A method and platform for placing orders in automobile mall

Abstract

The present invention relates to the field of automobile recommendation prediction technology, and in particular to a method and platform for placing an order in an automobile mall. The method comprises the following steps: obtaining historical browsing information data of automobile mall users and customer service consultation information data of automobile mall users, and performing user automobile preference demand analysis and user vehicle matching recommendation prediction to obtain automobile vehicles matched and recommended by the mall users; performing user interface display processing and virtual test drive space modeling on automobile vehicles matched and recommended by the mall users to obtain a virtual test drive space model of the mall display vehicle; performing virtual test drive experience analysis and recommended vehicle purchase screening processing on the virtual test drive space model of the mall display vehicle to obtain automobile vehicles adapted to be purchased by the mall users; performing intelligent quotation and ordering processing on automobile vehicles adapted to be purchased by the mall users to obtain intelligent ordering results for automobile vehicles of the automobile mall users. The present invention can realize intelligent processing of the automobile recommendation process.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile recommendation prediction, and in particular to an automobile mall ordering method and platform. Background Art

[0002] With the rapid development of Internet technology and people's increasing demand for convenient shopping experience, online car malls have become a new trend in car purchases. Online car malls can provide a convenient and fast car purchase channel. Consumers can browse multiple car brands and models through the Internet to compare and choose. In the traditional car purchase method, consumers need to go to car dealers in person to inquire, test drive and place orders, which is time-consuming and cumbersome. In addition, consumers have limited understanding of the car market and find it difficult to make wise choices. At present, some car malls have launched online ordering services, but there are still some limitations, such as inaccurate predictions of preferred vehicle recommendations and cumbersome vehicle test drive processes. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and platform for placing orders in a car mall to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for placing an order in a car mall includes the following modules:

[0005] Step S1: obtaining the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, and performing a user car preference demand analysis on the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users to obtain the car preference demand data of the mall users;

[0006] Step S2: obtaining the purchase budget data of the automobile mall user, and performing user vehicle matching recommendation prediction for the automobile mall according to the automobile preference demand data of the mall user and the purchase budget data of the automobile mall user, so as to obtain the automobile vehicle matched and recommended by the mall user; performing user interface display processing on the automobile vehicle matched and recommended by the mall user, so as to generate the interface display result of the vehicle recommended by the mall user;

[0007] Step S3: virtual test drive space modeling is performed on the interface display vehicle in the interface display result of the mall user recommended vehicle by using virtual reality technology to obtain a virtual test drive space model of the mall display vehicle; virtual test drive experience analysis is performed on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle;

[0008] Step S4: Based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended automobiles and vehicles are matched with the mall users for recommended vehicle purchase screening to obtain the automobiles and vehicles suitable for the mall users to be purchased; the automobiles and vehicles suitable for the mall users to be purchased are intelligently quoted and ordered to obtain the intelligent ordering results of the automobile mall users' automobiles and vehicles.

[0009] The present invention first collects the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, so that important information about the user's behavior and needs can be obtained. The historical browsing information data can tell the user which car pages are interested in, and the customer service consultation information data can provide detailed information about which car models the user inquires about, thereby providing a data basis guarantee for the subsequent processing process. By analyzing the user's car preference demand on the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, the user's preference for different car models, the car purchase demand and the specific insight of the potential market demand can be obtained, and the car mall is provided with important data on the user's car preference to support the work of product selection, marketing and business decision-making, thereby providing data support for the subsequent car recommendation process. Secondly, through various channels, such as user questionnaires, purchase intention expressions, etc., the purchase budget data of the car mall users is obtained, and these data will provide basic information for subsequent analysis and recommendation, thereby helping to understand the user's purchasing power and budget range. By predicting the user vehicle matching recommendation for various car models in the car mall based on the car preference demand data of the mall users and the purchase budget data of the car mall users, this step compares the user's purchase budget and the price of the recommended vehicle to screen out the car vehicles that meet the user's budget, thereby forming a list of matching recommended car vehicles for the mall users, which helps to provide users with car choices that fit the budget, enhance the user's purchase intention and satisfaction, and thus improve the prediction accuracy of the user's preferred vehicle recommendation. At the same time, by performing user interface display processing on the matching recommended car vehicles of the mall users, this step designs an intuitive and easy-to-use user interface to display the detailed information of the final recommended vehicle, including pictures, configurations, prices and other aspects, to help users better understand and choose the recommended vehicle, which will enhance the reference value of the user's purchase decision, thereby improving the sales conversion rate and user experience of the car mall. Then, by using virtual reality technology to model the virtual test drive space of the interface display vehicle in the interface display result of the mall user's recommended vehicle, it is possible to present the virtual test drive space model of the mall display vehicle, which will allow users to experience the real scene of driving the vehicle in a virtual environment and provide a more intuitive car buying experience, thereby avoiding the tedious process of users going to offline test drives. By conducting a virtual test drive experience analysis on the virtual test drive space model of the vehicle displayed in the mall, we can collect user behavior data, feeling feedback and other information during the virtual test drive process, so as to evaluate the user's satisfaction, comfort and other aspects of the test drive experience. The analysis of this step will help optimize the virtual test drive system, thereby improving the user's car buying experience and satisfaction.Finally, based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended vehicles are matched and screened for purchase by the mall users to exclude vehicles that do not meet the user's preferences and needs. In this way, the mall users can obtain the vehicles to be purchased. The processing process of this step will help users narrow down the scope of car purchases and only keep the vehicle selections that meet their preferences and needs. By making intelligent quotations for the vehicles to be purchased by the mall users, the preferential quotations for each vehicle are calculated using intelligent algorithms according to the user's customized configuration requirements and market conditions, including relevant discounts, preferential activities, etc. This will help users understand the price advantages of each vehicle and conduct corresponding car purchase signing and order processing, so as to provide users with customized car purchase contracts and orders according to their choices and wishes, and complete the corresponding ordering process, which will help users successfully complete the car purchase procedures, thereby obtaining the intelligent ordering results of the car mall and realizing the quick car purchase experience of the car mall.

[0010] Preferably, the present invention further provides a car mall ordering platform, which is used to execute the car mall ordering method as described above, and the car mall ordering platform comprises:

[0011] The car preference demand analysis module of the shopping mall user is used to obtain the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, and to analyze the user's car preference demand on the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, so as to obtain the car preference demand data of the shopping mall user;

[0012] The user recommended vehicle interface display module is used to obtain the purchase budget data of the car mall user, and make user vehicle matching recommendation predictions for the car mall based on the car preference demand data of the mall user and the purchase budget data of the car mall user, so as to obtain the car vehicles matched and recommended by the mall user; perform user interface display processing on the car vehicles matched and recommended by the mall user, so as to generate the interface display results of the vehicle recommended by the mall user;

[0013] The display vehicle virtual test drive analysis module is used to perform virtual test drive space modeling on the interface display vehicle in the display result of the mall user recommended vehicle interface through virtual reality technology to obtain the virtual test drive space model of the mall display vehicle; perform virtual test drive experience analysis on the virtual test drive space model of the mall display vehicle, so as to obtain the virtual test drive user experience data of the mall display vehicle;

[0014] The intelligent ordering module for vehicles suitable for purchase by users is used to perform recommended vehicle purchase screening processing on matching recommended vehicles for mall users based on user experience data of virtual test drives of vehicles displayed in the mall, and obtain vehicles suitable for purchase by mall users; and to perform intelligent quotation and ordering processing on vehicles suitable for purchase by mall users, so as to obtain intelligent ordering results for vehicles of automobile mall users.

[0015] In summary, the present invention provides a car mall ordering platform, which consists of a mall user car preference demand analysis module, a user recommended vehicle interface display module, a displayed vehicle virtual test drive analysis module and a user adapted vehicle to be purchased intelligent ordering module, which can implement any car mall ordering method described in the present invention, and is used to combine the operations between computer programs running on various modules to implement any car mall ordering method. The internal structures of the platform cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient car mall ordering process, thereby simplifying the operation process of the car mall ordering platform based on data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0017] Figure 1 A schematic diagram of the steps of the method for placing an order in the automobile mall of the present invention;

[0018] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0019] Figure 3 for Figure 2 Detailed step flow chart of step S13 in FIG. DETAILED DESCRIPTION

[0020] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0022] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0023] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for placing an order in a car mall, the method comprising the following modules:

[0024] Step S1: obtaining the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, and performing a user car preference demand analysis on the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users to obtain the car preference demand data of the mall users;

[0025] Step S2: obtaining the purchase budget data of the automobile mall user, and performing user vehicle matching recommendation prediction for the automobile mall according to the automobile preference demand data of the mall user and the purchase budget data of the automobile mall user, so as to obtain the automobile vehicle matched and recommended by the mall user; performing user interface display processing on the automobile vehicle matched and recommended by the mall user, so as to generate the interface display result of the vehicle recommended by the mall user;

[0026] Step S3: virtual test drive space modeling is performed on the interface display vehicle in the interface display result of the mall user recommended vehicle by using virtual reality technology to obtain a virtual test drive space model of the mall display vehicle; virtual test drive experience analysis is performed on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle;

[0027] Step S4: Based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended automobiles and vehicles are matched with the mall users for recommended vehicle purchase screening to obtain the automobiles and vehicles suitable for the mall users to be purchased; the automobiles and vehicles suitable for the mall users to be purchased are intelligently quoted and ordered to obtain the intelligent ordering results of the automobile mall users' automobiles and vehicles.

