Big data-based highway vehicle profile generation method and apparatus, and medium

Abstract

The present invention belongs to the technical field of big data processing, and relates to a big data-based highway vehicle profile generation method and apparatus, and a medium. The method comprises: preprocessing structured data in high-speed traffic data of a vehicle, to obtain preprocessed target data, the high-speed traffic data comprising transaction data, gantry license plate identification data, and vehicle model identification data; on the basis of the target data, extracting a target feature of the vehicle, target features comprising a shape feature, a traveling feature, a driving feature, a consumption feature, and a fee evasion feature; on the basis of the target feature, constructing a profile model of the vehicle by means of HiveSql; and on the basis of the profile model, generating a vehicle profile. The big data-based highway vehicle profile generation method provided by the present invention constructs a profile model of a vehicle by using an extracted target feature by means of HiveSql, and the constructed profile model can quickly and accurately generate a vehicle profile.

Description

Methods, devices, and media for generating highway vehicle profiles based on big data Technical Field

[0001] This invention relates to the field of big data processing technology, and in particular to a method, apparatus and medium for generating highway vehicle profiles based on big data. Background Technology

[0002] With the development of intelligent transportation systems, vehicle management has become a crucial part of traffic management, making the accurate acquisition and analysis of vehicle information particularly important. In highway toll collection scenarios, vehicle type identification is fundamental to the entire operation. As many regions begin constructing unmanned, standardized new toll collection systems, accurately and quickly identifying vehicle types is essential for achieving precise toll calculation in unmanned toll collection models.

[0003] Traditional vehicle recognition methods mainly rely on the analysis of static images or video streams. However, in practical applications, problems such as the huge amount of data, the high requirements for real-time data, and the great influence of environmental factors make it difficult to accurately and quickly create vehicle profiles. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, device and medium for generating highway vehicle profiles based on big data, so as to solve the problems of low accuracy and efficiency of existing vehicle profile creation methods.

[0005] To address the aforementioned problems, this invention provides a method for generating highway vehicle profiles based on big data, comprising:

[0006] The structured data in the vehicle's highway traffic data is preprocessed to obtain the preprocessed target data; the highway traffic data includes transaction data, gantry license plate data, and vehicle type identification data.

[0007] Based on the target data, target features of the vehicle are extracted; the target features include appearance features, driving features, driving characteristics, consumption features, and toll evasion features.

[0008] Based on the target features, a vehicle profile model is constructed using HiveSql;

[0009] Based on the portrait model, a vehicle portrait is generated.

[0010] In one possible implementation, extracting the target features of the vehicle based on the target data includes:

[0011] Data analysis is performed on the target data to obtain the target features;

[0012] The data analysis includes at least one of the following:

[0013] Cluster analysis, association rule mining, time series analysis, behavioral data analysis, and vehicle status analysis.

[0014] In one possible implementation, constructing a vehicle profile model using HiveSql based on the target features includes:

[0015] Based on the target features, generate vehicle tags;

[0016] Based on the vehicle tags, the profile model is constructed using HiveSql.

[0017] In one possible implementation, after generating the vehicle profile based on the profile model, the method further includes:

[0018] The vehicle profile is visualized using charts or images.

[0019] In one possible implementation, the preprocessing includes at least one of the following:

[0020] The process includes parsing, deduplication, descrambling, cleaning, filtering, classification, transformation, and summarization. In one possible implementation, before preprocessing the structured data in the high-speed vehicle traffic data to obtain the preprocessed target data, the process further includes:

[0021] The high-speed traffic data is divided into structured data and unstructured data;

[0022] The structured data is stored in the big data platform;

[0023] The unstructured data is stored in an FTP server. This invention also provides a highway vehicle profile generation device based on big data, comprising:

[0024] The processing module is used to preprocess the structured data in the vehicle's highway traffic data to obtain the preprocessed target data; the highway traffic data includes transaction data, gantry license plate data, and vehicle type identification data.

[0025] The extraction module is used to extract target features of the vehicle based on the target data; the target features include appearance features, driving features, driving characteristics, consumption features, and toll evasion features;

[0026] A construction module is used to build a vehicle profile model using HiveSql based on the target features;

[0027] The generation module is used to generate vehicle portraits based on the portrait model.

[0028] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0029] The memory is used to store programs;

[0030] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the highway vehicle profile generation method based on big data as described in any of the above implementations.

