A noise vehicle control method and system based on multi-source data

Abstract

The present invention discloses a noisy vehicle control method and system based on multi-source data, including: acquiring report data; acquiring noise report data; preprocessing noise report data; acquiring historical data on illegally modified vehicles; comparing the noise report data with historical data on illegally modified vehicles to determine historical patterns in the travel of illegally modified vehicles; and implementing control based on the determined historical patterns. The present invention does not rely on the sound collected by noise collection equipment as a basis for judgment, eliminating interference from other high-noise vehicles. It also eliminates the issue of low equipment coverage.

Description

Technical Field

[0001] The present invention belongs to the field of traffic detection and control, and in particular relates to a noise vehicle control method and system based on multi-source data. Background Art

[0002] In recent years, "street-blasting vehicles" (the so-called "street-blasting vehicles" are vehicles that have illegally modified their exhaust pipes, tires, air intakes, etc. to varying degrees, causing the vehicle's throttle to roar harshly) have attracted prominent public response and have been relatively difficult to manage in urban environments. The main trends are: their whereabouts are difficult to detect, evidence is difficult to obtain, and incidents are difficult to prevent and capture.

[0003] In existing technologies, the usual solution is to identify the noise of "street-blasting vehicles". However, in addition to the horns of motor vehicles, traffic noise also includes other high-noise vehicles, such as various large trucks and buses. These vehicles will affect the screening of "street-blasting vehicles". Secondly, most cities currently do not have complete road sound collection equipment. Using noise to identify and screen "street-blasting vehicles" will have an impact. The efficiency of identifying "street-blasting vehicles" through noise is not high, which affects the success rate of deployment and control. Summary of the Invention

[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a noise vehicle control method and system based on multi-source data to solve the problems in the prior art of imperfect road sound collection equipment and low noise resolution of sound collection equipment.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A noise vehicle control method based on multi-source data of the present invention comprises the following steps:

[0007] 1) Acquisition of reporting data: Obtain traffic nuisance reporting data from relevant reporting platforms;

[0008] 2) Acquisition of noise reporting data: Analyze the traffic nuisance reporting data through the open source code library to obtain noise reporting data;

[0009] 3) Noise report data preprocessing: Natural language processing (NLP) is performed on the noise report data using an open-source code library to obtain the license plate type, license plate number, noise time period, and noise location of the noisy vehicle;

[0010] 4) Acquisition of historical illegal vehicle modification data: Acquisition of historical illegal modification violation data from the violation database, including license plate type and license plate number;

[0011] 5) Compare noise reporting data with historical data on illegally modified vehicles: Query checkpoint vehicle passing data, including license plate type, license plate number, passing time, and checkpoint equipment number. Compare noise reporting data with historical data on illegally modified vehicles to obtain historical patterns of illegal modified vehicle travel (high-frequency time periods and high-frequency locations).

[0012] 6) Deploy surveillance based on the historical patterns of illegally modified vehicles' travel obtained in step 5).

[0013] Furthermore, the traffic nuisance reporting data includes: reporting time and reporting content.

[0014] Furthermore, the specific steps of step 2) are as follows:

[0015] 21) Use the open source Python code library and the third-party Python word segmentation library Jieba to segment the traffic nuisance report data;

[0016] 22) Perform keyword filtering on the array outputted from each report content, and filter out data containing keywords including but not limited to noise, modification, and roar;

[0017] 23) According to the screening results in step 22), screening is performed to obtain noise reporting data.

[0018] Furthermore, the specific steps of step 3) are as follows:

[0019] 31) Perform natural language processing on the content of each noise reporting data and use the Python third-party library Jieba to segment the sentences;

[0020] 32) Performing regular expression matching on the word segmentation result array outputted in step 31) through natural language processing to match the corresponding license plate type (small car by default), license plate number, noise time and noise location;

[0021] 33) Generate a noise vehicle details table, the fields of which include license plate type, license plate number, noise time, noise location and remarks.