[0028] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the method for placing an order in a car mall of the present invention. In this example, the method for placing an order in a car mall includes the following steps:

[0029] Step S1: obtaining the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, and performing a user car preference demand analysis on the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users to obtain the car preference demand data of the mall users;

[0030] The embodiment of the present invention obtains the historical browsing information data of the users of the auto mall by collecting the historical browsing information data of the users of the auto mall from the database of the auto mall, including the pages browsed by the users on the mall website and the browsing time and other related information. At the same time, the customer service consultation information data of the users is obtained, including the questions consulted by the users, the time point and the interaction records with the customer service, etc., thereby obtaining the customer service consultation information data of the users of the auto mall. Secondly, by using statistical analysis methods to evaluate the browsing dwell time of the analyzed auto mall user historical browsing information data, the browsing dwell time and frequency of different pages are calculated to evaluate the average browsing dwell time preference of users for different pages, that is, the average length of time users stay on the page. At the same time, by evaluating and analyzing the user consultations of different car models based on the analyzed auto mall user customer service consultation information data, the number of consultations of different car models and the interactive records with user consultations are statistically analyzed to evaluate the user's preference for different car models. Then, by combining the average browsing dwell time preference of different car pages in the auto mall and the user consultation preference degree of different car models in the auto mall, the user car preference demand analysis is performed on the corresponding car models in the auto mall, so as to comprehensively consider the user's browsing dwell preference for different pages and the consultation preference for different car models, and obtain the user's preference demand for different car types and functions, including the user's preference degree for different car models, car purchase demand and specific insights into the potential market demand, and finally obtain the mall user car preference demand data.

[0031] Step S2: obtaining the purchase budget data of the automobile mall user, and performing user vehicle matching recommendation prediction for the automobile mall according to the automobile preference demand data of the mall user and the purchase budget data of the automobile mall user, so as to obtain the automobile vehicle matched and recommended by the mall user; performing user interface display processing on the automobile vehicle matched and recommended by the mall user, so as to generate the interface display result of the vehicle recommended by the mall user;

[0032] The embodiment of the present invention collects the purchase budget data of the mall users through various ways, such as user questionnaires, purchase intention expressions, etc., including the specific car purchase budget amount of the users and the information such as installment payment and loan amount, and determines the purchase budget of each user, thereby obtaining the purchase budget data of the automobile mall users. At the same time, by analyzing the corresponding user's demand data on automobile preferences obtained by the automobile mall, including information on brand, model, color, function, etc., and combining the analyzed automobile mall user purchase budget data, a matching analysis of automobile vehicles is performed to match and filter out automobile vehicle options that meet the user's purchase budget ability, and further filter the recommended vehicles by fully considering the user's loan, installment payment, etc., to ensure that the user's purchase budget can cover the price range of the selected vehicle, thereby obtaining the matching recommended automobile vehicles for the mall users. Then, by displaying the relevant information of these vehicles on the mall user interface according to the selected matching recommended automobile vehicles, the information may include photos, detailed descriptions, prices, configurations, etc. of the vehicles, and through appropriate interface design and display methods, users can intuitively browse and compare these vehicle options, and finally generate the display results of the mall user recommended vehicle interface.

[0033] Step S3: virtual test drive space modeling is performed on the interface display vehicle in the interface display result of the mall user recommended vehicle by using virtual reality technology to obtain a virtual test drive space model of the mall display vehicle; virtual test drive experience analysis is performed on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle;

[0034] The embodiment of the present invention uses virtual reality technology to model and render the virtual test drive space of the interface display vehicle in the interface display result of the recommended vehicle by the mall user, so as to construct a three-dimensional space model of the corresponding display vehicle and present the vehicle model as a realistic virtual scene by adding details such as lighting, material, texture, etc. At the same time, according to the user's operation and input, through real-time interaction with the virtual reality device, the user can simulate the actual driving experience in the virtual scene, ensuring that the user can feel the spatial structure and driving experience of the mall recommended vehicle in the virtual test drive, thereby obtaining the virtual test drive space model of the mall display vehicle. Then, by recording the operation behavior and feedback data of the mall user in the virtual test drive, including data on acceleration, braking, steering, speed perception, comfort, etc., and analyzing and evaluating these data, the user's feelings and evaluation of the mall recommended vehicle in the virtual test drive are analyzed and understood, and finally the virtual test drive user experience data of the mall display vehicle is obtained.

[0035] Step S4: Based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended automobiles and vehicles are matched with the mall users for recommended vehicle purchase screening to obtain the automobiles and vehicles suitable for the mall users to be purchased; the automobiles and vehicles suitable for the mall users to be purchased are intelligently quoted and ordered to obtain the intelligent ordering results of the automobile mall users' automobiles and vehicles.

[0036] The embodiment of the present invention first evaluates and analyzes the collected user experience data of virtual test drive of vehicles displayed in the mall (including user's test drive time, mileage, ride comfort, acceleration performance, handling stability and other experience data) by using technical means such as statistical analysis or machine learning, so as to evaluate the satisfaction degree of the virtual test drive experience of each matched recommended automobile vehicle, and screens the corresponding mall user-matched recommended automobile vehicles for purchase by combining the virtual test drive experience satisfaction degree obtained by the analysis, so as to sort the recommended vehicles according to the user's satisfaction degree with the test drive experience of each recommended vehicle, and find out the vehicles with higher satisfaction, and determine them as the automobile vehicles to be purchased that are adapted for the user, thereby obtaining the automobile vehicles to be purchased that are adapted for the mall user. Secondly, by customizing the selected vehicle and querying the relevant preferential policies and promotional activities, the applicable preferential amount or discount is calculated based on the preferential policies and promotional activities obtained by the query, and then it is calculated with the price of the customized configured vehicle to calculate the preferential quotation for each vehicle. Then, the user's purchase intention for the vehicle is confirmed based on the user's satisfaction with the suitable vehicle and the preferential quotation. At the same time, the relevant vehicle purchase information is sorted and checked, including the purchase model, configuration options, price, etc., to generate the corresponding vehicle purchase contract and order. After the user confirms that it is correct, the vehicle purchase signing and ordering process is completed, and finally the intelligent ordering result of the car mall user's vehicle is obtained.

[0037] The present invention first collects the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, so that important information about the user's behavior and needs can be obtained. The historical browsing information data can tell the user which car pages are interested in, and the customer service consultation information data can provide detailed information about which car models the user inquires about, thereby providing a data basis guarantee for the subsequent processing process. By analyzing the user's car preference demand on the historical browsing information data of the car mall users and the customer service consultation information data of the car mall users, the user's preference for different car models, the car purchase demand and the specific insight of the potential market demand can be obtained, and the car mall is provided with important data on the user's car preference to support the work of product selection, marketing and business decision-making, thereby providing data support for the subsequent car recommendation process. Secondly, through various channels, such as user questionnaires, purchase intention expressions, etc., the purchase budget data of the car mall users is obtained, and these data will provide basic information for subsequent analysis and recommendation, thereby helping to understand the user's purchasing power and budget range. By predicting the user vehicle matching recommendation for various car models in the car mall based on the car preference demand data of the mall users and the purchase budget data of the car mall users, this step compares the user's purchase budget and the price of the recommended vehicle to screen out the car vehicles that meet the user's budget, thereby forming a list of matching recommended car vehicles for the mall users, which helps to provide users with car choices that fit the budget, enhance the user's purchase intention and satisfaction, and thus improve the prediction accuracy of the user's preferred vehicle recommendation. At the same time, by performing user interface display processing on the matching recommended car vehicles of the mall users, this step designs an intuitive and easy-to-use user interface to display the detailed information of the final recommended vehicle, including pictures, configurations, prices and other aspects, to help users better understand and choose the recommended vehicle, which will enhance the reference value of the user's purchase decision, thereby improving the sales conversion rate and user experience of the car mall. Then, by using virtual reality technology to model the virtual test drive space of the interface display vehicle in the interface display result of the mall user's recommended vehicle, it is possible to present the virtual test drive space model of the mall display vehicle, which will allow users to experience the real scene of driving the vehicle in a virtual environment and provide a more intuitive car buying experience, thereby avoiding the tedious process of users going to offline test drives. By conducting a virtual test drive experience analysis on the virtual test drive space model of the vehicle displayed in the mall, we can collect user behavior data, feeling feedback and other information during the virtual test drive process, so as to evaluate the user's satisfaction, comfort and other aspects of the test drive experience. The analysis of this step will help optimize the virtual test drive system, thereby improving the user's car buying experience and satisfaction.Finally, based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended vehicles are matched and screened for purchase by the mall users to exclude vehicles that do not meet the user's preferences and needs. In this way, the mall users can obtain the vehicles to be purchased. The processing process of this step will help users narrow down the scope of car purchases and only keep the vehicle selections that meet their preferences and needs. By making intelligent quotations for the vehicles to be purchased by the mall users, the preferential quotations for each vehicle are calculated using intelligent algorithms according to the user's customized configuration requirements and market conditions, including relevant discounts, preferential activities, etc. This will help users understand the price advantages of each vehicle and conduct corresponding car purchase signing and order processing, so as to provide users with customized car purchase contracts and orders according to their choices and wishes, and complete the corresponding ordering process, which will help users successfully complete the car purchase procedures, thereby obtaining the intelligent ordering results of the car mall and realizing the quick car purchase experience of the car mall.

