Highway safety intelligent active early warning system data cleaning method

Abstract

The invention discloses a data cleaning method of a highway safety intelligent active early warning system, which comprises the following steps: generating a structured data table by collecting highway environment data and data in a three-axis acceleration sensor in real time, and transmitting the data in the structured data table to a cloud for storage by using an encryption algorithm of a communication protocol; performing data exception judgment on the stored data, and cleaning the stored exceptional data by adopting different data cleaning modes according to a data exception judgment result; and performing data reconstruction and result verification on the cleaned abnormal data to form the data cleaning method for the highway safety intelligent active early warning system. Through research on data cleaning, the method not only can improve the validity and reliability of data, reduce misjudgment of an early warning system and improve the operation efficiency of the early warning system, but also can guarantee the travel safety of vehicles and personnel on a highway, and effectively reduces the probability of traffic accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing under highway safety warning, and in particular to a data cleaning method for a highway safety intelligent active warning system. Background Art

[0002] With the increasing mileage of highways and the number of cars, more and more residents are choosing to travel by car. At the same time, with the rapid development of social economy, not only the number of various freight vehicles is surging, but also the number of vehicles running on highways is increasing year by year.

[0003] However, on highways, due to the high speed of vehicles, once an accident occurs in front, the rear vehicles may not be able to obtain the information of the accident in time, which may lead to rear-end collisions and chain accidents. In order to solve this problem, a highway safety intelligent active warning system came into being. The system collects highway on-site data by multifunctional intelligent sensing equipment, which is first transmitted to the cloud platform through communication equipment. The cloud platform server determines the status of the highway through the data, such as whether there is an ice and snow covered area in front, whether a vehicle collision failure has occurred, whether there is a crosswind, etc. Secondly, the rear vehicles are notified in time through flash warnings and voice warnings to avoid them. In addition, once a major accident such as a vehicle collision accident or a road collapse accident occurs, the cloud platform server can promptly notify the relevant rescue department for first aid to avoid delaying the rescue time.

[0004] But for now, the cloud platform server needs to process data collected by a large number of multifunctional intelligent sensor devices. Once the data is wrong, it may cause the cloud platform server to misjudge the traffic status of the road, which will not only reduce the travel efficiency of residents, but also cause once an accident occurs on the road ahead, if the early warning system does not issue a warning information, it is easy to cause a chain traffic accident, resulting in a series of serious consequences. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a data cleaning method for a highway safety intelligent active warning system to solve the problems raised in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a data cleaning method for a highway safety intelligent active warning system, comprising:

[0008] By collecting highway environmental data and data from a three-axis acceleration sensor in real time, a structured data table is generated, and the data in the structured data table is transmitted to the cloud for storage using an encryption algorithm of a communication protocol;

[0009] Perform data anomaly judgment on the stored data, and use different data cleaning methods to clean the stored abnormal data according to the data anomaly judgment results;

[0010] The cleaned abnormal data is reconstructed and the results are verified to form a data cleaning method for the highway safety intelligent active warning system.

[0011] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system described in the present invention, wherein: by real-time collection of highway environmental data and data from a three-axis acceleration sensor, a structured data table is generated, including:

[0012] The structure of the structured data table includes data number, device type, device number, Beidou reception information, temperature, humidity, light, wind speed, wind direction, rain and snow, three-axis acceleration sensor information, noise decibel and device status.

[0013] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system described in the present invention, the encryption algorithm of the communication protocol includes:

[0014] The packet symmetric encryption algorithm SM4 is used to divide the transmitted message into groups of 128 bits, and each group is iterated through 32 rounds of round functions.

[0015] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, wherein: the stored data is judged for data anomaly, and different data cleaning methods are used to clean the stored abnormal data according to the data anomaly judgment results, including:

[0016] The data cleaning method includes data redundancy cleaning, data conflict cleaning, data default conflict and data outlier conflict.

[0017] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, the data redundancy cleaning includes:

[0018] The passing time between the front and rear vehicles is set as the total collection time for storing data. If any two sets of collected data are the same data, but the time interval between the two sets of data is less than the total collection time, it is considered that the collected data is redundant and data redundancy cleaning is performed.