[0022] Furthermore, the specific steps of step 5) are as follows:

[0023] 51) According to the noise vehicle details table generated in step 33), extract the noise time period, cluster the noise time period and noise location respectively, and obtain the top five time periods (t1, t2, t3, t4, t5) and the top five noise locations (addr1, addr2, addr3, addr4, addr5) ranked by the number of reports;

[0024] 52) Based on the five noise locations obtained in step 51), select the checkpoint equipment within 0 to 3 km around each noise location on the map and obtain the equipment number of each checkpoint equipment;

[0025] 53) Query the vehicle track data (obtained from the traffic management department) of all historical illegally modified vehicles in the previous 30 days (the number of times the vehicle was photographed by the checkpoint device within a certain time range). The time limit condition is the five time periods in step 51), and the checkpoint device limit condition is the device number of the checkpoint device in step 52);

[0026] 54) Sort the query results of step 53) in reverse order by the number of times the vehicle has passed, and query the checkpoint vehicle passing data for the n (adjusted according to the needs of the traffic control department) illegally modified vehicles that have passed in the past 30 days (without setting time period or equipment restrictions);

[0027] 55) Aggregate the results of step 54) to obtain the high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) of historical illegally modified vehicles.

[0028] Furthermore, the specific steps of step 6) are as follows:

[0029] 61) The high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) in step 55) are entered into the traffic police monitoring system. At the same time, the n vehicles in step 54) are entered as key focus vehicles and personnel are assigned to monitor them.

[0030] The present invention also provides a noise vehicle control system based on multi-source data, comprising:

[0031] Reporting data acquisition module, used to obtain traffic nuisance reporting data from relevant reporting platforms;

[0032] A noise reporting data acquisition module is used to analyze the traffic nuisance reporting data through an open source code library to obtain noise reporting data;

[0033] The noise reporting data preprocessing module is used to perform natural language processing on the noise reporting data obtained through the open source code library to obtain the license plate type, license plate number, noise time period and noise location of the noisy vehicle;

[0034] The module for acquiring historical illegally modified vehicle data is used to obtain historical illegal modification violation data from the violation database, including license plate type and license plate number;

[0035] The data comparison module is used to query the vehicle passing data at the checkpoint, including license plate type, license plate number, passing time, and checkpoint equipment number. It also compares the noise reporting data with the historical data of illegally modified vehicles to obtain the historical travel patterns of illegally modified vehicles (high-frequency time periods and high-frequency locations).

[0036] The control module is used to carry out control based on the historical travel patterns of illegally modified vehicles.

[0037] Beneficial effects of the present invention:

[0038] 1. The present invention does not use the sound collected by the noise collection device as the basis for judgment, thus eliminating the interference of other high-noise vehicles; at the same time, there is no need to consider the problem of low equipment coverage.

[0039] 2. The present invention uses multiple data sources as the basis for analysis, making the prediction of noisy vehicle travel patterns more realistic.

[0040] 3. The method of the present invention can be used to monitor noisy vehicles accurately to the time period, area, and even vehicle, thus saving police force costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the method of the present invention.

[0042] Figure 2 Flow chart of data comparison in the present invention. DETAILED DESCRIPTION

[0043] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and drawings. The contents mentioned in the embodiments are not intended to limit the present invention.

[0044] Reference Figure 1 As shown, a noise vehicle control method based on multi-source data of the present invention includes the following steps:

[0045] 1) Acquisition of reporting data: Acquisition of traffic nuisance reporting data from relevant reporting platforms; wherein, the traffic nuisance reporting data includes: reporting time and reporting content.

[0046] 2) Acquisition of noise reporting data: Analyze the traffic nuisance reporting data through the open source code library to obtain noise reporting data;

[0047] Wherein, the specific steps of step 2) are as follows:

[0048] 21) Use the open source Python code library and the third-party Python word segmentation library Jieba to segment the traffic nuisance reporting data;

[0049] 22) Perform keyword filtering on the array outputted from each report content, and filter out data containing keywords including but not limited to noise, modification, and roar;

[0050] 23) According to the screening results in step 22), screening is performed to obtain noise reporting data.

[0051] 3) Noise report data preprocessing: Natural language processing (NLP) is performed on the noise report data obtained using an open source code library to obtain the license plate type and number of the noisy vehicle, the noise time period (e.g., 2022-01-04 22:23:05, the time period is 22), and the noise location;

[0052] Wherein, the specific steps of step 3) are as follows:

[0053] 31) Perform natural language processing on the content of each noise reporting data and use the Python third-party library Jieba to segment the sentences;

[0054] 32) Performing regular expression matching on the word segmentation result array outputted in step 31) through natural language processing to match the corresponding license plate type (small car by default), license plate number, noise time and noise location;

[0055] 33) Generate a noise vehicle details table, the fields of which include license plate type, license plate number, noise time, noise location and remarks.