[0031] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the highway vehicle profile generation method based on big data as described in any of the above implementations.

[0032] On the other hand, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the highway vehicle profile generation method based on big data as described in any of the above implementations.

[0033] The beneficial effects of this invention are as follows: The method, apparatus, and medium for generating highway vehicle profiles based on big data provided by this invention preprocess the structured data in the acquired highway vehicle traffic data to ensure the accuracy and efficiency of subsequent analysis. Based on the preprocessed target data, target features of the vehicle are extracted. These target features may include appearance features, driving features, driving characteristics, consumption features, and toll evasion features. The extracted target features are then used to construct a vehicle profile model using HiveSql. The constructed profile model can quickly and accurately generate vehicle profiles, which can be used for traffic flow analysis, safety monitoring, toll management, etc. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 is one of the flowcharts of an embodiment of the highway vehicle profile generation method based on big data provided by the present invention;

[0036] Figure 2 is a schematic diagram of the labeling system provided by the present invention;

[0037] Figure 3 is a second flowchart of an embodiment of the highway vehicle profile generation method based on big data provided by the present invention;

[0038] Figure 4 is an architecture diagram of the highway vehicle profile generation method based on big data provided by the present invention;

[0039] Figure 5 is the third flowchart of the highway vehicle profile generation method based on big data provided by the present invention;

[0040] Figure 6 is a schematic diagram of an embodiment of the highway vehicle profile generation device based on big data provided by the present invention;

[0041] Figure 7 is a schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0043] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0044] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0045] Figure 1 is a flowchart of an embodiment of the highway vehicle profile generation method based on big data provided by the present invention. As shown in Figure 1, the highway vehicle profile generation method based on big data includes:

[0046] S101. Preprocess the structured data in the vehicle's high-speed traffic data to obtain preprocessed target data; the high-speed traffic data includes transaction data, gantry license plate data, and vehicle type identification data;

[0047] S102. Based on the target data, extract the target features of the vehicle; the target features include shape features, driving features, driving characteristics, consumption features, and toll evasion features;

[0048] S103. Based on the target features, construct a vehicle profile model using HiveSql;

[0049] S104. Generate a vehicle profile based on the profile model.

[0050] It should be noted that vehicle highway passage data can be obtained through integration with gantry equipment and toll station equipment services. This highway passage data can include transaction data, gantry license plate data, and vehicle type identification data. HiveSQL is a language used to execute SQL queries within Apache Hive. Hive is a data warehouse system used to process large-scale structured data. HiveSQL allows users to manipulate and analyze data stored in the Hadoop file system using SQL query language, primarily for data querying and processing in big data environments.

[0051] Compared with existing technologies, the highway vehicle profile generation method based on big data provided in this invention preprocesses the structured data in the acquired highway vehicle traffic data to ensure the accuracy and efficiency of subsequent analysis. Based on the preprocessed target data, target features of the vehicle are extracted. These target features may include appearance features, driving features, driving characteristics, consumption features, and toll evasion features. The extracted target features are then used to construct a vehicle profile model using HiveSql. This constructed profile model can quickly and accurately generate vehicle profiles, which can be used for traffic flow analysis, safety monitoring, toll management, and other purposes.

[0052] In some embodiments of the present invention, the preprocessing includes at least one of the following:

[0053] The data processing steps include parsing, deduplication, cleansing, filtering, classification, transformation, and summarization. Parsing converts raw data (which may be in unstructured or semi-structured formats such as XML and JSON) into structured data for easier subsequent processing. Deduplication removes duplicate records, ensuring the uniqueness of each data point and preventing analytical bias. Cleansing removes errors or meaningless information from the data, such as incorrect character input or invalid data values. Cleansing involves more detailed data organization, including correcting inconsistent data, handling missing values, and removing outliers. Filtering selects relevant fields or records from the dataset based on analytical needs, excluding irrelevant data. Classification groups data according to certain criteria or features, providing an organized dataset for model training or analysis. Necessary format transformations are performed to make the data suitable for specific analytical methods or tools, such as standardization and normalization. Statistical summarization reduces the size of the dataset and extracts key information.

[0054] The highway vehicle profile generation method based on big data provided in this invention can effectively improve the quality and reliability of data analysis by preprocessing the data.