[0019] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, the data conflict cleaning includes:

[0020] If the device number and longitude in any two sets of collected data are the same, but the latitude is different; or the device number and latitude are the same, but the longitude is different; or the longitude and latitude are the same, but the device number is different; then the data is considered to be conflicting and data conflict cleaning is performed;

[0021] It also includes that if the temperature, humidity, light intensity, x-axis acceleration, y-axis acceleration, z-axis acceleration and noise in the collected data are respectively greater than the maximum value of the collected data or lower than the minimum value of the collected data, it is considered that the data exceeds the limit and there is a conflict, and data conflict cleaning is performed;

[0022] It also includes that if the collected data exceeds the constraint range of its own data, the group of data is considered to be conflicting and data conflict cleaning is performed;

[0023] It also includes setting a maximum value of the mean square error of the collected data. If the mean square error of the previous data, the current data and the next data collected exceeds the maximum value of the mean square error, the collected data is incorrect and needs to be collected again.

[0024] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, the data default conflict includes:

[0025] If the collected data is missing one or more items of the stored data, the data will be cleaned by default.

[0026] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, the data outlier conflict includes:

[0027] The x-axis acceleration, y-axis acceleration and z-axis acceleration in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the first three-dimensional space;

[0028] The temperature, humidity and light in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the second three-dimensional space;

[0029] The wind speed, wind direction and noise decibel in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the third three-dimensional space.

[0030] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, it also includes:

[0031] The outlier detection adopts a density-based outlier detection method, and obtains the contribution of the qth point to the cluster through the local outlier factor and local reachable density of the qth point in the three-dimensional space;

[0032] According to the contribution degree, a local outlier is obtained.

[0033] As a preferred solution of the data cleaning method of the highway safety intelligent active warning system of the present invention, it also includes:

[0034] If an outlier is detected in any three-dimensional space, the data constructed in this group will be cleaned. That is, if the nth data is detected as a local outlier in the first three-dimensional space, but the second and third three-dimensional spaces both indicate that the nth data is a cluster point, the nth data is still determined to be outlier data and the outlier data will be cleaned.

[0035] Compared with the prior art, the invention has the following beneficial effects:

[0036] 1. The present invention significantly improves the validity of data and reduces misjudgment caused by data anomalies by adopting targeted anomaly detection and corresponding data cleaning methods (redundancy cleaning, conflict cleaning, default completion, and outlier processing), ensuring that the cloud platform server has high accuracy and stability when processing highway status data;

[0037] 2. Abnormal data is efficiently cleaned and reconstructed through cloud servers, useless data is eliminated, the waste of computing resources is reduced, the data cleaning process is optimized, and the early warning system's judgment and warning speed of the highway status is accelerated. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0039] Figure 1 The overall flow chart of the data cleaning method of the highway safety intelligent active warning system according to one embodiment of the present invention;

[0040] Figure 2 A schematic diagram of a plurality of multifunctional intelligent sensing devices arranged along a highway in a data cleaning method for a highway safety intelligent active warning system according to an embodiment of the present invention;

[0041] Figure 3A schematic diagram of outliers in a data cleaning method for a highway safety intelligent active warning system according to an embodiment of the present invention;

[0042] Figure 4 This is an acceleration scatter plot of a data cleaning method for a highway safety intelligent active warning system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0044] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0045] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0046] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0047] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0048] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] Example 1

[0050] Reference Figures 1 to 4 , which is the first embodiment of the present invention, and provides a method for cleaning data of a highway safety intelligent active warning system, comprising:

[0051] S1. Generate a structured data table by collecting highway environmental data and data from a three-axis acceleration sensor in real time, and use an encryption algorithm of a communication protocol to transmit the data in the structured data table to the cloud for storage;

[0052] Specifically, the highway environment data and the data from the three-axis acceleration sensor are collected in real time through multifunctional intelligent sensing equipment;

[0053] Specifically, the multifunctional intelligent sensor device integrates Beidou receiver, three-axis acceleration sensor ADXL362, temperature and humidity sensor DHT11, noise sensor JHM-NS02, CPU STM32L431RCT6, power module, solar charging module, LORA communication module, 4G communication module, modbus communication module, light sensor bh1750, wind speed and direction sensor ZQZ-TF and rain and snow sensor RY-CYX, etc.;

