Automobile recommendation method and system based on user characteristics and automobile performance demand matching

Abstract

The invention provides an automobile recommendation method and system based on user characteristics and automobile performance demand matching, and relates to the technical field of automobile recommendation, and the method comprises the steps: obtaining user personality characteristics based on basic data of a user and user driving behavior data, and forming a first automobile type set through the personality characteristics and brand mapping; acquiring a driving speed parameter and a driving turning parameter of a driver; turning sensitivity preference classification and speed preference classification are carried out based on the driving turning parameters and the driving speed parameters; vehicle speed type classification is carried out based on the speed parameters of various vehicle types; clustering analysis is carried out based on turning data of various vehicle types, and vehicle turning sensitive vehicle types are classified; the vehicle speed models and the speed preference types are mapped to form a second vehicle model set, and the vehicle turning sensitive models and the turning sensitive preference types are mapped to form a third vehicle model set; and taking an intersection of the first vehicle type set, the second vehicle type set and the third vehicle type set to obtain a final brand vehicle type recommendation result.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vehicle recommendation, and in particular to a method and system for recommending vehicles based on matching user characteristics with vehicle performance requirements. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] The automobile pre-sale recommendation system refers to a system that implements targeted promotion and personalized service of automobile products to users before they purchase a car. It saves users the process of searching for automobile brands and models, and directly recommends to users based on big data and artificial intelligence algorithms, making it convenient for users to make recommendations before purchasing a vehicle, allowing users to obtain automobile brand recommendations more conveniently.

[0004] However, after investigation, it was found that the current mainstream recommendation method is still to promote through online and offline advertising, user satisfaction surveys, user maintenance activities, etc., which requires a lot of manpower and material costs. The usual practice is to conduct market positioning based on the survey data by conducting a survey on the user's market demand, and then conduct advertising marketing. However, if the car is approaching the end of its service life, the car pre-sale recommendation system automatically recommends the next car that meets the user's preferences, eliminating the need for advertising marketing. For example, there are N sub-brands under a certain brand, each brand has a different market positioning, and each sub-brand has a variety of different models. However, the current recommendation system method is not highly automated, and cannot accurately and quickly recommend according to the preferences and characteristics of each user. Summary of the invention

[0005] In order to solve the above problems, the present disclosure proposes a car recommendation method and system based on matching user characteristics and vehicle performance requirements. Based on the user characteristics, the user's brand preference is determined from the user characteristics, and the user's requirements for vehicle performance configuration are determined from the vehicle data such as vehicle turning and acceleration based on the user's vehicle usage characteristics, thereby realizing automated vehicle recommendation.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions:

[0007] The car recommendation method based on matching user characteristics and vehicle performance requirements includes:

[0008] Obtain the user's basic data and driving behavior data;

[0009] Based on the basic data of the user and the driving behavior data of the user, the user's personality characteristics are obtained by using a machine learning algorithm, and the user's personality characteristics are mapped to the vehicle brand to form a first vehicle model set;

[0010] Acquire the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data;

[0011] Clustering users’ turning control preferences based on driving turning parameters and classifying turning agility preferences; clustering users’ driving speed preferences based on driving speed parameters and classifying speed preferences;

[0012] Cluster analysis is performed based on the speed parameters of various vehicle models to classify vehicle speed types; cluster analysis is performed based on the turning data of various vehicle models to classify vehicle turning-sensitive models;

[0013] The vehicle speed model and the speed preference type are mapped to form a second model set, and the vehicle turning sensitivity model and the turning sensitivity preference type are mapped to form a third model set;

[0014] The intersection of the first model set, the second model set and the third model set is taken to obtain the final brand model recommendation result.

