WO2021027158A1 - 车辆信息的推送方法、装置、设备及计算机可读存储介质 - Google Patents

车辆信息的推送方法、装置、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2021027158A1
WO2021027158A1 PCT/CN2019/118364 CN2019118364W WO2021027158A1 WO 2021027158 A1 WO2021027158 A1 WO 2021027158A1 CN 2019118364 W CN2019118364 W CN 2019118364W WO 2021027158 A1 WO2021027158 A1 WO 2021027158A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
vehicle
user
preferred
car
Prior art date
Application number
PCT/CN2019/118364
Other languages
English (en)
French (fr)
Inventor
徐光飞
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021027158A1 publication Critical patent/WO2021027158A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations

Definitions

  • This application mainly relates to the field of data processing technology, and specifically, to a method, device, device, and computer-readable storage medium for pushing vehicle information.
  • the vehicle information provided by the vehicle sales platform is numerous and constantly updated.
  • the vehicle sales platform usually has a recommendation mechanism; according to the recent historical information browsed by the user for the vehicle, the vehicle is recommended to the user .
  • the recent historical information may be generated by the user's misoperation, which is inaccurate; the vehicle recommended to the user is also inaccurate and cannot meet the user's needs.
  • the main purpose of this application is to provide a method, device, device, and computer-readable storage medium for pushing vehicle information, aiming to solve the problem that vehicles recommended to users in the prior art are inaccurate and cannot meet user needs.
  • this application provides a method for pushing vehicle information, and the method for pushing vehicle information includes the following steps:
  • the step of determining the user's preferred car model according to the number of operations and the duration of each operation includes:
  • this application also proposes a device for pushing vehicle information, and the device for pushing vehicle information includes:
  • the collection module is used to collect the operation data generated by the user browsing each preset vehicle information based on the network, and to filter the operation data to determine the vehicle type information that the user browses;
  • the determining module is configured to read the number of operations and the length of operation corresponding to each of the vehicle type information in the operation data, and determine the user's preferred vehicle type according to the number of operations and the length of each operation;
  • the sorting module is used to sort each of the preferred car models to generate a car model sequence, and obtain the information of each target car model according to the order of the preferred car models in the car model sequence;
  • a recommendation module configured to output each of the target vehicle type information to the terminal held by the user based on the arrangement sequence
  • the determining module further includes:
  • a first comparison unit configured to compare each of the number of operations with a first preset threshold, and determine a target number of operations that is greater than the first preset threshold among the number of operations;
  • a second comparison unit configured to compare each of the operation durations with a second preset threshold, and determine a target operation duration of each of the operation durations that is greater than the second preset threshold;
  • the determining unit is configured to determine the preferred car model information corresponding to the target operation times and/or target operation duration in each of the car model information, and determine the car model corresponding to each of the preferred car model information as the user's preferred car model .
  • this application also proposes a vehicle information pushing device, which includes a memory, a processor, a communication bus, and a readable instruction for pushing vehicle information stored on the memory. ;
  • the communication bus is used to realize connection and communication between the processor and the memory
  • the processor is configured to execute the push readable instruction of the vehicle information to implement the following steps:
  • the step of determining the user's preferred car model according to the number of operations and the duration of each operation includes:
  • the present application also provides a computer-readable storage medium that stores one or more readable instructions, and the one or more readable instructions can be The above processor is executed for:
  • the step of determining the user's preferred car model according to the number of operations and the duration of each operation includes:
  • the vehicle information push method of this embodiment collects operation data generated by the user browsing various preset vehicle information based on the network, and filters the collected operation data to determine the vehicle type information that the user browses;
  • the number of operations and operation duration corresponding to the information of each vehicle type in the operation data, and the user's preferred car model is determined according to the number of operations and each operation duration; after that, the preferred car models are sorted to generate a car model sequence, and according to each preference in the car model sequence
  • the order of the car models is to obtain the target car model information; and then the target car model information is output to the terminal held by the user based on the order of arrangement, so as to realize the recommendation to the user of the vehicle corresponding to the target car model information.
  • the preferred car model is generated based on the number of operations and operating time the user browses, and the car model sequence is arranged according to the preferred car model; the target car model information obtained according to the car model sequence is the car model information that meets the user's preference, and the target car model information is output to the user
  • the recommendation by the terminal can enable the recommended vehicle to accurately meet the user's preference requirements and improve the accuracy of pushing vehicle information.
  • Fig. 1 is a schematic flowchart of a first embodiment of a method for pushing vehicle information of the present application
  • FIG. 2 is a schematic diagram of functional modules of the first embodiment of the vehicle information pushing device of the present application.