[0055] In some embodiments of the present invention, before preprocessing the structured data in the high-speed traffic data of vehicles to obtain the preprocessed target data, the method further includes:

[0056] The high-speed traffic data is divided into structured data and unstructured data;

[0057] The structured data is stored in the big data platform;

[0058] The unstructured data is stored on an FTP server. Structured data refers to data with a clear format that can be directly used for analysis, such as tabular data. Unstructured data includes images, text, videos, etc., which require special processing before they can be used for analysis.

[0059] Structured data is stored in a big data platform. This platform provides easy access and analysis of structured data, making subsequent data processing and analysis more efficient.

[0060] Unstructured data is stored on an FTP server. An FTP server provides a centralized storage location for unstructured data, facilitating data management and transfer.

[0061] In some embodiments of the present invention, extracting target features of the vehicle based on the target data includes:

[0062] Data analysis is performed on the target data to obtain the target features;

[0063] The data analysis includes at least one of the following:

[0064] Cluster analysis, association rule mining, time series analysis, behavioral data analysis, and vehicle status analysis.

[0065] By analyzing the target data, the target characteristics of the vehicle can be obtained. These characteristics can include: appearance characteristics (e.g., basic vehicle information, vehicle exterior features, license plate features, vehicle brand features, vehicle accessories, driver characteristics, etc.), driving characteristics (e.g., vehicle trajectory, speed, driving habits, driving calendar, high-frequency routes, frequency of passage, etc.), driving characteristics (e.g., driver behavior, recent driving status, and risk factor, including information on the number of passages for speeding, overloading, and fatigued driving), consumption characteristics (e.g., whether the vehicle made purchases at service areas, gas stations, or paid tolls during highway driving), and toll evasion characteristics (whether the vehicle engaged in toll evasion after highway driving, whether suspicious work orders were generated, and the type of toll evasion).

[0066] Cluster analysis is used to group data points based on similarity. In vehicle data analysis, cluster analysis can help identify common driving patterns or vehicle usage characteristics, such as features or behaviors that often appear together, thereby helping to segment different vehicle types or behavior groups.

[0067] Association rule mining is used to discover the relationships between variables in a dataset. In vehicle data, association rules can reveal the relationship between specific vehicle features and other features, such as the relationship between a certain vehicle model and a specific toll payment pattern or toll evasion behavior.

[0068] Time series analysis is used to analyze data points that change over time. It is very effective in understanding vehicle behavior patterns within a specific time period, such as traffic trends during peak hours and the impact of seasonal changes on traffic flow.

[0069] Behavioral data analysis primarily focuses on vehicle driving behavior, including speed, acceleration, and driving route. It can help identify abnormal driving behaviors, provide a basis for traffic safety monitoring, and improve traffic flow management.

[0070] Vehicle condition analysis focuses on the vehicle's physical condition and performance. By combining vehicle profile data, such as brand, model, mileage, frequent travel routes, road conditions, maintenance records, and the owner's travel habits and driving behavior, it helps identify potential safety hazards. These include brake system wear caused by frequent rapid acceleration and braking, or tire aging that may result from prolonged driving in harsh road conditions. This provides a basis for vehicle maintenance and repair. Once these potential risks are identified, measures can be taken quickly to repair or replace parts, thereby ensuring the long-term stability and safe operation of the vehicle.

[0071] The highway vehicle profile generation method based on big data provided in this invention analyzes the target data using the above-mentioned analysis method to obtain target features, and can extract rich vehicle feature information from the target data, thereby constructing an accurate vehicle profile model.

[0072] In some embodiments of the present invention, constructing a vehicle profile model using HiveSql based on the target features includes:

[0073] Based on the target features, generate vehicle tags;

[0074] Based on the vehicle tags, the profile model is constructed using HiveSql.

[0075] Based on the vehicle target features extracted from data analysis, specific vehicle tags are first generated. These tags are typically defined based on qualitative or quantitative information such as vehicle behavior, characteristics, or habits, such as "high-speed driver," "nighttime driver," and "high-spending user." Figure 2 shows a schematic diagram of the tagging system provided by this invention.

[0076] After vehicle tags are generated, HiveSQL can be used to build a profile model by writing query scripts. The profile model comprehensively considers various vehicle tags and features, and classifies or groups vehicles through logic and algorithms (such as classification algorithms, association rules, etc.).

