Automobile user portrait construction method and device

Abstract

The application relates to the technical field of intelligent cockpits, in particular to a car user portrait construction method and device, wherein the method comprises the following steps: associating car user behavior data and vehicle state data, constructing user classification features and user behavior features, identifying the actual user classification of a car user according to the user classification features, and matching the user corresponding behavior features according to the actual user classification, so as to construct a user portrait. The application embodiment can associate the behavior data of a car user and the vehicle state data, identify the actual user classification of the car user according to the user classification features, and match the user corresponding behavior features, so as to construct a user portrait, understand the intelligent acceptance degree and product preference of the cockpit user, and then formulate product design and optimization schemes for different types of users, improve the use value of the intelligent cockpit, and improve the human-computer interaction level of the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent cockpit, and in particular to a method and device for constructing a user portrait of a car. BACKGROUND

[0002] With the accelerated development of car intelligence, the functions of leisure, entertainment and office in the car are gradually enriched, and the importance of intelligent cockpit, as a space for carrying and realizing a series of intelligent applications and services of the car, is increasingly apparent in the development of intelligent cars.

[0003] In the related art, the related consumption habits of cockpit intelligent technology configuration needs are still in the cultivation stage, some users can understand various intelligent functions and use them skillfully in daily life, and some users are still used to using traditional operations, while the data collection technology of the vehicle intelligent cockpit has gradually matured. Compared with the initial user preference analysis using user research data, the user behavior tracking data of the intelligent cockpit can more truly reflect the function use of the user in different scenarios.

[0004] However, in the related art, there is a lack of relevant data support when planning and designing intelligent cockpit products, which leads to the fact that product personnel are not clear about the intelligent acceptance of current car users, reduces the pertinence of cockpit intelligent function design, and cannot highlight the value of the intelligent cockpit for the whole vehicle, which needs to be solved urgently. SUMMARY

[0005] The present application provides a method and device for constructing a user portrait of a car to solve the problem that there is a lack of relevant data support when planning and designing intelligent cockpit products in the related art, which leads to the fact that product personnel are not clear about the intelligent acceptance of current car users, reduces the pertinence of cockpit intelligent function design, and cannot highlight the value of the intelligent cockpit for the whole vehicle.

[0006] The first aspect embodiment of the present application provides a method for constructing a user portrait of a car, comprising the following steps: collecting behavior data and vehicle state data of a car user; associating the behavior data and the vehicle state data according to a preset association strategy, constructing user classification features and user behavior features; identifying the actual user classification of the car user in the user classification according to the user classification features, and matching the corresponding behavior features of the user behavior features according to the actual user classification, to construct a user portrait.

[0007] According to the technical means, the behavior data of the automobile user and the vehicle state data can be associated, the actual user classification of the automobile user is recognized according to the user classification feature, the behavior feature corresponding to the user is matched, the user portrait is constructed, the intelligent acceptance degree of the user in the vehicle cabin and the product preference are understood, and then the product design and optimization scheme is formulated for different types of users, the use value of the intelligent vehicle cabin is improved, and the human-computer interaction level of the vehicle is improved.

[0008] Optionally, in an embodiment of the present application, after the behavior data of the automobile user and the vehicle state data are collected, the data satisfying a preset invalid condition in the behavior data of the automobile user, the vehicle state data and the related feature data required by the business are filtered, wherein the preset invalid condition includes that a key field is empty, a field value content does not conform to a field definition or a field reporting rule.

[0009] According to the technical means, after the behavior data of the automobile user and the vehicle state data are collected, the data satisfying a preset invalid condition in the behavior data of the automobile user, the vehicle state data and the related feature data required by the business are filtered, so that data redundancy in the database is avoided, and the utilization efficiency of the data is improved.

[0010] Optionally, in an embodiment of the present application, the behavior data and the vehicle state data are associated according to a preset association strategy, including: obtaining an identity of a current automobile; and associating the behavior data and the vehicle state data according to a preset time rule based on the identity.

[0011] According to the technical means, the behavior data and the vehicle state data are associated according to a preset association strategy, the identity of the current automobile is obtained, and the behavior data and the vehicle state data are associated according to a preset time rule based on the identity, so that the frequency of a certain behavior of the user in the vehicle within a certain time is obtained, the use preference of the user is further analyzed, and the practicability of the data is improved.