  • FIG. 3 is a schematic diagram of the device structure of the hardware operating environment involved in the method of the embodiment of the present application.
  • This application provides a method for pushing vehicle information.
  • FIG. 1 is a schematic flowchart of a first embodiment of a method for pushing vehicle information according to this application.
  • the method for pushing the vehicle information includes:
  • Step S10 Collect the operation data generated by the user browsing each preset vehicle information based on the network, and filter the operation data to determine the vehicle type information that the user browses;
  • the method for pushing vehicle information of the present application is applied to a server, and is suitable for recommending a vehicle that meets the user's preferences through the server based on the operating data generated by the user browsing the vehicle on the network.
  • users When users have vehicle purchase needs, they usually browse the information of various vehicles on the network platform that sells vehicles to find vehicles that meet their purchase needs. Browsing operations will generate various types of operational data, such as the type of vehicle targeted by each browse, the number of views of each vehicle model, etc., or the viewing data for viewing vehicle configuration information, price, loan support, loan limit, etc. .
  • the vehicle type and the number of views in the operation data represent the user's demand preference.
  • the operation data generated by the user browsing each preset vehicle information based on the network is collected, where the preset vehicle information is various types of vehicle information that can be viewed on the network platform, and the collected operation data is a preset period of time Generated within one month from the current time to ensure that the collected operating data accurately reflects the current needs of users.
  • the operation data is filtered to determine the vehicle type information that the user browses.
  • the vehicle type information is the vehicle type involved in the user's browsing of various preset vehicle information, and represents the vehicle type that the user may need to purchase.
  • the various types of vehicle information involved in the preset vehicle information are distinguished by different identifiers. After the operating data is obtained, the various types of information in the corresponding operating data also carry identifiers that characterize their types. Model information is filtered out from the operating data.
  • Step S20 Read the operation times and operation duration corresponding to each of the vehicle type information in the operation data, and determine the user's preferred vehicle type according to each of the operation times and each of the operation durations;
  • the number of times the user browses for different car models and the length of time during the browsing process are different, the number of times browsed for each car model is regarded as the number of operations corresponding to the information of each car model, and the length of time browsed for each car model is regarded as The operating time corresponding to the information of each vehicle type.
  • the user clicks on the vehicle type information, and the operation of viewing the vehicle type information is regarded as the number of operations of the vehicle type; in the operation data generated within the preset time, the number of times the user has viewed the information of each vehicle type is counted. Generate the number of operations in the operation data.
  • the viewing time of the user's one-time viewing operation of vehicle information is regarded as the single viewing time of the vehicle type; among the operation data generated within the preset time, the user viewing the information of each vehicle type is counted for each single viewing time To generate the duration of each operation in the operation data.
  • the operation times and operation duration corresponding to each vehicle type information are read from the operation data, that is, the user browses the vehicle type corresponding to each vehicle type information, and the generated operation times of each vehicle type and Operation time; and then determine the user's preferred car model based on the number of operations and the length of each operation.
  • the steps of determining the user's preferred car model include:
  • Step S21 comparing each number of operations with a first preset threshold, and determining a target number of operations greater than the first preset threshold among the number of operations;
  • Step S22 comparing each of the operation durations with a second preset threshold, and determining a target operation duration of each of the operation durations that is greater than the second preset threshold;
  • a first preset threshold and a second preset threshold are preset. Compare the number of operations with the first preset threshold one by one to determine the number of operations greater than the first preset threshold among the number of operations; at the same time, compare the duration of each operation with the second preset threshold one by one to determine the duration of each operation.
  • the operation duration is greater than the second preset threshold.
  • the number of operations greater than the first preset threshold is determined as the target number of operations
  • the operation duration greater than the second preset threshold is determined as the target operation duration; indicating that among the vehicle models browsed by the user, the number of browsing times or the duration of browsing is large Longer models.
  • Step S23 Determine the preferred car model information corresponding to the target operation number and/or target operation duration in each of the car model information, and determine the car model corresponding to each preferred car model information as the user's preferred car model.
  • the preferred car model information can be determined from the car model information according to the target operation times and the target operation duration. Both the number of operations and the length of operation correspond to the information of a certain vehicle type.
  • the vehicle type information corresponding to the target number of operations is the vehicle type information that has been viewed more frequently by the user, and it is determined as the information of the preferred vehicle type; the vehicle type information corresponding to the target operating time is viewed by the user
  • the long-term model information is also determined as the preferred model information.
