Vehicle user classification method and apparatus, vehicle, and storage medium

Abstract

The application relates to a vehicle user classification method and device, a vehicle and a storage medium, wherein the method comprises the following steps: obtaining at least one vehicle user data of historical chat data, driving behavior data and a vehicle type of a vehicle user; performing data cleaning on the at least one vehicle user data to obtain cleaned vehicle user data; inputting the cleaned vehicle user data into a pre-constructed clustering model to obtain a classification result of the vehicle user; and performing active degree label division on the vehicle user based on the classification result and a preset vehicle user active degree model to obtain a final active degree classification result of the vehicle user. According to the embodiment of the application, the vehicle user is automatically divided through the clustering model, the classified vehicle user is combined with the vehicle user active degree model, the business label is set, the different vehicle users are targetedly operated, the activity of the vehicle user is accurately mobilized, and the satisfaction of the vehicle user is improved.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a method, device, vehicle, and storage medium for classifying vehicle users. Background Technology

[0002] The automotive industry is a vital pillar of the national economy. In recent years, with the booming development of my country's automotive market and the increasing competitiveness of the automotive industry, a comprehensive understanding of users is crucial. This can improve customer satisfaction and enhance corporate competitiveness. Accurately identifying and understanding users is of significant value in helping companies ultimately expand market share, increase sales, and predict the potential for future growth.

[0003] In related technologies, it is possible to acquire vehicle driving data from multiple vehicles, perform classification and preprocessing on the driving data of each vehicle to obtain the parking time and parking location of each vehicle trip, and generate user classification information corresponding to the vehicle after clustering through a clustering model.

[0004] However, in related technologies, the results obtained by using only clustering models are difficult to set business tags, while the results obtained by using only rule-based classification cannot determine the rule classification threshold, making it difficult to conduct targeted operations for different users, thus failing to accurately mobilize user activity and reducing user satisfaction, which urgently needs to be improved. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for classifying vehicle users, in order to solve the problem in related technologies where the results of classification using only clustering models are “0, 1, 2, 3, 4…”, which are labels without business meaning, while rule-based classification has the problem that the threshold cannot be determined and usually needs to be manually set.

[0006] The first aspect of this application provides a method for classifying vehicle users, comprising the following steps: acquiring at least one vehicle user data from historical chat data, driving behavior data, and vehicle type; cleaning the at least one vehicle user data to obtain cleaned vehicle user data; inputting the cleaned vehicle user data into a pre-constructed clustering model to obtain a classification result of the vehicle users; and classifying the vehicle users by activity tags based on the classification result and a preset vehicle user activity model to obtain a final activity classification result of the vehicle users.

[0007] Optionally, in one embodiment of this application, obtaining the vehicle user's historical chat data includes: obtaining at least one of the vehicle user's chat count, chat time difference, and chat days within a preset time period; and obtaining the vehicle user's historical chat data based on at least one of the chat count, chat time difference, and chat days.

[0008] Optionally, in one embodiment of this application, the calculation formula for the vehicle user activity model is:

[0009]

[0010] Where X is the number of chats within the preset time period, Y is the number of chat days, Z is the chat time difference, n is the nth chat record, i is the ith chat record, and N is the total number of chat messages.

[0011] Optionally, in one embodiment of this application, the data cleaning of the at least one vehicle user data includes: cleaning the at least one vehicle user data to remove special symbols, spaces, and outliers from the at least one vehicle user data to obtain the cleaned vehicle user data.

[0012] Optionally, in one embodiment of this application, the step of inputting the cleaned vehicle user data into a pre-built clustering model to obtain the classification result of the vehicle users includes: inputting the cleaned vehicle user data into the pre-built clustering model, and dividing the vehicle users into corresponding clusters according to the pre-built clustering model to obtain the division result; obtaining the classification label of the vehicle users according to the division result, and generating the classification result of the vehicle users according to the classification label of the vehicle users.

[0013] Optionally, in one embodiment of this application, obtaining the vehicle user activity model based on the classification result includes: acquiring the target features of the vehicle user; constructing the vehicle user activity model based on the target features; and obtaining the activity tag corresponding to the vehicle user based on the classification result and the vehicle user activity model.