[0054] Furthermore, the structure of the structured data table (as shown in Table 1) includes data number, device type, device number, Beidou reception information, temperature, humidity, light, wind speed, wind direction, rain and snow, three-axis acceleration sensor information, noise decibel, and device status;

[0055] Table 1 Data table structure

[0056]

[0057] Specifically, Beidou receiving information includes longitude, latitude and receiving time;

[0058] Specifically, the three-axis acceleration sensor includes x-axis acceleration, y-axis acceleration and z-axis acceleration;

[0059] It should be noted that the table structure shows the field information in the table, and each field information contains the specific data that needs to be collected;

[0060] Furthermore, the data transmission method uses the packet symmetric encryption algorithm SM4, which divides the transmitted message into groups of 128 bits, and each group is iterated through 32 rounds of the round function;

[0061] It should be noted that the use of the group symmetric encryption algorithm SM4 is the preferred embodiment of the present invention. For SM4, encryption operations can be completed with relatively low computing resources, especially in resource-constrained devices (multi-function sensor devices on highways), and real-time transmission and data collection can be supported.

[0062] It should be explained that the round function is a concept in cryptography, usually used in symmetric encryption algorithms; it represents the core computing unit of multiple rounds of iterations in the encryption process, and the security of encryption is enhanced by repeatedly using the round function, and each round performs specific mathematical and logical operations on the data;

[0063] Furthermore, the data collected by the multifunctional intelligent sensor device is transmitted to the cloud through the LoRA communication protocol;

[0064] Specifically, the cloud uses a cloud data storage device and a cloud data backup storage device to store the data collected by the multifunctional intelligent sensor device;

[0065] S2. Perform data anomaly judgment on the stored data, and use different data cleaning methods to clean the stored abnormal data according to the data anomaly judgment results;

[0066] Specifically, there is a one-to-one relationship between the result of data anomaly judgment and the data cleaning method; for example, if the data contains redundancy, the data redundancy cleaning method is used;

[0067] Specifically, data cleaning methods include data redundancy cleaning, data conflict cleaning, data default conflict, and data outlier conflict;

[0068] Furthermore, the data redundancy cleaning method is as follows:

[0069] The passing time between the two vehicles is set as the total collection time of the stored data. If any two sets of collected data are the same data, but the time interval between the two sets of data is less than the total collection time, the collected data is considered redundant and data redundancy cleaning is performed;

[0070] Furthermore, the data conflict cleaning method is as follows:

[0071] Condition 1: If the device number and longitude in any two sets of data collected are the same, but the latitude is different; or the device number and latitude are the same, but the longitude is different; or the longitude and latitude are the same, but the device number is different; then the data is considered to be conflicting and data conflict cleaning is performed;

[0072] Condition 2: If the temperature, humidity, light intensity, x-axis acceleration, y-axis acceleration, z-axis acceleration and noise in the collected data are respectively greater than the maximum value of the collected data or lower than the minimum value of the collected data, the data is considered to be out of limit and conflicting, and data conflict cleaning is performed;

[0073] Specifically, the maximum value of the collected data and the minimum value of the collected data are the maximum value and the minimum value of the corresponding parameters of all the collected data;

[0074] Condition 3: If the collected data exceeds the constraint range of its own data, the group of data is considered to be conflicting and data conflict cleaning is performed;

[0075] Specifically, exceeding its own constraint range means, for example, when the x-axis acceleration and y-axis acceleration are normal, the z-axis acceleration data should be 9.8m / s 2 Nearby areas, but the data is lower than 9.5m / s 2 or greater than 10.1m / s 2 (the deviation is too large and exceeds the neighborhood range), then the group of data is considered to be conflicting and data conflict cleaning is required;

[0076] Condition 4: Set the maximum value of the mean square error of the collected data. If the mean square error of the previous data, the current data, and the next data collected exceeds the maximum value of the mean square error of the data, the collected data is incorrect and needs to be collected again, that is, re-execute conditions 1 to 4;

[0077] Furthermore, condition 4 is as follows:

[0078] like Figure 2 As shown in the figure, if the mean square error of the data collected by the i-th device and the data collected by the i-1-th device and the i+1-th device exceeds the maximum value of the mean square error of the data, the data collected by the i-th device is considered to be incorrect;