[0012] Optionally, in an embodiment of the present application, the user classification feature and the behavior feature of the user are constructed, including: calculating a feature value of the user classification by using the number of started functions, the number of carried functions, the number of function start times, the number of vehicle start times, the function use rate and the function use frequency of the user in a preset period in the related feature data, and constructing the user classification feature by using the behavior data; and calculating the function type preference, the function use time and the vehicle state of the user behavior by using the vehicle state data and the behavior data, and constructing the behavior feature of the user.

[0013] According to the technical means, the embodiment of the application can use the behavior data to construct user classification features, use the vehicle state data and the user use preference data of the use function to construct user behavior features, obtain the related feature values of the user using the intelligent function in the vehicle, and enhance the fine degree of data construction.

[0014] Optionally, in an embodiment of the application, the calculating the function type preference, the function use time, and the vehicle state of the user behavior by using the vehicle state data and the behavior data comprises: classifying the intelligent function carried in the vehicle, and calculating the category shelf weight of each type; calculating the user preference value of each type according to the category shelf weight of each type and the function start number of each type to obtain a shelf matching degree; and determining the function type preference according to the shelf matching degree.

[0015] According to the technical means, the category shelf weight of each type can be obtained, the user preference value of each type is calculated to obtain the shelf matching degree, and then the preference degree of the function type is determined, so as to further construct the user behavior data basis and make the user behavior portrait more accurate.

[0016] Optionally, in an embodiment of the application, the user classification comprises at least one of a cockpit value user, a cockpit expandable user, a cockpit activatable user, and a cockpit potential user.

[0017] According to the technical means, the user classification of the embodiment of the application comprises at least one of a cockpit value user, a cockpit expandable user, a cockpit activatable user, and a cockpit potential user, the constructed data is divided into different user categories by classifying the user types, and the utilization efficiency of the data is improved.

[0018] The second aspect embodiment of the application provides a car user portrait construction device, comprising: a collection module configured to collect behavior data and vehicle state data of a car user; a construction module configured to associate the behavior data and the vehicle state data according to a preset association strategy, and construct user classification features and user behavior features; and a construction module configured to identify an actual user classification of the car user in the user classification according to the user classification features, and match corresponding behavior features of the user behavior features according to the actual user classification, so as to construct a user portrait.

[0019] Optionally, in an embodiment of the application, the device further comprises a processing unit configured to filter data satisfying a preset invalid condition from the behavior data of the car user, the vehicle state data, and related feature data required by the business after collecting the behavior data of the car user and the vehicle state data, wherein the preset invalid condition comprises an empty key field, a field value content not conforming to a field definition or a field reporting rule.

[0020] Optionally, in an embodiment of the present application, the construction module comprises: an acquisition unit configured to acquire an identity of a current vehicle; and an association unit configured to associate the behavior data and the vehicle state data according to a preset time rule based on the identity.

[0021] Optionally, in an embodiment of the present application, the construction module further comprises: a first construction unit configured to calculate a feature value of a user classification by using a number of started functions, a number of carried functions, a number of function start times, a number of vehicle start times, a function usage rate, and a function usage frequency of the user in a preset period in the related feature data, to construct the user classification feature based on the behavior data; and a second construction unit configured to calculate a function type preference, a function usage time, and a vehicle state of a user behavior by using the vehicle state data and the behavior data, to construct the user behavior feature.

[0022] Optionally, in an embodiment of the present application, the second construction unit comprises: classifying intelligent functions carried in the vehicle, and calculating a product shelf weight of each type; calculating a user preference value of each type according to the product shelf weight of each type and the number of function start times of each type, to obtain a shelf matching degree; and determining the function type preference according to the shelf matching degree.

[0023] Optionally, in an embodiment of the present application, the user classification comprises at least one of a cockpit value user, a cockpit expandable user, a cockpit activatable user, and a cockpit potential user.

[0024] The third aspect embodiment of the present application provides a vehicle, comprising: 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 portrait construction method according to the above embodiments.

[0025] The fourth aspect embodiment of the present application provides a computer readable storage medium, which stores a computer program executable by a processor to implement the vehicle user portrait construction method as above.

[0026] The present application has the following beneficial effects:

[0027] (1) The embodiment of the present application can associate behavior data and vehicle state data of a vehicle user, recognize an actual user classification of the vehicle user according to a user classification feature, and match a behavior feature corresponding to the user, thereby constructing a user portrait, understanding an intelligent acceptance degree of a cockpit user and a product preference, and then formulating a product design and optimization scheme for different types of users, improving the use value of an intelligent cockpit, and improving the human-machine interaction level of a vehicle.