[0014] A second aspect of this application provides a vehicle user classification device, comprising: an acquisition module for acquiring at least one vehicle user data selected from historical chat data, driving behavior data, and vehicle type; a data cleaning module for cleaning the at least one vehicle user data to obtain cleaned vehicle user data; and a classification module for inputting the cleaned vehicle user data into a pre-constructed clustering model to obtain a classification result of the vehicle user, and classifying the vehicle user by activity tagging based on the classification result and a preset vehicle user activity model to obtain a final activity classification result of the vehicle user.

[0015] Optionally, in one embodiment of this application, the acquisition module includes: a first acquisition unit, configured to acquire at least one of the number of chats, chat time difference, and chat days of the vehicle user within a preset time period; and a second acquisition unit, configured to obtain the vehicle user's historical chat data based on at least one of the number of chats, the chat time difference, and the chat days.

[0016] Optionally, in one embodiment of this application, the calculation formula for the vehicle user activity model is:

[0017]

[0018] Where X is the number of chats within the preset time period, Y is the number of chat days, Z is the chat time difference, n is the nth chat record, i is the ith chat record, and N is the total number of chat messages.

[0019] Optionally, in one embodiment of this application, the data cleaning module includes: a data cleaning unit, used to clean the at least one vehicle user data to remove special symbols, spaces, and outliers from the at least one vehicle user data, thereby obtaining the cleaned vehicle user data.

[0020] Optionally, in one embodiment of this application, the classification module includes: a partitioning unit, configured to input the cleaned vehicle user data into the pre-built clustering model, and partition the vehicle users into corresponding clusters according to the pre-built clustering model to obtain partitioning results; and a generation unit, configured to obtain classification labels for vehicle users according to the partitioning results, and generate classification results for vehicle users according to the classification labels of vehicle users.

[0021] Optionally, in one embodiment of this application, the classification module further includes: a third acquisition unit, used to acquire the target features of the vehicle user; and a fourth acquisition unit, used to construct an activity model of the vehicle user based on the target features, and obtain the activity tag corresponding to the vehicle user based on the classification result and the activity model of the vehicle user.

[0022] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle user classification method as described in the above embodiments.

[0023] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle user classification method described above.

[0024] This application's embodiments can automatically segment users through clustering models, avoiding the problem of uncertain thresholds in rule-based classification. By combining the categorized vehicle users with a vehicle user activity model, business tags can be set, ensuring targeted operations for different vehicle users, accurately stimulating user activity, improving user satisfaction, and promoting transaction conversion rates. This solves the problems in related technologies where clustering models alone cannot achieve business tagging, and rule-based classification alone cannot determine the rule classification thresholds, making targeted operations for different vehicle users difficult, thus hindering accurate user activity stimulation and reducing user satisfaction.

[0025] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0027] Figure 1 This is a flowchart illustrating a method for classifying vehicle users according to an embodiment of this application;

[0028] Figure 2 A mind map of a vehicle user classification method according to an embodiment of this application;

[0029] Figure 3 A flowchart illustrating the algorithmic model implementation of a vehicle user classification method according to an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of raw data for a vehicle user classification method according to an embodiment of this application;

[0031] Figure 5 This is a schematic diagram illustrating the code example of a vehicle user classification method according to an embodiment of this application;

[0032] Figure 6 This is a schematic diagram showing the K-means clustering results of a vehicle user classification method according to an embodiment of this application;

[0033] Figure 7 This is a schematic diagram illustrating the analysis of the first model results of a vehicle user classification method according to an embodiment of this application;

[0034] Figure 8 This is a schematic diagram illustrating the second model result analysis of a vehicle user classification method according to an embodiment of this application;

[0035] Figure 9 This is a schematic diagram illustrating the third model result analysis of a vehicle user classification method according to an embodiment of this application;

[0036] Figure 10 This is a schematic diagram illustrating the fourth model result analysis of a vehicle user classification method according to an embodiment of this application;

[0037] Figure 11 This is a schematic diagram illustrating the training of a clustering model for a vehicle user classification method according to an embodiment of this application;

[0038] Figure 12 This is a schematic diagram showing the user activity model results of a vehicle user classification method according to an embodiment of this application;

[0039] Figure 13 This is a schematic diagram illustrating the output of a user classification result using a vehicle user classification method according to an embodiment of this application.

