High-quality user mining determination method and system based on automobile brand

Abstract

The invention relates to the technical field of automobile marketing, and particularly discloses a high-quality user mining determination method and system based on an automobile brand, and the method comprises the steps: obtaining the personal information of a user, and constructing a user data group based on the personal information of the user; determining a family relationship network based on the user data group, and determining the number of automobiles in the family relationship network based on the family relationship network; obtaining a message and published information of a user on a network platform in real time, and performing information integration based on the message and the published information to determine a user recognition degree; acquiring mark information of the 4S store side to the user in real time; certain weights are given to the number of automobiles, the user recognition degree and the mark information under the family relationship network, and the weighted sum of the number of automobiles, the user recognition degree and the mark information under the family relationship network is determined based on the given weights; the high-quality users are determined based on the weighted sum result, and in the process of mining the high-quality users, the high-quality users are determined more accurately through calculation of the weighted sum from the home side, the personal side and the 4S store.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile marketing, and specifically to a method and system for mining and determining high-quality users based on automobile brands. Background Art

[0002] With the development of the Internet and its continuous penetration into the automobile industry, the Internet marketing model has developed rapidly. The marketing model is no longer limited to non-targeted marketing. By using the Internet, potential users can be quickly and accurately analyzed, and relatively reasonable push or personalized marketing strategies can be implemented, which can greatly increase the probability of customer conversion.

[0003] In the actual marketing process, it is found that the credibility of users' self-promotion of their experiences during use is higher, and the marketing effect is also better. Users' spontaneous promotion requires no marketing cost but has the best marketing effect. Therefore, mining high-quality users who can promote spontaneously is part of automobile brand marketing. High-quality users can not only be transformed into automobile brand propagandists, but also provide reference opinions for the improvement of automobile brands. By mining high-quality users, corresponding user maintenance strategies can be carried out, increasing user stickiness while enhancing the automobile brand image. However, the existing technology still stays at mining high-quality potential customers and does not focus on high-quality users who have already purchased. The maintenance of high-quality users is also the focus of automobile brand image building. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for mining and determining high-quality users based on automobile brands to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A method for mining and determining high-quality users based on automobile brands, the method comprising: Obtain user personal information and construct a user data group based on the user personal information; Determine the family relationship network based on the user data group, and determine the number of automobiles under the family relationship network based on the family relationship network; Real-time obtain the messages and published information of the user on the network platform, and integrate the information based on the messages and published information to determine the user recognition; Real-time obtain the marking information of the user at the 4S store end; Respectively assign certain weights to the number of automobiles under the family relationship network, user recognition, and marking information, and determine the weighted sum of the number of automobiles under the family relationship network, user recognition, and marking information based on the assigned weights; Determine high-quality users based on the weighted sum result.

[0006] As a further solution of the present invention, the steps of obtaining the user's personal information and constructing a user data group based on the user's personal information specifically include: Obtain the information of car purchase registration users and vehicle information; Obtain the corresponding driving violation image information and parking lot video recording image information according to the vehicle information, and determine the actual driver based on the violation image information and the parking lot video recording image information. There may be multiple actual drivers; Construct a user data group based on the actual driver.

[0007] As a further solution of the present invention, the steps of determining the family relationship network based on the user data group and determining the number of cars under the family relationship network specifically include: Obtain the vehicle maintenance or repair information based on the vehicle information; Determine the user connected to the vehicle according to the vehicle maintenance or repair information; Classify the user connected to the vehicle and the actual driver into the same family relationship network; Determine the number of cars according to the members of the same family relationship network.

[0008] As a further solution of the present invention, the steps of obtaining the user's messages and published information on the network platform in real time and determining the user recognition degree based on the messages and published information specifically include: Obtain the user's messages and published information on the network platform in real time; Screen the messages and published information for car keywords to generate the screened messages and published information; Perform cluster analysis on the screened messages and published information; Determine the recognition degree based on the cluster analysis results.

[0009] As a further solution of the present invention, the steps of determining high-quality users based on the weighted sum result specifically include: Calculate the activity of users in the same family relationship network based on the messages and published information; Retain the user with the highest activity, and update the user data group; Sort the users in the user data group according to the weighted sum result; Determine high-quality users according to the preset weighted sum threshold.

[0010] As a further solution of the present invention, it further includes: Send a high-quality user binding invitation to the high-quality user terminal; When receiving the high-quality user confirmation binding information within the preset time period, bind the high-quality user to the car brand; When the high-quality user confirmation binding information is not received within a preset time period, the binding between the high-quality user and the automobile brand is cancelled.

