Intelligent automobile DTS data acquisition and query system

Abstract

The invention discloses an intelligent automobile DTS data acquisition and query system, which comprises a cloud platform, the cloud platform is provided with a data acquisition port and is used for acquiring automobile DTS data through the data acquisition port, the cloud platform carries out identification processing on the acquired DTS data and then stores the data into a database, and the database is used for storing the data. The database adopts a structured database. The system has the advantages that multiple data acquisition and query modes are realized by building the cloud platform, and the efficiency of data acquisition and data query is improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile DTS data processing, and in particular to an intelligent automobile DTS data collection and query system. Background Art

[0002] In order to meet consumers' ever-changing aesthetic needs and attract more people to buy new cars, OEMs must continuously launch new models and ensure that the design complies with the vehicle size technical specifications (DTS). To this end, detailed DTS data must be collected for each prototype vehicle to effectively learn from the designs of competitors and independently developed models.

[0003] Typically, most car models contain 150-200 sections, and the number of DTS measurement points for interior and exterior trim is usually between 1600 and 2000. Currently, there are various methods for DTS data collection, including manual measurement tools (such as flush gauges, gap gauges, laser measuring instruments, etc.) and handheld and robotic automatic gap and flush measurement equipment. During the manual measurement process, the data collector needs to record the measurement results one by one, and after completion, summarize all the data into an Excel file. Each sample car corresponds to an Excel file, and each file contains multiple Sheet pages, recording the actual DTS measurement results of different sections. During the automatic measurement process, it is necessary to first upload the cross-section image on the exclusive software provided by the equipment supplier, manually set the measurement point information one by one, including the name, position, nominal value and tolerance of the measurement point, and then use the automatic measurement equipment to measure the actual DTS value of the sample car one by one. After the measurement is completed, it is exported as a fixed template file.

[0004] However, there are many problems in the current workflow. First, data collectors need to have a basic understanding of the cross-sections and measurement points of the vehicle model and have relevant measurement experience, which is a big challenge for novices. Second, when designing a new vehicle model, it is necessary to understand all existing models, which makes it cumbersome to find the required information from many Excel files, thereby reducing work efficiency. When it is necessary to analyze multiple models or perform trend analysis on a certain model, the whole process is complicated and prone to errors. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a smart car DTS data collection and query system. By building a cloud platform, a variety of data collection and query methods can be realized to improve the efficiency of data collection and data query.

[0006] To achieve the above object, the technical solution adopted by the present invention is: an intelligent vehicle DTS data acquisition and query system, including a cloud platform, the cloud platform is configured with a data acquisition port for obtaining vehicle DTS data through the data acquisition port, the cloud platform identifies and processes the acquired DTS data, and then stores the data in a database, and the database uses a structured database.

[0007] The cloud platform includes a data acquisition module, the data acquisition module is connected to a data acquisition device through a data acquisition interface, the data acquisition device supports manual and automatic acquisition of DTS data and sends the DTS data to the data acquisition module through the data acquisition interface, and the data acquisition module parses and processes the uploaded DTS data to obtain storable DTS data and stores it in the database.

[0008] The data acquisition device is connected to the data acquisition interface through a network, the data acquisition interface is a network service interface, and the data is uploaded to the cloud platform through the network service interface by the data acquisition device and sent into the data acquisition device; the data acquisition device includes a web terminal device, a mobile terminal device and / or an automatic test device for realizing data entry and acquisition.

[0009] The web terminal device and the mobile terminal device both enter DTS data through a pre-developed templated web page or import an Excel format file through the web terminal device and the mobile terminal device, and the data acquisition module parses the DTS data in the Excel format file.

[0010] The cloud platform further includes a data processing module, and the data processing module calculates evaluation indicators according to the acquired DTS data, and the evaluation indicators are used to evaluate the vehicle design and manufacturing level.

[0011] Calculating evaluation indicators according to the acquired DTS data includes: DTS-related instruction indicators, DTS trend indicators of the same vehicle model, and DTS comparison indicators of different vehicle models.

[0012] The cloud platform further includes a permission management module, and the permission management module manages the user accounts accessing the cloud platform, and restricts and manages the permissions of users' data acquisition, upload, modification, and query operations.

[0013] A data query module is set in the cloud platform. A user with query permission sends a query request to the data query module after accessing the cloud platform. The query module analyzes and processes the received query request data to obtain a corresponding query result and feedbacks it to the user.