  • the target operation times and the target operation duration correspond to the same vehicle type information, it means that the user has browsed the vehicle type information more frequently and the browsing time is long. It is the vehicle type information that the user focuses on, and the vehicle type information needs to be determined as the preferred vehicle type information . Since the car model information of each car model is derived from each car model, the car model corresponding to the car model information of each car model can be determined as the user's preferred car model to represent the car model that the user needs and preferred.
  • Step S30 sorting each of the preferred car models to generate a car model sequence, and obtaining information of each target car model according to the sequence of the preferred car models in the car model sequence;
  • the preferred car models are sorted to generate a car model sequence; and the preferred car models with a higher degree of preference are ranked in the front row, and the preferred car models with a lower degree of preference are ranked in the back row; through the car model sequence , Which characterizes the decrease in user preference from high to low.
  • the steps to generate the model sequence include:
  • Step S31 Read the loan data in the operation data, generate a loan interest ratio based on the loan data and the operation data, compare the loan interest ratio with a preset ratio, and determine the loan interest Whether the degree ratio is greater than the preset ratio;
  • vehicle sellers usually set up a loan mechanism, that is, users can purchase their preferred vehicles through loans. If the user needs to purchase a vehicle through a loan, in the process of browsing the vehicle information, the loan information corresponding to each vehicle will be browsed, and the loan amount and loan time limit supported by each vehicle will be viewed.
  • the data generated by checking the loan information is used as the loan data in the operation data, and the loan data is read from the operation data according to the identification related to the loan, and the loan data is used to characterize the user's need to purchase the vehicle through the loan Strong and weak.
  • the demand is strong, it can be predicted that users have less consideration of vehicle price factors and can buy models with a high degree of preference to a large extent; when sorting the preferred models, the ranking is directly based on the degree of preference. If the demand is weak, when sorting the preferred models, the price factors of each preferred model need to be considered, and the ranking is based on the price factor.
  • a preset ratio is preset, and the loan interest ratio generated based on the loan data and operation data is compared with the preset ratio, and the loan interest ratio and The size relationship between the preset ratios is used to determine the strength of loan car purchase demand.
  • the loan data includes the number of times the user browses the loan information corresponding to each model, and the number of views corresponding to different models is different.
  • the number of views is added to obtain the total number of views related to the loan involved in the operation data frequency.
  • add the number of operations in the operation data to obtain the total number of operations for viewing each vehicle model; then use the total number of views and the total number of operations as the ratio, and the result of the ratio is the loan attention ratio, which represents The number of times the user checked the loan information during the course of checking the information of each vehicle.
  • the ratio of loan interest is larger, it means that the more times the user has to check the loan information, the stronger the user's demand for loan to buy a car; otherwise, the weaker the user's demand for loan to buy a car.
  • Step S32 if it is greater than the preset ratio, integrate the target operation times and/or target operation duration corresponding to each of the preferred car models to generate a preference coefficient for each of the preferred car models, and according to each of the preference coefficients
  • the size relationship between each of the preferred car models is sorted to generate a car model sequence.
  • the target operation times and/or target operation duration corresponding to each preferred car model are integrated to generate a preference coefficient for each preferred car model; the greater the value of the preference coefficient, the higher the degree of preference represented, and vice versa The lower.
  • each preferred car model is determined by any one of the target number of operations and the target operation duration, that is, when the number of operations corresponding to the model information of a certain model is or any of the operation durations is the target number of operations or the target duration of operation, Then the vehicle type is the preferred vehicle type; thus, when generating the preference coefficient of each preferred vehicle type, it is performed according to the target operation times and/or target operation duration actually corresponding to each preferred vehicle type.
  • the number of operations a1 corresponding to A is the target number of operations, and the corresponding operation duration a2 is not the target operation duration; the number of operations b1 corresponding to B is not the target number of operations, and its The corresponding operation duration b2 is the target operation duration; the operation count c1 corresponding to C is the target operation count, and the corresponding operation duration c2 is the target operation duration.
  • a1 is integrated; when generating the preference coefficient of the preferred model B, then b2 is integrated; when generating the preference coefficient of the preferred model C, c1 and c2 are integrated .
  • integrating the target operation times and/or target operation duration corresponding to each preferred car model, and generating the preference coefficient of each preferred car model includes:
  • Step S321 comparing the target operation times corresponding to each of the preferred car models with a preset interval of times to determine the frequency coefficient of each of the preferred car models;
  • a number of preset frequency intervals are preset, and each preset frequency interval is correspondingly set with different coefficients; for example, the coefficient corresponding to the preset frequency interval [50 ⁇ 100] is set It is 0.7, and the coefficient corresponding to the preset frequency interval [100 ⁇ 150] is 0.8, etc.
