35% of P0.

[0082] Specifically, in the simulation supplement of the route reference data for the target data, several flight trajectory route simulations are performed and the data obtained from the simulations are supplemented to the target data;

[0083] The number of the flight trajectory routes is negatively correlated with the route uniformity.

[0084] Users can simulate the flight of UAVs through the intelligent maneuvering simulation model to generate simulated flight data under different routes. The flight trajectory route is set by the user, but the flight trajectory routes should be different.

[0085] Specifically, in the parameter reference data simulation supplement for the target data, the highlighted data in the target data and the highlighted value of the highlighted data are detected, and the parameter simulation is performed several times for the highlighted data;

[0086] The number of parameter simulations of the highlighted data is positively correlated with the highlighted value of the highlighted data.

[0087] Specifically, the highlighted data are three monitoring parameters selected in descending order of parameter fluctuation values, the highlighted value is the parameter fluctuation value, and the parameter simulation is to use simulation software to simulate the UAV under different highlighted data values ​​and obtain simulation data, and supplement the simulation data to the target data.

[0088] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0089] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A digital data governance method, characterized in that: include: The user uploads the target data; Performing data status analysis on target data to obtain the data status of the target data and determining a data processing method according to the data status of the target data; Execute a data processing method, perform data recording processing on the target data, or perform data simulation supplement on the target data; In data record processing for target data, the data neighborhood status of missing data records is detected, and the data record processing method is determined according to the data neighborhood status; In data simulation supplementation for target data, the data simulation supplementation method is determined according to the data enrichment loss status of the target data; In the parameter benchmark data simulation supplement, parameter simulation is performed based on the highlighted data and highlighted values; The highlighted data are three monitoring parameters selected in descending order of parameter fluctuation values, and the highlighted value is the parameter fluctuation value; the absolute value of the difference between the maximum value and the minimum value of each same monitoring parameter corresponding to each flight record is recorded as the parameter fluctuation value; If the data integrity is within a first preset data integrity range and the data richness is within a second preset data richness range, determining that the data state is within the first preset data state; If the data integrity is within the second preset data integrity range and the data richness is within the first preset data richness range, determining that the data state is within the second preset data state; In the first preset data state, a first data processing mode for performing data recording processing on target data, the first data processing mode is performing data recording processing on target data; In the second preset data state, a second data processing method is used to perform data simulation and supplement on the target data. The second data processing method is to perform data simulation and supplement on the target data.

2. The digital data management method according to claim 1, characterized in that: Perform data record processing on the target data, detect the data neighborhood status of the missing data records, and determine the data record processing method based on the data neighborhood status, including mean interpolation, simulation interpolation or deletion for the missing data.

3. The digital data management method according to claim 2, characterized in that: The data neighborhood status is determined based on the proportion of the second type of data in the neighborhood.

4. The digital data management method according to claim 3, characterized in that: In data simulation supplementation for target data, the data simulation supplementation method is determined according to the data enrichment loss status of the target data, including simulation supplementation of route benchmark data for the target data, or simulation supplementation of parameter benchmark data for the target data.

5. The digital data management method according to claim 4, characterized in that: The data enrichment loss state of the target data is determined according to the route uniformity and parameter difference.

6. The digital data management method according to claim 5, characterized in that: In the simulation supplement of route reference data for target data, several flight trajectory route simulations are performed and the simulated data are supplemented to the target data; The number of the flight trajectory routes is negatively correlated with the route uniformity.

7. The digital data management method according to claim 6, characterized in that: In the parameter reference data simulation supplement for the target data, the highlighted data in the target data and the highlighted value of the highlighted data are detected, and the parameter simulation is performed several times for the highlighted data; The number of parameter simulations of the highlighted data is positively correlated with the highlighted value of the highlighted data.

8. A system using the digital data management method according to any one of claims 1 to 7, characterized in that: include: A data analysis unit connected to the user end, used to determine the data state of the target data according to the data completeness and data richness of the target data, and determine the data processing method according to the data state of the target data; A data processing unit connected to the data analysis unit, configured to perform data record processing on target data, detect a data neighborhood state of missing data records, and determine a data record processing method according to the data neighborhood state; A simulation supplement unit is connected to the data processing unit and is used to perform data simulation supplement on the target data. The data simulation supplement method is determined according to the data richness loss state of the target data, including performing route baseline data simulation supplement on the target data, or performing parameter baseline data simulation supplement on the target data.