Vehicle recommendation method and intelligent exhibition hall digital vehicle configuration interaction system
By obtaining and analyzing customer's car purchase behavior information, generating car purchase demand information and recommending car models and accessories, the problems of traditional car recommendation methods are solved, and the efficiency and satisfaction of car purchase are improved, and personalized car purchase is realized. Experience.
Patent Information
- Application Number
- CN202411630746.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-02-18
AI Technical Summary
Traditional car recommendation methods have problems such as strong subjectivity and incomplete information, which are difficult to effectively meet customers' car purchase needs.
By obtaining the customer's initial car purchase behavior information, generating car purchase demand information, and recommending pre-selected models and accessories to the customer based on this, combining the target models and accessories selected by the customer to display the target vehicle.
It improves the efficiency and experience of customers' car purchases, accurately grasps customers' car purchase needs and preferences, improves sales conversion rate and customer satisfaction, and realizes a personalized car purchase experience.
Smart Images
Figure CN119477477A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a vehicle recommendation method and a digital vehicle matching interactive system for a smart exhibition hall. Background Art
[0002] In the process of car purchase, customers are faced with many choices, such as car models, configurations, accessories, etc., and often need to spend a lot of time and energy to make decisions. The traditional car recommendation method mainly relies on sales staff to make recommendations based on the needs expressed by customers, but this method may have problems such as strong subjectivity and incomplete information. Therefore, a method is needed to automatically generate and recommend car models and accessories that meet customer needs based on car purchase behavior information. Summary of the invention
[0003] The present application provides a vehicle recommendation method, device, equipment and storage medium to solve the problems raised by the above background technology.
[0004] In a first aspect, the present application provides a vehicle recommendation method, comprising: Obtain information about the customer's initial car-buying behavior; generating the customer's car purchase demand information based on the initial car purchase behavior information; Based on the vehicle purchase demand information, recommend pre-selected vehicle models and pre-selected accessories to the customer; wherein the pre-selected vehicle models include multiple vehicle models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories; In response to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected by the customer from the pre-selected accessories, the target vehicle model and the target accessories are combined to obtain a target vehicle; The target vehicle is presented to the customer.
[0005] In a possible implementation, the generating the customer's car purchase demand information based on the initial car purchase behavior information includes: Cleaning the initial car purchase behavior information to obtain target car purchase behavior information; Performing matrix coding on the target car purchase behavior information to obtain a feature matrix corresponding to the target car purchase behavior information; The customer's car purchase demand information is generated based on the feature matrix.
[0006] In a possible implementation, matrix encoding the target car purchase behavior information to obtain a feature matrix corresponding to the target car purchase behavior information includes: Inputting the target car purchase behavior information into a preset information classification model to obtain multiple types of information; For each type of information, a label vector corresponding to the information is obtained from a preset database; wherein the label vector includes a category number and a feature vector space of the information; For each type of information, the information is input into a preset information feature extraction model to obtain a feature vector corresponding to the information, and the feature vector is inserted into a feature vector vacancy of a label vector corresponding to the information to obtain a target feature vector corresponding to the information; The target feature vectors are combined based on a preset feature vector combination method to obtain the feature matrix.
[0007] In a possible implementation, the generating the customer's car purchase demand information based on the feature matrix includes: For each target feature vector of the feature matrix, a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector is obtained in a preset database based on the category number corresponding to the target feature vector, and the car purchase demand corresponding to the target feature vector is determined based on the car purchase demand-feature vector mapping relationship table; The car purchase demand information is generated based on each of the car purchase demands.
[0008] In a possible implementation, the preset database includes a plurality of encrypted texts, and the step of obtaining a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector in the preset database based on the category number corresponding to the target feature vector includes: Based on the category number, a decrypted text corresponding to the target feature vector is obtained in a preset database; wherein the decrypted text includes an identification function and a plane rectangular coordinate system; Draw a function curve of the identification function in the plane rectangular coordinate system; Determine the extreme point of the function curve as a first target point, and determine the inflection point of the function curve as a second target point; wherein the first target point and the second target point each include a plurality; respectively adding the abscissa and the ordinate of each of the first target points to obtain a plurality of first numbers, and arranging the first numbers in sequence based on the position of the abscissa corresponding to each of the first numbers in the plane rectangular coordinate system to obtain a first digital sequence; respectively adding the abscissa and the ordinate of each of the second target points to obtain a plurality of second numbers, and arranging the second numbers in sequence based on the position of the abscissa corresponding to each of the second numbers in the plane rectangular coordinate system to obtain a second number sequence; Obtaining a hash value of the first digital sequence based on a preset hash algorithm to obtain a first hash value, and obtaining a hash value of the second digital sequence based on the hash algorithm to obtain a second hash value; Combining the first hash value and the second hash value based on a preset hash value combination method to obtain a decryption password; Decryption processing is performed on each of the encrypted texts based on the decryption password, and the successfully decrypted encrypted text is determined to be the target text; wherein the target text includes a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector.