[0011] The present invention further provides a high-quality user mining and determination system based on an automobile brand for implementing the high-quality user mining and determination method based on the automobile brand, characterized in that the system includes: A user data acquisition module for acquiring user personal information and constructing a user data group based on the user personal information; A relationship network determination module for determining a family relationship network based on the user data group and determining the number of automobiles under the family relationship network based on the family relationship network; An information integration module for acquiring the messages and published information of the user on the network platform in real time and determining the user recognition degree based on the messages and published information; A marking module for acquiring the marking information of the user by the 4S store end in real time; A weight assignment module for respectively assigning certain weights to the number of automobiles under the family relationship network, the user recognition degree and the marking information, and determining the weighted sum of the number of automobiles under the family relationship network, the user recognition degree and the marking information based on the assigned weights; A high-quality user determination module for determining high-quality users based on the weighted sum result.

[0012] As a further solution of the present invention, the user data acquisition module includes: An information acquisition unit for acquiring purchase registration user information and vehicle information; A driver determination unit for acquiring corresponding driving violation image information and parking lot recording image information according to the vehicle information, and determining the actual driver based on the violation image information and the parking lot recording image information, and the actual driver can be multiple; A data group construction unit for constructing a user data group based on the actual driver.

[0013] As a further solution of the present invention, the relationship network determination module includes: A maintenance or repair information acquisition unit for acquiring vehicle maintenance or repair information based on the vehicle information; A docking user determination unit for determining the user docked with the vehicle according to the vehicle maintenance or repair information; A relationship determination unit for classifying the user docked with the vehicle and the actual driver into the same family relationship network; A quantity determination unit for determining the number of automobiles according to the members of the same family relationship network.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: In the process of high-quality user mining, by determining the family relationship network, the degree of recognition of car brands under the family relationship network can be determined based on the number of cars under the family relationship network. In addition, by integrating the messages and published information about car brands on the network platform, the recognition data of users for car brands can be obtained. Moreover, the service personnel of 4S stores are involved in the process of high-quality user mining. The service personnel of 4S stores directly participate in the repair and maintenance process of users. Therefore, by calculating the weighted sum from the family side, the personal side and the 4S stores, the confirmation of high-quality users is made more accurate. Brief Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following-described drawings are only some embodiments of the present invention.

[0016] Figure 1 It is a flowchart of a method for determining high-quality user mining based on car brands provided by an embodiment of the present invention.

[0017] Figure 2 It is a flowchart of the steps of obtaining user personal information and constructing a user data group based on the user personal information provided by an embodiment of the present invention.

[0018] Figure 3 It is a flowchart of the steps of determining the family relationship network based on the user data group and determining the number of cars under the family relationship network based on the family relationship network provided by an embodiment of the present invention.

[0019] Figure 4 It is a flowchart of the steps of obtaining the messages and published information of users on the network platform in real time and determining the user recognition degree based on the integration of the messages and published information provided by an embodiment of the present invention.

[0020] Figure 5 It is a flowchart of the steps of determining high-quality users based on the weighted sum result provided by an embodiment of the present invention.

[0021] Figure 6 It is a block diagram of the composition structure of a system for determining high-quality user mining based on car brands provided by an embodiment of the present invention.

[0022] Figure 7 It is a block diagram of the composition structure of a user data acquisition module provided by an embodiment of the present invention.

[0023] Figure 8 It is a block diagram of the composition structure of a relationship network determination module provided by an embodiment of the present invention. Detailed Description of the Embodiments

[0024] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] Figure 1 As a flowchart of a method for determining high-quality users based on automobile brands, in an embodiment of the present invention, a method for determining high-quality users based on automobile brands, the method includes steps S100 to S600: A method for determining high-quality users based on automobile brands, the method includes: Step S100, obtain user personal information and construct a user data group based on the user personal information; Step S200, determine the family relationship network based on the user data group, and determine the number of automobiles under the family relationship network based on the family relationship network; Step S300, obtain the messages and published information of the user on the network platform in real time, and determine the user recognition degree based on the integration of the messages and the published information; Step S400, obtain the marking information of the user at the 4S store end in real time; Step S500, assign certain weights to the number of automobiles under the family relationship network, the user recognition degree and the marking information respectively, and determine the weighted sum of the number of automobiles under the family relationship network, the user recognition degree and the marking information based on the assigned weights; Step S600, determine high-quality users based on the weighted sum result.