[0040] Figure 14 This is a schematic diagram of a vehicle user classification device provided according to an embodiment of this application;

[0041] Figure 15 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0042] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0043] The following description, with reference to the accompanying drawings, outlines a method, apparatus, vehicle, and storage medium for classifying vehicle users according to embodiments of this application. Addressing the issues raised in the background art, where clustering models alone are insufficient for setting business tags, and rule-based classification lacks a defined threshold, hindering targeted operations for different vehicle users and ultimately reducing user satisfaction, this application provides a method for classifying vehicle users. This method automatically segments users using clustering models, avoiding the inability to determine thresholds in rule-based classification. By combining the classified vehicle users with a vehicle user activity model, business tags are set, ensuring targeted operations for different vehicle users, accurately stimulating user activity, improving user satisfaction, and increasing transaction conversion rates. This solves the problems in related technologies where clustering models alone are insufficient for setting business tags, and rule-based classification lacks a defined threshold, hindering targeted operations for different vehicle users and ultimately reducing user satisfaction.

[0044] Specifically, Figure 1 This is a flowchart illustrating a method for classifying vehicle users provided in an embodiment of this application.

[0045] like Figure 1 As shown, the method for classifying vehicle users includes the following steps:

[0046] In step S101, at least one type of vehicle user data is obtained, including the vehicle user's historical chat data, driving behavior data, and vehicle type.

[0047] It is understood that the driving behavior data in the embodiments of this application includes, but is not limited to, vehicle operation data, driving environment and driving habit data; the vehicle types in the embodiments of this application include, but are not limited to, cars, buses and trucks.

[0048] In actual implementation, this application embodiment can use chat tools such as social chat software to survey and collect real chat content of vehicle users, obtain historical chat data, driving behavior data and vehicle type of vehicle users, and then accurately classify vehicle users based on historical data such as chat content, help operations quickly identify user types, conduct refined user operations, and improve vehicle user satisfaction and conversion rate.

[0049] Optionally, in one embodiment of this application, obtaining the vehicle user's historical chat data includes: obtaining at least one of the vehicle user's chat count, chat time difference, and chat days within a preset time period; and obtaining the vehicle user's historical chat data based on at least one of the chat count, chat time difference, and chat days.

[0050] It is understood that the chat time difference in this application embodiment can be the time difference between the vehicle user's most recent chat and the last chat.

[0051] In actual implementation, this application embodiment can sort out feature vectors to obtain the number of chats a vehicle user has within a certain period of time. For example, this application embodiment can obtain the number of chats a vehicle user has had in the last day, the last 7 days, the last 14 days, and the last 45 days. This application embodiment can also obtain the time difference between the last chat and the last chat, the number of chat days, the number of days in the group, the province, and the vehicle model, etc. Based on the number of chats, the time difference of chats, and the number of chat days, the historical chat data of the vehicle user is obtained. By using correlation analysis, PCA data dimensionality reduction and other technical methods, it can further help operations quickly identify vehicle user types, conduct refined vehicle user operations, and improve vehicle user satisfaction and conversion rate.

[0052] For example, in this embodiment of the application, the historical chat data of a vehicle user can be obtained based on the number of chats in the most recent day, the chat time difference of 5 minutes, and the number of chat days of 50; as another example, in this embodiment of the application, the historical chat data of a vehicle user can be obtained based on the number of chats in the most recent 7 days, the chat time difference of 10 minutes, and the number of chat days of 150.

[0053] It should be noted that the preset time can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0054] In step S102, at least one vehicle user data is cleaned to obtain cleaned vehicle user data.

[0055] It is understood that the data cleaning in this application embodiment is text cleaning.

[0056] In actual implementation, the embodiments of this application can use Python to clean the data of at least one vehicle user, thereby obtaining cleaned vehicle user data, which can quickly identify vehicle users, accurately understand customer needs, improve vehicle user loyalty and satisfaction, enhance corporate brand and reputation, and increase product conversion rate.

[0057] Optionally, in one embodiment of this application, data cleaning of at least one vehicle user data includes: cleaning at least one vehicle user data to remove special symbols, spaces, and outliers from at least one vehicle user data to obtain cleaned vehicle user data.

[0058] It is understood that the data cleaning in this application embodiment is a process of re-examining and verifying the data.

[0059] In actual implementation, the embodiments of this application can perform data cleaning on at least one vehicle user data to remove outliers, special symbols, spaces, and missing values, thereby obtaining cleaned vehicle user data. This allows for a more accurate understanding of customer needs, improves vehicle user loyalty and satisfaction, enhances corporate brand and reputation, and increases product conversion rates.