[0009] In a possible implementation, determining the car purchase demand corresponding to the target feature vector based on the car purchase demand-feature vector mapping relationship table includes: The similarities between the target feature vector and each feature vector in the car purchase demand-feature vector mapping relationship table are calculated respectively, and the car purchase demand corresponding to the maximum similarity among the similarities is determined as the car purchase demand corresponding to the target feature vector.
[0010] In a second aspect, the present application provides a smart exhibition hall digital car matching interactive system, including: Acquisition module: used to obtain the customer's initial car purchase behavior information; Data analysis module: used to generate the customer's car purchase demand information based on the initial car purchase behavior information; Intelligent recommendation module: used for recommending pre-selected models and pre-selected accessories to the customer based on the car purchase demand information; wherein the pre-selected models include multiple models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories; Intelligent combination module: used for responding to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected by the customer from the pre-selected accessories, combining the target vehicle model and the target accessories to obtain a target vehicle; A digital display module is used to display the target vehicle to the customer.
[0011] The present application provides a vehicle recommendation method and a smart exhibition hall digital car matching interactive system, wherein the method includes: obtaining the initial car purchase behavior information of the customer; generating the car purchase demand information of the customer based on the initial car purchase behavior information; recommending pre-selected models and pre-selected accessories to the customer based on the car purchase demand information; wherein the pre-selected models include multiple models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories; in response to the target model selected by the customer in the pre-selected models and the target accessories selected by the pre-selected accessories, the target model and the target accessories are combined to obtain a target vehicle; and the target vehicle is displayed to the customer. The method, on the one hand, enables customers to quickly understand the information and characteristics of automobile models through digital display and real-time interactive functions, and make personalized choices and configurations, thereby improving the customer's car purchase efficiency and car purchase experience. On the other hand, through data analysis and intelligent recommendation functions, it can accurately grasp the customer's car purchase needs and preferences and provide personalized recommendation services. This helps to improve sales conversion rate and customer satisfaction and achieve precision marketing. On the other hand, the selection of models and accessories is carried out according to the customer's preferences and needs, realizing a personalized car purchase experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.
[0013] Figure 1 A schematic diagram of a vehicle recommendation method according to an embodiment of the present application; Figure 2 A schematic block diagram of the structure of the digital car matching interactive system for a smart showroom provided in an embodiment of the present application; DETAILED DESCRIPTION
[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0015] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0016] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0017] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0018] In the process of car purchase, customers are faced with many choices, such as car models, configurations, accessories, etc., and it often takes a lot of time and energy to make decisions. The traditional way of recommending cars mainly relies on sales staff to make recommendations based on the needs expressed by customers, but this method may have problems such as strong subjectivity and incomplete information. Therefore, there is a need for a method that can automatically generate and recommend car models and accessories that meet customer needs based on car purchase behavior information. To this end, the present application provides a vehicle recommendation method and a smart showroom digital car matching interactive system to solve the above problems.
[0019] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0020] See also Figure 1 , Figure 1 A flow chart of a vehicle recommendation method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the vehicle recommendation method provided in the embodiment of the present application includes steps S100 to S500.
[0021] Step S100: Obtain the customer's initial car purchase behavior information.
[0022] It should be noted that the execution subject of this embodiment is the smart exhibition hall digital car matching interactive system 100. The smart exhibition hall digital car matching interactive system 100 includes an acquisition module 110, a data analysis module 120, an intelligent recommendation module 130, an intelligent combination module 140, and a digital display module 150.