[0038] Preferably, step S1 comprises the following steps:

[0039] Step S11: Acquire the historical browsing information data of the automobile mall user and the customer service consultation information data of the automobile mall user;

[0040] Step S12: extracting the user cursor browsing behavior and browsing interaction time of the automobile mall user historical browsing information data to obtain the automobile mall user cursor browsing behavior data and the automobile mall user browsing interaction time;

[0041] Step S13: Car browsing dwell evaluation analysis is performed based on the car mall user cursor browsing behavior data and the car mall user browsing interaction time to obtain the average browsing dwell preference time of different car pages in the car mall;

[0042] Step S14: Car model consultation evaluation and analysis is performed on the car mall user customer service consultation information data to obtain user consultation preference levels for different car models in the car mall;

[0043] Step S15: analyzing the user car preference demand of the car mall according to the average browsing dwelling preference time of different car pages in the car mall and the user consultation preference degree of different car models in the car mall to obtain the car preference demand data of the mall users.

[0044] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0045] Step S11: Acquire the historical browsing information data of the automobile mall user and the customer service consultation information data of the automobile mall user;

[0046] The embodiment of the present invention obtains the historical browsing information data of the users of the auto mall by collecting the historical browsing information data of the users of the auto mall from the database of the auto mall, including the pages browsed by the users on the mall website and the browsing time and other related information. At the same time, the customer service consultation information data of the users is obtained, including the questions consulted by the users, the time point and the interaction records with the customer service, and finally the customer service consultation information data of the users of the auto mall is obtained.

[0047] Step S12: extracting the user cursor browsing behavior and browsing interaction time of the automobile mall user historical browsing information data to obtain the automobile mall user cursor browsing behavior data and the automobile mall user browsing interaction time;

[0048] The embodiment of the present invention uses a statistical analysis method to analyze the historical browsing information data of automobile mall users to extract the user's cursor browsing behavior and browsing interaction time data therefrom, and understand the user's specific behavior and browsing interaction time when browsing the automobile mall, such as the mouse movement trajectory, click behavior and the specific interaction time length of the entire browsing process, and finally obtain the automobile mall user's cursor browsing behavior data and the automobile mall user's browsing interaction time.

[0049] Step S13: Car browsing dwell evaluation analysis is performed based on the car mall user cursor browsing behavior data and the car mall user browsing interaction time to obtain the average browsing dwell preference time of different car pages in the car mall;

[0050] The embodiment of the present invention evaluates and analyzes the browsing residence time of different automobile pages in the automobile mall by combining the analyzed automobile mall user cursor browsing behavior data and the automobile mall user browsing interaction time, so as to calculate the browsing residence time and frequency of different pages to evaluate the user's preference for different pages. At the same time, for each page, the user's average browsing residence preference time is calculated by using the arithmetic average calculation method, that is, the average length of time the user stays on the page, and finally the browsing residence preference average time of different automobile pages in the automobile mall is obtained.

[0051] Step S14: Car model consultation evaluation and analysis is performed on the car mall user customer service consultation information data to obtain user consultation preference levels for different car models in the car mall;

[0052] The embodiment of the present invention evaluates and analyzes user inquiries for different car models based on the analyzed car mall user customer service consultation information data, so as to statistically analyze the number of inquiries for different car models and the interaction records with user inquiries to evaluate user preferences for different car models, and finally obtain the user consultation preference degree for different car models in the car mall.

[0053] Step S15: analyzing the user car preference demand of the car mall according to the average browsing dwelling preference time of different car pages in the car mall and the user consultation preference degree of different car models in the car mall to obtain the car preference demand data of the mall users.

[0054] The embodiment of the present invention conducts a demand analysis of user car preferences for corresponding car models in the car mall by combining the average browsing dwelling preference time of different car pages in the car mall and the user consultation preference degree of different car models in the car mall, so as to comprehensively consider the user's browsing dwelling preference for different pages and the consultation preference for different car models, and derive the user's preference demand for different car types and functions, including the user's preference degree for different car models, car purchase demand and potential market demand. Specific insights, and finally obtain the mall user car preference demand data.

[0055] The present invention first collects the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, so as to obtain important information about the user's behavior and needs. The historical browsing information data can tell the user which car pages are interested in, and the customer service consultation information data can provide detailed information about which car models the user inquires about, thereby providing a data basis guarantee for the subsequent processing process. Secondly, the user's cursor browsing behavior and browsing interaction time extraction processing is performed on the historical browsing information data of the car mall user to extract the user's cursor browsing behavior and browsing interaction time data. This step can understand the user's specific behavior and browsing interaction time when browsing the car mall, such as the mouse movement trajectory, click behavior and the specific interaction time length of the entire browsing process, by analyzing the user's cursor browsing behavior and browsing interaction time. Then, the car browsing stay evaluation analysis is performed according to the car mall user's cursor browsing behavior data and the car mall user's browsing interaction time, so as to evaluate and quantify the average browsing stay preference time of different car pages. Through this analysis, the user's interest in different car pages can be understood, thereby understanding the user's attention to various car models and traffic distribution. Next, we conduct an automobile model consultation evaluation and analysis on the automobile mall user customer service consultation information data to understand the user's consultation preference for different automobile models. This step can be used to analyze the user's consultation behavior and the specific models they inquire about, and thus the user's attention and preference for various models can be obtained. This information is very important for understanding user needs and market trends. Finally, by analyzing the user's automobile preference demand for the automobile mall based on the average browsing dwelling preference time of different automobile pages in the automobile mall and the user consultation preference for different automobile models in the automobile mall, we can obtain specific insights into the user's preference for different models, car purchase needs, and potential market demand, and provide the automobile mall with important data on user automobile preferences to support product selection, marketing promotion, and business decision-making, thereby providing data support for the subsequent automobile recommendation process.

[0056] Preferably, step S13 comprises the following steps:

[0057] Step S131: performing cursor motion trajectory simulation analysis on the automobile mall user's cursor browsing behavior data to obtain the automobile mall user's cursor browsing motion simulation trajectory;

[0058] Step S132: performing motion speed decay analysis on the simulated trajectory of the automobile mall user's cursor browsing motion to obtain the automobile mall user's cursor browsing decay speed;

[0059] Step S133: monitoring the motion range of the automobile mall user's cursor browsing motion simulation trajectory to obtain the automobile mall user's cursor browsing page range area;

[0060] Step S134: Based on the decay speed of the car mall user's cursor browsing, a cursor browsing stay degree calculation formula is used to perform stay statistics calculation on the car mall user's cursor browsing page range area to obtain the car mall user's cursor browsing stay degree;

[0061] Step S135: Based on the degree of cursor browsing of the automobile mall user, a retention area recognition analysis is performed on the range area of ​​the automobile mall user's cursor browsing page to obtain the retention area of ​​the automobile mall user's cursor browsing page; based on the automobile mall user's cursor browsing behavior data, a browsing frequency statistical analysis is performed on the retention area of ​​the automobile mall user's cursor browsing page to obtain the browsing frequency of each browsing page retention area;

[0062] Step S136: Perform a statistical analysis of the browsing preference time according to the browsing interaction time of the automobile mall users and the browsing frequency of each browsing page stay area to obtain the average browsing preference time of different automobile pages in the automobile mall.

[0063] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S13 in FIG. 1 . In this embodiment, step S13 includes the following steps:

[0064] Step S131: performing cursor motion trajectory simulation analysis on the automobile mall user's cursor browsing behavior data to obtain the automobile mall user's cursor browsing motion simulation trajectory;

[0065] The embodiment of the present invention obtains the cursor browsing behavior data of the car mall user, including the position and time point of the cursor on the web page, and connects the continuous position points according to these data to form a motion trajectory, thereby simulating the user's cursor motion trajectory, and finally obtaining the car mall user's cursor browsing motion simulation trajectory.

[0066] Step S132: performing motion speed decay analysis on the simulated trajectory of the automobile mall user's cursor browsing motion to obtain the automobile mall user's cursor browsing decay speed;

[0067] The embodiment of the present invention calculates the movement speed of the user cursor by calculating the movement speed of the simulated trajectory of the browsing movement of the automobile mall user cursor, and draws a change curve according to the calculated movement speed, and analyzes the speed change and extrapolation trend of different series intervals according to the drawn change curve, and then analyzes and understands the speed decay between the curves of different series intervals according to the speed change and extrapolation trend of different series intervals obtained by analysis, and finally obtains the browsing decay speed of the automobile mall user cursor.