[0014] The data query module includes a hierarchical retrieval unit, an image search by image unit, and an interactive Q&A unit. The hierarchical retrieval unit is used to perform hierarchical positioning according to various dimensions such as brand, vehicle series, vehicle model, region, and cross-section based on the user's request to achieve data query positioning.

[0015] The image search by image unit queries the DTS data of similar images stored in the database of the cloud platform in a similarity manner according to the image uploaded by the user's query request.

[0016] The interactive Q&A unit is used to perform text queries according to the keywords input in the user's query request, analyze the user's request, and feedback the corresponding results.

[0017] The data query module further includes a data export unit, which is used to export the queried data into a preset file format according to the user's request signal.

[0018] The advantages of the present invention are as follows: By building a cloud platform, various data collection and query methods are realized, and the efficiency of data collection and data query is improved. The data is stored in a structured database, which is convenient for subsequent query and processing. In the query, multiple methods are supported to upload data, and users who collect and upload data are monitored and managed based on permission management, improving the reliability and traceability of data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The following briefly describes the content expressed in each drawing of the present invention specification and the marks in the drawings:

[0020] Figure 1 It is a functional module diagram of the intelligent vehicle DTS data collection and query system of the present invention;

[0021] Figure 2 It is a schematic diagram of the principle of the data collection lock module of the present invention;

[0022] Figure 3 It is a schematic diagram of the principle of image search by image corresponding to the query function of the present invention;

[0023] Figure 4 It is a schematic diagram of the principle of voice interactive query of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following further describes the specific embodiments of the present invention in detail by describing the optimal embodiments with reference to the drawings.

[0025] This solution proposes an "intelligent vehicle DTS data collection and query system". This system belongs to a multi-terminal application, including a Web end and a mobile end, integrating various data collection and query methods, aiming to improve the efficiency of data collection and data query.

[0026] During manual testing, users can input data one by one on the Web side or import an Excel file for data entry, or they can enter data while measuring on the mobile side. During automatic testing, after completing the preliminary preparations, the system can communicate with the automatic measurement device via the network, start automatic measurement with one key, and directly enter the data into the database. The system uses a structured database to store data, facilitating subsequent querying and analysis.

[0027] The system also provides multiple query methods, greatly facilitating users' information acquisition, including:

[0028] (1). Hierarchical query: Conduct hierarchical queries based on brand, vehicle series, model, region, cross-section, etc., to quickly locate the required data.

[0029] (2). Image search by image: Users can quickly find data of similar cross-sections by uploading cross-section images.

[0030] (3). Interactive Q&A: Users can conduct large model Q&A in the field based on text to obtain relevant information.

[0031] The launch of the intelligent vehicle DTS data collection and query system aims to build and manage a knowledge base of automotive DTS information, effectively improve data processing efficiency, lower the threshold of work experience, and provide more scientific and systematic support for vehicle design.

[0032] As Figure 1 shown, an intelligent vehicle DTS data collection and query system includes a cloud platform. The cloud platform is configured with a data collection port for obtaining automotive DTS data through the data collection port. The cloud platform identifies and processes the collected DTS data, and then stores the data in a database. The database uses a structured database. The cloud platform is built with servers. It forms a data collection port through software development, obtains automotive DTS data through the data collection port, and stores the collected data in the database after processing. The cloud platform is connected to the network, and users with access rights can access the cloud platform and perform query operations on the database through the query service module to obtain the required query data.

[0033] The cloud platform includes a data acquisition module. The data acquisition module is connected to the data acquisition device through a data acquisition interface. The data acquisition device supports manual and automatic acquisition of DTS data and sends the DTS data to the data acquisition module through the data acquisition interface. The data acquisition module parses and processes the uploaded DTS data to obtain storable DTS data and stores it in the database. The data acquisition module includes, but is not limited to, mobile phones, computers, and professional devices. When using a mobile phone or a computer, the DTS data is manually entered by opening a pre-set web page. When using a professional device, the data is collected and entered according to the device's usage instructions and uploaded to the cloud platform. The cloud platform is provided with a server, a database, and a data acquisition module, etc. The data acquisition module is used to collect, process, and convert the data and then store it in the database through the server. The cloud platform is built through the server and realizes the corresponding data acquisition, storage, and query functions through software service programs or software function modules.