[0023] The acquisition module 110 acquires the customer's initial car purchase behavior information. Specifically, the customer can interact with the smart exhibition hall digital car matching interactive system 100 in real time through the touch screen or AI voice module of the smart exhibition hall digital car matching interactive system 100, customize the color, wheels, spare parts and interior of the vehicle, and browse on the smart exhibition hall digital car matching interactive system 100 to view the content of interest or choose their own preferences. It can be understood that the customer's customized content, the content browsed on the smart exhibition hall digital car matching interactive system 100, and the selected content are the initial car purchase behavior information. That is, the content of the interaction between the customer and the smart exhibition hall digital car matching interactive system 100 can be used as the initial car purchase behavior information.
[0024] Step S200: generating the customer's car purchase demand information based on the initial car purchase behavior information.
[0025] The data analysis module 120 generates the customer's car purchase demand information based on the initial car purchase behavior information. Specifically, first, the repeated information in the initial car purchase behavior information is cleaned to obtain the target car purchase behavior information. Then, the target car purchase behavior information is matrix-encoded to obtain the feature matrix corresponding to the target car purchase behavior information. Finally, the customer's car purchase demand information is generated based on the feature matrix.
[0026] Step S300: recommending pre-selected vehicle models and pre-selected accessories to the customer based on the vehicle purchase demand information; wherein the pre-selected vehicle models include multiple vehicle models, the pre-selected accessories include multiple types of accessories, and each type of accessory includes multiple accessories.
[0027] The intelligent recommendation module 130 recommends pre-selected car models and pre-selected accessories to the customer based on the car purchase demand information. Specifically, it provides personalized car model recommendations and accessory recommendations to the customer based on the inventory and sales status of car models, as well as the inventory and sales status of accessories.
[0028] Step S400: In response to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected by the customer from the pre-selected accessories, the target vehicle model and the target accessories are combined to obtain a target vehicle.
[0029] The intelligent combination module 140 responds to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected from the pre-selected accessories, and combines the target vehicle model and the target accessories to obtain a target vehicle. Specifically, based on the function of each target accessory, each target accessory is combined at a corresponding position of the target vehicle model to obtain the target vehicle.
[0030] Step S500: display the target vehicle to the customer.
[0031] The digital display module 150 displays the target vehicle to the customer, specifically, the target vehicle is displayed through the high-definition transparent touch screen of the smart exhibition hall digital car matching interactive system 100. It should be noted that after the digital display module 150 displays the target vehicle on the high-definition transparent touch screen, the customer can have a global view of the target vehicle after performing corresponding operations on the high-definition transparent touch screen. The global view includes the appearance structure, internal structure and structure of each component of the target vehicle, which can provide an intuitive and vivid visual experience for the customer.
[0032] The method provided in this embodiment, on the one hand, enables customers to quickly understand the information and characteristics of automobile models through digital display and real-time interactive functions, and make personalized choices and configurations, thereby improving customers' car purchasing efficiency and car purchasing experience. On the other hand, through data analysis and intelligent recommendation functions, it can accurately grasp customers' car purchasing needs and preferences and provide personalized recommendation services. This helps to improve sales conversion rate and customer satisfaction, and realize precision marketing. On the other hand, the car model and accessories are selected according to the customer's preferences and needs, realizing a personalized car purchasing experience.
[0033] In some embodiments, performing matrix encoding on the target car purchase behavior information to obtain a feature matrix corresponding to the target car purchase behavior information includes the following steps: Input the target car purchase behavior information into a preset information classification model to obtain multiple types of information; wherein the information classification model includes an input layer, a feature extraction layer, a classification layer and an output layer, the input layer is used to receive the target car purchase behavior information, the feature extraction layer is used to extract features from the target car purchase behavior information to obtain classification feature information, the classification layer is used to generate multiple types of information based on the classification feature information, and the output layer is used to output multiple types of information; For each type of information, a label vector corresponding to the information is obtained from a preset database; wherein the label vector includes a category number and a feature vector space of the information; For each type of information, the information is input into a preset information feature extraction model to obtain a feature vector corresponding to the information, and the feature vector is inserted into a feature vector vacancy of a label vector corresponding to the information to obtain a target feature vector corresponding to the information; wherein the information feature extraction model comprises an input layer, a feature extraction layer, a feature vector generation layer and an output layer, the input layer is used to receive the information, the feature extraction layer is used to extract the features of the information, the feature vector generation layer is used to generate a feature vector of the information based on the features of the information, and the output layer is used to output the feature vector; The target feature vectors are combined based on a preset feature vector combination method to obtain the feature matrix.