[0068] Step S133: monitoring the motion range of the automobile mall user's cursor browsing motion simulation trajectory to obtain the automobile mall user's cursor browsing page range area;

[0069] The embodiment of the present invention determines the browsing range of the user's cursor on the automobile mall page by monitoring and analyzing the horizontal and vertical movement range of the cursor on the page, so as to understand the user's browsing behavior on the page and the degree of attention paid to different areas, and help determine the main area browsed by the user on the page, and finally obtain the page range area of ​​the automobile mall user's cursor browsing.

[0070] Step S134: Based on the decay speed of the car mall user's cursor browsing, a cursor browsing stay degree calculation formula is used to perform stay statistics calculation on the car mall user's cursor browsing page range area to obtain the car mall user's cursor browsing stay degree;

[0071] The embodiment of the present invention forms a suitable cursor browsing stay degree calculation formula by combining the start time, end time, time variable parameter, number of elements, element item index parameter, car mall user cursor browsing decay speed, element stay influence weight, content complexity, page attractiveness, navigation effect parameter and related parameters of the car mall user cursor browsing page range area to perform stay statistics calculation on the car mall user cursor browsing page range area, so as to quantitatively calculate the user's browsing stay degree in different areas, and finally obtain the car mall user cursor browsing stay degree.

[0072] Step S135: Based on the degree of cursor browsing of the automobile mall user, a retention area recognition analysis is performed on the range area of ​​the automobile mall user's cursor browsing page to obtain the retention area of ​​the automobile mall user's cursor browsing page; based on the automobile mall user's cursor browsing behavior data, a browsing frequency statistical analysis is performed on the retention area of ​​the automobile mall user's cursor browsing page to obtain the browsing frequency of each browsing page retention area;

[0073] The embodiment of the present invention compares and judges the calculated degree of user cursor browsing of the automobile mall according to the preset browsing dwelling threshold value, so as to identify the automobile mall user cursor browsing page range area corresponding to the automobile mall user cursor browsing degree greater than or equal to the browsing dwelling threshold value, that is, the main area where the user stays on the automobile mall page, thereby obtaining the automobile mall user cursor browsing page dwelling area. Then, by combining the automobile mall user cursor browsing behavior data obtained by analysis, the corresponding automobile mall user cursor browsing page dwelling area is statistically analyzed for the number of browsing times, so as to understand the user's browsing times and preferences for different areas, and finally obtain the browsing frequency of each browsing page dwelling area.

[0074] Step S136: Perform a statistical analysis of the browsing preference time according to the browsing interaction time of the automobile mall users and the browsing frequency of each browsing page stay area to obtain the average browsing preference time of different automobile pages in the automobile mall.

[0075] The embodiment of the present invention statistically analyzes the browsing dwell time on each browsing page dwell area according to the analyzed automobile mall user browsing interaction time, and performs arithmetic average analysis on the analyzed browsing dwell time by using the browsing frequency of each browsing page dwell area to calculate the average browsing time of different page dwell areas, and understand the user's browsing dwell preference for different pages of the automobile mall, and finally obtain the average browsing dwell preference time of different automobile pages in the automobile mall.

[0076] The present invention firstly simulates and analyzes the cursor motion trajectory of the user's cursor browsing behavior data of the car mall, so as to understand the cursor motion trajectory of the user when browsing the page, that is, the path of the cursor moving from one position to another. By performing motion speed decay analysis on the simulated trajectory of the cursor browsing motion of the car mall user, this step can understand the decay change of the speed of the cursor motion of the user during the browsing process through decay analysis, which can also help understand the user's interest in different pages and the changing trend of the dwell time, thereby providing basic data guarantee for the subsequent dwell time statistical process. Secondly, by monitoring the motion range of the simulated trajectory of the cursor browsing motion of the car mall user, the motion range area of ​​the cursor of the user during the browsing process can be obtained, which can also help determine the main area of ​​the user browsing on the page, so as to better understand the user's focus and behavior. Then, by using a suitable cursor browsing dwell degree calculation formula based on the decay speed of the cursor browsing of the car mall user to perform a dwell statistical calculation on the range area of ​​the cursor browsing page of the car mall user, the degree of the user's browsing dwell in different areas can be obtained, so as to understand the user's attention distribution and preference degree for different page areas. Next, by performing a retention area identification analysis on the range of the car mall user cursor browsing pages based on the degree of retention of the car mall user cursor, the specific area where the user stays for a long time when browsing the page can be determined through this analysis. At the same time, by performing a browsing frequency statistical analysis on the retention area of ​​the car mall user cursor browsing pages based on the car mall user cursor browsing behavior data, it is possible to understand the number of times and preferences of users for different areas. Finally, by performing a browsing retention preference time statistical analysis based on the browsing interaction time of the car mall user and the browsing frequency of the retention area of ​​each browsing page, the average browsing retention preference time of different car pages can be obtained, which can help understand the user's attention and interest level for different pages, and then understand the user's interest level in different car pages, and thus understand the user's attention to various car models and traffic distribution.

[0077] Preferably, step S132 includes the following steps:

[0078] Performing a motion speed change trend analysis on the simulated trajectory of the user's cursor browsing motion in the car mall to obtain the user's cursor browsing motion speed change trend data; drawing a speed change curve on the user's cursor browsing motion speed change trend data to obtain the user's cursor browsing motion speed change curve;

[0079] The embodiment of the present invention collects the simulated trajectory of the user's cursor browsing motion on the car mall webpage, including the position of the cursor on the time axis and the corresponding time point, and obtains the user's cursor browsing motion speed by using a statistical analysis method to calculate the distance and time difference between adjacent positions. At the same time, a trend analysis is performed on the analyzed motion speed using a time series change analysis method to understand the change of the user's cursor motion speed during the browsing process, such as the trend of acceleration, deceleration or maintaining stability, thereby obtaining the user's cursor browsing motion speed change trend data. Then, the user's cursor browsing motion speed change trend data obtained by the analysis is plotted by using a corresponding visualization tool to draw a speed change curve, wherein time is used as the horizontal axis and speed is used as the vertical axis, and a curve graph representing the user's cursor browsing speed change is drawn, and finally a user's cursor browsing motion speed change curve is obtained.

[0080] Preferably, based on the user cursor browsing motion speed change trend data, the user cursor browsing motion speed change curve is subjected to speed change transition point identification and analysis to obtain the user cursor browsing motion speed change transition point; the user cursor browsing motion speed change curve is subjected to curve division according to the user cursor browsing motion speed change transition point to obtain the user cursor speed change grouping curve;

[0081] The embodiment of the present invention analyzes the user cursor browsing motion speed change curve by combining the analyzed user cursor browsing motion speed change trend data using a threshold method or a mutation detection algorithm, so as to identify the speed change transition points therein according to the speed change amplitude and change trend, and these transition points are the positions where the speed changes from fast to slow or from slow to fast, thereby obtaining the user cursor browsing motion speed change transition points. Then, the user cursor browsing motion speed change curve is divided into different curve intervals according to the areas between the identified user cursor browsing motion speed change transition points, and finally the user cursor speed change grouping curve is obtained.

[0082] Preferably, an extrapolation trend analysis is performed on the grouped curve of the user cursor speed change to obtain the grouped curve speed change extrapolation trend data; a speed change series interval is calculated on the grouped curve of the user cursor speed change according to the grouped curve speed change extrapolation trend data to obtain the grouped cursor speed change series interval;

[0083] The embodiment of the present invention uses regression analysis or trend line fitting methods to identify and analyze the extrapolation trend of the user cursor speed change group curve to infer the speed change trend of the curve in the future, and predict the extrapolation trend change of the user's cursor speed during browsing, thereby obtaining the group curve speed change extrapolation trend data. Then, by calculating the speed change series interval for each group curve based on the group curve speed change extrapolation trend data obtained by analysis, similar speed change curves are classified into the same series interval according to the speed change trend and amplitude, and help understand the different levels of the user's cursor speed change to further analyze the user's browsing behavior, and finally obtain the group cursor speed change series interval.

[0084] Preferably, the user cursor speed change grouping curve is subjected to speed decay analysis between groups according to the group cursor speed change series interval and the group curve speed change extrapolation trend data, so as to obtain the car mall user cursor browsing decay speed.

[0085] The embodiment of the present invention performs speed change decay analysis between each group on the corresponding user cursor speed change group curve by combining the group cursor speed change level interval and the group curve speed change extrapolation trend data obtained by analysis, so as to analyze the speed change and extrapolation trend of different level intervals to understand the speed decay between curves of different level intervals, and finally obtain the car mall user cursor browsing decay speed.

