Map construction method for oil points with abnormal quality based on data analysis of Internet of Vehicles

Abstract

The invention provides a map construction method for oil points with abnormal quality based on vehicle network data analysis, and the method comprises the steps: recognizing a first target vehicle with standard-exceeding emission and catalyst poisoning faults based on vehicle network data; acquiring oil liquid level time sequence data of the first target vehicle, and acquiring a refueling record of the first target vehicle based on the oil liquid level time sequence data of the first target vehicle; clustering the refueling position of the first target vehicle to obtain a clustering result; the clustering result comprises predicted gas station positions, the number of refueling vehicles at each predicted gas station position and the number of refueling times at each predicted gas station position; and based on the position information of the gas stations recorded by the industry and the commerce and the clustering result, the position information of the regular gas stations and the suspected black gas stations with the suspected oil quality problem is identified through a neural network, and the regular gas stations with the suspected oil quality problem are accurately identified.

Description

Technical Field

[0001] The present application relates to the technical field of big data analysis of Internet of Vehicles, and in particular to a method for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis. Background Art

[0002] For commercial vehicles, increasing customer demands and the increasing complexity and diversity of engine software, coupled with diverse user scenarios, have made accurate and timely assessment of diesel fuel quality at gas stations a challenge in emissions control. Consequently, there is an urgent need to accurately identify vehicles with emissions on the road and leverage connected vehicle data through big data models to effectively identify refueling locations with abnormal fuel quality. Summary of the Invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of this application is to propose a method for constructing a map of abnormal quality oil points based on vehicle network data analysis, so as to accurately identify regular gas stations suspected of having oil quality problems.

[0005] The second purpose of this application is to propose a device for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis.

[0006] The third objective of this application is to provide an electronic device.

[0007] The fourth object of this application is to provide a computer-readable storage medium.

[0008] A fifth object of this application is to provide a computer program product.

[0009] To achieve the above objectives, the first embodiment of the present application proposes a method for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis, comprising:

[0010] Acquire vehicle network data, and identify a first target vehicle having excessive emissions and a catalyst poisoning fault based on the vehicle network data;

[0011] Obtaining time series data of the oil level of the first target vehicle, and obtaining a refueling record of the first target vehicle based on the time series data of the oil level of the first target vehicle; wherein the refueling record includes a refueling location and a refueling time;

[0012] Clustering the refueling locations of the first target vehicle to obtain a clustering result; the clustering result includes predicted gas station locations, the number of refueling vehicles at each predicted gas station location, and the number of refueling times at each predicted gas station location;

[0013] Obtaining location information of gas stations registered with the Industrial and Commercial Administration, and based on the location information of the gas stations registered with the Industrial and Commercial Administration and the clustering results, using a neural network to identify the location information of legitimate gas stations suspected of having oil quality problems and suspected illegal gas stations;

[0014] Based on the location information of the regular gas stations and suspected illegal gas stations suspected of having oil quality problems, a map of oil quality abnormality points is constructed.

[0015] To achieve the above objectives, the second embodiment of the present application proposes a device for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis, comprising:

[0016] a data analysis module, configured to obtain vehicle network data and, based on the vehicle network data, identify a first target vehicle having excessive emissions and a catalyst poisoning fault;

[0017] a position acquisition module, configured to acquire the oil level time series data of the first target vehicle, and based on the oil level time series data of the first target vehicle, acquire the refueling position data of the vehicle and the corresponding refueling time;

[0018] a cluster analysis module, configured to cluster the refueling locations of the first target vehicle to obtain clustering results; the clustering results including predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location;

[0019] A site identification module is used to obtain the location information of gas stations registered with the Industrial and Commercial Administration, and based on the location information of gas stations registered with the Industrial and Commercial Administration and the clustering results, identify the location information of legitimate gas stations suspected of having oil quality problems and suspected illegal gas stations through a neural network;

[0020] The map construction module is used to construct a map of oil quality abnormality points based on the location information of the regular gas stations suspected of having oil quality problems and the suspected black gas stations.

[0021] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0022] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0023] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0024] The present application provides a method, device, electronic device and storage medium for constructing a map of oil quality points abnormalities based on vehicle network data analysis. By analyzing vehicle network data, target vehicles with excessive emissions and catalyst poisoning faults are identified, and the oil level data of these target vehicles are obtained from the vehicle network data, and refueling records are identified based on the oil level data. After clustering the refueling records, a deep neural network is used to identify regular gas stations suspected of having oil quality problems and suspected illegal gas stations based on the clustering results and the gas station information registered with the industrial and commercial administration, thereby constructing a map of oil quality points abnormalities. The method of the present invention can determine the quality of oil used by vehicles nationwide, and accurately identify regular gas stations suspected of having oil quality problems based on the oil quality.