[0028] (2) The embodiment of the present application can use behavior data to construct user classification features, use vehicle state data and user use function use preference data to construct user behavior features, obtain related feature values of user use of in-vehicle intelligent functions, and enhance the refinement degree of data construction.

[0029] (3) The embodiment of the present application can filter data that meets a preset invalid condition among the behavior data, vehicle state data and business required related feature data of the automobile user after collecting the behavior data and vehicle state data of the automobile user, thereby avoiding data redundancy in the database and improving the utilization efficiency of the data.

[0030] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0032] Figure 1 A flowchart of a method for constructing a portrait of an automobile user according to an embodiment of the present application;

[0033] Figure 2 A schematic diagram of user classification for an embodiment of the present application;

[0034] Figure 3 A flowchart of a method for constructing a portrait of an automobile user according to an embodiment of the present application;

[0035] Figure 4 A structural schematic diagram of a device for constructing a portrait of an automobile user according to an embodiment of the present application;

[0036] Figure 5 A structural schematic diagram of a vehicle according to an embodiment of the present application.

[0037] Among them, 10 is a device for constructing a portrait of an automobile user; 100 is a collection module, 200 is a construction module, and 300 is a construction module; 501 is a storage, 502 is a processor, and 503 is a communication interface. DETAILED DESCRIPTION

[0038] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0039] The automobile user portrait construction method and device of the embodiment of the application are described below with reference to the accompanying drawings. In view of the problems in the related art that there is a lack of relevant data support when planning and designing an intelligent cockpit product, which leads to the fact that product personnel are not clear about the intelligent acceptance of current vehicle users, reduces the pertinence of cockpit intelligent function design, and cannot highlight the value of the intelligent cockpit for the whole vehicle, the application provides an automobile user portrait construction method, which can collect behavior data and vehicle state data of automobile users, associate the behavior data and the vehicle state data according to a preset association strategy, construct user classification features and user behavior features, identify the actual user classification of the automobile users according to the user classification features, and match the corresponding behavior features of the users according to the actual user classification, so as to construct a user portrait and further understand the intelligent acceptance degree and product preference of the cockpit users, formulate product design and optimization schemes for different types of users, improve the use value of the intelligent cockpit, and improve the human-computer interaction level of the vehicle. Thus, the problems in the related art that there is a lack of relevant data support when planning and designing an intelligent cockpit product, which leads to the fact that product personnel are not clear about the intelligent acceptance of current vehicle users, reduces the pertinence of cockpit intelligent function design, and cannot highlight the value of the intelligent cockpit for the whole vehicle are solved.

[0040] Specifically, Figure 1 A flowchart of an automobile user portrait construction method provided by the embodiment of the application is shown.

[0041] As Figure 1 shown, the automobile user portrait construction method includes the following steps:

[0042] In step S101, behavior data and vehicle state data of automobile users are collected.

[0043] It can be understood that the collection of automobile user behavior data in the embodiment of the application can be the collection of buried point data of a user starting an intelligent function in an automobile intelligent cockpit, which can include a data unique identifier, a function name, a function starting time, and a vehicle unique identifier, etc. The in-vehicle activities of the user are tracked, specific user behaviors or events are captured, and the captured results are processed and sent. The collection of vehicle state data can include vehicle starting state, vehicle driving state, and road state. For example, the road state can be determined by the road type of the current road provided by the map data of the in-vehicle navigation. The relevant feature data required by the business can be obtained from the actual loading and use of the vehicle intelligent function, such as the actual loading and use of the control system, the entertainment system, the air conditioning system, the communication system, the seat system, the interaction system, and the perception system in the vehicle.

[0044] The embodiment of the application can collect behavior data and vehicle state data of a car user, collect data from three aspects of people, cars and machines through use of intelligent functions in the car, enrich the collection channel and collection scale of user behavior data, and improve the comprehensiveness of data collection.

[0045] Optionally, in an embodiment of the application, after collecting the behavior data and the vehicle state data of the car user, the method further includes: filtering data satisfying a preset invalid condition from the behavior data, the vehicle state data and the related feature data required by the business, wherein the preset invalid condition includes that a key field is empty, a field value content does not conform to a field definition or a field reporting rule.