[0034] The data acquisition device is connected to the data acquisition interface through the network. The data acquisition interface is a network service interface. Through the network service interface, the data acquisition device uploads the data to the cloud platform and sends it into the data acquisition device; the data acquisition device includes a web-side device, a mobile-side device, and / or an automatic test device, which is used to realize data entry and acquisition. Both the web-side device and the mobile-side device enter the DTS data through a pre-developed templated web page or import an Excel format file through the web-side device and the mobile-side device, and the data acquisition module parses the DTS data in the Excel format file. If it is the DTS data in the Excel format file, the corresponding DTS data in the Excel can be parsed and obtained through the parsing method of the data acquisition module.

[0035] The cloud platform is provided with a data processing module. The data processing module calculates evaluation indicators based on the collected DTS data. The evaluation indicators are used to evaluate the vehicle design and manufacturing level. Calculating the evaluation indicators based on the collected DTS data includes: DTS-related instruction indicators, DTS trend indicators of the same vehicle model, and DTS comparison indicators of different vehicle models. When using, users can evaluate the vehicle according to the indicators and provide corresponding DTS data for the subsequent upgrade and transformation of the vehicle.

[0036] Since the cloud platform stores DTS data in the database, not everyone has the right to access, query, collect, and upload, etc. operations. In order to manage the data of the cloud platform, a permission management module is set up. The permission management module manages the user accounts connected to the cloud platform and restricts and manages the permissions of users' data collection, upload, modification, and query operations.

[0037] A data query module is set up in the cloud platform. After a user with query permission accesses the cloud platform, the user sends a query request to the data query module. The query module analyzes and processes the received query request data to obtain the corresponding query result and feedback it to the user. The cloud platform records each user's access and the user's operations of data collection, upload, and query, and saves them in the form of logs, providing basic data for the subsequent traceability of DTS data and the data management of the cloud platform.

[0038] The cloud platform can not only upload the collected DTS data through a data interface, but also query the stored DTS data by sending a query request. The data query is realized through the data query module, which includes a hierarchical retrieval unit, an image search by image unit, and an interactive Q&A unit. The hierarchical retrieval unit is used to perform hierarchical positioning according to the user's request through multiple dimensions such as brand, vehicle series, vehicle model, region, and cross-section to achieve data query positioning; the image search by image unit queries the DTS data of similar images stored in the database of the cloud platform according to the image uploaded by the user's query request in a similarity manner;

[0039] The interactive Q&A unit is used to perform text queries according to the keywords input in the user's query request, analyze the user's request, and feedback the corresponding results.

[0040] The data query module also includes a data export unit, which is used to export the queried data into a preset file format according to the user's request signal, facilitating the user to obtain the required DTS data after the query.

[0041] The intelligent vehicle DTS data collection and query system is an intelligent platform designed for vehicle data collection, storage, and query, which can efficiently process and store the DTS data of vehicles, and help users obtain the required information conveniently in different scenarios. The system supports two data collection methods, automatic and manual, to meet the needs of different users, and also greatly improves the user's data acquisition efficiency through the intelligent query function. As Figure 1 shown in the functional module diagram of the intelligent vehicle DTS data collection and query system, it includes:

[0042] 1. Permission management module

[0043] Set access permissions according to the user role to ensure that users of different roles can access the system functions flexibly and securely, protecting the security and integrity of the data.

[0044] 2. Basic data maintenance module

[0045] Manage and maintain basic data, such as cross-sections, vehicles, part information, etc., ensure the accuracy and consistency of the data, and provide video tutorial support to improve the data collection efficiency.

[0046] 3. Data Acquisition Module

[0047] Supports multiple data acquisition methods (manual input, Excel import, automatic measuring devices) and communicates with devices in real time via network, automatically entering data to improve data acquisition efficiency and accuracy.

[0048] 4. Data Processing Module

[0049] Calculates key quality indicators, conducts trend analysis and vehicle model comparison to help users monitor the quality of measurement data and support quality management and design optimization.

[0050] 5. Data Query Module

[0051] Provides multiple query methods, including hierarchical retrieval, image search and interactive Q&A, to help users quickly obtain data and support data export, improving decision-making efficiency.

[0052] 6. Log Management Module

[0053] Automatically records and manages user operation logs, supports log query, exception monitoring and cleaning, improving system transparency, security and traceability.

[0054] The intelligent vehicle DTS data acquisition and query system not only effectively improves the data acquisition and analysis efficiency in the field of intelligent vehicles, but also provides strong technical support for automobile manufacturers, R & D personnel and technical support personnel, helping to accelerate the process of product R & D and quality control and enhancing the digital level of the entire industrial chain.