[0025] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 A flowchart of a method for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis provided by an embodiment of the present application;

[0028] Figure 2 A block diagram of a device for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis provided by an embodiment of the present application;

[0029] Figure 3 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] The following describes, with reference to the accompanying drawings, a method, device, and apparatus for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis in an embodiment of the present application.

[0032] Figure 1A flowchart of a method for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis provided in an embodiment of the present application.

[0033] It should be noted that the executor of the map construction method of abnormal quality oil points based on vehicle network data analysis in the embodiment of the present application is the map construction device of abnormal quality oil points based on vehicle network data analysis in the embodiment of the present application. The map construction device of abnormal quality oil points based on vehicle network data analysis can be configured in an electronic device so that the electronic device can perform the map construction function of abnormal quality oil points based on vehicle network data analysis.

[0034] like Figure 1 As shown, the method for constructing a map of abnormal oil quality points based on vehicle network data analysis includes the following steps:

[0035] Step 101: Acquire vehicle network data, and identify a first target vehicle having excessive emissions and a catalyst poisoning fault based on the vehicle network data.

[0036] In some embodiments, a reliable IoV data source is selected. These data sources are provided by various automakers' IoV systems. The latest IoV data is obtained from the data source in real time through an API interface. The IoV data is pre-processed, such as removing duplicate, erroneous, or abnormal data to ensure data accuracy and consistency. Requests are periodically sent to the data source to obtain the latest IoV data. For example, polling may be performed once a minute, depending on the data source's update frequency and user needs. If the data source supports push functionality, a push mechanism can be established to receive new data pushed by the data source in real time. This approach reduces polling latency and enables true real-time updates.

[0037] As an implementation method, a method for identifying a first target vehicle with excessive emissions and a catalyst poisoning fault comprises: obtaining an average emission rate of nitrogen oxides within a first preset time period based on the nitrogen oxide emission concentration in vehicle network data using a moving average method; obtaining the emission amount of the vehicle within the first preset time period based on the average emission rate and the first preset time period; obtaining the fuel injection amount based on the vehicle operating condition information in the vehicle network data; determining the authenticity of the emission data in the vehicle network data by determining the proportion of the nitrogen oxide emission concentration in the emission concentration corresponding to the fuel injection amount; after confirming the authenticity of the emission data in the vehicle network data, determining whether the emission amount of the vehicle within the first preset time period exceeds the standard based on the vehicle operation data in the vehicle network data; obtaining fault code information of a second target vehicle with excessive emissions, and identifying the first target vehicle with excessive emissions and a catalyst poisoning fault based on the fault code information.

[0038] This can be understood as using the moving average method to calculate the NOx concentration collected by the Internet of Vehicles, averaging the NOx emission rate over a continuous period of time, and multiplying the average NOx emission rate by the window length to obtain the corresponding NOx emissions within each window. After determining the authenticity of the vehicle data collection based on the operating conditions (the ratio of fuel injection volume to emitted NOx concentration needs to be maintained within the range of 0.8-1.2), it is necessary to calculate the vehicle's operating exceeding standards based on the actual vehicle operating data. Based on the exceeding standards, it is necessary to infer whether the emission data is at a high emission level. Based on the high emission level and engine version, it is determined whether the engine version is within the national filing range. For emission versions that are compliant and have high emissions, the cause of the high emissions needs to be analyzed. For normal oil injection and oil addition behavior, the quality of the oil is determined based on the emission exceeding standards and vehicle fault information. The catalyst poisoning fault code is used to determine whether there is catalyst poisoning. If there is catalyst poisoning, it means that the vehicle's oil has a quality problem of excessive sulfur content.

[0039] For example, for vehicles refueling at regular gas stations, vehicles with high emission data statistics are counted, and invalid emission data and other factors (such as no urea addition, no urea spraying, abnormal urea quality) are eliminated according to the rules. Vehicles whose emission data seriously exceeds the standard (more than 5% of the time) within 15 days is greater than the threshold (500ppm) and there is a catalyst poisoning fault are judged to have an abnormal oil quality problem.