[0060] In step S103, the cleaned vehicle user data is input into a pre-built clustering model to obtain the classification results of the vehicle users. Based on the classification results and the preset vehicle user activity model, the vehicle users are divided into activity labels to obtain the final activity classification results of the vehicle users.

[0061] It is understood that the clustering model pre-built in the embodiments of this application can be a Kmeans clustering algorithm model.

[0062] In actual implementation, after data cleaning, the cleaned vehicle user data can be input into the K-means clustering algorithm model to classify vehicle users, obtain the classification results, determine the three most important features based on the classification results, build a vehicle user activity model using the importance of the three most important features and business characteristics, and divide the vehicle user activity into activity labels based on the vehicle user activity model to obtain the final activity classification results of vehicle users, identify vehicle users with very high activity, high activity, medium activity, low activity, and inactive activity, output the final results, and verify the data analysis results.

[0063] This application embodiment can combine the several categories of vehicle users (0, 1, 2, 3...) output by the clustering model with the vehicle user activity model, and output vehicle user activity business tags for each category. Once the business tags are output for each category, the activity level of each vehicle user in each category can be obtained, which facilitates the analysis of vehicle user hierarchical classification results.

[0064] It should be noted that the embodiments of this application can use database query languages ​​such as SQL, Hive, Python, and PySpark to solve hierarchical classification problems. Data collection requires database support (DBEAVER, SQLSERVER), and algorithm prediction requires the support of Python's numpy, pandas, sklearn, and kmeans modules.

[0065] Optionally, in one embodiment of this application, the calculation formula for the vehicle user activity model is as follows:

[0066]

[0067] Where X is the number of chats within the preset time period, Y is the number of chat days, Z is the chat time difference, n is the nth chat record, i is the ith chat record, and N is the total number of chat messages.

[0068] In practical implementation, this application embodiment can indicate that a higher output value from the vehicle user activity model signifies higher vehicle user activity. The vehicle user activity model is constructed based on the first three important features and business characteristics. The three most important features have been determined through clustering model feature importance ranking (based on importance ranking: number of chats in the last 45 days, number of chat days, and time difference between the last and previous chats). Considering actual business conditions, for example, the more chats a vehicle user has in the last 45 days, the more chat days they have, and the smaller the time difference between the last and previous chats, the higher their activity level. Therefore, when constructing the vehicle user activity model, the formula should reflect that larger values ​​should be larger, and smaller values ​​should be smaller.

[0069] Therefore, an addition-subtraction method can be used, dividing features that require large values ​​into two categories: those that require small values ​​and those that require large values. This method is used when constructing the vehicle user activity model, further dividing positive and negative features into two categories. The sum of the coefficients for each category is 1. The coefficient allocation method is based on the feature importance multiple. For example, the importance of a vehicle user's chat count in the last 45 days is twice the importance of the number of chat days. Using rounding, the coefficients can be divided into 0.7 and 0.3. Features requiring small values ​​have a coefficient of 1 because there is only one feature. However, considering the different feature magnitudes, normalization or multiplication by a coefficient can be used to classify them into the same magnitude. Then, the mean of the three features for each category (0, 1, 2, 3…) of vehicle users is calculated and substituted into the coefficient formula. Finally, the larger the vehicle user activity model, the higher the vehicle user activity.

[0070] The formula for the vehicle user activity model is as follows:

[0071]

[0072] Table 1 shows the output results, as illustrated in Table 1:

[0073] Table 1

[0074]

[0075] This application embodiment can combine the classified vehicle users with the vehicle user activity model to set business tags, making the classification results meaningful.

[0076] Optionally, in one embodiment of this application, the cleaned vehicle user data is input into a pre-built clustering model to obtain the classification results of the vehicle users, including: inputting the cleaned vehicle user data into a pre-built clustering model, and dividing the vehicle users into corresponding clusters according to the pre-built clustering model to obtain the division results; obtaining the classification labels of the vehicle users according to the division results, and generating the classification results of the vehicle users according to the classification labels of the vehicle users.