[0026] In this embodiment, high-quality users refer to those who can participate in automobile promotion and improvement, have a high degree of recognition of the automobile brand, and can be transformed into propagandists when facing potential customers, thus directly increasing credibility and achieving better publicity effects. During the process of identifying high-quality users, the degree of recognition of the automobile brand within the family relationship network can be determined by the number of automobiles under the family relationship network through the determination of the family relationship network. In addition, by integrating the messages and published information about the automobile brand on the network platform, the recognition data of users for the automobile brand can be obtained. Furthermore, the service personnel of 4S stores are involved in the process of identifying high-quality users. The service personnel of 4S stores are directly involved in the maintenance and servicing process of users. Therefore, they can have a certain understanding of the degree of recognition of users. Through the 4S store terminal, users can be marked, and users who do not recognize the automobile brand can be initially screened out. The weights are determined using the analytic hierarchy process. By determining the weights, the final recognition data of each user can be further calculated, and high-quality users can be determined according to the recognition data. Thus, the audience of the user activities planned by the automobile brand can be determined, user stickiness can be increased, and at the same time, the degree of recognition of the automobile brand can be further increased, so that high-quality users and their vehicles can be transformed into mobile publicity stations.

[0027] As Figure 2 shown, as a preferred embodiment of the present invention, the steps of obtaining user personal information and constructing a user data group based on the user personal information specifically include: Step S101, obtaining purchase registration user information and vehicle information; Step S102, obtaining corresponding driving violation image information and parking lot surveillance image information according to the vehicle information, and determining the actual driver based on the violation image information and the parking lot surveillance image information. There can be multiple actual drivers; Step S103, constructing a user data group based on the actual driver.

[0028] In this embodiment, during the process of purchasing a vehicle at a 4S store, information registration is generally carried out. The registration information includes the mobile phone number, name, and purchased vehicle model, so as to facilitate later quality assurance and maintenance. Considering that some users who register the vehicle are not the actual drivers, and some vehicle-registering users even do not have a driver's license. Therefore, taking the registered users alone as high-quality users will cause waste of later maintenance costs. Therefore, in this embodiment, by obtaining driving violation image information and parking lot recording image information, the actual driver can be further determined. When a violation occurs during road driving, the electronic eye will take a timely photo of the vehicle and retain it as evidence of the violation. Similarly, when entering a toll parking lot, photos will be taken and recorded when entering and leaving. Therefore, the portrait information of the driver can be obtained through the driving violation image information and the parking lot recording image information, and the actual driver can be determined through the portrait information. At this time, the registered users can be excluded, and the actual driver can be classified into the user dataset alone, so as to improve the efficiency of maintaining high-quality users and increase the probability of high-quality users being converted into publicity personnel later.

[0029] As Figure 3 shown, as a preferred embodiment of the present invention, the steps of determining the family relationship network based on the user data group and determining the number of vehicles under the family relationship network specifically include: Step S201, obtaining vehicle repair or maintenance information based on the vehicle information; Step S202, determining the user docking with the vehicle according to the vehicle repair or maintenance information; Step S203, classifying the user docking with the vehicle and the actual driver into the same family relationship network; Step S204, determining the number of vehicles according to the members of the same family relationship network.

[0030] In this embodiment, considering the license plate number restriction factor, in the city, it is quite common for a family to have two vehicles, or even more than two, generally in the form of a combination of fuel drive and new energy drive. The current vehicle repair and maintenance information can be obtained through the vehicle information. When the vehicle is driven to the repair and maintenance place, the information of the vehicle delivery person, including the contact phone number, name, etc., is generally retained. The vehicle delivery person is the user docking with the vehicle. In the same family relationship network, the vehicle under the father's name may be entrusted to the children for repair or maintenance. Similarly, the children's vehicles may be entrusted to the parents for repair or maintenance. There are also cases of entrusted repair and maintenance between children or spouses. When all the vehicles in the same family relationship network are of this car brand, it can be considered that the family relationship network has a high recognition of this car brand. By obtaining the information of the vehicle delivery person, the vehicle delivery person and the actual driver can be classified into the same family relationship network, and the number of vehicles of this car brand under the same family relationship network can also be determined.

[0031] As Figure 4 shown, as a preferred embodiment of the present invention, the steps of obtaining the user's messages and published information on the network platform in real time and determining the user recognition degree based on the messages and published information specifically include: Step S301: Obtain the user's messages and published information on the network platform in real time; Step S302: Screen the messages and published information for car keywords to generate the screened messages and published information; Step S303: Conduct a clustering analysis on the screened messages and published information; Step S304: Determine the recognition degree based on the clustering analysis result.