[0040] In some embodiments, before identifying the first target vehicle with excessive emissions and a catalyst poisoning fault, the method includes: connecting a data acquisition device to the vehicle bus through a vehicle diagnostic port; when the vehicle's engine is powered off, simulating the engine's excessive data with the data acquisition device, and checking whether the Internet of Vehicles platform displays data consistent with the excessive data; when the Internet of Vehicles platform displays data consistent with the excessive data, determining that the vehicle's TBOX has not been tampered with, so as to determine the authenticity of the emission data in the vehicle network data.

[0041] During the specific implementation, the inspector will connect the portable data acquisition device to the vehicle bus through the vehicle diagnostic port; when the vehicle's engine is powered off, the data acquisition device will be used to simulate the engine's excessive data, and at the same time, the vehicle network platform will be checked to see whether the data displayed is consistent with the excessive data, that is, the excessive data is transmitted to the vehicle network platform. If there is any inconsistency, it will be judged that the vehicle's TBOX has been tampered with, and the relevant emission data in the vehicle network data is not true, so that the owner can correct the wrong behavior and ensure the authenticity of the vehicle network data.

[0042] Therefore, the embodiment of the present application can be used to verify whether the data obtained by the Internet of Vehicles platform from TBOX is consistent with the real data based on the commercial vehicle engine OBD-related data and data flow information stipulated by the state, and to determine whether there is a problem of software data tampering in the vehicle.

[0043] Step 102: Obtain the oil level time series data of the first target vehicle, and based on the oil level time series data of the first target vehicle, obtain the refueling record of the first target vehicle; wherein the refueling record includes the refueling location and refueling time.

[0044] As an implementation method, a method for obtaining a refueling record of a first target vehicle includes: using a time window of a second preset duration to filter and sample the oil level time series data of the first target vehicle to obtain a peak / trough sequence; screening out a detection window based on the peak / trough sequence and a first preset threshold; obtaining a jump point in the oil level data within the inspection window, and determining that the vehicle has refueled based on the oil level before and after the jump point meeting the second preset threshold; and obtaining the refueling record of the first target vehicle based on the location and time of the refueling behavior.

[0045] For example, the original oil level time series data in the Internet of Vehicles data is filtered and sampled using a 15-minute window to obtain a peak / trough sequence, and the detection window is screened out based on the threshold. The oil level threshold before and after the jump point is used to screen the refueling behavior.

[0046] Step 103 , clustering the refueling locations of the first target vehicle to obtain a clustering result; the clustering result includes the predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location.

[0047] As an implementation method, a method for obtaining clustering results includes: clustering the refueling locations of a first target vehicle to obtain multiple refueling location clusters; calculating the cluster area of ​​each refueling location cluster in the multiple refueling location clusters, and based on the cluster areas of the multiple refueling location clusters, obtaining predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location.

[0048] For example, to cluster refueling locations and calculate cluster areas and the total amount of refueling products, Grid-Search can be used to select the optimal parameters and output the results. The output parameters include: the number of refueling product points, the total amount of refueling products, the cluster area, and the longitude and latitude. The number of refueling product points refers to the location of the gas station and the number of refueling vehicles, and the total amount of refueling products refers to the number of refueling times at each refueling location.

[0049] Step 104: Obtain the location information of the gas stations registered with the industrial and commercial authorities. Based on the location information of the gas stations registered with the industrial and commercial authorities and the clustering results, use a neural network to identify the location information of regular gas stations suspected of having oil quality problems and suspected illegal gas stations.

[0050] It should be noted that by directly matching the refueling locations in the clustering results with the refueling locations in the gas station information registered with the Industrial and Commercial Bureau, it is possible to identify suspected black gas stations and regular gas stations suspected of having oil quality problems.

[0051] Although direct location matching can be used to identify regular gas stations with oil quality problems and suspected illegal gas stations, this identification result is based on the single-vehicle level and has the problem of poor accuracy. Therefore, this embodiment uses deep learning of a deep neural network to identify regular gas stations with oil quality problems and suspected illegal gas stations, and can identify target gas stations with the highest oil quality problems. The identification method using a deep neural network is described in detail below.

[0052] As an implementation method, a method for identifying the location information of legitimate gas stations suspected of having oil quality problems and suspected illegal gas stations includes:

[0053] The first target vehicle's fuel level time series data, refueling time, predicted gas station location, and gas station location information registered with the Industrial and Commercial Administration are input into the trained first deep neural network to obtain a first recognition result. The first recognition result includes refueling popularity, location information of suspected illegal gas stations, popularity of legitimate gas stations suspected of having fuel quality issues, and the first target vehicle's single refueling record. Refueling popularity refers to the number of refueling vehicles at a gas station, which is formed after the number of refueling vehicles is clustered.