[0056] 4) Acquisition of historical illegal vehicle modification data: Acquisition of historical illegal modification violation data from the violation database, including license plate type and license plate number;

[0057] 5) Compare noise reporting data with historical data on illegally modified vehicles: Query checkpoint vehicle passing data, including license plate type, license plate number, passing time, and checkpoint equipment number. Compare noise reporting data with historical data on illegally modified vehicles to obtain historical patterns of illegal modified vehicle travel (high-frequency time periods and high-frequency locations).

[0058] Among them, reference Figure 2 As shown, the specific steps of step 5) are as follows:

[0059] 51) According to the noise vehicle details table generated in step 33), extract the noise time period, cluster the noise time period and noise location respectively, and obtain the top five time periods (t1, t2, t3, t4, t5) and the top five noise locations (addr1, addr2, addr3, addr4, addr5) ranked by the number of reports;

[0060] 52) Based on the five noise locations obtained in step 51), select the checkpoint equipment within 3 km around each noise location on the map and obtain the equipment number of each checkpoint equipment;

[0061] 53) Query the vehicle track data (obtained from the traffic management department) of all historical illegally modified vehicles in the previous 30 days (the number of times the vehicle was photographed by the checkpoint device within a certain time range). The time limit condition is the five time periods in step 51), and the checkpoint device limit condition is the device number of the checkpoint device in step 52);

[0062] 54) The query results of step 53) are sorted in reverse order by the number of times the vehicle has passed, and the time and location of the first 200 illegally modified vehicles (in other examples, the number can be adjusted according to the needs of the traffic control department) in the checkpoint vehicle passing data in the previous 30 days are searched (no time period or device restrictions are set);

[0063] 55) Aggregate the results of step 54) to obtain the high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) of historical illegally modified vehicles.

[0064] 6) Deploy surveillance based on the historical patterns of illegally modified vehicles obtained in step 5);

[0065] Wherein, the specific steps of step 6) are as follows:

[0066] 61) The high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) in step 55) are entered into the traffic police monitoring system. At the same time, the 200 vehicles in step 54) are entered as key focus vehicles and personnel are assigned to monitor them.

[0067] The present invention also provides a noise vehicle control system based on multi-source data, comprising:

[0068] Reporting data acquisition module, used to obtain traffic nuisance reporting data from relevant reporting platforms;

[0069] A noise reporting data acquisition module is used to analyze the traffic nuisance reporting data through an open source code library to obtain noise reporting data;

[0070] The noise reporting data preprocessing module is used to perform natural language processing on the noise reporting data obtained through the open source code library to obtain the license plate type, license plate number, noise time period and noise location of the noisy vehicle;

[0071] The module for acquiring historical illegally modified vehicle data is used to obtain historical illegal modification violation data from the violation database, including license plate type and license plate number;

[0072] The data comparison module is used to query the vehicle passing data at the checkpoint, including license plate type, license plate number, passing time, and checkpoint equipment number. It also compares the noise reporting data with the historical data of illegally modified vehicles to obtain the historical travel patterns of illegally modified vehicles (high-frequency time periods and high-frequency locations).

[0073] The control module is used to carry out control based on the historical travel patterns of illegally modified vehicles.

[0074] The present invention has many specific application paths. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements can be made without departing from the principles of the present invention. These improvements should also be considered as the scope of protection of the present invention.

Claims

1. A noise vehicle control method based on multi-source data, characterized in that: The steps are as follows: 1) Acquisition of reporting data: Obtain traffic nuisance reporting data from relevant reporting platforms; 2) Acquisition of noise reporting data: Analyze the traffic nuisance reporting data through the open source code library to obtain noise reporting data; 3) Noise reporting data preprocessing: natural language processing of the noise reporting data obtained is performed using an open source code library; Obtain the license plate type, license plate number, noise time period and noise location of the noisy vehicle; 4) Acquisition of historical illegal vehicle modification data: Acquisition of historical illegal modification violation data from the violation database, including license plate type and license plate number; 5) Comparing noise reporting data with historical data on illegally modified vehicles: Query the checkpoint vehicle passing data, including license plate type, license plate number, passing time, and checkpoint equipment number. Compare the noise reporting data with historical data on illegally modified vehicles to obtain historical patterns of illegally modified vehicle travel; 6) Deploy surveillance based on the historical patterns of illegally modified vehicles obtained in step 5); The specific steps of step 3) are as follows: 31) Perform natural language processing on the content of each noise reporting data and use the Python third-party library Jieba to segment the sentences; 32) Performing regular expression matching on the word segmentation result array outputted in step 31) through natural language processing to match the corresponding license plate type, license plate number, noise time and noise location; 33) Generate a noise vehicle details table, the fields of which include license plate type, license plate number, noise time, noise location and remarks; The specific steps of step 5) are as follows: 51) According to the noise vehicle details table generated in step 33), extract the noise time period, cluster the noise time period and noise location respectively, and obtain the top five time periods (t1, t2, t3, t4, t5) and the top five noise locations (addr1, addr2, addr3, addr4, addr5) ranked by the number of reports; 52) Based on the five noise locations obtained in step 51), select the checkpoint equipment within 0 to 3 km around each noise location on the map and obtain the equipment number of each checkpoint equipment; 53) Query the track data of all illegally modified vehicles in the past 30 days in the checkpoint vehicle data, with the time limit being the five time periods in step 51), and the checkpoint device limit being the device number of the checkpoint device in step 52); 54) Arrange the query results of step 53) in reverse order according to the number of times the vehicle has passed, and query the checkpoint vehicle passing data for the time and location of the n illegally modified vehicles that have passed in the past 30 days; 55) Aggregating the results of step 54) to obtain the high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) of historical illegally modified vehicles; The specific steps of step 6) are as follows: The high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) in step 55) are entered into the traffic police monitoring system. At the same time, the n vehicles in step 54) are entered as key focus vehicles and personnel are arranged to monitor them.