[0055] Equipment required to implement each step of this method: manual measuring device or automatic measuring device, mobile device or work computer.

[0056] Beneficial effects that can be achieved after adopting the method of this patent technical solution:

[0057] After adopting the method of this patent technical solution, it can greatly improve the work efficiency of users in automobile design and provide strong data support for vehicle design and production.

[0058] 1. The system integrates multiple data entry methods, improving data entry efficiency and accuracy, reducing repetitive labor, enhancing work efficiency and measurement quality. Users can select appropriate entry methods according to different scenarios and requirements, greatly improving work flexibility and facilitating the digital transformation of enterprises in measurement and management work.

[0059] 2. Through the image search by image and interactive Q&A query methods provided by the system, users do not need to have professional terms or experience. They only need to upload images or ask questions in natural language, and the system will automatically process and return corresponding accurate information, making the whole query process more intuitive and friendly, reducing users' dependence on professional knowledge, being especially suitable for novice users or scenarios where data needs to be obtained quickly, greatly simplifying the query process, and improving work efficiency.

[0060] The intelligent vehicle DTS data acquisition and query system is divided into 6 major functional modules, as Figure 1 shown:

[0061] 1. Permission management module

[0062] Permission management can set corresponding access permissions according to different user roles, involving multiple data structures such as user information tables, menu information tables, role information tables, department information tables, and position information tables. The system administrator is responsible for granting corresponding roles to users who need to use the system according to their departments and positions, and opening the corresponding module menus. The system verifies the permissions of users and opens the authorized module functions for users. This design ensures that users with different roles can flexibly and securely access the required functions, while effectively protecting the security and integrity of system data. Through this meticulous permission management, users can focus on their respective work tasks and improve the overall work efficiency.

[0063] 2. Basic data maintenance module

[0064] The basic database includes cross-section information tables, vehicle type tables, structure type tables, material type tables, part lists, dictionary information tables, etc. To ensure the normal use of the system, these basic information need to be maintained and updated regularly. Maintaining this information not only helps to ensure the accuracy and consistency of data, but also provides reliable query and analysis support for users. This systematic management will improve the overall performance of the system, ensure that users obtain accurate and timely information during use, and thus optimize the work process.

[0065] Among them, the cross-section information table is used to manage information related to cross-sections. According to different positions, cross-sections can be divided into interior and exterior trims, and are divided into multiple regions according to different parts of the vehicle. Each region contains multiple parts, and there are cross-sections between adjacent parts. The system not only provides operations such as adding, deleting, modifying, and querying region, part, and cross-section information, but also provides the function of uploading and playing operation videos. Experts can record video tutorials for DTS acquisition and upload them to the system to help novices view and learn the required skills at any time. This function not only facilitates users to manage data, but also helps users better understand and master relevant operations through video tutorials, thereby improving the efficiency and accuracy of data acquisition.

[0066] 3. Data Acquisition Module

[0067] As Figure 2 shown, the automotive DTS information acquisition module is a module used to collect and manage data related to automotive dimensional technical specifications (DTS). The main functions of this module include:

[0068] Measurement Point Setting: According to the measurement requirements, users can visually, conveniently and quickly add, delete, move and rotate measurement points on the system, and flexibly set the measurement point positions of each cross-section of the vehicle to ensure the accuracy of measurement.

[0069] Integrate Multiple Data Entry Methods: This module supports data entry methods for multiple measurement methods and can adapt to the user needs in different working scenarios. Specifically, it includes:

[0070] 1. Manual Input: Users can find the corresponding information display page of the sample vehicle according to the levels of brand, vehicle series, model and sample vehicle, and manually enter the measurement data into the system one by one.

[0071] 2. Excel File Import: The system supports the import of measurement data in multiple Excel templates. Users can directly import historical measurement files for convenient data integration and use.

[0072] 3. Direct Import from Automatic Measuring Equipment:

[0073] Before measuring the DTS information of a sample vehicle of a certain unmeasured model, users need to upload cross-section pictures one by one on the system and set information such as the name, position, nominal value, tolerance, etc. of the measurement points. This setting only needs to be done once, and subsequent sample vehicles of the same model do not need to be set repeatedly. For self-developed models, information such as the nominal value and tolerance of the measurement points will be directly obtained from the cross-section DTS design values in the system, eliminating the need to input the DTS design values of the measurement points again, breaking the barrier between design and measurement, reducing a large amount of repetitive labor, and accelerating work efficiency. In addition, users need to ensure that the network connection between the system and the automatic measuring equipment is normal for effective communication.