[0046] It can be understood that the preset invalid condition in the embodiment of the application can include data with an empty key field and data with a field value content not conforming to a field definition or a field reporting rule in the user behavior data, wherein the key field can refer to a data unique identifier, a function name, a function start time and a vehicle unique identifier.

[0047] It should be noted that the preset invalid condition is set by a person skilled in the art according to actual conditions, which is not specifically limited here.

[0048] For example, in the collected behavior data, vehicle state data and related feature data required by the business of the car user, there is data with an empty key field in the behavior data of the car user, which can cause index invalidation in some databases, occupy database storage space, and complicate the database query analysis process. The empty key field and the field value content not conforming to the field definition or the field reporting rule can cause data that cannot be recognized or utilized in the database analysis and recognition process, and reduce the database search efficiency.

[0049] The embodiment of the application can filter data satisfying a preset invalid condition from the behavior data, the vehicle state data and the related feature data required by the business of the car user after collecting the behavior data and the vehicle state data of the car user, thereby avoiding data redundancy in the database and improving the utilization efficiency of the data.

[0050] In step S102, the behavior data and the vehicle state data are associated according to a preset association strategy, and user classification features and user behavior features are constructed.

[0051] It can be understood that the preset association strategy for associating the behavior data and the vehicle state data in the embodiment of the application can be to obtain the driving state of the car and the road state when the user uses the intelligent function, for example, to associate the use of the in-car navigation and the overspeed monitoring radar when the car is driving on the urban road with the road condition at that time, and to obtain the road state of the car when the user uses the in-car road driving assistance function.

[0052] It should be noted that the preset association strategy is set by a person skilled in the art according to actual conditions, and is not specifically limited here.

[0053] The embodiment of the application can associate the behavior data and the vehicle state data according to the preset association strategy, construct user classification features and user behavior features, expand the data connection relationship between the in-vehicle cabin use and the driving condition, and improve the application value of the data.

[0054] Optionally, in an embodiment of the application, the behavior data and the vehicle state data are associated according to the preset association strategy, including: obtaining an identity of a current vehicle; and associating the behavior data and the vehicle state data according to a preset time rule based on the identity.

[0055] It can be understood that the identity of the vehicle in the embodiment of the application can be a vehicle identification code, and by obtaining the vehicle identification code, the general characteristic information of the vehicle can be indicated, which generally includes but is not limited to the vehicle type, the vehicle structure feature, the vehicle device feature and the vehicle technical characteristic parameter, and the obtained data is classified to the corresponding specific vehicle and user. The preset time rule can refer to a statistical period set in advance by the vehicle, and the behavior data and the vehicle state data are associated within the statistical period, so as to obtain the behavior frequency of the user.

[0056] It should be noted that the preset time rule is set by a person skilled in the art according to actual conditions, and is not specifically limited here.

[0057] The embodiment of the application can associate the behavior data and the vehicle state data according to the preset association strategy, obtain the identity of the current vehicle, and associate the behavior data and the vehicle state data according to the preset time rule based on the identity, so as to obtain the occurrence frequency of a certain behavior of the user in the vehicle within a certain time, further analyze the use preference of the user, and improve the practicability of the data.

[0058] Optionally, in an embodiment of the application, the user classification features and the user behavior features are constructed, including: calculating a feature value of user classification by using the number of started functions, the number of carried functions, the number of function start times, the number of vehicle start times, the function use rate and the function use frequency of the user in a preset period in the related feature data, to construct the user classification features by the behavior data; and calculating the function type preference, the function use time and the vehicle state of the user behavior by using the vehicle state data and the behavior data, to construct the user behavior features.

[0059] It can be understood that the user classification features in the embodiments of the present application can be constituted by the number of started functions, the number of carried functions, the number of function starts, the number of vehicle starts, the function usage rate and the function usage frequency of the user in a certain period. The user behavior features can include the function type preference of the user, the shelf matching degree, the user preference category, the function usage time and the vehicle state, etc.

[0060] It should be noted that the preset period is set by a person skilled in the art according to the actual situation, and is not specifically limited here.

[0061] Among them, the function usage rate FUR (Function Usage Ratio) of the user is obtained by data production on the number of started functions, the number of carried functions, the number of function starts and the number of vehicle starts,

[0062]

[0063] Among them, the function usage rate is the starting percentage rate of the number of intelligent functions carried by the user on the vehicle in the statistical time, the number of started functions can be the number of intelligent functions started by the user in the statistical period, and the number of carried functions can be the number of intelligent functions carried by the user on the vehicle in the statistical period.