[0077] The advantage of using HiveSql to build profiling models lies in its ability to handle large amounts of data, making it suitable for highway management systems that require analysis of large-scale vehicle datasets. Furthermore, this query language supports SQL syntax, allowing data analysts to easily write complex queries for data mining and analysis, thereby effectively building profiling models that reflect vehicle characteristics and behavioral patterns.

[0078] The highway vehicle profile generation method based on big data provided in this invention constructs a vehicle profile model using HiveSql and summarizes the generated vehicle type identification data, gantry transaction data, toll station transaction data, and historical transaction data into indicators, including basic data, driving trajectory, driving behavior, consumption value, toll evasion behavior, and other multi-dimensional information, to form a comprehensive description of the vehicle.

[0079] In some embodiments of the present invention, after generating the vehicle portrait based on the portrait model, the method further includes:

[0080] The vehicle profile is visualized using charts or images.

[0081] The generated vehicle profiles are presented in the form of charts or images through visualization technology, and can be applied to real-world scenarios such as basic management systems, visualization dashboards, gantry audit systems, group monitoring dashboards, cloud verification of license plates and vehicle models, and precise marketing to members based on vehicle profiles.

[0082] This invention explores and establishes a vehicle-to-vehicle electronic profiling system. Utilizing data collected from various highway systems, externally accessed data, and business review data, it leverages big data technology to fully mine various data resources related to vehicles on highways. This allows for detailed qualitative descriptions of driving preferences, route selection, travel time patterns, and safety risks during highway travel, providing data support for highway operation management and traffic control, and offering precise services to vehicles. Furthermore, the invention analyzes individual and group vehicles using electronic profiling, analyzing changes in vehicle type and traffic characteristics, identifying key service vehicles, and providing safety management guidance for passenger vehicles, hazardous materials transport vehicles, and cold chain transport vehicles. By analyzing the OD (Origin-Destination) traffic hotspot distribution of vehicle group profiling, it provides assessment data on route revenue contribution. This contributes to improving traffic management efficiency and enhancing safety.

[0083] This invention proposes a big data-based algorithm for creating and analyzing highway vehicle profiles. Centered on business operations, it utilizes multi-source heterogeneous data, including ETC gantry transaction data, toll station entrance and exit transaction logs, gantry vehicle type recognition data, Hubei Province green channel inspection data, and BeiDou passenger, hazardous materials, and heavy-duty vehicle data. Based on vehicle traffic behavior habits, it labels vehicle characteristics to form a multi-dimensional evaluation for each vehicle (including basic vehicle information, driving status, toll evasion analysis, traffic behavior habits, and vehicle value analysis). Furthermore, it fully leverages the vehicle profile system to establish a vehicle archive database, forming multi-dimensional tag libraries, thematic libraries, and group profiles, creating a digital vehicle profile service to support business applications.

[0084] Figure 3 is a second flowchart of an embodiment of the highway vehicle profile generation method based on big data provided by the present invention. As shown in Figure 3, the highway vehicle profile generation method based on big data includes:

[0085] S301, collect transaction data, gantry license plate recognition data, and vehicle model recognition data.

[0086] To ensure the scale and diversity of the dataset, the raw data was primarily collected from road sections under the jurisdiction of Hubei Transportation Investment Group. The dataset was integrated with gantry and toll station equipment services to collect vehicle model recognition data, transaction data, and various other basic data.

[0087] After the data collection is completed, the raw structured data is stored in the raw data layer (ods) of the big data platform, and the unstructured data is stored in the FTP server.

[0088] S302. Preprocess the raw data.

[0089] After acquiring the raw data layer (ODS), data warehouse and HiveSQL computation methods are used to process the raw structured data. This includes removing duplicate data, handling missing values, data format conversion, and data standardization. The processed data is then stored in the detailed data layer (DWD). To prepare for establishing a vehicle profile tagging system dataset, the dataset to be analyzed includes basic vehicle data analysis, vehicle driving trajectory analysis, vehicle driving behavior analysis, vehicle consumption value analysis, and vehicle toll evasion behavior analysis.

[0090] S303. Analyze and summarize the detailed data.

[0091] Preprocessed data from the detailed data layer (DWD) is acquired and then deeply mined and analyzed. Through methods such as cluster analysis, association rule mining, time series analysis, behavioral data analysis, and vehicle status analysis, vehicle driving characteristics, behavioral models, and correlations with other factors can be discovered. Based on the data analysis, a data summary is established to form vehicle profiles. The analysis results are summarized and organized according to different dimensions, such as classification by vehicle type, vehicle category, and driving region, and the data is stored in the data application layer (ADS).