[0074] During measurement, users only need to click the "Start Automatic Measurement" button on the information page of the sample vehicle of this model, and the system will automatically transmit the set measurement point information to the automatic measuring equipment through the network. After receiving the measurement point information, the equipment will perform automatic measurement according to this information. When the measurement of all measurement points is completed, the equipment will automatically generate a DTS measurement information table in a fixed template and transmit it back to the system.

[0075] After receiving the DTS measurement information table, the system will automatically parse the file and store the parsed information in the measurement point information table of the database. The optimization of this process not only significantly reduces the workload of manual entry, improves work efficiency, but also enhances data consistency and measurement accuracy.

[0076] Data storage and management: The collected data will be stored in a structured manner, facilitating subsequent querying, analysis, and report generation. This storage method ensures data security and consistency, enabling users to quickly obtain the required information when needed.

[0077] Through these functions, the automotive DTS information collection module not only improves the efficiency and accuracy of data collection but also provides important technical support for automotive design and R & D.

[0078] 4. Data processing module

[0079] The main functions of the data processing module include:

[0080] Calculation of DTS-related indicators: This module can calculate key quality indicators including CP, CPK, 6σ, symmetry, parallelism, etc. to evaluate and monitor the quality and consistency of measurement data.

[0081] Trend analysis of DTS for the same vehicle model: The module supports trend analysis of DTS data for the same vehicle model, helping users identify potential problems in the design or manufacturing process and track performance change trends.

[0082] Comparison of DTS between different vehicle models: Users can conduct DTS comparisons between different vehicle models to intuitively understand the differences in dimensional technical specifications among various models, supporting more effective decision-making and design optimization.

[0083] Calculation of indicators related to self-developed vehicle models: This module can calculate the out-of-tolerance rate and qualification rate of self-developed vehicle models, further enhancing the quality monitoring ability.

[0084] Through these functions, the data processing module provides users with powerful analysis tools to help them deeply understand the data and improve the quality management level of automotive design and manufacturing.

[0085] 5. Data query module

[0086] The data query module can comprehensively query all relevant information, covering various basic data (such as matching, vehicle series, vehicle model, section, DTS design value, etc.), as well as sample vehicle measurement point measurement information, statistical information, trend analysis, and comparison research results. These functions help users deeply understand the data and its changes, providing strong support for them to make more informed decisions.

[0087] The main functions of the data query module include:

[0088] Hierarchical retrieval: Users can perform hierarchical positioning according to multiple dimensions such as brand, vehicle series, model, region, and section, so as to quickly find the required information.

[0089] Image search by image: Users can upload a section image, and the system uses an improved perceptual hashing algorithm to quickly find relevant data of similar sections, significantly improving the query efficiency.

[0090] Interactive Q&A: Based on technologies such as natural language processing and knowledge base, users can perform text queries by entering keywords. The system will automatically analyze the user's request and provide relevant information. This module is an interactive Q&A system within the field, aiming to enhance the user experience and make information acquisition more intuitive and convenient. Through natural language interaction with the system, users can quickly find the required data, enhancing the practicality and efficiency of the system.

[0091] Data export function: The system supports exporting query results to Excel or other formats, facilitating subsequent analysis and report generation by users and improving the utilization efficiency of data.

[0092] Through these functions, the data query module significantly improves the efficiency of users to obtain information, simplifies the data retrieval process, and helps with decision-making support for automotive design and manufacturing.

[0093] 6. Log management module

[0094] The functions of the log management module mainly include:

[0095] Log recording: The system automatically records detailed information of all user operations, including operations such as login, data query, data entry, modification, and deletion. Each log record contains the operation time, user ID, operation type, and specific content, facilitating subsequent auditing and tracking. This function helps analyze the reasons and backgrounds of operation errors, thereby more effectively locating and fixing problems.

[0096] Log query: Users can quickly query specific log records according to conditions such as time range, user ID, and operation type. This function helps administrators and users promptly understand the usage situation of the system and ensures a clear grasp of the operation history.

[0097] Abnormal monitoring: The module has the function of monitoring abnormal operations, can automatically identify and record abnormal behaviors, such as frequent login failures or unauthorized data access, etc., and send alerts to administrators in a timely manner to ensure the security of the system.

