Big data-based expressway vehicle portrait generation method and device, and medium

Abstract

The invention relates to a highway vehicle portrait generation method and device based on big data and a medium, and belongs to the technical field of big data processing, and the method comprises the steps: carrying out the preprocessing of structural data in the highway traffic data of a vehicle, and obtaining the preprocessed target data; the expressway passing data comprises transaction data, portal license identification data and vehicle type identification data; extracting target features of the vehicle based on the target data; the target features comprise an appearance feature, a driving feature, a driving feature, a consumption feature and a fee evasion feature; based on the target features, constructing a portrait model of the vehicle through HiveSql; and generating a vehicle portrait based on the portrait model. According to the big data-based highway vehicle portrait generation method provided by the invention, the vehicle portrait model is constructed by using the extracted target features through HiveSql, and the vehicle portrait can be quickly and accurately generated by the constructed portrait model.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to a method, device and medium for generating highway vehicle portraits based on big data. Background Art

[0002] With the development of intelligent transportation systems, vehicle management has become an important part of traffic management, and the accurate acquisition and analysis of vehicle information has become particularly important. In the highway toll collection business scenario, the judgment of vehicle type is the basis of the entire business. As many places have begun to build unmanned and standardized new toll collection systems. In the unmanned toll collection model, how to accurately and quickly judge the vehicle type is the basis for achieving accurate billing.

[0003] Traditional vehicle recognition methods mainly rely on static images or video streams for analysis. However, in actual applications, due to the huge amount of data, high real-time requirements for data, and the influence of environmental factors, it is difficult to accurately and quickly create vehicle portraits. Summary of the invention

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

[0005] In order to solve the above problems, the present invention provides a method for generating highway vehicle portraits based on big data, comprising: Preprocessing the structured data in the high-speed traffic data of the vehicle to obtain preprocessed target data; the high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; Based on the target data, extracting target features of the vehicle; the target features include appearance features, travel features, driving features, consumption features and evasion features; Based on the target features, a vehicle portrait model is constructed through HiveSql; Based on the portrait model, a vehicle portrait is generated.

[0006] In a possible implementation, extracting the target features of the vehicle based on the target data includes: Performing data analysis 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.

[0007] In a possible implementation, building a vehicle portrait model based on the target feature through HiveSql includes: Based on the target features, generating a vehicle label; Based on the vehicle label, the portrait model is constructed through HiveSql.

[0008] In a possible implementation, after generating the vehicle portrait based on the portrait model, the method further includes: The vehicle portrait is visualized in the form of a chart or image.

[0009] In a possible implementation, the preprocessing includes at least one of the following: In one possible implementation, the structured data in the high-speed traffic data of the vehicle is preprocessed to obtain the preprocessed target data, and the method further includes: dividing the high-speed traffic data into structured data and unstructured data; Storing the structured data in a big data platform; The unstructured data is stored in an FTP server. The present invention also provides a highway vehicle portrait generation device based on big data, comprising: A processing module, used to pre-process the structured data in the high-speed traffic data of the vehicle to obtain the pre-processed target data; the high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; An extraction module, used to extract target features of the vehicle based on the target data; the target features include appearance features, travel features, driving features, consumption features and evasion features; A construction module, used to construct a vehicle portrait model through HiveSql based on the target features; A generation module is used to generate a vehicle portrait based on the portrait model.

[0010] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the highway vehicle portrait generation method based on big data described in any of the above implementation methods.

[0011] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating highway vehicle portraits based on big data described in any of the above-mentioned implementation methods is implemented.

[0012] On the other hand, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for generating highway vehicle portraits based on big data as described in any of the above-mentioned implementation methods.

[0013] The beneficial effects of the present invention are as follows: the highway vehicle portrait generation method, device and medium based on big data provided by the present invention preprocess the structured data in the acquired vehicle highway passage data to ensure the accuracy and efficiency of subsequent analysis, thereby extracting the target features of the vehicle according to the preprocessed target data, and the target features may include appearance features, travel features, driving features, consumption features and evasion features, etc. The extracted target features are used to construct a vehicle portrait model through HiveSql, so that the constructed portrait model can quickly and accurately generate vehicle portraits, and the vehicle portraits can be used for traffic flow analysis, safety monitoring, toll management, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the 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 work.