[0079] Specifically, the mean square error of the data can be expressed as:

[0080]

[0081] …

[0082] Among them, X i is the temperature collected by the i-th device, Y i is the humidity collected by the i-th device, Z i is the illumination collected by the i-th device, A i The wind speed collected by the ith device is calculated by the formula, and so on, until all the data in the table are expressed as mean square error; are the mean square errors of temperature, humidity, light and wind speed data respectively;

[0083] Furthermore, if any of the mean square deviations of the data exceeds the maximum value of the mean square deviation of the collected data, it is considered that the data collected by the i-th device is incorrect and the corresponding data needs to be collected again;

[0084] Furthermore, the default data conflict cleaning method is as follows:

[0085] If the collected data is missing one or more items in the stored data, the data will be cleaned by default;

[0086] Specifically, missing means that the collected data is incomplete, that is, the field information in Table 1 is missing;

[0087] Furthermore, the data outlier conflict cleaning method is as follows:

[0088] The x-axis acceleration, y-axis acceleration and z-axis acceleration in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the first three-dimensional space;

[0089] The temperature, humidity and light in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the second three-dimensional space;

[0090] The wind speed, wind direction and noise decibel in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the third three-dimensional space;

[0091] It should be noted that the data collected by the same multifunctional intelligent sensor should meet the time uniformity, that is, the data collected by the same multifunctional intelligent sensor should be clustered (data with clusters are cluster points), and outlier data should be cleared. Figure 3 (The data corresponding to outlier 1, outlier 2, and outlier 3 should be cleaned in a data outlier conflict manner);

[0092] Furthermore, outlier detection adopts a density-based outlier detection method, which obtains the contribution of the qth point to the cluster through the local outlier factor and local reachable density of the qth point in the three-dimensional space;

[0093] Specifically, the local outlier factor and local reachability density of the qth point in three-dimensional space can be expressed as:

[0094]

[0095] Among them, LOF represents the local outlier factor, Lrd represents the local reachability density, and N k (q) represents the k nearest neighbors of the qth point, reach-distk(q,p) is the reachable distance between the qth point and the pth point;

[0096] Specifically, the reachable distance is expressed as:

[0097] reach-distk(q,p)=max{d(q,p),k(p)}

[0098] Among them, d(q,p) represents the distance between the qth point and the pth point, and k(p) represents the distance between the pth point and the kth point closest to it;

[0099] Furthermore, according to the contribution, local outliers are obtained;

[0100] Specifically, the contribution of the qth point to the cluster can be expressed as:

[0101]

[0102] Among them, C i is the i-th cluster, n is q. After joining the i-th cluster, if q belongs to the neighboring point of other sample points, the number of other sample points is n; LOF k (p j ) means that after the qth point joins the i-th cluster, the pth j LOF value of sample points; LOF′ k (p j ) indicates that after the qth point is not added to the i-th cluster, the pth j LOF value of sample points, α represents the adjustment factor;

[0103] Furthermore, if Contr(q,C i ) is less than 0, then q is considered not to belong to the i-th cluster C i points, and is a cluster C i Local outliers of ;

[0104] Furthermore, if an outlier is detected in any three-dimensional space, the data constructed in this group is cleaned, that is, if the nth data is detected as a local outlier in the first three-dimensional space, but the second three-dimensional space and the third three-dimensional space both indicate that the nth data is a cluster point, the nth data is still determined to be an outlier data and the outlier data is cleaned;

[0105] It should be noted that the reference Figure 4 , Taking acceleration data as an example, it can be seen that the method of the present invention can effectively identify outliers;

[0106] S3, reconstructing and verifying the cleaned abnormal data to form a data cleaning method for the highway safety intelligent active warning system;

[0107] Specifically, the cleaned data is reconstructed to become normal data, and the cleaned normal data is sent to the cloud for verification. The purpose of the verification is to check the security and accuracy of the data.

[0108] It should be noted that the above-mentioned data reconstruction and result verification methods can be implemented through existing technologies, and therefore, they will not be described in detail in the solution of the present invention.