[0098] Log cleaning: The module supports regular cleaning of expired logs to maintain the efficient operation of the system and the cleanliness of data. At the same time, this function ensures compliance with relevant regulations on data storage and privacy protection, preventing unnecessary data accumulation.

[0099] Through these functions, the log management module not only improves the transparency and traceability of the system, but also enhances security, providing comprehensive operation records and data analysis support for users and administrators. In this way, users can better understand the system operation and ensure the stability and security of the system.

[0100] The data query module provides three query methods. Among them, hierarchical retrieval is a traditional information query method that requires users to make multiple selections to locate the specified information. This process is relatively cumbersome and inefficient. Therefore, the query module also provides two more intelligent and convenient query methods: image search by image and interactive Q&A.

[0101] As Figure 3 shown, for the image search by image query method, image search by image, that is, similar cross-section query, allows users to search for all similar images in the cloud cross-section image set by uploading a cross-section image. The system will sort these images according to the similarity and return the top M results with the highest similarity for users to view. This query method greatly improves the efficiency of information retrieval, enabling users to quickly find relevant cross-section data, thus more effectively supporting design and decision-making.

[0102] As Figure 3 shown, it mainly processes the cross-section image set stored in the cloud and the query cross-section image uploaded by the user.

[0103] For each image in the cross-section image set, the process is as follows:

[0104] 1. Image preprocessing:

[0105] Color space conversion: Convert the RGB image to a grayscale image to reduce data complexity.

[0106] Image scaling: Uniformly scale the image to 800x800 pixels to ensure consistency in subsequent processing.

[0107] Mean filtering: Apply mean filtering to remove noise in the image, make the image smoother, and improve the effect of subsequent feature extraction.

[0108] 2. Feature extraction:

[0109] Edge detection: Use the Canny edge detection algorithm to extract edge information in the image to help identify shape contours.

[0110] Feature descriptor calculation: Use the ORB algorithm to extract key points and their descriptors in the image, and these features effectively represent the uniqueness of the image.

[0111] Feature vector construction: Integrate the extracted feature descriptors into a feature vector to form the feature representation of each image.

[0112] 3. Image secondary processing:

[0113] Image secondary scaling: Scale the image to 8x8 pixels for efficient matching.

[0114] Secondary mean filtering: Apply mean filtering again to further remove noise.

[0115] Binarization: Convert the grayscale image to a black-and-white image to highlight specific features or objects for subsequent analysis.

[0116] 4. Hash value generation:

[0117] Flatten the secondarily processed image into a one-dimensional array and generate a fixed-length hash value as the unique identifier of the image.

[0118] 5. Feature index library update:

[0119] Write information such as the image ID, feature vector, and hash value into the image feature index library for quick query.

[0120] For the cross-sectional image to be queried, the process is as follows:

[0121] 1. Image upload:

[0122] Users can upload or take a clear cross-sectional picture for the system to perform similarity analysis. This step supports devices such as mobile phones to ensure the smoothness of the user experience.

[0123] 2. Image preprocessing:

[0124] Perform color space conversion, scale to 800x800 pixels, mean filtering, etc. on the uploaded picture in sequence to reduce the computational complexity and highlight the shape features, thereby improving the matching accuracy.

[0125] 3. Image secondary processing:

[0126] Perform secondary scaling to 8x8 pixels, secondary mean filtering, and binarization on the preprocessed image.

[0127] 4. Hash value generation:

[0128] Generate the hash value of the query image.

[0129] 5. Coarseness similarity calculation:

[0130] Calculate the Hamming distance between the hash value of the query image and the hash values of all images in the feature index library to obtain the coarseness similarity scores for each pair of images.

[0131] 6. Result Sorting and Extraction:

[0132] Result Sorting: Sort the matching results according to the coarseness similarity scores and select the image with the highest similarity.

[0133] Top N Result Extraction: Extract the top N matching results with the highest similarity for subsequent analysis.

[0134] 7. Feature Extraction:

[0135] Perform edge detection, feature descriptor calculation, and feature vector construction on the preprocessed image.

[0136] 8. Fineness Similarity Calculation:

[0137] Calculate the Euclidean distance between the feature vector of the query image and the feature vectors of the top N matching results to obtain the fineness similarity scores for each pair of images.

[0138] 9. Secondary Sorting and Extraction:

[0139] Sort the results of the fineness similarity calculation and extract the top M matching information.