[0015] Figure 1 One of the method flow charts of an embodiment of the method for generating highway vehicle portraits based on big data provided by the present invention; Figure 2 A schematic diagram of a labeling system provided by the present invention; Figure 3 A second method flow chart of an embodiment of a method for generating highway vehicle portraits based on big data provided by the present invention; Figure 4 The architecture diagram of the highway vehicle portrait generation method based on big data provided by the present invention; Figure 5 The third flowchart of the method for generating highway vehicle portraits based on big data provided by the present invention; Figure 6 A schematic diagram of the structure of an embodiment of a highway vehicle portrait generation device based on big data provided by the present invention; Figure 7 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0018] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0019] Figure 1 A method flow chart of an embodiment of a method for generating highway vehicle portraits based on big data provided by the present invention is as follows: Figure 1 As shown, the highway vehicle portrait generation method based on big data includes: S101, preprocessing structured data in the high-speed traffic data of the vehicle to obtain preprocessed target data; the high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; S102, extracting target features of the vehicle based on the target data; the target features include appearance features, travel features, driving features, consumption features and evasion features; S103, constructing a vehicle portrait model through HiveSql based on the target features; S104: Generate a vehicle portrait based on the portrait model.

[0020] It should be noted that: vehicle high-speed traffic data can be obtained by connecting to the gantry equipment and toll station equipment fusion service. High-speed traffic data may include transaction data, gantry license plate recognition data, and vehicle model recognition data. HiveSQL is a language used to execute SQL queries in Apache Hive. Hive is a data warehouse system for processing large-scale structured data. HiveSQL allows users to operate and analyze data stored in the Hadoop file system through the SQL query language, and is mainly used for data query and processing in a big data environment.

[0021] Compared with the prior art, the highway vehicle portrait generation method based on big data provided by the embodiment of the present invention preprocesses the structured data in the acquired vehicle highway passage data to ensure the accuracy and efficiency of subsequent analysis, thereby extracting the target features of the vehicle according to the preprocessed target data. The target features may include appearance features, travel features, driving features, consumption features, and toll evasion features, etc. The extracted target features are used to construct a vehicle portrait model through HiveSql, so that the constructed portrait model can quickly and accurately generate vehicle portraits, and the vehicle portraits can be used for traffic flow analysis, safety monitoring, toll management, etc.

[0022] In some embodiments of the present invention, the preprocessing includes at least one of the following: Parsing, deduplication, cleaning, filtering, classification, conversion and aggregation. Parsing can convert raw data (which may be in unstructured or semi-structured formats, such as XML, JSON, etc.) into structured data for subsequent processing. Deduplication can remove duplicate records in the data to ensure the uniqueness of each data and avoid analysis bias. Deduplication can remove errors or meaningless information in the data, such as incorrect character input, invalid data values, etc. Cleaning can organize the data in a more detailed manner, including correcting inconsistent data, processing missing values, removing outliers, etc. Filtering can select relevant fields or records in the data set according to analysis requirements and exclude irrelevant data. Classification can group data according to certain standards or features to provide an organized data set for model training or analysis. Perform necessary format conversion on the data to make it suitable for specific analysis methods or tools, such as standardization and normalization. Statistical aggregation of data to reduce the size of the data set and extract key information.

[0023] The method for generating highway vehicle portraits based on big data provided in an embodiment of the present invention can effectively improve the quality and reliability of data analysis by preprocessing the data.

[0024] In some embodiments of the present invention, before preprocessing the structured data in the high-speed traffic data of the vehicle to obtain the preprocessed target data, the method further includes: dividing the high-speed traffic data into structured data and unstructured data; Storing the structured data in a big data platform; The unstructured data is stored in an FTP server. Structured data refers to data with a clear format that can be directly used for analysis, such as table data. Unstructured data includes pictures, text, videos, etc., which require special processing before they can be used for analysis.