[0064] The function usage frequency FUF (Function Usage Frequency) of the user can also be obtained,

[0065]

[0066] Among them, the function usage frequency is the usage frequency of the intelligent function by the user in the number of vehicle starts in the statistical time, the number of function starts can be the number of times of starting the intelligent function by the user in the statistical period, and the number of vehicle starts can be the number of times of starting the car by the user in the statistical period. The obtained function usage rate and function usage frequency are arranged according to the current business demand, according to the rules of average value, mode, median or business target value, etc., to obtain the feature value of user classification.

[0067] The function use time in the user behavior feature can be classified according to business requirements, such as use time period (for example, morning, noon, and afternoon) and date type (for example, weekday and holiday). The vehicle state can include the driving state of the vehicle when the user uses the intelligent function, such as driving or not driving. If the vehicle is driving, the driving road state can be recorded, such as urban road or expressway. According to actual analysis requirements, the collection of vehicle state information can be increased or reduced. For example, when analyzing the use of the vehicle music playing function by the user, the collection of vehicle driving state information can be reduced. In actual application, more user behavior features can be constructed according to actual business requirements, and the data required by the business can be accurately collected and analyzed.

[0068] The embodiment of the present application can construct user classification features by using behavior data, construct user behavior features by using vehicle state data and user use preference data of the function, and obtain related feature values of the user using the in-vehicle intelligent function, thereby enhancing the fine degree of data construction.

[0069] Optionally, in an embodiment of the present application, the function type preference, function use time, and vehicle state of the user behavior are calculated by using the vehicle state data and the behavior data, including: classifying the in-vehicle intelligent function, and calculating the category shelf weight of each type; calculating the user preference value of each type according to the category shelf weight of each type and the function start number of each type, to obtain the shelf matching degree; and determining the function type preference according to the shelf matching degree.

[0070] It can be understood that in the embodiment of the present application, the function type preference of the user behavior can be obtained by calculation based on the vehicle state data and the behavior data, to further realize the construction of the user behavior feature.

[0071] Specifically, the function type preference can be classified according to business requirements, such as social class, music class, video class, game class, tool class, and setting class, to analyze the use preference of the user for the function class.

[0072]

[0073] wherein, c i , i = 1, 2, …, n, is the category shelf weight of different types set according to business priority or directly calculated, the number of category functions is the number of functions contained in the type, the total number of functions is the total number of in-vehicle intelligent functions, and then the function type preference is calculated as

[0074]

[0075] wherein, y i, i = 1, 2, …, n, is the user preference value of each type, x i , i = 1, 2, …, n, is the number of function activations of each type. When y i ≥ c i , i = 1, 2, …, n, the product shelf planning of the current category meets the actual needs of the user, and the user is satisfied with the category. Calculate

[0076]

[0077] Wherein, z is the shelf matching degree, 0 < z < 100%, the number of user satisfaction categories is the number of categories whose user preference value is greater than or equal to the type weight value, and the total number of categories is the total number of intelligent function categories carried in the vehicle. The user preferred category is the category with the preference value y i , i = 1, 2, …, n, arranged in descending order, and the head category is the user preferred category.

[0078] The embodiment of the application can obtain the shelf weight of each type of category, calculate the user preference value of each type, obtain the shelf matching degree, and further determine the preference degree of the function type, so as to further build a user behavior data base and make the user behavior portrait more accurate.

[0079] In step S103, the actual user classification of the automobile user in the user classification is identified according to the user classification feature, and the corresponding behavior feature of the user behavior feature is matched according to the actual user classification, so as to construct the user portrait.

[0080] It can be understood that in the embodiment of the application, the actual user classification of the automobile user in the user classification can be obtained by matching the user according to the divided different user classifications by using the constructed user classification feature, obtaining the actual classification to which the user belongs, and matching the constructed user classification feature to the corresponding behavior feature according to the actual classification. The user portrait can include the shelf matching degree of the user, the user preferred category, the preferred period and the vehicle state, etc. For example, different categories of users can be clustered according to the clustering algorithm to obtain the user portrait of different user types.