[0032] In this embodiment, the network platforms include "Autohome", "Douyin", "Pacific Auto", etc. In the above platforms, driving doubts can be answered and interactions can be carried out with other car owners. Therefore, in this embodiment, by obtaining the interaction information of the user on each network platform, the attitude of the user towards the car brand can be understood. The obtained messages and published information first need to be screened for keywords, and the keywords include cars, specific brands, brand features, etc. The keywords need to be set specifically according to the specific car brand. The screened messages and published information are the texts related to the car brand. Then, by conducting a clustering analysis on the screened messages and published information, the screened messages and published information are divided into medium evaluations, negative evaluations, and positive evaluations, and the recognition degree is determined by calculating the proportion of positive evaluations.

[0033] As Figure 5 shown, as a preferred embodiment of the present invention, the steps of determining high-quality users based on the weighted sum result specifically include: Step S601: Calculate the activity of users in the same family relationship network based on the messages and published information; Step S602: Retain the user with the highest activity and update the user data group; Step S603: Sort the users in the user data group according to the weighted sum result; Step S604: Determine high-quality users according to the preset weighted sum threshold.

[0034] In this embodiment, by calculating the activity of users in the same family relationship network based on the messages and published information of users on the network platform, it can be considered that one user is selected as the representative of high-quality users in the same family relationship network, avoiding waste of quota in later event planning. The representativeness of the family is reflected in the activity on the network platform, which can indirectly indicate the degree of acceptance of new things. In the maintenance of high-quality users, activities such as quiz with prizes, driving tours, and fun driving games may be planned. Therefore, high-quality users are required to have the ability to accept new things. Therefore, the family representative is selected through the degree of interaction with the network platform, and the data group is updated according to the selected family representative. Here, the update means removing other users in the same family relationship network, which can reduce the later maintenance cost and make the brand information promotion more concentrated, and then determine high-quality users through weighted sum and threshold.

[0035] As a preferred embodiment of the present invention, it further includes: Sending a high-quality user binding invitation to the high-quality user terminal; When receiving the high-quality user confirmation binding information within a preset time period, binding the high-quality user with the car brand; When not receiving the high-quality user confirmation binding information within a preset time period, canceling the binding of the high-quality user with the car brand.

[0036] In this embodiment, considering that some users have a high recognition of the car brand, but have a negative attitude towards brand promotion activities and user maintenance, or cannot be contacted, therefore, in this embodiment, the determined high-quality users are sent high-quality user binding invitations by text message or in the form of a pop-up window on the network platform. When the high-quality user receives the invitation, the confirmation of the binding invitation is completed by clicking "confirm" or sending a specified character. Secondly, by setting a preset time period, a certain buffer time can be given, and the high-quality user binding invitation is repeatedly sent at regular intervals within the preset time period, so as to ensure that the high-quality user can receive the high-quality user binding invitation.

[0037] As Figure 6 shown, the embodiment of the present invention also provides a high-quality user mining and determination system based on a car brand. The system includes: A user data acquisition module 100, configured to acquire user personal information and construct a user data group based on the user personal information; A relationship network determination module 200, configured to determine a family relationship network based on the user data group and determine the number of cars under the family relationship network based on the family relationship network; An information integration module 300, configured to acquire the messages and published information of users on the network platform in real time and determine the user recognition degree based on the messages and published information for information integration; A marking module 400 for obtaining in real time the marking information of users by the 4S store A weight assignment module 500 for respectively assigning certain weights to the number of vehicles under the family relationship network, user recognition, and marking information, and determining the weighted sum of the number of vehicles under the family relationship network, user recognition, and marking information based on the assigned weights An excellent user determination module 600 for determining excellent users based on the weighted sum result

[0038] As Figure 7 shown, as a preferred embodiment of the present invention, the user data acquisition module 100 includes: An information acquisition unit 101 for acquiring purchase registration user information and vehicle information A driver determination unit 102 for acquiring corresponding driving violation image information and parking lot recording image information according to the vehicle information, and determining the actual driver based on the violation image information and the parking lot recording image information. The actual driver can be multiple A data group construction unit 103 for constructing a user data group based on the actual driver

[0039] As Figure 8 shown, as a preferred embodiment of the present invention, the relationship network determination module 200 includes: A repair or maintenance information acquisition unit 201 for acquiring vehicle repair or maintenance information based on the vehicle information A docking user determination unit 202 for determining the user docked with the vehicle according to the vehicle repair or maintenance information A relationship determination unit 203 for classifying the user docked with the vehicle and the actual driver into the same family relationship network A quantity determination unit 204 for determining the number of vehicles according to the members of the same family relationship network

[0040] The data involved in the disclosure of the present invention can be data authorized by users or fully authorized by all parties. The collection, dissemination, use, etc. of the data all comply with the requirements of relevant national laws and regulations