[0025] Store structured data in the big data platform. The big data platform provides a platform for easy access and analysis of structured data, making subsequent data processing and analysis more efficient.

[0026] Store unstructured data in an FTP server. An FTP server provides a centralized storage location for unstructured data, making it easier to manage and transfer data.

[0027] In some embodiments of the present invention, extracting the target features of the vehicle based on the target data includes: Performing data analysis 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.

[0028] By analyzing the target data, the target features of the vehicle can be obtained. The target features can include appearance features (such as basic vehicle information, vehicle appearance feature information, license plate feature information, vehicle brand features, vehicle pendant features, vehicle driver feature information, vehicle brand information, etc.), driving features (such as the vehicle's driving trajectory, driving speed, behavioral habits, driving calendar, high-frequency paths, passing frequency, etc.), driving features (such as the driver's driving behavior, recent driving status and dangerous driving coefficient, the number of passes through speeding, overloading and fatigue driving, etc.), consumption features (such as whether the vehicle consumes service area consumption, gas station consumption, tolls, etc. during high-speed driving) and evasion features (whether the vehicle has evaded fees after driving at high speed, whether a suspected work order is generated, and the type of evasion), etc.

[0029] Cluster analysis is used to group data points based on similarities. 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 divide different vehicle types or behavior groups.

[0030] Association rule mining is used to discover the associations between variables in a data set. In vehicle data, association rules can reveal the associations between specific vehicle features and other features, such as the association between a certain vehicle model and a specific toll payment pattern or toll evasion behavior.

[0031] Time series analysis is used to analyze data points that change over time. It is very effective for 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.

[0032] Behavioral data analysis focuses on the driving behavior of vehicles, including speed, acceleration, driving route, etc. Behavioral data analysis can help identify abnormal driving behavior, provide a basis for traffic safety monitoring, and can be used to improve traffic flow management.

[0033] Vehicle status analysis focuses on the physical status and performance of the vehicle. By combining vehicle profile data, such as the vehicle's brand, model, mileage, high-frequency routes, driving conditions, maintenance records, and the owner's travel habits and driving behavior, it helps identify potential safety hazards, such as frequent sudden acceleration and braking that may cause wear of the brake system, or tire aging caused by long-term driving in harsh road conditions, and provides a basis for vehicle maintenance. Once these potential risks are discovered, measures can be taken quickly to repair or replace them, thereby ensuring the long-term stability and safe operation of the vehicle.

[0034] The method for generating highway vehicle portraits based on big data provided in an embodiment of the present invention performs data analysis on target data through 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 portrait model.

[0035] In some embodiments of the present invention, the step of constructing a vehicle portrait model through HiveSql based on the target feature includes: Based on the target features, generating a vehicle label; Based on the vehicle label, the portrait model is constructed through HiveSql.

[0036] Based on the vehicle target features extracted from data analysis, specific vehicle labels are first generated. These labels are usually defined based on qualitative or quantitative information such as vehicle behavior, characteristics, or habits, such as "high-speed drivers", "night driving", "high-spending users", etc. Figure 2 As shown, Figure 2 A schematic diagram of the labeling system provided by the present invention.

[0037] After the vehicle labels are generated, you can use HiveSql to write query scripts to build a portrait model. The portrait model comprehensively considers various vehicle labels and features, and classifies or groups vehicles through logic and algorithms (such as classification algorithms, association rules, etc.).

[0038] The advantage of building a portrait model through HiveSql is that it can process large amounts of data and is suitable for highway management systems that need to analyze large-scale vehicle data sets. In addition, the query language supports SQL syntax, making it easier for data analysts to write complex queries, conduct data mining and analysis, and effectively build a portrait model that reflects vehicle characteristics and behavior patterns.

[0039] The method for generating highway vehicle portraits based on big data provided in an embodiment of the present invention constructs a vehicle portrait model by means of HiveSql, and summarizes the generated vehicle model identification data, gantry transaction data, toll station transaction data and historical transaction data, 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.