[0015] According to some embodiments, the present disclosure adopts the following technical solutions:

[0016] The car recommendation system based on matching user characteristics and vehicle performance requirements includes:

[0017] Data acquisition module, used to obtain basic data of users and driving behavior data of users;

[0018] A clustering module, for obtaining the user's personality characteristics by using a machine learning algorithm based on the user's basic data and the user's driving behavior data, and mapping the user's personality characteristics with the vehicle brand to form a first vehicle model set;

[0019] Acquire the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data;

[0020] Clustering users’ turning control preferences based on driving turning parameters and classifying turning agility preferences; clustering users’ driving speed preferences based on driving speed parameters and classifying speed preferences;

[0021] Cluster analysis is performed based on the speed parameters of various vehicle models to classify vehicle speed types; cluster analysis is performed based on the turning data of various vehicle models to classify vehicle turning-sensitive models;

[0022] The vehicle speed model and the speed preference type are mapped to form a second model set, and the vehicle turning sensitivity model and the turning sensitivity preference type are mapped to form a third model set;

[0023] The recommendation module is used to take the intersection of the first model set, the second model set and the third model set to obtain the final brand model recommendation result.

[0024] According to some embodiments, the present disclosure adopts the following technical solutions:

[0025] A computer program product includes a computer program, and when the computer program is executed by a processor, the car recommendation method based on matching user characteristics and vehicle performance requirements is implemented.

[0026] According to some embodiments, the present disclosure adopts the following technical solutions:

[0027] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the car recommendation method based on matching user characteristics and vehicle performance requirements is implemented.

[0028] According to some embodiments, the present disclosure adopts the following technical solutions:

[0029] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the car recommendation method based on matching user characteristics and vehicle performance requirements.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The present invention discloses a car recommendation method based on matching user characteristics with vehicle performance requirements. The method extracts user driving behavior data based on vehicle travel big data, infers user personality characteristics based on user basic information, determines user brand preferences based on personality characteristics, determines user requirements for vehicle performance configuration based on user style data such as turning and acceleration, and searches for cars that meet user requirements and preferences online based on brand requirements and performance configuration requirements, thereby realizing automation of vehicle pre-sales marketing promotion.

[0032] The disclosed method for recommending cars based on matching user characteristics and vehicle performance requirements implements brand recommendations based on user personality characteristics, and then implements specific performance configuration recommendations based on user driving style data. The combination of the two automatically implements vehicle recommendations, optimizes the automotive product marketing process, and reduces automotive marketing and promotion costs. It can give priority to recommending vehicles of the same brand series as the system-equipped vehicle, thereby enhancing user stickiness. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0034] Figure 1A logic diagram of a method for recommending automobiles before sales according to an embodiment of the present disclosure;

[0035] Figure 2 A method for establishing a mapping relationship between basic user information, driving behavior data, and personality trait information in an embodiment of the present disclosure;

[0036] Figure 3 Establishing a process for mapping the speed preference and vehicle type in the embodiment of the present disclosure;

[0037] Figure 4 Establishing a process for mapping the turning sensitivity preference and the vehicle model in the embodiment of the present disclosure;

[0038] Figure 5 This is a flow chart of intersection recommendation according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0040] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0042] Example 1

[0043] In one embodiment of the present disclosure, a method for recommending a car based on matching user characteristics with vehicle performance requirements is provided, comprising:

[0044] Step 1: Obtain the user's basic data and driving behavior data;

[0045] Step 2: Based on the user's basic data and the user's driving behavior data, a machine learning algorithm is used to obtain the user's personality characteristics, and the user's personality characteristics are mapped to the vehicle brand to form a first vehicle model set;

[0046] Step 3: Obtain the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data;

[0047] Step 4: Clustering user turning control preferences based on driving turning parameters and classifying turning agility preferences; clustering user driving speed preferences based on driving speed parameters and classifying speed preferences;

[0048] Step 5: Perform cluster analysis based on the speed parameters of various vehicle models to classify vehicle speed types; perform cluster analysis based on the turning data of various vehicle models to classify vehicle turning-sensitive models;

[0049] Step 6: Mapping the vehicle speed model and the speed preference type to form a second model set, and mapping the vehicle turning sensitivity model and the turning sensitivity preference type to form a third model set;

[0050] Step 7: Take the intersection of the first model set, the second model set and the third model set to obtain the final brand model recommendation result.

[0051] As an embodiment, the specific implementation process of a car recommendation method based on matching of user characteristics and vehicle performance requirements disclosed in the present invention is as follows:

[0052] Step 1: Obtain the user's basic data and driving behavior data;

[0053] The basic data of the user includes gender, age, place of origin, occupation and driving experience information, and the user driving behavior data includes user driving data and application usage data.