[0109] Those skilled in the art will appreciate that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program codes. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0113] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A data cleaning method for a highway safety intelligent active warning system, characterized in that: include: By collecting highway environmental data and data from a three-axis acceleration sensor in real time, a structured data table is generated, and the data in the structured data table is transmitted to the cloud for storage using an encryption algorithm of a communication protocol; Perform data anomaly judgment on the stored data, and use different data cleaning methods to clean the stored abnormal data according to the data anomaly judgment results; The cleaned abnormal data is reconstructed and the results are verified to form a data cleaning method for the highway safety intelligent active warning system.

2. The method for cleaning data of the highway safety intelligent active warning system according to claim 1, characterized in that: By collecting highway environment data and data from the three-axis acceleration sensor in real time, a structured data table is generated, including: The structure of the structured data table includes data number, device type, device number, Beidou reception information, temperature, humidity, light, wind speed, wind direction, rain and snow, three-axis acceleration sensor information, noise decibel and device status.

3. The data cleaning method for the highway safety intelligent active warning system according to claim 1 is characterized in that: The encryption algorithm of the communication protocol includes: The packet symmetric encryption algorithm SM4 is used to divide the transmitted message into groups of 128 bits, and each group is iterated through 32 rounds of round functions.

4. The method for cleaning data of a highway safety intelligent active warning system according to claim 1, characterized in that: The stored data is judged for data anomalies, and different data cleaning methods are used to clean the stored abnormal data according to the data anomaly judgment results, including: The data cleaning method includes data redundancy cleaning, data conflict cleaning, data default conflict and data outlier conflict.

5. The method for cleaning data of the highway safety intelligent active warning system according to claim 4, characterized in that: The data redundancy cleaning includes: The passing time between the front and rear vehicles is set as the total collection time for storing data. If any two sets of collected data are the same data, but the time interval between the two sets of data is less than the total collection time, it is considered that the collected data is redundant and data redundancy cleaning is performed.

6. The method for cleaning data of a highway safety intelligent active warning system according to claim 2 or 4, characterized in that: The data conflict cleaning includes: If the device number and longitude in any two sets of collected data are the same, but the latitude is different; or the device number and latitude are the same, but the longitude is different; or the longitude and latitude are the same, but the device number is different; then the data is considered to be conflicting and data conflict cleaning is performed; It also includes that if the temperature, humidity, light intensity, x-axis acceleration, y-axis acceleration, z-axis acceleration and noise in the collected data are respectively greater than the maximum value of the collected data or lower than the minimum value of the collected data, it is considered that the data exceeds the limit and there is a conflict, and data conflict cleaning is performed; It also includes that if the collected data exceeds the constraint range of its own data, the group of data is considered to be conflicting and data conflict cleaning is performed; It also includes setting a maximum value of the mean square error of the collected data. If the mean square error of the previous data, the current data and the next data collected exceeds the maximum value of the mean square error, the collected data is incorrect and needs to be collected again.

7. The data cleaning method for the highway safety intelligent active warning system according to claim 2 or 4, characterized in that: The data default conflicts include: If the collected data is missing one or more items of the stored data, the data will be cleaned by default.

8. The method for cleaning data of a highway safety intelligent active warning system according to claim 2 or 4, characterized in that: The data outlier conflicts include: The x-axis acceleration, y-axis acceleration and z-axis acceleration in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the first three-dimensional space; The temperature, humidity and light in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the second three-dimensional space; The wind speed, wind direction and noise decibel in the collected data are used to construct the x-axis, y-axis and z-axis data respectively, and outlier detection is performed in the third three-dimensional space.

9. The method for cleaning data of a highway safety intelligent active warning system as claimed in claim 8, characterized in that: Also includes: The outlier detection adopts a density-based outlier detection method, and obtains the contribution of the qth point to the cluster through the local outlier factor and local reachable density of the qth point in the three-dimensional space; According to the contribution degree, a local outlier is obtained.

10. The method for cleaning data of the highway safety intelligent active warning system according to claim 9, characterized in that: Also includes: If an outlier is detected in any three-dimensional space, the data constructed in this group will be cleaned. That is, if the nth data is detected as a local outlier in the first three-dimensional space, but the second and third three-dimensional spaces both indicate that the nth data is a cluster point, the nth data is still determined to be outlier data and the outlier data will be cleaned.

Images