[0054] Based on the popularity of regular gas stations suspected of having fuel quality issues, the regular gas stations suspected of having fuel quality issues are identified; and the business status information of the regular gas stations suspected of having fuel quality issues is obtained, including business hours and the number of refueling vehicles;

[0055] The single-vehicle refueling record, catalyst poisoning fault code, nitrogen oxide emissions and business status information of regular gas stations suspected of having oil quality problems of the first target vehicle are input into the trained second deep neural network to obtain regular gas stations suspected of having oil quality problems.

[0056] The output of the second deep neural network is the output of the first deep neural network model, the business status information, and the gas station information on the map.

[0057] This step uses deep neural networks to more accurately identify regular gas stations suspected of having oil quality problems and suspected black gas stations.

[0058] The deep learning model of this embodiment can select convolutional neural network CNN, recurrent neural network RNN, etc. without limitation.

[0059] Two deep neural networks are trained using historical Internet of Vehicles data, and the model parameters and structure are adjusted to improve the accuracy of model recognition.

[0060] Step 105 : constructing a map of oil quality abnormality points based on the location information of regular gas stations suspected of having oil quality problems and suspected illegal gas stations.

[0061] After identifying regular gas stations suspected of having oil quality problems and suspected black gas stations, they are visualized in the form of maps or charts to help users intuitively understand the oil quality situation.

[0062] In the embodiment of the present application, a method for constructing a map of oil quality points abnormalities based on vehicle network data analysis analyzes vehicle network data to identify target vehicles with excessive emissions and catalyst poisoning faults, then obtains the oil level data of these target vehicles from the vehicle network data, and identifies refueling records based on the oil level data; after clustering the refueling records, a deep neural network is used to identify regular gas stations suspected of having oil quality problems and suspected illegal gas stations based on the clustering results and the gas station information registered with the industrial and commercial administration, thereby constructing a map of oil quality points abnormalities; the method of the present invention can determine the quality of oil used by vehicles nationwide, and accurately identify regular gas stations suspected of having oil quality problems based on the oil quality, and can also identify suspected illegal gas stations.

[0063] In order to implement the above embodiment, the present application also proposes a map construction device for abnormal quality oil points based on Internet of Vehicles data analysis. Figure 2 This is a schematic diagram of a device for mapping abnormal oil quality points based on vehicle network data analysis provided in an embodiment of the present application. Figure 2 As shown, the map construction device for abnormal quality oil points based on Internet of Vehicles data analysis may include: a data analysis module 201, a location acquisition module 202, a cluster analysis module 203, a site identification module 204 and a map construction module 205.

[0064] The data analysis module 201 is used to obtain vehicle network data and identify a first target vehicle that has excessive emissions and a catalyst poisoning fault based on the vehicle network data;

[0065] The position acquisition module 202 is used to obtain the oil level time series data of the first target vehicle, and based on the oil level time series data of the first target vehicle, obtain the vehicle's refueling position data and the corresponding refueling time;

[0066] Cluster analysis module 203 is used to cluster the refueling locations of the first target vehicle to obtain clustering results; the clustering results include predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location;

[0067] The site identification module 204 is used to obtain the location information of gas stations registered with the Industrial and Commercial Administration Bureau. Based on the location information of gas stations registered with the Industrial and Commercial Administration Bureau and the clustering results, the module uses a neural network to identify the location information of legitimate gas stations suspected of having fuel quality problems and suspected illegal gas stations.

[0068] The map construction module 205 is used to construct a map of oil quality abnormality points based on the location information of regular gas stations suspected of having oil quality problems and suspected illegal gas stations.

[0069] In some implementations, the data analysis module 201 is specifically configured to:

[0070] Based on the nitrogen oxide emission concentration in the vehicle network data, the moving average method is used to obtain the average emission rate of nitrogen oxides within the first preset time period;

[0071] Obtaining an emission amount of the vehicle within the first preset time period based on the average emission rate and the first preset time period;

[0072] Obtain fuel injection quantity based on vehicle operating condition information in the Internet of Vehicles data;

[0073] Determine the proportion of nitrogen oxide emission concentration in the emission concentration corresponding to the fuel injection amount, and judge the authenticity of emission data in the Internet of Vehicles data;

[0074] After confirming the authenticity of the emission data in the Internet of Vehicles data, determining whether the vehicle's emissions within a first preset time period exceed the standard based on the vehicle operation data in the Internet of Vehicles data;

[0075] Obtain fault code information of a second target vehicle having an excessive emission problem, and identify a first target vehicle having excessive emission and a catalyst poisoning fault based on the fault code information.