[0092] S304. Apply the summarized data in practice.

[0093] The system acquires data from the data application layer (ads), synchronizes the data to databases such as Clickhouse and MySQL, and uses visualization technology to present the analyzed and summarized results in the form of charts, images, etc., for application in real-world scenarios such as basic management systems, visualization dashboards, gantry audit systems, group monitoring dashboards, cloud verification of license plates and vehicle models, and precise marketing to members based on vehicle profiles.

[0094] For example, Figure 4 is an architecture diagram of the highway vehicle profile generation method based on big data provided by the present invention, and Figure 5 is a flowchart of the third step of the highway vehicle profile generation method based on big data provided by the present invention. As shown in Figures 4 and 5, the highway vehicle profile generation method based on big data includes the following steps:

[0095] (1) By integrating with gantry equipment and toll station equipment, collect vehicle identification data, gantry transaction data, toll station transaction data and various basic data.

[0096] (2) Data transmission is essentially a continuous and uninterrupted data relay process. On the one hand, it receives data from data collection and reporting through interfaces and SFTP services. On the other hand, it forwards and aggregates this data to the aggregation server by calling the aggregation interface and SFTP service. The aggregation server then aggregates data from different edge intelligent terminals again through both interfaces and SFTP services, and caches it in the Clickhouse database and local directory. At the same time, it pushes the data to the Kafka message queue of the big data platform and the FTP server.

[0097] (3) Upon receiving data from the Kafka message queue, the data is divided into structured and unstructured data. Structured data (vehicle identification data (including summaries)) is stored in HDFS, ES, and HBase through the consumer program, while other data is written to MySQL and Clickhouse. Unstructured data (vehicle image data) is aggregated to the FTP server.

[0098] (4) Clean and process the various types of data written to the HDFS detailed data layer, including removing duplicate data, handling missing values, data format conversion, and cleaning, to ensure the quality and availability of the data, and store the processed data to the detailed data layer.

[0099] (5) Conduct in-depth analysis of vehicle data using data analysis and mining techniques, including:

[0100] Vehicle basic data analysis: Analyze information such as common vehicle models, common vehicle types, cumulative number of passages, cumulative mileage, cumulative toll fees, special vehicle markings, and transit vehicle markings to understand the basic information of the vehicles.

[0101] Vehicle Feature Analysis: Based on the image structured data provided by the image search engine, a vehicle feature database is established according to vehicle basic information, vehicle appearance feature information, license plate feature information, vehicle brand feature information, vehicle accessory feature information, vehicle driver feature information, and vehicle brand information.

[0102] Vehicle driving trajectory analysis: Analyze information such as vehicle driving trajectory, driving speed, behavior habits, driving calendar, high-frequency routes, and traffic frequency to understand the vehicle's operating status.

[0103] Vehicle driving behavior analysis: This analyzes the driver's driving behavior, recent driving status, and risk factor, and assesses driving safety by using information such as the number of times the driver has driven while speeding, overloading, or fatigued.

[0104] Vehicle consumption value analysis: This involves analyzing whether there are service area or gas station purchases during high-speed driving, plus toll fees, to assess the driver's consumption value concept.

[0105] Vehicle toll evasion analysis: This involves analyzing whether a vehicle evades tolls after traveling on the highway, whether any suspicious work orders are generated, and what types of toll evasion are involved, in order to understand the vehicle's credit value.

[0106] (6) Based on the results of the above data analysis, a vehicle profile model is constructed using HiveSql, and the generated vehicle identification data, gantry transaction data, toll station transaction data and historical transaction data are summarized into indicators, including basic data, driving trajectory, driving behavior, consumption value, toll evasion behavior and other multi-dimensional information, to form a comprehensive description of the vehicle.

[0107] (7) Store the model results data in the data application layer and push it to MySQL and Clickhouse. Apply the vehicle profile model to real-world scenarios such as basic management systems, visualization screens, gantry audit systems, group monitoring screens, license plate and vehicle model cloud verification, and precise member marketing based on vehicle profiles.

[0108] The highway vehicle profile generation method based on big data provided by this invention has the following beneficial effects:

[0109] (1) Improve the speed and efficiency of vehicle profile creation. Through big data processing and machine learning technology, the vehicle information can be quickly and accurately acquired and analyzed, thereby improving the speed and efficiency of vehicle profile creation.