[0041] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention

Claims

1. A method for determining the excavation of high-quality users based on automobile brands, characterized in that, The method includes: Obtain user personal information and construct a user data group based on the user personal information; Determine the family relationship network based on the user data group, and determine the number of cars under the family relationship network based on the family relationship network; Obtain the messages and published information of the user on the network platform in real time, and determine the user recognition degree through information integration based on the messages and published information; Obtain the marking information of the user from the 4S store side in real time; Assign certain weights to the number of cars under the family relationship network, the user recognition degree, and the marking information respectively, and determine the weighted sum of the number of cars under the family relationship network, the user recognition degree, and the marking information based on the assigned weights; Determine high-quality users based on the weighted sum result.

2. The method for determining high-quality users based on automobile brands according to claim 1, wherein The step of obtaining user personal information and constructing a user data group based on the user personal information specifically includes: Obtain the information of car purchase registration users and vehicle information; Obtain the corresponding driving violation image information and parking lot video recording image information according to the vehicle information, and determine the actual drivers based on the violation image information and the parking lot video recording image information. There can be multiple actual drivers; Construct a user data group based on the actual drivers.

3. The method for determining high-quality users based on automobile brands according to claim 2, wherein The step of determining the family relationship network based on the user data group and determining the number of cars under the family relationship network based on the family relationship network specifically includes: Obtain vehicle maintenance or repair information based on the vehicle information; Determine the users connected to the vehicle according to the vehicle maintenance or repair information; Classify the users connected to the vehicle and the actual drivers into the same family relationship network; Determine the number of cars according to the members of the same family relationship network.

4. The method for determining high-quality users based on automobile brands according to claim 1, characterized in that The step of obtaining the messages and published information of the user on the network platform in real time and determining the user recognition degree through information integration based on the messages and published information specifically includes: Obtain the messages and published information of the user on the network platform in real time; Screen the messages and published information for car keywords to generate the screened messages and published information; Conduct cluster analysis on the screened messages and published information; Determine the recognition degree based on the cluster analysis result.

5. The method for determining high-quality users based on automobile brands according to claim 1, characterized in that The step of determining high-quality users based on the weighted sum result specifically includes: Calculate the activity of users in the same family relationship network based on the messages and published information; Retain the user with the highest activity and update the user data group; Sort the users in the user data group according to the weighted sum result; Determine high-quality users according to the preset weighted sum threshold.

6. The method for determining high-quality users based on automobile brands according to claim 1, wherein It also includes: Send a high-quality user binding invitation to the high-quality user side; When the high-quality user confirmation binding information is received within the preset time period, bind the high-quality user with the car brand; When the high-quality user confirmation binding information is not received within the preset time period, cancel the binding of the high-quality user with the car brand.

7. A high-quality user mining and determination system based on automobile brands, which is used to implement the high-quality user mining and determination method based on automobile brands according to any one of claims 1-6, and is characterized in that, The system includes: A user data acquisition module for obtaining user personal information and constructing a user data group based on the user personal information; A relationship network determination module for determining the family relationship network based on the user data group and determining the number of cars under the family relationship network based on the family relationship network; An information integration module for obtaining the messages and published information of the user on the network platform in real time and determining the user recognition degree through information integration based on the messages and published information; A marking module for obtaining the marking information of the user from the 4S store side in real time; A weight assignment module, which is used to assign certain weights to the number of vehicles, user recognition, and marking information under the family relationship network respectively, and determine the weighted sum of the number of vehicles, user recognition, and marking information under the family relationship network based on the assigned weights; An excellent user determination module, which is used to determine excellent users based on the weighted sum result.

8. The high-quality user mining and determination system based on automobile brands according to claim 7, wherein, The user data acquisition module includes: An information acquisition unit, which is used to acquire vehicle purchase registration user information and vehicle information; A driver determination unit, which is used to acquire corresponding driving violation image information and parking lot recording image information according to the vehicle information, and determine the actual driver based on the driving violation image information and the parking lot recording image information. There can be multiple actual drivers; A data group construction unit, which is used to construct a user data group based on the actual driver.

9. The high-quality user mining and determination system based on automobile brands according to claim 7, characterized in that The relationship network determination module includes: A maintenance or repair information acquisition unit, which is used to acquire vehicle maintenance or repair information based on the vehicle information; A docking user determination unit, which is used to determine the user docked with the vehicle according to the vehicle maintenance or repair information; A relationship determination unit, which is used to classify the user docked with the vehicle and the actual driver into the same family relationship network; A quantity determination unit, which is used to determine the number of vehicles according to the members of the same family relationship network.

Images