[0086] The present invention firstly analyzes the change trend of the motion speed of the user's cursor browsing motion simulation trajectory of the car mall to obtain the change trend data of the cursor browsing speed. By analyzing these data, the change of the cursor motion speed of the user during the browsing process can be understood, such as the trend of acceleration, deceleration or maintaining stability. By drawing the speed change curve of the user's cursor browsing motion speed change trend data, the speed change trend curve can be drawn by using a corresponding curve drawing tool. In this step, by drawing the curve, the change of the user's cursor browsing speed can be intuitively observed, and the existing speed change mode and trend can be captured. Secondly, based on the user's cursor browsing motion speed change trend data, the user's cursor browsing motion speed change curve is analyzed by speed change transition point identification to identify the speed change transition point in the curve graph. By identifying these transition points, the position and time at which the user's speed changes significantly during the browsing process can be determined, so as to understand the user's attention transfer and the important elements on the web page. In addition, by dividing the user's cursor browsing motion speed change curve according to the user's cursor browsing motion speed change transition point, the cursor speed change can be divided into different parts, which is convenient for subsequent analysis and research on the characteristics and influencing factors of each part. Then, by performing an extrapolation trend analysis on the user cursor speed change group curve, the speed change trend of the curve in the future can be inferred. This step can predict the extrapolation trend change of the user's cursor speed during browsing through extrapolation analysis, thereby providing a basis and reference for the subsequent speed decay analysis. Next, by calculating the speed change series interval of the user cursor speed change group curve according to the extrapolation trend data of the group curve speed change, the speed change group curve can be divided into different series intervals, and a hierarchical speed change index can be formed to better represent the degree of change of the user's cursor speed. Finally, by performing inter-group speed decay analysis on the user cursor speed change group curve according to the group cursor speed change series interval and the extrapolation trend data of the group curve speed change, the speed decay between curves of different series intervals can be analyzed. At the same time, the speed decay speed of the user's cursor browsing in the car mall can be obtained, which helps to understand the intensity and duration of the speed change of the user during browsing, so as to further understand the user's behavior pattern and attention changes.

[0087] Preferably, the calculation formula for the cursor browsing dwelling degree in step S134 is specifically:

[0088] In the formula, The degree of cursor browsing of users in the car mall. The starting time when the user's cursor stays in the page browsing range of the car mall. The end time of the user's cursor browsing page range in the car mall. is the time variable parameter, The number of elements in the page browsed by the car mall user. is the element item index parameter, For car mall users browsing the page The stay influence weight of each element, For in time The decay speed of the user's cursor browsing in the car mall at For car mall users browsing the page The complexity of the content of each element, For car mall users browsing the page The page attractiveness of each element, For car mall users browsing the page The navigation effect parameters of the element, It is the correction factor for the degree of cursor browsing of automobile mall users.

[0089] The present invention obtains a cursor browsing stay degree calculation formula by using a specific mathematical model and verifying it, which is used to perform stay statistics calculation on the range area of ​​the cursor browsing page of the automobile mall user. The cursor browsing stay degree calculation formula comprehensively considers the influence of multiple factors on the cursor browsing stay degree, including the stay influence weight, the cursor browsing decay speed, the content complexity, the page attractiveness and the navigation effect parameters, etc. These factors together determine the degree to which the user stays in a specific page area. Secondly, the time variable parameter is also introduced in the formula, and the cursor browsing stay degree can be calculated as time changes, which enables the formula to take into account the differences in the cursor browsing behavior of users in different time periods. The element item index parameter in the formula enables the formula to be applicable to multiple elements in different pages, and each element can be indexed to calculate the stay influence weight. In addition, the correction coefficient in the formula can correct the calculation result, which helps to further adjust the calculation result of the cursor browsing stay degree, so that the result is more accurate. Therefore, the formula for calculating the degree of cursor browsing retention can comprehensively consider multiple factors, and introduce time variable parameters and element item index parameters, making the formula highly flexible and adaptable. This formula can calculate the degree of stay of car mall users in different page areas, thereby providing basic data support for subsequent identification of retention areas and statistical analysis of browsing frequency. In summary, this formula fully considers the degree of cursor browsing retention of car mall users. The starting time when the user's cursor stays in the car mall page browsing range The end time of the user's cursor browsing page range in the car mall , time variable parameter , the number of elements in the page browsed by car mall users , element item index parameter , the first page that users browse in the car mall The influence weight of the element , at time The decay speed of the user's cursor browsing in the car mall at , the first page that users browse in the car mall The complexity of the content of the element , the first page that users browse in the car mall The attractiveness of the page elements , the first page that users browse in the car mall Navigation effect parameters for elements , the correction factor of the user's cursor browsing duration in the car mall , based on the degree of cursor browsing of car mall users The correlation between the above parameters constitutes a functional relationship This formula can realize the statistical calculation process of the stay of the car mall user's cursor browsing page range area, and at the same time, the correction coefficient of the car mall user's cursor browsing stay degree is used The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for the cursor browsing stay degree.

[0090] Preferably, step S14 comprises the following steps:

[0091] Step S141: performing automobile model vocabulary mining analysis on the automobile mall user customer service consultation information data to obtain an automobile model vocabulary set consulted by automobile mall users;

[0092] The embodiment of the present invention collects customer service consultation information data of car mall users, which may include questions raised by users, consultation content, etc., and extracts keywords in the customer service consultation information by using text mining technology to perform word frequency statistics and association analysis on car-related vocabulary, thereby establishing a vocabulary set containing multiple car models, and finally obtaining a vocabulary set of car models consulted by car mall users.

[0093] Step S142: performing cluster analysis on the vocabulary set of automobile models consulted by automobile mall users to obtain a classification set of automobile models consulted by automobile mall users;

[0094] The embodiment of the present invention selects an appropriate clustering algorithm according to the automobile model vocabulary set consulted by automobile mall users to perform cluster analysis on the corresponding vocabulary, so as to classify the vocabulary with similar characteristics into the same category by calculating the similarity between each automobile vocabulary, and finally obtain the automobile model classification set consulted by automobile mall users.

[0095] Step S143: performing classification statistical analysis on the vocabulary set of automobile models consulted by automobile mall users based on the automobile model classification set consulted by automobile mall users, so as to obtain the user consultation frequency of different automobile models in the automobile mall;

[0096] The embodiment of the present invention performs statistical analysis on the automobile model vocabulary set consulted by automobile mall users according to the classification results of the automobile model classification set consulted by automobile mall users, so as to statistically calculate the frequency of occurrence of each automobile model in user consultations, and understand the degree of user attention to different car models, and finally obtain the user consultation frequency of different automobile models in the automobile mall.

[0097] Step S144: performing sentiment evaluation analysis on the car mall user customer service consultation information data based on the car mall user consultation car model classification set to obtain user consultation sentiment attitude data of different car models in the car mall;

[0098] The embodiment of the present invention classifies the customer service consultation information data of the car mall users according to the car model classification set, and analyzes the consultation information data of each classification by using sentiment analysis technology to evaluate and analyze the language expression and sentiment vocabulary in the consultation information to identify the user's emotional attitude, and understand the user's attitude and preference for different car models, and finally obtain the user consultation sentiment attitude data of different car models in the car mall.

[0099] Step S145: Conduct consultation preference evaluation and analysis on the automobile model classification set consulted by automobile mall users according to the user consultation frequency of different automobile models in the automobile mall and the user consultation emotional attitude data to obtain the user consultation preference degree of different automobile models in the automobile mall.

[0100] The embodiment of the present invention evaluates and analyzes the consultation preferences of corresponding automobile models in the automobile mall user consultation automobile model classification set according to the analyzed user consultation frequencies and user consultation emotional attitude data of different automobile models in the automobile mall, so as to evaluate and analyze the user's preference degree for different automobile models according to the user's consultation frequencies and emotional attitudes towards different automobile models, and finally obtain the user consultation preference degree for different automobile models in the automobile mall.

[0101] The present invention firstly mines and analyzes the automobile model vocabulary of the automobile mall user customer service consultation information data. The purpose of this step is to extract the automobile model vocabulary involved in the user consultation. By analyzing the vocabulary with high frequency in the user consultation information, a vocabulary set containing multiple automobile models can be established, so as to help the subsequent user consultation to be analyzed in more detail. Secondly, by clustering the automobile model vocabulary set consulted by the automobile mall user, similar model vocabulary can be classified into one category, so as to obtain a classification set of automobile models. Through clustering analysis, the correlation and commonality between different models can be clarified, so that the subsequent analysis is more accurate and targeted. Then, by classifying and statistically analyzing the automobile model vocabulary set consulted by the automobile mall user based on the automobile model classification set consulted by the automobile mall user, the frequency of each model vocabulary appearing in the user consultation can be counted, so that the degree of attention paid to different models in the automobile mall and the concentration of user consultation can be understood, which provides important reference and basis for subsequent analysis and decision-making. Next, by conducting sentiment evaluation analysis on the car mall user customer service consultation information data based on the car model classification set consulted by the car mall users, the sentiment attitude in the user consultation information corresponding to each car model can be analyzed, so that the user's sentiment tendency and attitude towards different car models can be understood, such as like, satisfaction, dissatisfaction, etc., which helps to understand user needs and evaluate product satisfaction. Finally, by conducting consultation preference evaluation analysis on the car model classification set consulted by the car mall users according to the user consultation frequency of different car models in the car mall and the user consultation sentiment attitude data, the user consultation frequency and sentiment attitude can be comprehensively considered to evaluate the user's preference for different car models, which helps to understand the user's needs and tendencies, so as to optimize the product recommendation and service strategy of the car mall, thereby improving user satisfaction and purchasing experience.