[0140] 10. Result Display:

[0141] Integrate the relevant vehicle model information for each matching result, including brand, model, production year, DTS design value, measurement value, etc., and display it on the user interface. This not only allows users to intuitively understand the appearance of similar cross-sections but also obtain necessary background information such as materials and production processes to assist them in making decisions and design references.

[0142] Through this series of processes, users can quickly and accurately find vehicle model cross-sections similar to the target cross-section, significantly improving design efficiency and innovation ability, and helping enterprises maintain their advantages in the fierce market competition.

[0143] Interactive Q&A query method, such as Figure 4 shown,

[0144] The interactive Q&A query method is an important function in the intelligent vehicle DTS data collection and query system, aiming to provide users with a convenient information acquisition channel through natural language processing technology. Specifically, this function has the following key features:

[0145] Natural Language Understanding: Users can ask questions in natural language without the need to use complex technical terms or fixed query formats. For example, users can ask "What is the latest measured DTS pass rate of a certain vehicle model?" or "How to measure the measuring points of the headlight to the front bumper cross-section?" The system will automatically parse the user's question and extract key information.

[0146] Knowledge Base Support: The system has a rich built-in knowledge base, covering DTS standards, measurement methods, common problems and solutions of various vehicle models, etc. The interactive Q&A function can extract relevant information from the knowledge base in real time to ensure that users get accurate and timely answers.

[0147] Diverse Question Types: Users can ask various types of questions, including querying DTS measurement data of specific vehicle models; understanding the usage methods and applicable scenarios of different measurement tools; obtaining historical trends or comparative analysis information of DTS data; seeking technical support or solutions, such as "How to handle measurement errors?" etc.

[0148] Database Enhancement: The system regularly updates the knowledge base to enhance its intelligence and practicality.

[0149] User-Friendly Interface: This function is presented through an intuitive user interface. Users only need to enter their questions in the input box, and the system will return the answers in a clear format, enhancing the user experience.

[0150] Multi-Language Support: To meet the needs of different users, the system supports multiple languages to ensure that a wider user group can use it smoothly.

[0151] Interactive Suggestions: After the user asks a question, the system not only provides direct answers but also recommends relevant questions or topics to help users understand relevant information in depth. For example, when a user asks about the DTS data of a certain vehicle model, the system can recommend subsequent topics such as "The measurement method of this vehicle model" or "Comparative analysis of similar vehicle models".

[0152] Through the above features, the interactive Q&A query method can effectively improve the user's work efficiency, reduce the dependence on professional knowledge, and at the same time provide users with richer information support, promoting the rapid collection and analysis of DTS data for intelligent vehicles.

[0153] The specific query process of the interactive Q&A query method is described as follows:

[0154] Enter Query Statement: Users first enter in the system's query box what they want to know, usually in the form of a question or instruction in natural language.

[0155] Text preprocessing: The system performs preliminary text preprocessing on the user's query statement, including removing unnecessary punctuation marks, stop words (such as "de", "le", etc.), and lemmatization (converting different forms of vocabulary into their basic forms, such as "measurement" and "measured") and other processing steps to ensure that the system can understand the user's question more accurately.

[0156] Word vector conversion: The preprocessed text is converted into word vectors, which are a numerical representation form that encodes text information for machine understanding and processing.

[0157] Knowledge retrieval: The converted word vectors will be matched and retrieved with the data in the vehicle DTS knowledge base. This knowledge base contains a large amount of DTS data and related information, and the system searches the knowledge base to find the content most relevant to the user's query.

[0158] Answer generation: The system generates a suitable answer using a large language model in the DTS field based on the retrieved relevant information. This language model will comprehensively consider the information in the knowledge base as well as domain-specific terms and rules.

[0159] Answer postprocessing: After the answer is generated, the system will further process the generated answer to ensure the accuracy and comprehensibility of the answer, including optimizing the word order, adjusting the format, etc.

[0160] Answer display: The processed answer is presented to the user, and the user can perform further operations or submit new queries based on the returned results.

[0161] The implementation of this embodiment makes the acquisition and query of DTS data have the following characteristics:

[0162] 1. Provide multiple query methods to speed up the user's information acquisition efficiency: The system designs diverse query functions, enabling users to quickly find the required information in different ways. Users can perform image search by uploading cross-section pictures to quickly obtain relevant information on similar cross-sections; through interactive Q&A, interact with the system based on natural language to obtain accurate domain information; at the same time, the hierarchical query function allows users to perform precise searches according to multi-level classifications such as brand, vehicle series, and vehicle model. This flexible query method significantly improves the speed and accuracy of information retrieval and remarkably enhances the user's work efficiency.