[0034] In the method provided by this embodiment, since each target feature vector of the feature matrix includes a corresponding category number, the feature matrix provided by this embodiment helps to prevent calculation disorder and improve the accuracy of the car purchase demand information during the process of generating the car purchase demand information.
[0035] In some embodiments, generating the customer's car purchase demand information based on the feature matrix includes: For each target feature vector of the feature matrix, a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector is obtained in a preset database based on the category number corresponding to the target feature vector, and the car purchase demand corresponding to the target feature vector is determined based on the car purchase demand-feature vector mapping relationship table; The car purchase demand information is generated based on each of the car purchase demands.
[0036] Specifically, the preset database includes a plurality of encrypted texts, and obtaining a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector in the preset database based on the category number corresponding to the target feature vector includes the following steps: Based on the category number, a decrypted text corresponding to the target feature vector is obtained in a preset database; wherein the decrypted text includes an identification function and a plane rectangular coordinate system; Draw a function curve of the identification function in the plane rectangular coordinate system; Determine the extreme point of the function curve as a first target point, and determine the inflection point of the function curve as a second target point; wherein the first target point and the second target point each include a plurality; respectively adding the abscissa and the ordinate of each of the first target points to obtain a plurality of first numbers, and arranging the first numbers in sequence based on the position of the abscissa corresponding to each of the first numbers in the plane rectangular coordinate system to obtain a first digital sequence; respectively adding the abscissa and the ordinate of each of the second target points to obtain a plurality of second numbers, and arranging the second numbers in sequence based on the position of the abscissa corresponding to each of the second numbers in the plane rectangular coordinate system to obtain a second number sequence; Obtaining a hash value of the first digital sequence based on a preset hash algorithm to obtain a first hash value, and obtaining a hash value of the second digital sequence based on the hash algorithm to obtain a second hash value; Combining the first hash value and the second hash value based on a preset hash value combination method to obtain a decryption password; Decryption processing is performed on each of the encrypted texts based on the decryption password, and the successfully decrypted encrypted text is determined to be the target text; wherein the target text includes a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector.
[0037] Specifically, determining the car purchase demand corresponding to the target feature vector based on the car purchase demand-feature vector mapping relationship table includes: The similarities between the target feature vector and each feature vector in the car purchase demand-feature vector mapping relationship table are calculated respectively, and the car purchase demand corresponding to the maximum similarity among the similarities is determined as the car purchase demand corresponding to the target feature vector.
[0038] The method provided in this embodiment can prevent the car purchase demand-feature vector mapping relationship table from being tampered with by unauthorized personnel, thereby improving the security of the car purchase demand-feature vector mapping relationship table, thereby improving the accuracy of the car purchase demand information, and further improving the customer's car purchase experience.
[0039] See also Figure 2 , Figure 2 The structure schematic block diagram of the smart exhibition hall digital car matching interactive system 100 provided in the embodiment of the present application is as follows: Figure 2 As shown, the smart exhibition hall digital car matching interactive system 100 includes: Acquisition module 110: used to acquire the customer's initial car purchase behavior information.
[0040] Data analysis module 120: used to generate the customer's car purchase demand information based on the initial car purchase behavior information.
[0041] Intelligent recommendation module 130: used to recommend pre-selected car models and pre-selected accessories to the customer based on the car purchase demand information; wherein the pre-selected car models include multiple car models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories.
[0042] Intelligent combination module 140: used for responding to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected by the customer from the pre-selected accessories, combining the target vehicle model and the target accessories to obtain a target vehicle.
[0043] The digital display module 150 is used to display the target vehicle to the customer.
[0044] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system and each module can refer to the corresponding processes in the aforementioned vehicle recommendation method embodiment, and will not be repeated here.
[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A vehicle recommendation method, characterized in that: include: Obtain information about the customer's initial car-buying behavior; generating the customer's car purchase demand information based on the initial car purchase behavior information; Based on the vehicle purchase demand information, recommend pre-selected vehicle models and pre-selected accessories to the customer; wherein the pre-selected vehicle models include multiple vehicle models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories; In response to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected from the pre-selected accessories, the target vehicle model and the target accessories are combined to obtain a target vehicle; The target vehicle is presented to the customer.