[0110] (2) Accurately represent vehicle features. By extracting vehicle features and performing correlation analysis, the generated vehicle profile can accurately represent vehicle features and provide precise data support for related fields.

[0111] (3) Provides multi-field application support. Vehicle profiles can be applied to multiple fields such as operation management, ETC issuance, toll inspection, and membership marketing. They can establish basic models and provide data support for personalized travel services, roadside value-added business development, and the operation of expressway digital assets.

[0112] The main application scenarios are as follows:

[0113] (1) Vehicle model and license plate cloud verification. The vehicle profiling system is used to perform cloud verification of vehicle models and license plates for import and export vehicles. Based on big data, a second verification is performed to provide highly reliable vehicle model and license plate data.

[0114] (2) Vehicle driving behavior analysis. Based on the vehicle profile results, the vehicle driving behavior is identified and analyzed to identify or predict whether the vehicle will engage in abnormal driving behaviors such as speeding (three sudden speeds and one slow speed), prolonged low-speed driving, fatigued driving, continuous lane changes, driving outside the designated lane, and prolonged occupation of the emergency lane.

[0115] (3) Assist in toll collection audit. By sharing resources and exchanging information, assist in toll collection audit and reduce toll revenue losses.

[0116] (4) Service area traffic generation. Based on vehicle profiles, the positioning and target customers of service areas are matched with specific marketing strategies for service areas to generate revenue through data-driven operations.

[0117] (5) Near-field monitoring. Using vehicle profiling systems, vehicle credit scores, and other information, early warnings are issued for vehicles entering toll stations and provincial border gantries to detect issues such as vehicle size discrepancies and axle abnormalities.

[0118] (6) Assist in ETC issuance. Assist in ETC issuance to ensure accurate issuance of ETC from the source. Based on the existing ETC issuance data and traffic data of Hubei Province, timely screen target users and accurately identify high-frequency traffic vehicles without ETC, and promptly push the information to the plaza staff for targeted ETC marketing.

[0119] (7) Precision marketing to members, enabling data empowerment. Based on precise member profiles, more efficient outreach is provided, reducing marketing costs. By strengthening the application of data results, a collaborative mechanism is established with new business formats such as logistics, insurance, finance, and public welfare services to achieve data empowerment and value-added.

[0120] Furthermore, in this embodiment of the invention, the vehicle profiling platform is business-centric, establishing a vehicle profiling system to form a digital service supporting business applications. It fully utilizes the vehicle profiling system to establish a vehicle archive, forming a multi-dimensional tag library, topic library, and group profile.

[0121] A vehicle data indicator database is established, which is based on vehicle license plate information, passage records, audit special cases, driving trajectory, behavior habits, behavior analysis, vehicle behavior, vehicle stratification, vehicle activity, and other tag dimensions to create a toll data indicator database for vehicles.

[0122] A gantry vehicle model recognition index library is established. This library is created based on the vehicle's license plate database, special vehicle information, axle group information, and other tag dimensions. The library can also generate actual vehicle trajectory information by combining gantry vehicle model recognition and gantry license plate recognition data, establish a detailed vehicle trajectory library, and derive a vehicle trajectory-related index library through the analysis of vehicle trajectories.

[0123] Vehicle Feature Database: Establish a vehicle feature database based on structured image data provided by an image search engine, according to vehicle basic information, vehicle appearance features, license plate features, vehicle brand features, vehicle accessories features, driver features, and vehicle brand information.

[0124] To establish a vehicle model and license plate index database, it is necessary to integrate and analyze the toll data index database for vehicle models, the gantry vehicle model recognition index database, and the vehicle feature database. The database should be built based on information such as basic vehicle information, vehicle traffic information, vehicle behavior information, vehicle feature information, and vehicle driving trajectory information.

[0125] Vehicle data processing and analysis includes:

[0126] Data preprocessing requires filtering and preprocessing the collected vehicle data to remove dirty, duplicate, invalid, and abnormal data, and then classifying and storing the main information of the preprocessed toll data.

[0127] Data analysis involves integrating the main information of the preprocessed vehicle data according to transaction time, license plate, and other information, as well as relevant indicators of the toll data, accumulating traffic information, analyzing behavioral trends, and analyzing vehicle traffic behavior. The analyzed indicator data is then stored.