[0040] In some embodiments of the present invention, after generating the vehicle portrait based on the portrait model, the method further includes: The vehicle portrait is visualized in the form of a chart or image.

[0041] The generated vehicle portrait is presented in the form of charts or images through visualization technology for application in actual scenarios, such as basic management systems, visualization screens, gantry audit systems, group monitoring screens, cloud verification of license plates and vehicle models, and precision marketing for members based on vehicle portraits.

[0042] The present invention establishes a one-car-one-file and electronic portrait system for passing vehicles through research and exploration, uses data collected by various highway systems, external access data, and business audit data, and fully mines various data resources of vehicles on highways through big data technology, and makes a detailed qualitative description of the driving preferences, route selection, travel time rules, safety risks, etc. of vehicles during highway driving, providing data support for highway operation management, traffic command and dispatch, and providing precise services for vehicles. And the electronic portrait of vehicles is studied to analyze individual and group vehicles, analyze the changes in the models and traffic characteristics of passing vehicles, count key service vehicles, and provide safety control guidance for vehicles such as two passenger and one dangerous goods, cold chain transportation, etc. Through the analysis of the hot spot distribution of OD traffic routes of vehicle group portraits, evaluation data is provided for the revenue contribution rate of the route. It is helpful to improve traffic management efficiency and enhance safety assurance.

[0043] The present invention proposes a creation and analysis algorithm for a highway vehicle portrait system based on big data. It is business-centric and based on multi-source heterogeneous data such as ETC gantry transaction data, toll station entrance and exit transaction flow, gantry vehicle model identification data, Hubei Province Green Pass inspection data, and Beidou two passenger, one dangerous, and one heavy data, and based on vehicle traffic behavior habits, the vehicle characteristics are labeled to form a one-car-one-file multi-dimensional evaluation (including vehicle basic information, vehicle driving status, toll evasion behavior analysis, traffic behavior habits, vehicle value analysis, etc.). The vehicle portrait system is fully utilized to establish a vehicle archive library, form a multi-dimensional label library, thematic library, and group portraits, and form a vehicle portrait digital service to support business applications.

[0044] Figure 3The second method flow chart of an embodiment of the method for generating highway vehicle portraits based on big data provided by the present invention is as follows: Figure 3 As shown, the highway vehicle portrait generation method based on big data includes: S301, collect transaction data, door frame plate recognition data, and vehicle model recognition data.

[0045] In order to ensure the scale and diversity of the data set, the original data is mainly collected from the road sections under the jurisdiction of Hubei Jiaotong Investment Group. It is connected with the fusion service of gantry equipment and toll station equipment to realize the collection of vehicle type recognition data, transaction data and various basic data.

[0046] After the data collection work is completed, the original structured data is stored in the original data layer (ods) of the big data platform, and the unstructured data is stored in the FTP server.

[0047] S302: Preprocess the original data.

[0048] After obtaining the data from the original data layer (ods), the data warehouse and HiveSql calculation method are used to process the original structured data, including removing duplicate data, processing missing values, data format conversion, data standardization, etc., and the processed data is stored in the detailed data layer (dwd). In preparation for establishing a vehicle portrait label system data set, the data set that needs to be analyzed includes vehicle basic data analysis, vehicle driving trajectory analysis, vehicle driving behavior analysis, vehicle consumption value analysis, and vehicle evasion behavior analysis.

[0049] S303. Analyze and summarize the detailed data.

[0050] Get the pre-processed data of the detailed data layer (dwd) and conduct in-depth mining and analysis of the data. Through cluster analysis, association rule mining, time series analysis, behavior data analysis, vehicle status analysis and other methods, we can find the vehicle driving characteristics, behavior model and the relationship between other factors. On the basis of data analysis, establish data aggregation to form a vehicle portrait, summarize and organize the analysis results according to different dimensions, such as by vehicle model, vehicle type, driving area, etc., and store the data in the data application layer (ads).

[0051] S304: Practically apply the summarized data.