[0076] In some implementations, the location acquisition module 202 is specifically configured to:

[0077] Using a time window of a second preset length, filtering and sampling the oil level time series data of the first target vehicle to obtain a peak / trough sequence;

[0078] Filtering a detection window based on the peak / trough sequence and a first preset threshold;

[0079] Obtaining a jump point in the oil level data within the inspection window, and determining that the vehicle has been refueled based on the oil level before and after the jump point meeting a second preset threshold;

[0080] Based on the location and time at which the refueling behavior occurs, the refueling record of the first target vehicle is obtained.

[0081] In some implementations, the cluster analysis module 203 is specifically configured to:

[0082] Clustering the refueling locations of the first target vehicle to obtain multiple refueling location clusters;

[0083] The cluster area of ​​each refueling location cluster in the multiple refueling location clusters is calculated, and based on the cluster areas of the multiple refueling location clusters, the predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location are obtained.

[0084] In some implementations, the site identification module 204 is specifically configured to:

[0085] The first target vehicle's oil level time series data, refueling time, predicted gas station location, and gas station location information registered with the Industrial and Commercial Administration are input into the trained first deep neural network to obtain a first recognition result. The first recognition result includes refueling popularity, location information of suspected illegal gas stations, popularity of legitimate gas stations suspected of having oil quality problems, and the first target vehicle's individual refueling records.

[0086] Based on the popularity of regular gas stations suspected of having fuel quality issues, the regular gas stations suspected of having fuel quality issues are identified; and the business status information of the regular gas stations suspected of having fuel quality issues is obtained, including business hours and the number of refueling vehicles;

[0087] The single-vehicle refueling record, catalyst poisoning fault code, nitrogen oxide emissions and business status information of regular gas stations suspected of having oil quality problems of the first target vehicle are input into the trained second deep neural network to obtain regular gas stations suspected of having oil quality problems.

[0088] In some implementations, the apparatus further includes a data verification module 206 configured to:

[0089] Connect the data acquisition device to the vehicle bus through the vehicle diagnostic port;

[0090] When the vehicle's engine is powered off, use data acquisition equipment to simulate the engine's exceeding-standard data, and check whether the connected vehicle platform displays data consistent with the exceeding-standard data;

[0091] When the Internet of Vehicles platform displays data that is consistent with the exceeded data, it is determined that there is no tampering with the vehicle's TBOX to confirm the authenticity of the emission data in the vehicle network data.

[0092] It should be noted that the above explanation of the embodiment of the method for constructing a map of abnormal quality oil points based on vehicle network data analysis is also applicable to the device for constructing a map of abnormal quality oil points based on vehicle network data analysis in this embodiment, and will not be repeated here.

[0093] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 3 , Figure 3 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 3 As shown, the electronic device 300 includes: a processor 301, and a memory 302 communicatively connected to the processor 301; the memory 302 stores computer-executable instructions; the processor 301 executes the computer-executable instructions stored in the memory to implement the method provided by the aforementioned embodiment.

[0094] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0095] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0096] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0097] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0098] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0099] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0100] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0101] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis, characterized in that: The following steps are involved: Acquire vehicle network data, and identify a first target vehicle having excessive emissions and a catalyst poisoning fault based on the vehicle network data; Obtaining time series data of the oil level of the first target vehicle, and obtaining a refueling record of the first target vehicle based on the time series data of the oil level of the first target vehicle; wherein the refueling record includes a refueling location and a refueling time; Clustering the refueling locations of the first target vehicle to obtain a clustering result; the clustering result includes predicted gas station locations, the number of refueling vehicles at each predicted gas station location, and the number of refueling times at each predicted gas station location; Obtaining location information of gas stations registered with the Industrial and Commercial Administration, and based on the location information of the gas stations registered with the Industrial and Commercial Administration and the clustering results, using a neural network to identify the location information of legitimate gas stations suspected of having oil quality problems and suspected illegal gas stations; Based on the location information of the regular gas stations suspected of having oil quality problems and the suspected illegal gas stations, a map of oil quality abnormality points is constructed.