[0054] Furthermore, the user driving data includes speed, longitudinal acceleration, lateral acceleration, steering wheel acceleration, accelerator pedal angle and brake pedal angle; the application usage data includes music playback type, style preference, navigation voice type and average volume data.

[0055] Step 2: Based on the user's basic data and the user's driving behavior data, a machine learning algorithm is used to obtain the user's personality characteristics, and the user's personality characteristics are mapped to the vehicle brand to form a first vehicle model set;

[0056] Specifically, the machine learning model can be a decision tree, random forest, support vector machine, deep learning and other models. Through market research, a large number of volunteers are recruited to fill in their basic information such as age, gender, region, occupation, education, region, driving experience, the brand of car purchased, and fill in the Big Five personality questionnaire to obtain their personality traits. Control the basic information variables, and determine the corresponding relationship between personality traits and brand selection by comparing and analyzing the distribution of personality characteristics of users of different car brands. For example, there are four brands, ABCD. There are a total of n personality classifications (p, 1 ,p 2 ,…,p n). Determine the values ​​and ranges of basic information such as age, gender, region, occupation, education, region, and driving experience. If, under a certain range of basic information, most of the users of brand A belong to p i and p j These two, then it can be considered that under this condition, p i and p j People with personality traits will tend to choose brand A. Thus, a mapping between personality traits and brand choice is established.

[0057] The workload can be reduced by placing questionnaires on various vehicle platforms and encouraging drivers to fill them out. The construction process of the machine learning algorithm model includes:

[0058] The construction process of the machine learning algorithm model includes:

[0059] 1) Recruit a certain number of samples, fill out the Big Five Personality Questionnaire, and obtain the Big Five personality traits of the car owners.

[0060] 2) Collect basic user information, including age, gender, region, occupation, education, region, driving experience, etc.

[0061] 3) User driving behavior data includes driving data and application usage data.

[0062] Driving data includes speed, longitudinal acceleration, lateral acceleration, steering wheel angular velocity, accelerator pedal angle, brake pedal angle, and other driving behavior data; application usage data includes music playback type, style preference, navigation voice type, average volume, and other car usage data.

[0063] 4) Personality trait researchers use machine learning algorithms to build a model that predicts personality traits based on user basic information and driving information.

[0064] Further, mapping the user personality characteristics with the vehicle brands to form a first vehicle model set;

[0065] Through the research between user brands and personality traits, we analyze the personality trait portraits of consumer groups of different brands, thereby establishing a mapping relationship between personality traits and brands.

[0066] Step 3: Obtain the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data; cluster the user's driving speed preferences based on the driving speed parameters and classify the speed preferences;

[0067] Specifically, on the Internet of Vehicles big data platform, the driving speed parameters of the driver over a period of time are obtained, including speed, accelerator pedal usage percentage and brake pedal usage percentage data. After data cleaning, they are simplified to average speed, average accelerator pedal usage percentage and average brake pedal usage percentage to perform cluster analysis on all users' driving speed preferences.

[0068] The specific method of data cleaning is: assign negative data to 0, and then perform percentage calculation.

[0069] Clustering methods can include k-means, KNN, hierarchical clustering, mean shift clustering, Ward's method, DBSCAN, OPTICS and spectral clustering.

[0070] The present disclosure adopts the k-means method for clustering, but the protected content is not limited to this method.

[0071] The k-means method randomly selects K objects as the initial cluster centers. In this example, K=3. The distance between each object and each cluster center is calculated, and the closest cluster center and the object are considered to be in the same category. After all data objects are assigned, the cluster center needs to be updated according to the center point of the category object point. Then the distance between each object and the cluster center is calculated repeatedly. This process will be repeated until a certain termination condition is met. The termination condition can be any of the following:

[0072] 1. No (or a minimum number) of objects are reassigned to different clusters.

[0073] 2. No (or a minimum number of) cluster centers change again.

[0074] 3. The sum of squared errors is locally minimum.