[0052] The result data of the data application layer (ads) is obtained, and the data is synchronized to databases such as Clickhouse and MySQL. The analysis and summary results are presented in the form of charts, images, etc. with the help of visualization technology, and applied to actual scenarios, such as basic management systems, visualization large screens, gantry audit systems, group monitoring large screens, cloud verification of license plates and vehicle models, and precision marketing for members based on vehicle portraits.

[0053] For example, Figure 4 The architecture diagram of the highway vehicle portrait generation method based on big data provided by the present invention is as follows: Figure 5 The third flowchart of the method for generating highway vehicle portraits based on big data provided by the present invention is as follows: Figure 4 He Ru Figure 5 As shown, the highway vehicle portrait generation method based on big data includes the following steps: (1) Through the integration service connection with gantry equipment and toll station equipment, vehicle type identification data, gantry transaction data, toll station transaction data and various basic data are collected.

[0054] (2) Data transmission is essentially a continuous and uninterrupted data transfer program. On the one hand, it receives data from data collection reports through interfaces and sftp services, and on the other hand, it forwards and aggregates these data to the aggregation server by calling the aggregation interface and sftp service. The aggregation server aggregates data from different edge smart terminals again through interfaces and SFTP services, and caches them in the Clickhouse database and local directory, and pushes the data to the big data platform Kafka message queue and FTP server.

[0055] (3) Receive data from the Kafka message queue and divide the data into structured data and unstructured data. The structured data (car model identification data (including summary)) is stored in HDFS, ES and Hbase through the consumer program, and other data is written to MySQL and Clickhouse. The unstructured data (car model image data) is aggregated to the FTP server.

[0056] (4) Clean and process all types of data written to the HDFS detail data layer, including removing duplicate data, processing missing values, converting data formats, and removing dirty data, to ensure data quality and availability, and store the processed data in the detail data layer.

[0057] (5) Use data analysis and mining techniques to conduct in-depth analysis of vehicle data, including: Vehicle basic data analysis: Analyze the common vehicle models, common vehicle types, cumulative number of passes, cumulative mileage, cumulative tolls, special vehicle identification, transit vehicle identification and other information to understand the basic information of the vehicle.

[0058] Vehicle feature analysis: Based on the image structured data provided by the image search engine, a vehicle feature database is established according to the basic vehicle information, vehicle appearance feature information, license plate feature information, vehicle brand features, vehicle pendant features, vehicle driver and passenger feature information, and vehicle brand information.

[0059] Vehicle driving trajectory analysis: Analyze the vehicle's driving trajectory, driving speed, behavior habits, driving calendar, high-frequency paths, passing frequency and other information to understand the vehicle's operating conditions.

[0060] Vehicle driving behavior analysis: Analyze the driver's driving behavior, recent driving status and risky driving coefficient, and evaluate driving safety through information such as the number of speeding, overloading and fatigue driving.

[0061] Vehicle consumption value analysis: Analyze whether there is any consumption at service areas and gas stations while the vehicle is driving on the highway, and add tolls to evaluate the driver's consumption value concept.

[0062] Vehicle evasion behavior analysis: Analyze whether the vehicle has evaded fees after driving on the highway, whether suspicious work orders are generated, and what types of evasion are there, so as to understand the credit value of the vehicle.

[0063] (6) Based on the results of the above data analysis, a vehicle portrait model is constructed through HiveSql, and the generated vehicle model identification data, gantry transaction data, toll station transaction data and historical transaction data are summarized, 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.

[0064] (7) The model result data is stored in the data application layer and pushed to MySQL and Clickhouse, and the vehicle portrait model is applied to actual scenarios, such as basic management systems, visualization screens, gantry audit systems, group monitoring screens, license plate and vehicle model cloud verification, and member precision marketing based on vehicle portraits.

[0065] The method for generating highway vehicle portraits based on big data provided by the present invention has the following beneficial effects: (1) Improving the speed and efficiency of vehicle portrait creation. Through big data processing and machine learning technology, rapid and accurate acquisition and analysis of vehicle information can be achieved, thereby improving the speed and efficiency of vehicle portrait creation.