[0077] In actual implementation, mean clustering is an unsupervised learning algorithm. This embodiment inputs cleaned vehicle user data into a pre-built clustering model, and classifies vehicle users into corresponding clusters based on the model, obtaining the classification results. Classification labels for vehicle users are then obtained based on these labels, and classification results are generated. The better the similarity between samples within a cluster and the less similar the samples between clusters, the better. The calculation process involves: first, randomly selecting K cluster centroids; second, assigning samples to the nearest centroid; and third, recalculating the similarity of the K cluster centroids based on the samples in their respective clusters, repeating steps two and three. The distance from a sample to a centroid is calculated using Euclidean distance; a larger Euclidean distance indicates lower similarity. The calculation formula is as follows:

[0078]

[0079] Where A is the sample point, B is the center point, n is the nth dimension, i is the i-th dimension, and A i Let B be the i-th dimension of the sample points. i Let i be the i-th dimension of the center point.

[0080] This application embodiment can automatically classify vehicle users through a clustering model, avoiding the problem of uncertain classification thresholds when using rules. Then, the classified vehicle users are combined with a vehicle user activity model to set business tags, making the classification results meaningful.

[0081] Optionally, in one embodiment of this application, constructing a vehicle user activity model based on the classification results includes: obtaining target features of vehicle users; constructing a vehicle user activity model based on the target features; and obtaining the activity label corresponding to the vehicle user based on the classification results and the vehicle user activity model.

[0082] It is understood that the target features in the embodiments of this application can be the top three most important features.

[0083] In actual implementation, this application embodiment can identify the top three importance features from the above clustering model, and construct a user activity model based on the top three importance features and business characteristics. This application embodiment can rank the importance of the identified TOP3 importance features and determine the polarity of the indicators, i.e., whether the indicator value is positively or negatively correlated with user activity. The constructed vehicle user activity model can accurately understand customer needs, improve vehicle user loyalty and satisfaction, enhance corporate brand and reputation, identify the concentrated demands of vehicle users, and drive the business to solve corresponding problems.

[0084] Specifically, it can be combined with Figures 2 to 13 As shown, the working principle of the vehicle user classification method in this application is explained in detail with a specific embodiment.

[0085] like Figure 2 As shown, the embodiments of this application can be implemented as follows: First, collect vehicle user chat text data through chat tools; second, sort out features, including the number of chats in the last day, the number of chats in the last 14 days, the number of chats in the last 45 days, the time difference between the last chat and the second to last chat, and the number of chat days, using techniques such as association analysis and PCA data dimensionality reduction; third, clean the text by using Python code to remove special symbols, spaces, etc.; fourth, perform cluster analysis on the cleaned text using the k-means clustering algorithm model; fifth, determine the three most important features based on the model results; sixth, build a vehicle user activity model using the three most important features and output the final result; seventh, verify the data analysis results; and eighth, output the results.

[0086] like Figure 3 As shown, embodiments of this application may include the following steps:

[0087] Step S301: Obtain vehicle user chat information.

[0088] Step S302: Text cleaning.

[0089] Step S303: Feature recognition.

[0090] Step S304: K-means model identification.

[0091] Step S305: Vehicle User Activity Model.

[0092] Step S306: Output the result.

[0093] Figure 4 This is a sample image of the original data from a vehicle user community chat. For example, the user ID is 9, the user nickname is Xiao A, the province is Anhui, the city is Hefei, the vehicle type is C, the chat content is "Don't step on the brake hard", the chat time is 2024 / 1 / 11, 17:02:04, and the group name is Group 6.

[0094] Furthermore, Figure 5 Here is a sample code image. Figure 6 Based on features such as the number of chats in the last 1 day, the last 7 days, the last 14 days, the last 30 days, the last 45 days, the time difference between the last chat and the second to last chat, and the number of chat days, the results of vehicle user classification are obtained using the K-means model.

[0095] Furthermore, Figure 7 , Figure 8 , Figure 9 and Figure 10 This is a feature analysis diagram after model clustering, through... Figure 7 It can be seen that the chat frequency characteristics in the last 45 days can reasonably separate vehicle users. The values ​​are divided into 5 categories: 0 to 98, 43 to 260, 172 to 550, 396 to 1160, and 1262 to 2073. Figure 8 It can be seen that the maximum range of the most recent chat time interval between the last chat and the uploaded chat is significantly different for each type of vehicle user, and the classification results are obvious; Figure 9 It can be seen that there were many chat days; Figure 10 It can be seen that the average number of chats per day varies significantly for each type of vehicle user, ranging from as high as 14.9 times to as low as 0.6 times.