[0075] The clustered data are divided into three categories: high-speed preference class, medium-speed preference class and low-speed preference class.

[0076] Step 4: Clustering user turning control preferences based on driving turning parameters and classifying turning agility preferences;

[0077] Specifically, on the Internet of Vehicles big data platform, the absolute values ​​of the driver's steering wheel speed and lateral acceleration data over a period of time are obtained. After data cleaning, the average steering wheel speed and average lateral acceleration data are calculated, and then a cluster analysis is performed on all users' turning control preferences.

[0078] The data cleaning method is to assign negative data to 0 and then perform percentage calculation.

[0079] The clustered data are divided into three categories: high turning sensitivity preference class, medium turning sensitivity preference class and low turning sensitivity preference class.

[0080] Step 5: Perform cluster analysis based on the speed parameters of various vehicle models to classify vehicle speed types; perform cluster analysis based on the turning data of various vehicle models to classify vehicle turning-sensitive models;

[0081] Specifically, the wheelbase and minimum turning radius of the current cars on the market are collected, and the popular cars are divided into three categories through cluster analysis: high turning sensitivity models, medium turning sensitivity models and low turning sensitivity models. In the recommendation system, the high turning sensitivity preference class, medium turning sensitivity preference class and low turning sensitivity preference class correspond to the high turning sensitivity models, medium turning sensitivity models and low turning sensitivity models one by one.

[0082] The maximum speed and acceleration per 100 kilometers of the current cars on the market are collected, and the popular cars are divided into three categories through cluster analysis: high-speed models, medium-speed models and low-speed models. In the recommendation system, the high-speed preference category, medium-speed preference category and low-speed preference category correspond to high-speed models, medium-speed models and low-speed models one by one.

[0083] Finally, the vehicle speed models and speed preference types are mapped to form a second model set, and the vehicle turning sensitivity models and turning sensitivity preference types are mapped to form a third model set.

[0084] Step 6: Take the intersection of the first model set, the second model set and the third model set to obtain the final brand model recommendation result.

[0085] Specifically, based on a specific driver: a set of cars related to brands corresponding to his / her personality traits are analyzed; a set of car models related to speed corresponding to his / her speed preference; and a set of car models related to turning sensitivity corresponding to his / her turning preference.

[0086] The intersection of the three sets is taken to obtain a specific car collection recommended based on the driver's personality traits and driving data. The corresponding car collection is pushed to the driver's car home screen.

[0087] The user can then select the corresponding brand based on the recommended car brand, conduct the next step of pre-sales consultation, obtain contact information and purchase links, and make an appointment for a test drive.

[0088] Example 2

[0089] In one embodiment of the present disclosure, a car recommendation system based on matching user characteristics and vehicle performance requirements is provided, including:

[0090] Data acquisition module, used to obtain basic data of users and driving behavior data of users;

[0091] A clustering module, for obtaining the user's personality characteristics by using a machine learning algorithm based on the user's basic data and the user's driving behavior data, and mapping the user's personality characteristics with the vehicle brand to form a first vehicle model set;

[0092] Acquire the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data;

[0093] Clustering users’ turning control preferences based on driving turning parameters and classifying turning agility preferences; clustering users’ driving speed preferences based on driving speed parameters and classifying speed preferences;

[0094] Cluster analysis is performed based on the speed parameters of various vehicle models to classify vehicle speed types; cluster analysis is performed based on the turning data of various vehicle models to classify vehicle turning-sensitive models;

[0095] The vehicle speed model and the speed preference type are mapped to form a second model set, and the vehicle turning sensitivity model and the turning sensitivity preference type are mapped to form a third model set;

[0096] The recommendation module is used to take the intersection of the first model set, the second model set and the third model set to obtain the final brand model recommendation result.

[0097] Example 3

[0098] In one embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the car recommendation method based on matching user characteristics and vehicle performance requirements is implemented.

[0099] Example 4

[0100] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the car recommendation method based on matching user characteristics and vehicle performance requirements is implemented.

[0101] Example 5

[0102] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the car recommendation method based on matching user characteristics and vehicle performance requirements.