[0102] Preferably, step S2 comprises the following steps:

[0103] Step S21: Obtaining the purchase budget data of the automobile mall user;

[0104] The embodiment of the present invention collects the purchase budget data of the mall users through various means, such as user questionnaires, purchase intention expressions, etc., including the user's specific car purchase budget amount and installment payment, loan amount and other information, and determines the purchase budget of each user therefrom, and finally obtains the purchase budget data of the car mall users.

[0105] Step S22: predicting the user vehicle preference recommendation of the automobiles in the automobile mall according to the automobile preference demand data of the mall users, so as to obtain the initial recommended automobiles of the mall users' automobile preference;

[0106] The embodiment of the present invention obtains the demand data on automobile preferences of corresponding users according to the automobile mall analysis, including information on brand, model, color, function, etc., and predicts vehicle preferences by using an intelligent recommendation algorithm to select automobiles with similar characteristics as initial recommended vehicles, and help users quickly find automobile options that meet their preferences, and finally obtain the initial recommended automobiles based on the mall users' automobile preferences.

[0107] Step S23: performing a purchase budget capability evaluation and analysis on the purchase budget data of the automobile mall users to obtain purchase budget capability level data of the automobile mall users;

[0108] The embodiment of the present invention compares and analyzes the user's purchase budget data with information such as market prices and vehicle loan plans, so as to fully consider factors such as the user's income level and family financial status to evaluate and analyze the user's purchase budget ability, so as to understand the user's purchasing ability level and ultimately obtain the car mall user's purchase budget ability level data.

[0109] Step S24: performing budget matching screening analysis on the initially recommended automobile vehicles of the automobile preferences of the automobile mall users based on the purchasing budget capability level data of the automobile mall users, so as to obtain automobile vehicles matched and recommended by the automobile mall users;

[0110] The embodiment of the present invention performs matching analysis by combining the automobile mall user's purchasing budget ability level data obtained through analysis with the price data of the initially recommended vehicles, so as to match and screen out automobile vehicle options that meet the user's purchasing budget ability, and further screen the recommended vehicles by fully considering the user's loan, installment payment and other situations, to ensure that the user's purchasing budget can cover the price range of the selected vehicle, and finally obtain the mall user's matching recommended automobile vehicle.

[0111] Step S25: Perform user interface display processing on the automobile vehicles recommended by the mall user to generate a mall user recommended vehicle interface display result.

[0112] The embodiment of the present invention recommends automobiles based on the screened matches and displays the relevant information of these vehicles on the mall user interface. This information may include photos, detailed descriptions, prices, configurations, etc. of the vehicles, and through appropriate interface design and display methods, users can intuitively browse and compare these vehicle options, and finally generate a mall user recommended vehicle interface display result.

[0113] The present invention first obtains the purchase budget data of the users of the car mall through various channels, such as user questionnaires, purchase intention expressions, etc. These data will provide basic information for subsequent analysis and recommendation, thereby helping to understand the purchasing power and budget range of users. Secondly, by predicting the user vehicle preference recommendation of the automobile vehicles in the car mall according to the automobile preference demand data of the mall users, the user's preference needs, including information on brands, models, prices, etc., can be predicted and analyzed. In this way, the user's preference for different automobile vehicles can also be predicted, thereby obtaining the initial recommended automobile vehicle list of the mall users. Then, by evaluating and analyzing the purchase budget ability of the users of the car mall, the purchase budget ability level of the users can be understood. By comparing the purchase budget of the users with the car prices on the market, the user's purchasing ability level can be obtained, including high, medium, low and other different levels of budget ability, which will provide an important reference basis for subsequent car recommendations and budget matching. Next, the budget matching screening analysis is performed on the initial recommended automobile vehicles of the mall users' automobile preferences based on the purchasing budget ability level data of the auto mall users. This step compares the user's purchase budget and the price of the recommended vehicle to screen out the automobile vehicles that meet the user's budget, thereby forming a list of matching recommended automobile vehicles for the mall users. This helps to provide users with automobile choices that fit the budget and enhance the user's purchase intention and satisfaction. Finally, the user interface display processing is performed on the matching recommended automobile vehicles of the mall users. This step displays the detailed information of the final recommended vehicle, including pictures, configurations, prices, etc., by designing an intuitive and easy-to-use user interface to help users better understand and choose the recommended vehicle, which will enhance the reference value of the user's purchase decision, thereby improving the sales conversion rate and user experience of the auto mall.

[0114] Preferably, step S3 comprises the following steps:

[0115] Step S31: analyzing the vehicle space structure characteristics of the interface display vehicles in the interface display result of the mall user recommended vehicle to obtain the space structure characteristic data of the mall user recommended display vehicle;

[0116] The embodiment of the present invention uses a spatial structure feature analysis method to perform feature analysis on the interface display vehicle corresponding to the interface display result of the mall user recommended vehicle, so as to analyze the vehicle's appearance, internal space layout and other features, and obtain relevant feature data such as the size, seat layout, storage space and the like of the recommended vehicle, and finally obtain the spatial structure feature data of the mall user recommended display vehicle.

[0117] Step S32: using a 3D corner point detection algorithm to perform feature corner point sampling processing on the spatial structure feature data of the vehicles recommended for display by the mall users, so as to obtain a set of feature corner points of the spatial structure of the vehicles recommended by the mall users;

[0118] The embodiment of the present invention imports the spatial structure feature data of vehicles recommended for display by mall users into a 3D corner point detection algorithm, and detects and samples the feature points of the vehicle space through the algorithm to select representative feature corner points. These feature corner points can represent the key structural points of the vehicle, such as the front, rear, and doors, and finally obtain a set of spatial structure feature corner points of vehicles recommended by mall users.

[0119] Step S33: performing three-dimensional vehicle space modeling processing on the interface display vehicle in the interface display result of the mall user recommended vehicle based on the spatial structure feature corner point set of the mall user recommended vehicle to obtain a three-dimensional space model of the mall user recommended vehicle;

[0120] The embodiment of the present invention uses a three-dimensional modeling software to model the body, compartment, wheels and other components of the vehicle displayed in the corresponding interface in the interface display result of the mall user recommended vehicle by combining the spatial structure feature corner point set of the mall user recommended vehicle obtained by sampling, so as to integrate the modeling data of each component, thereby constructing a corresponding three-dimensional space model. This model can display the appearance, internal space layout and other important geometric properties of the vehicle, and finally obtain the three-dimensional space model of the mall user recommended vehicle.

[0121] Step S34: performing virtual test drive scene rendering processing on the three-dimensional space model of the vehicle recommended by the mall user through virtual reality technology to obtain a virtual test drive space model of the vehicle displayed in the mall;

[0122] The embodiment of the present invention uses virtual reality technology to perform scene rendering on the constructed three-dimensional space model of the vehicle recommended by the mall user, so as to present the vehicle model as a realistic virtual scene by adding details such as lighting, material, texture, etc., and interacts in real time through the virtual reality device according to the user's operation and input, so that the user can simulate the actual driving experience in the virtual scene, and at the same time ensure that the user can feel the spatial structure and driving experience of the vehicle recommended by the mall in the virtual test drive, and finally obtain the virtual test drive space model of the vehicle displayed in the mall.

[0123] Step S35: Perform virtual test drive experience analysis on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle.

[0124] The embodiment of the present invention records the operation behaviors and feedback data of mall users in the virtual test drive, including data on acceleration, braking, steering, speed perception, comfort, etc., and analyzes and evaluates these data to analyze and understand the users' feelings and evaluations of the mall's recommended vehicles in the virtual test drive, and finally obtains the virtual test drive user experience data of the mall's displayed vehicles.

[0125] The present invention first analyzes the vehicle space structure characteristics of the interface display vehicle in the interface display result of the recommended vehicle by the mall user to analyze the appearance, internal space layout and other characteristics of the vehicle, so that the relevant data on the size, seat layout, storage space and other related data of the recommended vehicle can be obtained, and these characteristic data will provide key information for the subsequent virtual test drive and user experience. Secondly, by using the 3D corner point detection algorithm to perform characteristic corner point sampling processing on the spatial structure characteristic data of the recommended vehicle displayed by the mall user, the key corner points of the vehicle, such as the vertices, edges and other characteristic points of the vehicle, can be identified, thereby extracting the spatial structure characteristic corner point set of the vehicle, and the processing process of this step will provide the necessary data basis for the subsequent three-dimensional modeling. Then, by performing three-dimensional vehicle space modeling processing on the interface display vehicle in the interface display result of the recommended vehicle by the mall user based on the spatial structure characteristic corner point set of the recommended vehicle by the mall user, the characteristic corner points can be connected and the surface filled, so that the three-dimensional space model of the vehicle recommended by the mall user can be generated, and the processing process of this step will provide realism and interactivity for the subsequent virtual test drive. Next, virtual reality technology is used to render the virtual test drive scene of the three-dimensional space model of the vehicle recommended by the mall user, so that the virtual test drive space model of the mall's displayed vehicles can be presented. This will allow users to experience the real scene of driving a vehicle in a virtual environment and provide a more intuitive car buying experience. Finally, by analyzing the virtual test drive experience of the virtual test drive space model of the mall's displayed vehicles, it is possible to collect user behavior data, feeling feedback and other information during the virtual test drive process, so as to evaluate the user's satisfaction and comfort with the test drive experience. The analysis of this step will help optimize the virtual test drive system, thereby improving the user's car buying experience and satisfaction.