[0096] Figure 11 These are the iterative steps of the mean clustering algorithm. Figure 12 The output graph of the vehicle user activity model shows that the larger the value, the higher the vehicle user activity. Figure 13 To output a chart showing the results of classifying each vehicle user, some examples are shown. Each vehicle user is labeled with a category label. For example, user 13's K-means model label is 3, and the user activity model result is low activity; another example is user 20's K-means model label is 4, and the user activity model result is medium activity.

[0097] The vehicle user classification method proposed in this application can automatically segment users through a clustering model, avoiding the problem of uncertain thresholds when using rule-based classification. By combining the classified vehicle users with a vehicle user activity model, business tags can be set, ensuring targeted operations for different vehicle users, accurately stimulating user activity, improving user satisfaction, and promoting transaction conversion rates. This solves the problems in related technologies where clustering models alone cannot achieve business tag setting, and rule-based classification alone cannot determine the rule classification threshold, making targeted operations for different vehicle users difficult, thus hindering accurate user activity stimulation and reducing user satisfaction.

[0098] Next, the vehicle user classification device proposed according to an embodiment of this application is described with reference to the accompanying drawings.

[0099] Figure 14 This is a schematic diagram of the vehicle user classification device according to an embodiment of this application.

[0100] like Figure 14 As shown, the vehicle user classification device 10 includes: an acquisition module 100, a data cleaning module 200, and a classification module 300.

[0101] Specifically, the acquisition module 100 is used to acquire vehicle user data from at least one of the following: historical chat data, driving behavior data, and vehicle type.

[0102] The data cleaning module 200 is used to clean the data of at least one vehicle user to obtain cleaned vehicle user data.

[0103] The classification module 300 is used to input the cleaned vehicle user data into a pre-built clustering model to obtain the classification results of vehicle users. Based on the classification results and the preset vehicle user activity model, the vehicle users are divided into activity labels to obtain the final activity classification results of vehicle users.

[0104] Optionally, in one embodiment of this application, the acquisition module 100 includes: a first acquisition unit and a second acquisition unit.

[0105] The first acquisition unit is used to acquire at least one of the following: the number of chats, the chat time difference, and the number of chat days of the vehicle user within a preset time period.

[0106] The second acquisition unit is used to obtain the vehicle user's historical chat data based on at least one of the following: number of chats, chat time difference, and chat days.

[0107] Optionally, in one embodiment of this application, the calculation formula for the vehicle user activity model is as follows:

[0108]

[0109] Where X is the number of chats within the preset time period, Y is the number of chat days, Z is the chat time difference, n is the nth chat record, i is the ith chat record, and N is the total number of chat messages.

[0110] Optionally, in one embodiment of this application, the data cleaning module 200 includes a data cleaning unit.

[0111] The data cleaning unit is used to clean at least one vehicle user data to remove special symbols, spaces, and outliers from the data, thus obtaining cleaned vehicle user data.

[0112] Optionally, in one embodiment of this application, the classification module 300 includes a division unit and a generation unit.

[0113] The partitioning unit is used to input the cleaned vehicle user data into a pre-built clustering model, and to partition the vehicle users into corresponding clusters according to the pre-built clustering model to obtain the partitioning results.

[0114] The generation unit is used to obtain the classification labels of vehicle users based on the segmentation results, and to generate the classification results of vehicle users based on the classification labels of vehicle users.

[0115] Optionally, in one embodiment of this application, the classification module 300 further includes a third acquisition unit and a construction unit.

[0116] The third acquisition unit is used to acquire the target features of vehicle users.

[0117] The construction unit is used to build an activity model of vehicle users based on target features, and to obtain the activity label corresponding to the vehicle user based on the classification results and the activity model of vehicle users.

[0118] It should be noted that the explanation of the above-mentioned vehicle user classification method embodiment also applies to the vehicle user classification device of this embodiment, and will not be repeated here.

[0119] The vehicle user classification device proposed in this application can automatically segment users through a clustering model, avoiding the problem of uncertain thresholds when using rule-based classification. By combining the classified vehicle users with a vehicle user activity model, business tags can be set, ensuring targeted operations for different vehicle users, accurately stimulating user activity, improving user satisfaction, and promoting transaction conversion rates. This solves the problems in related technologies where clustering models alone cannot achieve business tag setting, and rule-based classification alone cannot determine rule-based classification thresholds, making targeted operations for different vehicle users difficult, thus hindering accurate user activity stimulation and reducing user satisfaction.