[0081] The embodiment of the application can identify the actual user classification of the automobile user in the user classification according to the user classification feature, and match the corresponding behavior feature of the user behavior feature according to the actual user classification, so as to construct the user portrait, so as to understand the intelligent acceptance degree of the current cockpit user and the product preference, improve the pertinence of formulating product optimization scheme and configuring intelligent product shelf, and improve the interaction of the vehicle.

[0082] Optionally, in an embodiment of the application, the user classification includes at least one of the cockpit value user, the cockpit expandable user, the cockpit activatable user and the cockpit potential user.

[0083] It can be understood that in the embodiment of the present application, the cockpit value user may be a user who has used multiple intelligent functions with a high frequency of use, the cockpit activation user may be a user who has used multiple intelligent functions with a low frequency of use, the cockpit expandable user may be a user who uses fewer intelligent functions but with a high frequency of use, and the cockpit potential user may be a user who has only used fewer intelligent functions and does not use them frequently.

[0084] For example, Figure 2 As shown, it is a schematic diagram of user classification of an embodiment of the present application, where the horizontal axis is the function utilization rate FUR, the vertical axis is the function utilization frequency FUF, and the characteristic values ​​a and b are obtained by arranging data according to the current business needs, according to the rules such as average value, mode, median or business target value, and the characteristic values ​​of the user classification are assigned FUR=a and FUF=b respectively.

[0085] Among them, user categories are divided into four categories, including:

[0086] Cabin value users, this category is located in the first quadrant of the horizontal and vertical axes, satisfying FUR>a and FUF>b, that is, the user has used multiple intelligent functions and the frequency of use is high.

[0087] The cockpit can activate users. This category is located in the fourth quadrant of the horizontal and vertical axes, satisfying FUR≥a and FUF<b, that is, the user has used multiple intelligent functions but not frequently.

[0088] The cockpit can expand users. This category is located in the fourth quadrant of the horizontal and vertical axes, satisfying FUR<a and FUF≥b, that is, users have used fewer intelligent functions but have used them frequently.

[0089] Potential cockpit users, this category is located in the fourth quadrant of the horizontal and vertical axes, satisfying FUR<a and FUF<b, that is, users have only used a few intelligent functions and do not use them frequently.

[0090] The user classification in the embodiment of the present application includes at least one of cabin value users, cabin expandable users, cabin activated users and cabin potential users. By dividing the user types, the constructed data is divided into different user categories, thereby improving the efficiency of data utilization.

[0091] like Figure 3 As shown, the working content of the embodiment of this application is described in detail below with a flow chart of a method for constructing a user portrait based on smart cockpit user behavior data in one embodiment.

[0092] Step S301: Data collection.

[0093] That is, the user behavior data related to the intelligent function of the cockpit and the vehicle state data are collected, the embedded point data collection of the user starting the intelligent function in the intelligent cockpit is used, data contents including data unique identifier, function name, function starting time, vehicle unique identifier, and vehicle starting state, vehicle driving state and road state are collected, and the vehicle intelligent function loading condition is obtained.

[0094] Step S302: data quality management.

[0095] That is, invalid data in the obtained data is filtered, key fields in the user behavior data are filtered, and data in which the field value content does not conform to the field definition or field reporting rule is filtered.

[0096] Step S303: data association.

[0097] That is, the vehicle unique identifier is used to associate the user behavior data and the vehicle state data according to the time rule, and the driving state and the road state of the vehicle when the user uses the intelligent function are obtained.

[0098] Step S304: feature engineering construction.

[0099] That is, user classification features and user behavior features are constructed, function use rate FUR and function use frequency FUF, user function type preference, shelf matching degree, user preference category, function use time and vehicle state are obtained, and more user behavior features are constructed according to actual business needs.

[0100] Step S305: user classification.

[0101] That is, the user classification features are used to classify the users based on user classification rules, the users are classified into four categories of cockpit value users, cockpit active promotion users, cockpit expandable users and cockpit potential users, and the function use rate FUR and the function use frequency FUF are used to match the user types for the users.

[0102] Step S306: classification user portrait construction

[0103] That is, the classified users are used to construct portraits, different categories of users are clustered using clustering algorithms, user portraits of different user types are obtained, and the user portraits include shelf matching degree, user preference category, preference period, vehicle state and other features.