[0126] Preferably, step S4 comprises the following steps:

[0127] Step S41: Based on the virtual test drive user experience data of the vehicles displayed in the mall, a test drive experience evaluation and analysis is performed on the automobiles recommended by the mall users to obtain the virtual test drive experience satisfaction of each recommended automobile;

[0128] The embodiment of the present invention first collects user experience data of virtual test drives of vehicles displayed in the mall, including user experience data such as test drive time, mileage, ride comfort, acceleration performance, handling stability, etc., and organizes and cleans these data to ensure the accuracy and completeness of the data. Then, the corresponding mall user matching recommended automobiles are evaluated and analyzed by using technical means such as statistical analysis or machine learning to evaluate the satisfaction level of the virtual test drive experience of each matching recommended automobile, and finally the satisfaction level of the virtual test drive experience of each matching recommended automobile is obtained.

[0129] Step S42: performing a recommended vehicle purchase screening process on the automobiles recommended by the mall user according to the satisfaction degree of the virtual test drive experience of each matched recommended automobile vehicle, and obtaining automobiles to be purchased by the mall user;

[0130] The embodiment of the present invention performs screening processing on the purchase vehicles of the corresponding mall user matching recommended vehicles by combining the virtual test drive experience satisfaction levels of each matching recommended vehicle obtained through analysis, so as to sort the vehicles according to the user's satisfaction level with the test drive experience of each recommended vehicle, and find out the vehicles with higher satisfaction levels, and determine them as the vehicles to be purchased that are suitable for the user, and finally obtain the vehicles to be purchased that are suitable for the mall user.

[0131] Step S43: performing customized configuration processing on the automobile vehicle to be purchased by the mall user, and obtaining the customized configured automobile vehicle adapted for the mall user;

[0132] The embodiment of the present invention provides users with corresponding customized configuration options by adapting the automobile to be purchased according to the selected mall user, such as configuring the engine type, color, interior, optional accessories, etc., so as to customize the selected automobile to be purchased according to the personalized needs of the user, and ensure that the automobile to be purchased can meet the unique needs of the user, and finally obtain a customized automobile adapted by the mall user.

[0133] Step S44: performing intelligent preferential quotation processing on the automobiles adapted to the customized configuration of the mall users to obtain preferential quotation data of the automobiles adapted to the users;

[0134] The embodiment of the present invention queries relevant preferential policies and promotional activities according to the detailed information of the selected customized automobile, calculates the applicable preferential amount or discount according to the preferential policies and promotional activities obtained, and calculates it with the price of the customized automobile to calculate the preferential quotation for each vehicle, and finally obtains user-adapted automobile preferential quotation data.

[0135] Step S45: Based on the user-adapted automobile vehicle preferential quotation data, the mall user's customized automobile vehicle is adapted and an order is placed to purchase the vehicle, so as to obtain the automobile mall user's automobile vehicle intelligent order result.

[0136] The embodiment of the present invention confirms the user's purchase intention for a car based on the user's satisfaction with the adapted vehicle and the preferential quotation data, and at the same time organizes and verifies the relevant car purchase information, including the purchase model, configuration options, price, etc., so as to generate a corresponding car purchase contract and order. After the user confirms that they are correct, the car purchase signing and ordering process is completed, and finally the car mall user's car intelligent ordering result is obtained.

[0137] The present invention firstly evaluates and analyzes the test drive experience of the recommended automobiles matched by the users of the mall based on the user experience data of the virtual test drive of the vehicles displayed in the mall. This step collects various experience data of the users in the virtual test drive, such as feedback information on driving experience, seat comfort, spatial perception, etc., to evaluate the satisfaction of the virtual test drive experience of each recommended automobile, which will help to understand the user's preferences and actual needs for each vehicle, thereby providing a basis for subsequent car purchase screening. Secondly, the recommended vehicle purchase screening process is performed on the recommended automobiles matched by the users of the mall according to the satisfaction of the virtual test drive experience of each recommended automobile, so as to exclude vehicles that do not meet the user's preferences and needs, so that the automobiles that the users of the mall are adapted to purchase can be obtained. The processing process of this step will help users narrow the scope of car purchase and only retain the vehicle selection that meets their preferences and needs. Then, the customized configuration process is performed on the automobiles that the users of the mall are adapted to purchase, so as to provide corresponding configuration options for each vehicle according to the personalized needs and preferences of the users, including vehicle model, color, interior material, functional configuration, etc. Through customized configuration, the personalized requirements of users can be met, so as to provide user-adapted automobiles for subsequent processing. Next, by processing the intelligent preferential quotation of the customized configuration automobiles adapted by the mall users, the preferential quotation of each vehicle is calculated using intelligent algorithms according to the customized configuration requirements of the users and market conditions, including relevant discounts, preferential activities, etc. This will help users understand the price advantage of each vehicle and provide users with competitive quotation data. Finally, by processing the purchase order of the customized configuration automobiles adapted by the mall users based on the preferential quotation data of the user-adapted automobiles, customized car purchase contracts and orders are provided to users according to their choices and wishes, and the corresponding ordering process is completed, which will help users smoothly complete the car purchase procedures, thereby obtaining the intelligent ordering results of the car mall and realizing the quick car purchase experience of the car mall.

[0138] Preferably, the present invention further provides a car mall ordering platform, which is used to execute the car mall ordering method as described above, and the car mall ordering platform comprises:

[0139] The car preference demand analysis module of the shopping mall user is used to obtain the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, and to analyze the user's car preference demand on the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, so as to obtain the car preference demand data of the shopping mall user;

[0140] The user recommended vehicle interface display module is used to obtain the purchase budget data of the car mall user, and make user vehicle matching recommendation predictions for the car mall based on the car preference demand data of the mall user and the purchase budget data of the car mall user, so as to obtain the car vehicles matched and recommended by the mall user; perform user interface display processing on the car vehicles matched and recommended by the mall user, so as to generate the interface display results of the vehicle recommended by the mall user;

[0141] The display vehicle virtual test drive analysis module is used to perform virtual test drive space modeling on the interface display vehicle in the display result of the mall user recommended vehicle interface through virtual reality technology to obtain the virtual test drive space model of the mall display vehicle; perform virtual test drive experience analysis on the virtual test drive space model of the mall display vehicle, so as to obtain the virtual test drive user experience data of the mall display vehicle;

[0142] The intelligent ordering module for vehicles suitable for purchase by users is used to perform recommended vehicle purchase screening processing on matching recommended vehicles for mall users based on user experience data of virtual test drives of vehicles displayed in the mall, and obtain vehicles suitable for purchase by mall users; and to perform intelligent quotation and ordering processing on vehicles suitable for purchase by mall users, so as to obtain intelligent ordering results for vehicles of automobile mall users.