[0066] (2) Accurately represent vehicle characteristics. By extracting vehicle characteristics and performing correlation analysis, the generated vehicle portrait can accurately represent vehicle characteristics and provide accurate data support for related fields.

[0067] (3) Providing multi-field application support. Vehicle profiling can be applied to multiple fields such as operation management, ETC issuance, toll inspection, and member marketing. It can establish basic models and provide data support for personalized travel services, roadside value-added business development, and highway digital asset operations.

[0068] The main application scenarios are as follows: (1) Cloud verification of vehicle model and license plate. The vehicle profiling system is used to conduct cloud verification of the license plate and model of imported and exported vehicles, and secondary verification is performed based on big data to provide highly reliable license plate and model data.

[0069] (2) Vehicle driving behavior analysis. The vehicle driving behavior is identified and analyzed based on the vehicle profiling results to identify or predict whether the vehicle will engage in abnormal driving behaviors such as speeding (three emergency and one speed), long-term low-speed driving, fatigue driving, continuous lane changes, driving outside the lane, and long-term occupation of the emergency lane.

[0070] (3) Assisting toll auditing: Through resource sharing and information exchange, assisting toll auditing can reduce toll losses.

[0071] (4) Service area traffic diversion. Based on vehicle portraits, service area positioning, target customers, and specific marketing strategies for the service area, data-based operations are used to divert traffic to the service area and increase revenue.

[0072] (5) Near-field monitoring: Using information such as the vehicle portrait system and vehicle credit value, early warnings are issued for vehicles entering toll stations and provincial boundary gantries, such as vehicles with larger vehicles and smaller vehicle logos, or abnormal axle shapes.

[0073] (6) Assisting ETC issuance. Assisting ETC issuance and ensuring accurate ETC issuance from the source. Based on the ETC issuance stock data and traffic data in Hubei Province, timely screening of target users, accurate identification of high-frequency vehicles without ETC installed, and timely push to square guards for ETC precision marketing.

[0074] (7) Precision marketing for members to achieve data empowerment. Based on the precise portraits of members, more efficient reach is provided to reduce marketing costs. By strengthening the application of data results, a collaborative linkage mechanism with new business forms such as logistics, insurance, finance, and public welfare services is established to achieve data empowerment and value-added.

[0075] In addition, the vehicle portrait platform in the embodiment of the present invention is business-centric, establishes a vehicle portrait system, and forms a vehicle portrait digital service to support business applications. Make full use of the vehicle portrait system, establish a vehicle archive, and form a multi-dimensional label library, thematic library and group portrait.

[0076] Vehicle data index library, establish a vehicle data index library, and establish a vehicle charging data index library according to the vehicle's basic license plate information, traffic files, audit special conditions, driving trajectory, behavioral habits, behavioral analysis, vehicle behavior, vehicle stratification, vehicle activity and other label dimensions.

[0077] Gantry model identification index library, establish a gantry model identification index library, establish a vehicle gantry model identification index library according to the vehicle's license plate library basic information, special vehicle information, axle group information and other note dimensions, and can form the vehicle's actual trajectory information based on the combination of gantry model identification and gantry license plate recognition data, establish a vehicle trajectory details library, and derive the vehicle trajectory-related index library through vehicle trajectory analysis.

[0078] Vehicle feature database, establish a vehicle feature database, based on the image structured data provided by the image search engine, establish a vehicle feature database according to vehicle basic information, vehicle appearance feature information, license plate feature information, vehicle brand features, vehicle pendant features, vehicle driver feature information, vehicle brand information, etc.

[0079] To establish a vehicle model and license plate index library, it is necessary to integrate and analyze the vehicle model's charging data index library, the gantry vehicle model identification index library, and the vehicle feature library, and establish a vehicle license plate index library based on vehicle basic information, vehicle traffic information, vehicle behavior information, vehicle feature information, vehicle driving trajectory information and other information.

[0080] Vehicle data processing and analysis include: Data preprocessing requires filtering and preprocessing the collected vehicle data for dirty data, duplicate data, invalid data, abnormal data, etc., and classifying and storing the main information of the preprocessed charging data.