[0104] The automobile user portrait construction method provided in the embodiments of the present application can collect behavior data and vehicle state data of automobile users, associate the behavior data and the vehicle state data according to a preset association strategy, construct user classification features and user behavior features, identify actual user classifications of the automobile users according to the user classification features, and match corresponding behavior features of the user behavior features according to the actual user classifications, so as to construct a user portrait, and further understand the intelligent acceptance degree and product preferences of the cabin user, formulate product design and optimization schemes for different types of users, improve the use value of the intelligent cabin, and improve the human-computer interaction level of the vehicle. Therefore, the problems in the related art that there is a lack of relevant data support when planning and designing the intelligent cabin product, the intelligent acceptance degree of the current vehicle user is not clear to the product personnel, the pertinence of the cabin intelligent function design is reduced, and the value of the intelligent cabin for the whole vehicle cannot be highlighted are solved.

[0105] Secondly, the automobile user portrait construction device provided in the embodiments of the present application is described with reference to the accompanying drawings.

[0106] Figure 4 is a block schematic diagram of the automobile user portrait construction device in the embodiments of the present application.

[0107] As shown in Figure 4 , the automobile user portrait construction device 10 includes an acquisition module 100, a construction module 200, and a construction module 300.

[0108] The acquisition module 100 is configured to acquire behavior data and vehicle state data of automobile users.

[0109] The construction module 200 is configured to associate the behavior data and the vehicle state data according to a preset association strategy, and construct user classification features and user behavior features.

[0110] The construction module 300 is configured to identify actual user classifications of the automobile users in the user classifications according to the user classification features, and match corresponding behavior features of the user behavior features according to the actual user classifications, so as to construct a user portrait.

[0111] Optionally, in an embodiment of the present application, a processing unit is further included.

[0112] The processing unit is configured to filter data satisfying a preset invalid condition from behavior data, vehicle state data, and relevant feature data required by a business of the automobile users after the behavior data and the vehicle state data of the automobile users are acquired, wherein the preset invalid condition includes that a key field is empty, a field value content does not conform to a field definition or a field reporting rule.

[0113] Optionally, in an embodiment of the present application, the construction module 200 includes an acquisition unit and an association unit.

[0114] The acquisition unit is configured to acquire an identity of the current vehicle.

[0115] The association unit is configured to associate the behavior data and the vehicle state data according to a preset time rule based on the identity.

[0116] Optionally, in an embodiment of the present application, the construction module 200 further comprises a first construction unit and a second construction unit.

[0117] The first construction unit is configured to calculate a feature value of user classification by using the number of started functions, the number of carried functions, the number of function starts, the number of vehicle starts, the function usage rate and the function usage frequency of the user in a preset period in the related feature data, so as to construct a user classification feature based on the behavior data.

[0118] The second construction unit is configured to calculate a function type preference, a function usage time and a vehicle state of user behavior by using the vehicle state data and the behavior data, so as to construct a user behavior feature.

[0119] Optionally, in an embodiment of the present application, the second construction unit comprises: classifying the intelligent functions carried in the vehicle, and calculating a category shelf weight of each type; calculating a user preference value of each type according to the category shelf weight of each type and the number of function starts of each type, so as to obtain a shelf matching degree; and determining the function type preference according to the shelf matching degree.

[0120] Optionally, in an embodiment of the present application, the user classification comprises at least one of a cockpit value user, a cockpit expandable user, a cockpit activatable user and a cockpit potential user.

[0121] It should be noted that the foregoing explanation and description of the embodiment of the method for constructing a portrait of a vehicle user also applies to the device for constructing a portrait of a vehicle user, which will not be described here again.

[0122] The device for constructing a portrait of a vehicle user according to the embodiment of the present application can collect behavior data and vehicle state data of a vehicle user, associate the behavior data and the vehicle state data according to a preset association strategy, construct a user classification feature and a user behavior feature, identify an actual user classification of the vehicle user according to the user classification feature, and match a corresponding behavior feature of the user according to the actual user classification, so as to construct a user portrait, further understand the intelligent acceptance degree of the cockpit user and the product preference, formulate a product design and optimization scheme for different types of users, improve the use value of the intelligent cockpit, and improve the human-machine interaction level of the vehicle. Thus, the problems in the related art that there is a lack of relevant data support when planning and designing an intelligent cockpit product, the product personnel cannot clearly understand the intelligent acceptance degree of the current vehicle user, the pertinence of the cockpit intelligent function design is reduced, and the value of the intelligent cockpit for the whole vehicle cannot be highlighted are solved.