2. The vehicle recommendation method according to claim 1, characterized in that: The generating the customer's car purchase demand information based on the initial car purchase behavior information includes: Cleaning the initial car purchase behavior information to obtain target car purchase behavior information; Performing matrix coding on the target car purchase behavior information to obtain a feature matrix corresponding to the target car purchase behavior information; The customer's car purchase demand information is generated based on the feature matrix.
3. The vehicle recommendation method according to claim 2, characterized in that: The matrix encoding of the target car purchase behavior information to obtain a feature matrix corresponding to the target car purchase behavior information includes: Inputting the target car purchase behavior information into a preset information classification model to obtain multiple types of information; For each type of information, a label vector corresponding to the information is obtained from a preset database; wherein the label vector includes a category number and a feature vector vacancy of the information; For each type of information, the information is input into a preset information feature extraction model to obtain a feature vector corresponding to the information, and the feature vector is inserted into a feature vector vacancy of a label vector corresponding to the information to obtain a target feature vector corresponding to the information; The target feature vectors are combined based on a preset feature vector combination method to obtain the feature matrix.
4. The vehicle recommendation method according to claim 3, characterized in that: The generating the customer's car purchase demand information based on the feature matrix includes: For each target feature vector of the feature matrix, a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector is obtained in a preset database based on the category number corresponding to the target feature vector, and the car purchase demand corresponding to the target feature vector is determined based on the car purchase demand-feature vector mapping relationship table; The car purchase demand information is generated based on each of the car purchase demands.
5. The vehicle recommendation method according to claim 4, characterized in that: The preset database includes a plurality of encrypted texts, and the method of obtaining a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector in the preset database based on the category number corresponding to the target feature vector includes: Based on the category number, a decrypted text corresponding to the target feature vector is obtained in a preset database; wherein the decrypted text includes an identification function and a plane rectangular coordinate system; Draw a function curve of the identification function in the plane rectangular coordinate system; Determine the extreme point of the function curve as a first target point, and determine the inflection point of the function curve as a second target point; wherein the first target point and the second target point each include a plurality; respectively adding the abscissa and the ordinate of each of the first target points to obtain a plurality of first numbers, and arranging the first numbers in sequence based on the position of the abscissa corresponding to each of the first numbers in the plane rectangular coordinate system to obtain a first digital sequence; respectively adding the abscissa and the ordinate of each of the second target points to obtain a plurality of second numbers, and arranging the second numbers in sequence based on the position of the abscissa corresponding to each of the second numbers in the plane rectangular coordinate system to obtain a second number sequence; Obtaining a hash value of the first digital sequence based on a preset hash algorithm to obtain a first hash value, and obtaining a hash value of the second digital sequence based on the hash algorithm to obtain a second hash value; Combining the first hash value and the second hash value based on a preset hash value combination method to obtain a decryption password; Decryption processing is performed on each of the encrypted texts based on the decryption password, and the successfully decrypted encrypted text is determined to be the target text; wherein the target text includes a car purchase demand-feature vector mapping relationship table corresponding to the target feature vector.
6. The vehicle recommendation method according to claim 4, characterized in that: The determining the car purchase demand corresponding to the target feature vector based on the car purchase demand-feature vector mapping relationship table includes: The similarities between the target feature vector and each feature vector in the car purchase demand-feature vector mapping relationship table are calculated respectively, and the car purchase demand corresponding to the maximum similarity among the similarities is determined as the car purchase demand corresponding to the target feature vector.
7. A digital car matching interactive system for a smart exhibition hall, characterized in that: include: Acquisition module: used to obtain the customer's initial car purchase behavior information; Data analysis module: used to generate the customer's car purchase demand information based on the initial car purchase behavior information; Intelligent recommendation module: used for recommending pre-selected models and pre-selected accessories to the customer based on the car purchase demand information; wherein the pre-selected models include multiple models, the pre-selected accessories include multiple types of accessories, and each type of accessories includes multiple accessories; Intelligent combination module: used for responding to the target vehicle model selected by the customer from the pre-selected vehicle models and the target accessories selected by the customer from the pre-selected accessories, combining the target vehicle model and the target accessories to obtain a target vehicle; A digital display module is used to display the target vehicle to the customer.