[0128] Data indicator analysis involves analyzing the trends of data related to vehicle increment indicators and existing toll indicators. Based on the constantly changing vehicle indicator data, vehicle information and the vehicle indicator database are revised to ensure the accuracy and real-time performance of the vehicle model and license plate database.

[0129] Mast vehicle identification data processing and analysis includes:

[0130] Data preprocessing requires filtering and preprocessing the collected gantry vehicle identification data to remove dirty data, duplicate data, invalid data, and abnormal data, and then classifying and storing the main information of the preprocessed gantry vehicle identification data.

[0131] Data analysis involves analyzing the main information of the pre-processed gantry vehicle recognition data according to the shooting time, license plate recognition, and other information, as well as the basic information of the license plate database, special vehicle information, axle group information, and other dimensions. The analyzed index data is then stored.

[0132] Data indicator analysis involves comparing the toll data related to new vehicle arrivals with existing toll data to analyze trends. Based on the constantly changing vehicle indicator data, vehicle information and the vehicle indicator database are updated to ensure the accuracy and real-time performance of the vehicle model and license plate database.

[0133] Vehicle feature data processing and analysis includes:

[0134] Data preprocessing requires filtering and preprocessing the structured image data provided by the image search engine, removing dirty data, duplicate data, invalid data, and abnormal data, and then classifying and storing the main information of the preprocessed structured image data.

[0135] Data analysis involves analyzing the main information of the preprocessed image structured data according to information such as shooting time and license plate, and then analyzing relevant indicators of the image structured data, including basic vehicle information, vehicle appearance feature information, license plate feature information, vehicle brand feature information, vehicle accessory feature information, vehicle driver feature information, and vehicle brand information. The analyzed indicator data is then stored.

[0136] Data indicator analysis involves comparing the incremental image structured data with the existing image structured data to analyze data trends. Based on the constantly changing vehicle indicator data, vehicle information and the vehicle indicator database are revised to ensure the accuracy and real-time performance of the vehicle model and license plate database.

[0137] The integrated analysis of vehicle model and license plate database indicators includes:

[0138] Data analysis involves categorizing the main information from the toll collection indicator database, gantry vehicle type recognition indicator database, and vehicle feature database according to time, license plate, and other information. The analysis includes vehicle basic information, vehicle passage information, vehicle behavior information, vehicle feature information, and vehicle driving trajectory information. The analyzed indicator data is then stored.

[0139] Vehicle profile index analysis involves comparing data from the incremental vehicle toll collection index library, gantry vehicle type recognition index library, and vehicle feature library with existing toll collection index library, gantry vehicle type recognition index library, and vehicle feature library to analyze data trends. Based on the constantly changing vehicle index data, vehicle information and vehicle index libraries are corrected to ensure the accuracy and real-time performance of the vehicle model and license plate database.

[0140] To better implement the highway vehicle profile generation method based on big data in this embodiment of the invention, this embodiment also provides a highway vehicle profile generation device based on big data. Figure 6 is a structural schematic diagram of an embodiment of the highway vehicle profile generation device based on big data provided by this invention. As shown in Figure 6, the highway vehicle profile generation device 600 based on big data includes:

[0141] The processing module 610 is used to preprocess the structured data in the high-speed traffic data of vehicles to obtain preprocessed target data; the high-speed traffic data includes transaction data, gantry license plate data and vehicle type identification data;

[0142] The extraction module 620 is used to extract target features of the vehicle based on the target data; the target features include shape features, driving features, driving characteristics, consumption features, and toll evasion features;

[0143] The construction module 630 is used to construct a vehicle profile model using HiveSql based on the target features;

[0144] The generation module 640 is used to generate a vehicle portrait based on the portrait model.

[0145] The highway vehicle profile generation device 600 based on big data provided in the above embodiments can realize the technical solutions described in the above embodiments of the highway vehicle profile generation method based on big data. The specific implementation principles of each module or unit can be found in the corresponding content in the embodiments of the highway vehicle profile generation method based on big data, and will not be repeated here.

[0146] As shown in Figure 7, the present invention also provides an electronic device 700. The electronic device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 only shows some components of the electronic device 700; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented alternatively.

[0147] In some embodiments, processor 701 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 702 or process data, such as the highway vehicle profile generation method based on big data in this invention.