[0123] Figure 5 A structural schematic diagram of a vehicle is provided for the embodiments of the present application. The vehicle can include:

[0124] The memory 501, the processor 502 and the computer program stored in the memory 501 and executable on the processor 502.

[0125] The processor 502 implements the automobile user portrait construction method provided in the above embodiments when executing the program.

[0126] Further, the vehicle further includes:

[0127] The communication interface 503 is used for communication between the memory 501 and the processor 502.

[0128] The memory 501 is used for storing the computer program executable on the processor 502.

[0129] The memory 501 can include a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0130] If the memory 501, the processor 502 and the communication interface 503 are independently implemented, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and complete the communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 5 Only one thick line is used in the middle, but it does not mean that there is only one bus or one type of bus.

[0131] Optionally, in specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can complete the communication between each other through an internal interface.

[0132] The processor 502 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the application.

[0133] The embodiment further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the automobile user portrait construction method.

[0134] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or N embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0135] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0136] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for performing a step of a process described in the specification, and that the scope of the preferred embodiments of the application encompasses additional implementation in which the functions described in the specification are performed in a different order, including substantially simultaneously, or in reverse order, or in an order that is different from the order described in the specification, as will be understood by those skilled in the art.

[0137] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the 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 (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program 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 the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0138] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0139] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0140] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0141] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for constructing a car user portrait, characterized in that: The following steps are involved: Collect car user behavior data and vehicle status data; Correlating the behavior data and the vehicle status data according to a preset correlation strategy to construct user classification features and user behavior features; as well as Identifying an actual user category of the car user in the user category based on the user category characteristics, and matching corresponding behavioral characteristics of the user behavior characteristics based on the actual user category to construct a user profile; The constructing of user classification features and user behavior features includes: Obtain relevant feature data required for business purposes based on the vehicle's intelligent function installation and usage; Calculate the characteristic value of user classification by using the number of activated functions, number of installed functions, number of function activations, number of vehicle activations, function utilization rate, and function utilization frequency of the user in a preset period in the relevant characteristic data, and construct the user classification feature by using the behavioral data; The vehicle status data and behavior data are used to calculate the function type preference, function usage time and vehicle status of the user behavior to construct the user behavior characteristics.

2. The method according to claim 1, characterized in that After collecting the behavior data of the car user and the vehicle status data, the method further includes: Filter the data that meets the preset invalid conditions in the car user's behavior data, the vehicle status data and the relevant feature data required by the business, wherein the preset invalid conditions include that the key field is empty and the field value content does not comply with the field definition or field reporting rules.

3. The method according to claim 1, characterized in that The associating the behavior data and the vehicle status data according to a preset association strategy includes: Get the current car's identity; Based on the identity identifier, the behavior data and the vehicle status data are associated according to a preset time rule.

4. The method according to claim 1, wherein The method of calculating the function type preference, function usage time and vehicle status of the user behavior by using the vehicle status data and behavior data includes: Classify the intelligent functions installed in the vehicle and calculate the category shelf weight of each type; Calculate the user preference value of each type according to the category shelf weight of each type and the number of function activations of each type to obtain a shelf matching degree; The function type preference is determined according to the shelf matching degree.

5. The method according to claim 1, wherein The user classification includes at least one of cabin value users, cabin expandable users, cabin activation users and cabin potential users.

6. A car user portrait construction device, applicable to the method according to any one of claims 1 to 5, characterized in that: include: The collection module is used to collect the behavior data of car users and vehicle status data; A construction module, configured to associate the behavior data with the vehicle status data according to a preset association strategy to construct user classification features and user behavior features; as well as A construction module is used to identify the actual user classification of the car user in the user classification based on the user classification characteristics, and match the corresponding behavioral characteristics of the user behavior characteristics according to the actual user classification to construct a user portrait.

7. The device according to claim 6, characterized in that Also includes: A processing unit is used to filter out data that meets preset invalid conditions from the car user's behavior data and the vehicle status data after collecting the car user's behavior data and the vehicle status data and the relevant characteristic data required by the business, wherein the preset invalid conditions include that the key field is empty and the field value content does not comply with the field definition or field reporting rules.

8. A vehicle, characterized in that: include: 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 method for constructing a car user portrait as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the automobile user portrait construction method as described in any one of claims 1 to 5.

Images