2. The method according to claim 1, characterized in that The step of identifying a first target vehicle having excessive emissions and a catalyst poisoning fault based on the vehicle network data includes: Based on the nitrogen oxide emission concentration in the vehicle network data, an average emission rate of nitrogen oxides within a first preset time period is obtained using a moving average method; Obtaining an emission amount of the vehicle within the first preset time period based on the average emission rate and the first preset time period; Obtaining a fuel injection amount based on vehicle operating condition information in the Internet of Vehicles data; Determining the proportion of the nitrogen oxide emission concentration in the emission concentration corresponding to the fuel injection amount, and determining the authenticity of the emission data in the vehicle networking data; After confirming the authenticity of the emission data in the Internet of Vehicles data, determining whether the vehicle's emissions within a first preset time period exceed the standard based on the vehicle operation data in the Internet of Vehicles data; Fault code information of a second target vehicle having an excessive emission problem is obtained, and based on the fault code information, a first target vehicle having excessive emission and a catalyst poisoning fault is identified.

3. The method according to claim 1, characterized in that The step of obtaining the refueling record of the first target vehicle based on the oil level time series data of the first target vehicle includes: Using a time window of a second preset length, filtering and sampling the oil level time series data of the first target vehicle to obtain a peak / trough sequence; Filtering a detection window based on the peak / trough sequence and a first preset threshold; Obtaining a jump point in the oil level data within the inspection window, and determining that the vehicle has refueled based on the oil level before and after the jump point meeting a second preset threshold; Based on the location and time at which the refueling behavior occurs, a refueling record of the first target vehicle is obtained.

4. The method according to claim 1, wherein Clustering the refueling positions of the first target vehicles to obtain a clustering result includes: Clustering the refueling locations of the first target vehicle to obtain a plurality of refueling location clusters; The cluster area of ​​each refueling location cluster in the multiple refueling location clusters is calculated, and based on the cluster areas of the multiple refueling location clusters, the predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location are obtained.

5. The method according to claim 1, wherein Based on the gas station location information registered with the industrial and commercial authorities and the clustering results, the location information of regular gas stations suspected of having oil quality problems and suspected illegal gas stations are identified through a neural network; including: Inputting the first target vehicle's oil level time series data, refueling time, predicted gas station location, and the gas station location information registered with the Industrial and Commercial Administration into a trained first deep neural network to obtain a first recognition result, the first recognition result including refueling popularity, location information of suspected illegal gas stations, popularity of legitimate gas stations suspected of having oil quality issues, and the first target vehicle's individual refueling record; Based on the popularity of the regular gas station suspected of having oil quality problems, determine the regular gas station suspected of having oil quality problems; and obtain business status information of the regular gas station suspected of having oil quality problems, the business status including business hours and number of refueling vehicles; The single-vehicle refueling record, catalyst poisoning fault code, nitrogen oxide emissions and business status information of regular gas stations suspected of having oil quality problems of the first target vehicle are input into the trained second deep neural network to obtain regular gas stations suspected of having oil quality problems.

6. The method according to claim 1, characterized in that Before identifying the first target vehicle having excessive emissions and a catalyst poisoning fault based on the vehicle network data, the method includes: Connect the data acquisition device to the vehicle bus through the vehicle diagnostic port; When the vehicle's engine is powered off, using the data acquisition device to simulate engine excess data, and checking whether the vehicle networking platform displays data consistent with the excess data; When the Internet of Vehicles platform displays data consistent with the exceeded data, it is determined that there is no tampering with the vehicle's TBOX to determine the authenticity of the emission data in the vehicle network data.

7. A device for constructing a map of abnormal oil quality points based on Internet of Vehicles data analysis, characterized in that: include: a data analysis module, configured to obtain vehicle network data and, based on the vehicle network data, identify a first target vehicle having excessive emissions and a catalyst poisoning fault; a position acquisition module, configured to acquire the oil level time series data of the first target vehicle, and based on the oil level time series data of the first target vehicle, acquire the refueling position data of the vehicle and the corresponding refueling time; a cluster analysis module, configured to cluster the refueling locations of the first target vehicle to obtain clustering results; the clustering results including predicted refueling station locations, the number of refueling vehicles at each predicted refueling station location, and the number of refueling times at each predicted refueling station location; A site identification module is used to obtain the location information of gas stations registered with the Industrial and Commercial Administration, and based on the location information of gas stations registered with the Industrial and Commercial Administration and the clustering results, identify the location information of legitimate gas stations suspected of having oil quality problems and suspected illegal gas stations through a neural network; The map construction module is used to construct a map of oil quality abnormality points based on the location information of the regular gas stations suspected of having oil quality problems and the suspected black gas stations.

8. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images