[0143] In summary, the present invention provides a car mall ordering platform, which consists of a mall user car preference demand analysis module, a user recommended vehicle interface display module, a displayed vehicle virtual test drive analysis module and a user adapted vehicle to be purchased intelligent ordering module, which can implement any car mall ordering method described in the present invention, and is used to combine the operations between computer programs running on various modules to implement any car mall ordering method. The internal structures of the platform cooperate with each other, which can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient car mall ordering process, thereby simplifying the operation process of the car mall ordering platform based on data analysis.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for placing an order in a car mall, characterized in that: The following steps are involved: Step S1: obtaining the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, and performing user car preference demand analysis on the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user to obtain the car preference demand data of the mall user; wherein step S1 includes the following steps: Step S11: Acquire the historical browsing information data of the automobile mall user and the customer service consultation information data of the automobile mall user; Step S12: extracting the user cursor browsing behavior and browsing interaction time of the automobile mall user historical browsing information data to obtain the automobile mall user cursor browsing behavior data and the automobile mall user browsing interaction time; Step S13: Car browsing dwell evaluation analysis is performed based on the car mall user cursor browsing behavior data and the car mall user browsing interaction time to obtain the average browsing dwell preference time of different car pages in the car mall; wherein step S13 includes the following steps: Step S131: performing cursor motion trajectory simulation analysis on the automobile mall user's cursor browsing behavior data to obtain the automobile mall user's cursor browsing motion simulation trajectory; Step S132: performing motion speed decay analysis on the simulated trajectory of the automobile mall user's cursor browsing motion to obtain the automobile mall user's cursor browsing decay speed; Step S133: monitoring the motion range of the automobile mall user's cursor browsing motion simulation trajectory to obtain the automobile mall user's cursor browsing page range area; Step S134: Based on the decay speed of the car mall user's cursor browsing, a cursor browsing retention degree calculation formula is used to perform retention statistics calculation on the car mall user's cursor browsing page range area to obtain the car mall user's cursor browsing retention degree; wherein the cursor browsing retention degree calculation formula is specifically: Where L is the degree of user cursor browsing of the car mall, t1 is the starting time of the user's stay in the range of the car mall user's cursor browsing page, t2 is the end time of the user's stay in the range of the car mall user's cursor browsing page, t is the time variable parameter, n is the number of elements in the car mall user's browsing page, i is the element item index parameter, and w is the time variable parameter. i is the stay influence weight of the i-th element in the car mall user browsing page, v s (t) is the decay speed of the user’s cursor browsing in the car mall at time t, P i is the content complexity of the i-th element in the car mall user browsing page, A i is the page attractiveness of the i-th element in the page browsed by the automobile mall user, G i is the navigation effect parameter of the ith element in the car mall user's browsing page, and η is the correction coefficient of the car mall user's cursor browsing stay degree; Step S135: Based on the degree of cursor browsing of the automobile mall user, a retention area recognition analysis is performed on the range area of ​​the automobile mall user's cursor browsing page to obtain the retention area of ​​the automobile mall user's cursor browsing page; based on the automobile mall user's cursor browsing behavior data, a browsing frequency statistical analysis is performed on the retention area of ​​the automobile mall user's cursor browsing page to obtain the browsing frequency of each browsing page retention area; Step S136: Statistical analysis of browsing dwelling preference time is performed based on the browsing interaction time of automobile mall users and the browsing frequency of each browsing page dwelling area to obtain the average browsing dwelling preference time of different automobile pages in the automobile mall; Step S14: Car model consultation evaluation and analysis is performed on the car mall user customer service consultation information data to obtain user consultation preference levels for different car models in the car mall; Step S15: analyzing the user car preference demand of the car mall according to the average browsing dwelling preference time of different car pages in the car mall and the user consultation preference degree of different car models in the car mall, and obtaining the car preference demand data of the mall users; Step S2: obtaining the purchase budget data of the automobile mall user, and performing user vehicle matching recommendation prediction for the automobile mall according to the automobile preference demand data of the mall user and the purchase budget data of the automobile mall user, so as to obtain the automobile vehicle matched and recommended by the mall user; performing user interface display processing on the automobile vehicle matched and recommended by the mall user, so as to generate the interface display result of the vehicle recommended by the mall user; Step S3: virtual test drive space modeling is performed on the interface display vehicle in the interface display result of the mall user recommended vehicle by using virtual reality technology to obtain a virtual test drive space model of the mall display vehicle; virtual test drive experience analysis is performed on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle; Step S4: Based on the user experience data of the virtual test drive of the vehicles displayed in the mall, the recommended automobiles and vehicles are matched with the mall users for recommended vehicle purchase screening to obtain the automobiles and vehicles suitable for the mall users to be purchased; the automobiles and vehicles suitable for the mall users to be purchased are intelligently quoted and ordered to obtain the intelligent ordering results of the automobile mall users' automobiles and vehicles.

2. The method for placing an order in a car mall according to claim 1, characterized in that: Step S132 includes the following steps: Performing a motion speed change trend analysis on the simulated trajectory of the user's cursor browsing motion in the car mall to obtain the user's cursor browsing motion speed change trend data; drawing a speed change curve on the user's cursor browsing motion speed change trend data to obtain the user's cursor browsing motion speed change curve; Based on the user cursor browsing motion speed change trend data, the user cursor browsing motion speed change curve is analyzed for speed change transition points, and the user cursor browsing motion speed change transition points are obtained; the user cursor browsing motion speed change curve is divided into curves according to the user cursor browsing motion speed change transition points, and the user cursor speed change grouping curve is obtained; Performing an extrapolation trend analysis on the grouped curve of user cursor speed change to obtain extrapolation trend data of grouped curve speed change; performing speed change series interval calculation on the grouped curve of user cursor speed change according to the extrapolation trend data of grouped curve speed change to obtain grouped cursor speed change series interval; According to the group cursor speed change series interval and the group curve speed change extrapolation trend data, the user cursor speed change group curve is analyzed for inter-group speed decay to obtain the car mall user cursor browsing decay speed.

3. The method for placing an order in a car mall according to claim 1, characterized in that: Step S14 includes the following steps: Step S141: performing automobile model vocabulary mining analysis on the automobile mall user customer service consultation information data to obtain an automobile model vocabulary set consulted by automobile mall users; Step S142: performing cluster analysis on the vocabulary set of automobile models consulted by automobile mall users to obtain a classification set of automobile models consulted by automobile mall users; Step S143: performing classification statistical analysis on the vocabulary set of automobile models consulted by automobile mall users based on the automobile model classification set consulted by automobile mall users, so as to obtain the user consultation frequency of different automobile models in the automobile mall; Step S144: performing sentiment evaluation analysis on the car mall user customer service consultation information data based on the car mall user consultation car model classification set to obtain user consultation sentiment attitude data of different car models in the car mall; Step S145: Conduct consultation preference evaluation and analysis on the automobile model classification set consulted by automobile mall users according to the user consultation frequency of different automobile models in the automobile mall and the user consultation emotional attitude data to obtain the user consultation preference degree of different automobile models in the automobile mall.

4. The method for placing an order in a car mall according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Obtaining the purchase budget data of the automobile mall user; Step S22: predicting the user vehicle preference recommendation of the automobiles in the automobile mall according to the automobile preference demand data of the mall users, so as to obtain the initial recommended automobiles of the mall users' automobile preference; Step S23: performing a purchase budget capability evaluation and analysis on the purchase budget data of the automobile mall users to obtain purchase budget capability level data of the automobile mall users; Step S24: performing budget matching screening analysis on the initially recommended automobile vehicles of the automobile preferences of the automobile mall users based on the purchasing budget capability level data of the automobile mall users, so as to obtain automobile vehicles matched and recommended by the automobile mall users; Step S25: Perform user interface display processing on the automobile vehicles recommended by the mall user to generate a mall user recommended vehicle interface display result.

5. The method for placing an order in a car mall according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: analyzing the vehicle space structure characteristics of the interface display vehicles in the interface display result of the mall user recommended vehicle to obtain the space structure characteristic data of the mall user recommended display vehicle; Step S32: using a 3D corner point detection algorithm to perform feature corner point sampling processing on the spatial structure feature data of the vehicles recommended for display by the mall users, so as to obtain a set of feature corner points of the spatial structure of the vehicles recommended by the mall users; Step S33: performing three-dimensional vehicle space modeling processing on the interface display vehicle in the interface display result of the mall user recommended vehicle based on the spatial structure feature corner point set of the mall user recommended vehicle to obtain a three-dimensional space model of the mall user recommended vehicle; Step S34: performing virtual test drive scene rendering processing on the three-dimensional space model of the vehicle recommended by the mall user through virtual reality technology to obtain a virtual test drive space model of the vehicle displayed in the mall; Step S35: Perform virtual test drive experience analysis on the virtual test drive space model of the mall display vehicle to obtain virtual test drive user experience data of the mall display vehicle.

6. The method for placing an order in a car mall according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Based on the virtual test drive user experience data of the vehicles displayed in the mall, a test drive experience evaluation and analysis is performed on the automobiles recommended by the mall users to obtain the virtual test drive experience satisfaction of each recommended automobile; Step S42: performing a recommended vehicle purchase screening process on the automobiles recommended by the mall user according to the satisfaction degree of the virtual test drive experience of each matched recommended automobile vehicle, and obtaining automobiles to be purchased by the mall user; Step S43: performing customized configuration processing on the automobile vehicle to be purchased by the mall user, and obtaining the customized configured automobile vehicle adapted for the mall user; Step S44: performing intelligent preferential quotation processing on the automobiles adapted to the customized configuration of the mall users to obtain preferential quotation data of the automobiles adapted to the users; Step S45: Based on the user-adapted automobile vehicle preferential quotation data, the mall user's customized automobile vehicle is adapted and an order is placed to purchase the vehicle, so as to obtain the automobile mall user's automobile vehicle intelligent order result.

7. A car mall ordering platform, characterized in that: Used to execute the automobile mall ordering method according to claim 1, the automobile mall ordering platform comprises: The car preference demand analysis module of the shopping mall user is used to obtain the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, and to analyze the user's car preference demand on the historical browsing information data of the car mall user and the customer service consultation information data of the car mall user, so as to obtain the car preference demand data of the shopping mall user; The user recommended vehicle interface display module is used to obtain the purchase budget data of the car mall user, and make user vehicle matching recommendation predictions for the car mall based on the car preference demand data of the mall user and the purchase budget data of the car mall user, so as to obtain the car vehicles matched and recommended by the mall user; perform user interface display processing on the car vehicles matched and recommended by the mall user, so as to generate the interface display results of the vehicle recommended by the mall user; The display vehicle virtual test drive analysis module is used to perform virtual test drive space modeling on the interface display vehicle in the display result of the mall user recommended vehicle interface through virtual reality technology to obtain the virtual test drive space model of the mall display vehicle; perform virtual test drive experience analysis on the virtual test drive space model of the mall display vehicle, so as to obtain the virtual test drive user experience data of the mall display vehicle; The intelligent ordering module for vehicles suitable for purchase by users is used to perform recommended vehicle purchase screening processing on matching recommended vehicles for mall users based on user experience data of virtual test drives of vehicles displayed in the mall, and obtain vehicles suitable for purchase by mall users; and to perform intelligent quotation and ordering processing on vehicles suitable for purchase by mall users, so as to obtain intelligent ordering results for vehicles of automobile mall users.

Images