[0081] Data analysis: the main information of the pre-processed vehicle data is used to integrate the relevant indicators of the toll data according to the transaction time, license plate and other information, accumulate traffic information, analyze behavioral trends, analyze vehicle traffic behavior, etc., and store the analyzed indicator data.

[0082] Data indicator analysis: conduct trend analysis on data related to vehicle incremental indicators and existing charging indicator data, correct vehicle information based on the vehicle's constantly changing indicator data, and correct the vehicle indicator database to ensure the accuracy and real-time nature of the vehicle model and license plate database.

[0083] Gantry vehicle model identification data processing and analysis include: Data preprocessing requires filtering and preprocessing the collected gantry vehicle model identification data for dirty data, duplicate data, invalid data, abnormal data, etc., and classifying and storing the main information of the preprocessed gantry vehicle model identification data.

[0084] Data analysis: the main information of the pre-processed gantry vehicle model recognition data is analyzed according to the shooting time, recognized license plate and other information on the basic information of the license plate library, special vehicle information, axle group information and other note dimensions, and the analyzed indicator data is stored.

[0085] Data indicator analysis: conduct trend analysis on the data related to the incremental charging data indicators of vehicles and the existing charging index data, and correct the vehicle information according to the constantly changing indicator data of the vehicle, and correct the vehicle index database to ensure the accuracy and real-time nature of the vehicle model and license plate database.

[0086] Vehicle feature data processing and analysis include: Data preprocessing requires filtering and preprocessing dirty data, duplicate data, invalid data, abnormal data, etc. of the image structured data provided by the image search engine, and classifying and storing the main information of the preprocessed image structured data.

[0087] Data analysis: the main information of the pre-processed image structured data is analyzed according to the shooting time, license plate and other information to the relevant indicators of the image structured data, including vehicle basic information, vehicle appearance feature information, license plate feature information, vehicle brand features, vehicle pendant features, vehicle driver feature information, vehicle brand information, etc., and the analyzed indicator data is stored.

[0088] Data indicator analysis: conduct data trend analysis on the data related to the incremental image structured data indicators of the vehicle and the existing image structured data, and correct the vehicle information and vehicle indicator database according to the vehicle's constantly changing indicator data to ensure the accuracy and real-time nature of the vehicle model and license plate database.

[0089] The vehicle model and license plate database indicator fusion analysis includes: Data analysis: the main information of the toll number index library, gantry vehicle type identification index library, and vehicle feature library are analyzed according to time, license plate and other information to analyze the relevant indicators of the toll data, including basic vehicle information, vehicle traffic information, vehicle behavior information, vehicle feature information, vehicle driving trajectory information, etc., and the analyzed index data are stored.

[0090] Vehicle portrait index analysis, conducts data trend analysis on the incremental vehicle charging index library, gantry vehicle model identification index library, and vehicle feature library with the existing charging index library, gantry vehicle model identification index library, and vehicle feature library, and corrects vehicle information based on the vehicle's constantly changing index data, and corrects the vehicle index library to ensure the accuracy and real-time nature of the vehicle model and license plate library.

[0091] In order to better implement the highway vehicle portrait generation method based on big data in the embodiment of the present invention, on the basis of the highway vehicle portrait generation method based on big data, the embodiment of the present invention also provides a highway vehicle portrait generation device based on big data. Figure 6 A schematic diagram of the structure of an embodiment of a highway vehicle portrait generation device based on big data provided by the present invention is shown in FIG. Figure 6 As shown, the highway vehicle portrait generation device 600 based on big data includes: The processing module 610 is used to pre-process the structured data in the high-speed traffic data of the vehicle to obtain the pre-processed target data; the high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; An extraction module 620 is used to extract target features of the vehicle based on the target data; the target features include appearance features, travel features, driving features, consumption features and evasion features; A construction module 630 is used to construct a vehicle portrait model through HiveSql based on the target features; The generation module 640 is used to generate a vehicle portrait based on the portrait model.