[0103] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0105] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A car recommendation method based on matching user characteristics and vehicle performance requirements, characterized in that: include: Obtain the user's basic data and driving behavior data; Based on the basic data of the user and the driving behavior data of the user, the user's personality characteristics are obtained by using a machine learning algorithm, and the user's personality characteristics are mapped to the vehicle brand to form a first vehicle model set; Acquire the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data; Clustering user turning control preferences based on driving turning parameters and classifying turning agility preferences; Clustering users’ driving speed preferences based on driving speed parameters and classifying speed preferences; Cluster analysis is performed based on the speed parameters of various vehicle models to classify vehicle speed types; Cluster analysis is performed based on the turning data of various vehicle models to classify vehicle models with sensitive turning ability; The vehicle speed model and the speed preference type are mapped to form a second model set, and the vehicle turning sensitivity model and the turning sensitivity preference type are mapped to form a third model set; The intersection of the first model set, the second model set and the third model set is taken to obtain the final brand model recommendation result.

2. The method for recommending a car based on matching user characteristics and vehicle performance requirements as claimed in claim 1, characterized in that: The user's basic data includes gender, age, place of origin, occupation and driving experience information, and the user's driving behavior data includes user driving data and application usage data.

3. The method for recommending cars based on matching user characteristics and vehicle performance requirements as claimed in claim 2, characterized in that: The user driving data includes speed, longitudinal acceleration, lateral acceleration, steering wheel acceleration, accelerator pedal angle and brake pedal angle; the application usage data includes music playback type, style preference, navigation voice type and average volume data.

4. The method for recommending cars based on matching user characteristics and vehicle performance requirements as claimed in claim 1, characterized in that: The user's basic data, user driving data and application usage data are input into a personality classification model to predict the user's personality characteristics; the personality classification model is a convolutional neural network.

5. The method for recommending cars based on matching user characteristics and vehicle performance requirements as claimed in claim 1, characterized in that: The speed parameters of the driver over a period of time are obtained, including speed, accelerator pedal usage percentage and brake pedal usage percentage data. After data cleaning, they are simplified to average speed, average accelerator pedal usage percentage and average brake pedal usage percentage. Cluster analysis is performed on all user driving speed preferences, and the clustered data are divided into high-speed preference class, medium-speed preference class and low-speed preference class.

6. The method for recommending cars based on matching user characteristics and vehicle performance requirements as claimed in claim 1, characterized in that: The driver's driving turning parameters over a period of time are obtained, including the absolute values ​​of the steering wheel speed and lateral acceleration data. After data cleaning, the average steering wheel speed and average lateral acceleration data are calculated. Then, a cluster analysis is performed on all users' turning control preferences, and the clustered data are divided into high turning sensitivity preference class, medium turning sensitivity preference class and low turning sensitivity preference class.

7. A car recommendation system based on matching user characteristics and vehicle performance requirements, characterized in that: include: A data acquisition module is used to obtain basic user data and user driving behavior data; A clustering module, for obtaining the user's personality characteristics by using a machine learning algorithm based on the user's basic data and the user's driving behavior data, and mapping the user's personality characteristics with the vehicle brand to form a first vehicle model set; Acquire the driver's driving speed parameters and driving turning parameters based on the user's driving behavior data; Clustering user turning control preferences based on driving turning parameters and classifying turning agility preferences; Clustering users’ driving speed preferences based on driving speed parameters and classifying speed preferences; Cluster analysis is performed based on the speed parameters of various vehicle models to classify vehicle speed types; Cluster analysis is performed based on the turning data of various vehicle models to classify vehicle models with sensitive turning ability; The vehicle speed model and the speed preference type are mapped to form a second model set, and the vehicle turning sensitivity model and the turning sensitivity preference type are mapped to form a third model set; The recommendation module is used to take the intersection of the first model set, the second model set and the third model set to obtain the final brand model recommendation result.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the car recommendation method based on matching user characteristics and vehicle performance requirements as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the car recommendation method based on matching user characteristics and vehicle performance requirements as described in any one of claims 1-6 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the car recommendation method based on matching user characteristics and vehicle performance requirements as described in any one of claims 1-6.

Images