2. The noise vehicle control method based on multi-source data according to claim 1 is characterized in that: The traffic nuisance reporting data includes: reporting time and reporting content.

3. The noise vehicle control method based on multi-source data according to claim 2 is characterized in that: The specific steps of step 2) are as follows: 21) Use the open source Python code library and the third-party Python word segmentation library Jieba to segment the traffic nuisance report data; 22) Perform keyword filtering on the array outputted from each report content, and filter out data containing keywords including but not limited to noise, modification, and roar; 23) According to the screening results in step 22), screening is performed to obtain noise reporting data.

4. A noise vehicle control system based on multi-source data, characterized in that: include: Reporting data acquisition module, used to obtain traffic nuisance reporting data from relevant reporting platforms; A noise reporting data acquisition module is used to analyze the traffic nuisance reporting data through an open source code library to obtain noise reporting data; A noise reporting data preprocessing module is used to perform natural language processing on the reported content of the noise reporting data obtained through an open source code library; Obtain the license plate type, license plate number, noise time period and noise location of the noisy vehicle; The module for acquiring historical illegally modified vehicle data is used to obtain historical illegal modification violation data from the violation database, including license plate type and license plate number; The data comparison module is used to query the vehicle passing data at the checkpoint, including license plate type, license plate number, passing time, and checkpoint equipment number. It also compares noise reporting data with historical data on illegally modified vehicles to obtain historical patterns of illegally modified vehicle travel. A monitoring module is used to monitor and control the travel patterns of illegally modified vehicles based on historical data. The specific steps for noise reporting data preprocessing are as follows: 31) Perform natural language processing on the content of each noise reporting data and use the Python third-party library Jieba to segment the sentences; 32) Performing regular expression matching on the word segmentation result array outputted in step 31) through natural language processing to match the corresponding license plate type, license plate number, noise time and noise location; 33) Generate a noise vehicle details table, the fields of which include license plate type, license plate number, noise time, noise location and remarks; The specific steps for comparing noise reporting data and historical illegally modified vehicle data are as follows: 51) According to the noise vehicle details table generated in step 33), extract the noise time period, cluster the noise time period and noise location respectively, and obtain the top five time periods (t1, t2, t3, t4, t5) and the top five noise locations (addr1, addr2, addr3, addr4, addr5) ranked by the number of reports; 52) Based on the five noise locations obtained in step 51), select the checkpoint equipment within 0 to 3 km around each noise location on the map and obtain the equipment number of each checkpoint equipment; 53) Query the track data of all illegally modified vehicles in the past 30 days in the checkpoint vehicle data, with the time limit being the five time periods in step 51), and the checkpoint device limit being the device number of the checkpoint device in step 52); 54) Arrange the query results of step 53) in reverse order according to the number of times the vehicle has passed, and query the checkpoint vehicle passing data for the time and location of the n illegally modified vehicles that have passed in the past 30 days; 55) Aggregating the results of step 54) to obtain the high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) of historical illegally modified vehicles; The high-frequency time periods (T1, T2, T3, T4, T5) and high-frequency locations (Addr1, Addr2, Addr3, Addr4, Addr5) in step 55) are entered into the traffic police monitoring system. At the same time, the n vehicles in step 54) are entered as key focus vehicles and personnel are arranged to monitor them.

Images