[0092] The device 600 for generating a highway vehicle portrait based on big data provided in the above embodiment can implement the technical solution described in the above embodiment of the method for generating a highway vehicle portrait based on big data. The specific implementation principles of the above modules or units can be found in the corresponding contents in the embodiment of the method for generating a highway vehicle portrait based on big data, which will not be repeated here.

[0093] like Figure 7 As shown, 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 some components of the electronic device 700 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0094] In some embodiments, the processor 701 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 702, such as the highway vehicle portrait generation method based on big data in the present invention.

[0095] In some embodiments, the processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 701 may be local or remote. In some embodiments, the processor 701 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0096] In some embodiments, the memory 702 may be an internal storage unit of the electronic device 700, such as a hard disk or memory of the electronic device 700. In other embodiments, the memory 702 may also be an external storage device of the electronic device 700, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 700.

[0097] Furthermore, the memory 702 may include both an internal storage unit of the electronic device 700 and an external storage device. The memory 702 is used to store application software installed in the electronic device 700 and various data.

[0098] In some embodiments, the display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (OLED) touch device, etc. The display 703 is used to display information on the electronic device 700 and to display a visual user interface. The components 701-703 of the electronic device 700 communicate with each other via a system bus.

[0099] In one embodiment, when the processor 701 executes the highway vehicle portrait generation program based on big data in the memory 702, the following steps may be implemented: Preprocessing the structured data in the high-speed traffic data of the vehicle to obtain preprocessed target data; the high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; Based on the target data, extracting target features of the vehicle; the target features include appearance features, travel features, driving features, consumption features and evasion features; Based on the target features, a vehicle portrait model is constructed through HiveSql; Based on the portrait model, a vehicle portrait is generated.

[0100] It should be understood that: when the processor 701 executes the highway vehicle portrait generation program based on big data in the memory 702, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0101] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 700 mentioned, and the electronic device 700 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may 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, the electronic device 700 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0102] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, it can implement the steps or functions of the highway vehicle portrait generation method based on big data provided in the above-mentioned method embodiments.

[0103] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps or functions of the highway vehicle portrait generation method based on big data provided in the above-mentioned method embodiments.

[0104] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0105] The above is a detailed introduction to the highway vehicle portrait generation method, device and medium based on big data provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for generating highway vehicle portraits based on big data, characterized in that: include: Preprocessing the structured data in the high-speed traffic data of the vehicle to obtain preprocessed target data; The high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; Based on the target data, extracting target features of the vehicle; the target features include appearance features, travel features, driving features, consumption features and evasion features; Based on the target features, a vehicle portrait model is constructed through HiveSql; Based on the portrait model, a vehicle portrait is generated.

2. The method for generating highway vehicle portraits based on big data according to claim 1 is characterized in that: The step of extracting target features of the vehicle based on the target data comprises: Performing data analysis 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 portraits based on big data according to claim 1 is characterized in that: The vehicle portrait model is constructed through HiveSql based on the target features, including: Based on the target features, generating a vehicle label; Based on the vehicle label, the portrait model is constructed through HiveSql.

4. The method for generating highway vehicle portraits based on big data according to claim 1 is characterized in that: After generating the vehicle portrait based on the portrait model, the method further includes: The vehicle portrait is visualized in the form of a chart or image.

5. The method for generating highway vehicle portraits based on big data according to claim 1 is characterized in that: The pre-processing includes at least one of the following: Parse, deduplicate, clean, filter, sort, transform and aggregate.

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

7. A highway vehicle portrait generation device based on big data, characterized in that: include: A processing module, used for preprocessing structured data in the high-speed traffic data of the vehicle to obtain preprocessed target data; The high-speed traffic data includes transaction data, door frame plate recognition data and vehicle type recognition data; An extraction module, used to extract target features of the vehicle based on the target data; the target features include appearance features, travel features, driving features, consumption features and evasion features; A construction module, used to construct a vehicle portrait model through HiveSql based on the target features; A generation module is used to generate a vehicle portrait based on the portrait model.

8. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the highway vehicle portrait 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 a processor, the method for generating highway vehicle portraits based on big data as described in any one of claims 1 to 6 is implemented.

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

Images