[0148] In some embodiments, processor 701 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, or any combination thereof.

[0149] In some embodiments, memory 702 may be an internal storage unit of electronic device 700, such as a hard disk or memory of electronic device 700. In other embodiments, memory 702 may also be an external storage device of electronic device 700, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 700.

[0150] Furthermore, the memory 702 may include both internal storage units of the electronic device 700 and external storage devices. The memory 702 is used to store application software and various types of data installed on the electronic device 700.

[0151] In some embodiments, display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 703 is used to display information from electronic device 700 and to display a visual user interface. Components 701-703 of electronic device 700 communicate with each other via a system bus.

[0152] In one embodiment, when processor 701 executes a highway vehicle profile generation program based on big data stored in memory 702, the following steps can be implemented:

[0153] The structured data in the vehicle's highway traffic data is preprocessed to obtain the preprocessed target data; the highway traffic data includes transaction data, gantry license plate data, and vehicle type identification data.

[0154] Based on the target data, target features of the vehicle are extracted; the target features include appearance features, driving features, driving characteristics, consumption features, and toll evasion features.

[0155] Based on the target features, a vehicle profile model is constructed using HiveSql;

[0156] Based on the portrait model, a vehicle portrait is generated.

[0157] It should be understood that when the processor 701 executes the highway vehicle profile generation program based on big data in the memory 702, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0158] Furthermore, the embodiments of the present invention do not specifically limit the type of electronic device 700 mentioned. Electronic device 700 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, electronic device 700 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0159] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the highway vehicle profile generation method based on big data provided in the above-described method embodiments.

[0160] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to perform the steps or functions in the highway vehicle profile generation method based on big data provided in the above-described method embodiments.

[0161] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0162] The above provides a detailed description of the highway vehicle profile generation method, apparatus, and medium based on big data provided by this invention. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for generating highway vehicle profiles based on big data, characterized in that, include: The structured data in the high-speed traffic data of vehicles is preprocessed to obtain the preprocessed target data; The high-speed traffic data includes transaction data, gantry license plate recognition data, and vehicle type recognition data; Based on the target data, target features of the vehicle are extracted; the target features include appearance features, driving features, driving characteristics, consumption features, and toll evasion features. Based on the target features, a vehicle profile model is constructed using HiveSql; Based on the portrait model, a vehicle portrait is generated.

2. The method for generating highway vehicle profiles based on big data according to claim 1, characterized in that, The step of extracting target features of the vehicle based on the target data includes: Data analysis is performed on the target data to obtain the target features; The data analysis includes at least one of the following: Cluster analysis, association rule mining, time series analysis, behavioral data analysis, and vehicle status analysis.

3. The method for generating highway vehicle profiles based on big data according to claim 1, characterized in that, The process of constructing a vehicle profile model using HiveSql based on the target features includes: Based on the target features, vehicle tags are generated; Based on the vehicle tags, the profile model is constructed using HiveSql.

4. The method for generating highway vehicle profiles based on big data according to claim 1, characterized in that, After generating the vehicle profile based on the profile model, the process further includes: The vehicle profile is visualized using charts or images.

5. The method for generating highway vehicle profiles based on big data according to claim 1, characterized in that, The preprocessing includes at least one of the following: Analysis, deduplication, decontamination, cleaning, screening, classification, conversion, and summarization.

6. The method for generating highway vehicle profiles based on big data according to claim 1, characterized in that, Before preprocessing the structured data in the high-speed traffic data of vehicles to obtain the preprocessed target data, the process also includes: The high-speed traffic data is divided into structured data and unstructured data; The structured data is stored in the big data platform; The unstructured data is stored on an FTP server.

7. A highway vehicle profile generation device based on big data, characterized in that, include: The processing module is used to preprocess the structured data in the high-speed traffic data of vehicles to obtain the preprocessed target data. The high-speed traffic data includes transaction data, gantry license plate recognition data, and vehicle type recognition data; The extraction module is used to extract target features of the vehicle based on the target data; the target features include appearance features, driving features, driving characteristics, consumption features, and toll evasion features; A construction module is used to build a vehicle profile model using HiveSql based on the target features; The generation module is used to generate vehicle portraits based on the portrait model.

8. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the highway vehicle profile generation method based on big data as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for generating highway vehicle profiles based on big data as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for generating highway vehicle profiles based on big data as described in any one of claims 1 to 6.

Images