[0120] Figure 15 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0121] The memory 1501, the processor 1502, and the computer program stored on the memory 1501 and executable on the processor 1502.

[0122] When the processor 1502 executes the program, it implements the vehicle user classification method provided in the above embodiments.

[0123] Furthermore, the vehicle also includes:

[0124] Communication interface 1503 is used for communication between memory 1501 and processor 1502.

[0125] The memory 1501 is used to store computer programs that can run on the processor 1502.

[0126] The memory 1501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0127] If the memory 1501, processor 1502, and communication interface 1503 are implemented independently, then the communication interface 1503, memory 1501, and processor 1502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 15The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0128] Optionally, in a specific implementation, if the memory 1501, processor 1502, and communication interface 1503 are integrated on a single chip, then the memory 1501, processor 1502, and communication interface 1503 can communicate with each other through an internal interface.

[0129] The processor 1502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0130] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle user classification method described above.

[0131] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0132] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0133] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0134] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0135] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0136] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0138] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method of classifying a user of a vehicle, characterized by, The method comprises the following steps: obtaining at least one vehicle user data of historical chat data, driving behavior data and vehicle type of a vehicle user; data cleaning is performed on the at least one vehicle user data to obtain cleaned vehicle user data; the cleaned vehicle user data is input into a pre-constructed clustering model to obtain a classification result of the vehicle user, and based on the classification result and a preset vehicle user activity model, the vehicle user is divided into an activity label to obtain a final activity classification result of the vehicle user; wherein, the obtaining of the historical chat data of the vehicle user comprises: obtaining at least one of the chat frequency, chat time difference and chat frequency of the vehicle user within a preset time; and obtaining the historical chat data of the vehicle user according to at least one of the chat frequency, the chat time difference and the chat frequency; the calculation formula of the vehicle user activity model is: ， wherein, is the number of chats in the preset time, is the chat time, is the chat time difference, is the first n chat record, is the first i chat record, is the total number of chat information.

2. The method of claim 1, wherein, the data cleaning of the at least one vehicle user data comprises: data cleaning is performed on the at least one vehicle user data to remove special symbols, space symbols and abnormal values in the at least one vehicle user data, so as to obtain the cleaned vehicle user data.

3. The method of claim 1, wherein, the input of the cleaned vehicle user data into the pre-constructed clustering model to obtain the classification result of the vehicle user comprises: the cleaned vehicle user data is input into the pre-constructed clustering model, and the vehicle user is divided into a corresponding cluster according to the pre-constructed clustering model to obtain a division result; according to the division result, a classification label of the vehicle user is obtained, and a classification result of the vehicle user is generated according to the classification label of the vehicle user.

4. The method of claim 1, wherein, the division of the vehicle user into an activity label according to the classification result and the preset vehicle user activity model comprises: obtaining target features of the vehicle user; constructing an activity model of the vehicle user according to the target features, and obtaining a corresponding activity label of the vehicle user according to the classification result and the activity model of the vehicle user.

5. An apparatus for classifying a user of a vehicle, characterized by comprise: an obtaining module for obtaining at least one vehicle user data of historical chat data, driving behavior data and vehicle type of a vehicle user; a data cleaning module for performing data cleaning on the at least one vehicle user data to obtain cleaned vehicle user data; a classification module for inputting the cleaned vehicle user data into a pre-constructed clustering model to obtain a classification result of the vehicle user, and based on the classification result and a preset vehicle user activity model, the vehicle user is divided into an activity label to obtain a final activity classification result of the vehicle user; wherein, the obtaining module comprises: a first obtaining unit for obtaining at least one of the chat frequency, chat time difference and chat frequency of the vehicle user within a preset time; and a second obtaining unit for obtaining the historical chat data of the vehicle user according to at least one of the chat frequency, the chat time difference and the chat frequency; the calculation formula of the vehicle user activity model is: ， wherein, is the chat times within the preset time, is the chat times, is the chat time difference, is the first n chat record, is the first i chat record, is the total chat information number.

6. A vehicle characterized by comprising: comprise: - a memory, a processor and a computer program stored on the memory and runable on the processor, the processor executing the program to implement the method of classifying a user of a vehicle according to any one of claims 1-4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by a processor for implementing the method of classifying a user of a vehicle according to any one of claims 1-4.

Images