[0163] 2. Provide multi-terminal applications to meet the needs of users in different usage scenarios: The system supports both the Web and mobile terminals, and is independently designed and implemented according to their respective usage scenarios. This multi-terminal application design enables users to easily access and use the system functions and efficiently enter data, whether in the office or at the measurement site, whether using automatic or manual collection equipment. This not only improves the user's operating experience, but also enables data collection and analysis to be carried out efficiently in various environments, fully meeting the user's flexible usage needs.

[0164] 3. Module-level permission management to meet the needs of users with different roles: The system implements detailed module-level permission management, allowing corresponding access rights to be set according to different user roles. This means that users with different roles, such as designers, data collectors, and management, can access and operate specific modules on the system according to their respective needs and responsibilities. This flexible permission management mechanism ensures data security while also improving work efficiency, allowing each user to focus on tasks within their responsibilities and effectively reducing errors or confusion caused by improper permissions.

[0165] Obviously, the specific implementation of the present invention is not limited to the above-mentioned methods. As long as various non-substantial improvements are made using the method concept and technical solution of the present invention, they are all within the protection scope of the present invention.

Claims

1. An intelligent vehicle DTS data acquisition and query system, characterized in that: It includes a cloud platform, which is configured with a data acquisition port for obtaining automotive DTS data through the data acquisition port. The cloud platform identifies and processes the acquired DTS data and then stores the data in a database, and the database uses a structured database.

2. The intelligent vehicle DTS data acquisition and query system according to claim 1, characterized in that: The cloud platform includes a data acquisition module. The data acquisition module is connected to a data acquisition device through a data acquisition interface. The data acquisition device supports manual and automatic acquisition of DTS data and sends the DTS data to the data acquisition module through the data acquisition interface. The data acquisition module parses and processes the uploaded DTS data to obtain storable DTS data and stores it in the database.

3. The intelligent vehicle DTS data acquisition and query system according to claim 2, characterized in that: The data acquisition device is connected to the data acquisition interface through a network. The data acquisition interface is a network service interface. Through the data acquisition device, data is uploaded to the cloud platform through the network service interface and sent into the data acquisition device. The data acquisition device includes a web device, a mobile device, and / or an automatic test device for data entry and acquisition.

4. The intelligent vehicle DTS data acquisition and query system according to claim 3, wherein: Both the web device and the mobile device enter DTS data through a pre-developed templated web page or import an Excel format file through the web device and the mobile device, and the data acquisition module parses the DTS data in the Excel format file.

5. The intelligent vehicle DTS data acquisition and query system according to claim 1, characterized in that: The cloud platform further includes a data processing module. The data processing module calculates evaluation indicators based on the acquired DTS data, and the evaluation indicators are used to evaluate vehicle design and manufacturing levels.

6. The intelligent vehicle DTS data acquisition and query system according to claim 5, characterized in that: Calculating evaluation indicators based on the acquired DTS data includes: DTS-related instruction indicators, DTS trend indicators for the same vehicle model, and DTS comparison indicators for different vehicle models.

7. The intelligent vehicle DTS data acquisition and query system according to claim 1, characterized in that: The cloud platform further includes a permission management module. The permission management module manages the user accounts accessing the cloud platform and restricts and manages the permissions for users' data acquisition, upload, modification, and query operations.

8. An intelligent vehicle DTS data acquisition and query system according to any one of claims 1-7, characterized in that: A data query module is set in the cloud platform. A user with query permission sends a query request to the data query module after accessing the cloud platform. The query module analyzes and processes the received query request data to obtain a corresponding query result and feedback it to the user.

9. The intelligent vehicle DTS data acquisition and query system according to claim 8, characterized in that: The data query module includes a hierarchical retrieval unit, an image search by image unit, and / or an interactive question and answer unit. The hierarchical retrieval unit is used to perform hierarchical positioning according to a user's request through multiple dimensions such as brand, vehicle series, vehicle model, region, and section to achieve data query positioning. The image search by image unit queries the DTS data of similar images stored in the database of the cloud platform in a similarity manner according to the image uploaded by the user's query request. The interactive question and answer unit is used to perform text queries according to the keywords input in the user's query request, analyze the user's request, and feedback the corresponding results.

10. The intelligent vehicle DTS data acquisition and query system according to claim 9, wherein: The data query module further includes a data export unit, which is used to export the queried data into a preset file format according to the user's request signal.

Images