  • Different coefficients are used to characterize different degrees of preference. When the value corresponding to the preset interval of times is larger, and the number of viewing times of the user is greater, the corresponding preference degree is higher, otherwise, the corresponding preference degree is lower.
  • the frequency coefficient of the car model indicates the number of times of viewing each preferred car model.
  • Step S322 comparing the target operation duration corresponding to each of the preferred vehicle models with the preset duration interval to determine the duration coefficient of each of the preferred vehicle models;
  • each preset duration interval is correspondingly set with different coefficients; for example, the preset duration interval is set [5h ⁇ 8h]
  • the corresponding coefficient is 0.7
  • the coefficient corresponding to the preset time interval [8h ⁇ 12h] is 0.8.
  • Different coefficients are used to characterize different degrees of preference. The larger the value corresponding to the preset duration interval, the longer the viewing time of the user, the higher the corresponding preference degree, and vice versa, the lower the corresponding preference degree.
  • the duration coefficient of the vehicle model indicates the length of time for viewing each preferred model.
  • Step S323 Read the first weight value and the second weight value respectively corresponding to the operation times and the operation duration, and use the first weight value and the second weight value to calculate the frequency coefficient of each of the preferred car models. And the duration coefficient weighting process to generate the preference coefficient of each of the preferred car models.
  • the target operation times and the target operation duration have different effects on the overall preference level.
  • the first weight value and the first weight value and the second operation duration are respectively set for the operation times and operation duration in advance.
  • Two weight value After determining the frequency factor and duration factor, read the first weight value and the second weight value, and use the read first weight value and second weight value to weight the frequency factor and duration factor respectively to generate The preference coefficient of each preferred model. Because there is only one of the target operation times and the target operation duration in each preferred car model, that is, there is only one of the frequency coefficient and the duration coefficient; therefore, in the process of weighting, it is based on each preferred car model With the order coefficient and duration coefficient.
  • the first weight value is used to weight the frequency coefficient
  • the second weight value is used to weight the duration coefficient
  • the first weight value is k1 and the second weight value is k2; then the preference coefficient generated for A is k1*a1, and the preference coefficient generated for B is k2*b2 ,
  • the preference coefficient generated for C is (k1*c1+k2*c2).
  • the preference coefficients of each preferred vehicle model obtained by weighting are used to characterize the user's preference degree for each preferred vehicle model. The larger the preference coefficient obtained, the higher the corresponding preference degree, and vice versa.
  • the preferred car models can be sorted according to the degree of preference represented by each preference coefficient to generate a car model sequence. Specifically, the preference coefficients are compared to determine the size relationship between the preference coefficients; according to the size relationship, the preferred car models are sorted, and the preferred car models with a large preference coefficient are ranked in the forefront, while the preference coefficient is small.
  • the preferred car models are arranged in the back column; after the arrangement of each preferred car model is completed, a car model sequence that characterizes the degree of user preference can be generated.
  • the step of judging whether the loan interest ratio is greater than the preset ratio includes:
  • Step S33 If it is not greater than the preset ratio, read the price information of each of the preferred car models, and collect basic information corresponding to the user's economic status;
  • the price information of each preferred car model is read, and the user's basic information is collected at the same time.
  • the basic information includes the user's gender, age, education, work nature, work industry, residential address, etc., so as to use this type of information to reflect the user's economic status.
  • Step S34 Determine the savings information of the user according to the basic information, and compare the savings information with each of the price information to generate each comparison result;
  • the user’s basic information reflects the user’s economic status
  • the user’s income information can be predicted based on the basic information; the residential address in the basic information represents the city where the user works, and the city’s city can be obtained.
  • Average income; while the job industry and the nature of work represent the income of the user’s industry relative to the city where the user is located, and the city’s average income can be optimized by the industry and nature of work.
  • the job industry and nature are relatively hot and high-paying industries, it is optimized to multiply the average urban income by a coefficient greater than 1, and when the job industry and nature are relatively unpopular basic industries, it is optimized to multiply the city’s average income by a factor less than 1.
  • the coefficient through optimization to get the user’s basic income.
  • the user’s basic expenditure is predicted, and the user’s basic expenditure is taken as the user’s basic expenditure by reading the average expenditure of people of the same gender and age in the user’s city.
  • the user's income data can be obtained by using the predicted basic income and basic expenditure, the user's working years can be estimated based on the age and education in the basic information, and the working years and the income data are multiplied to generate the user's savings data.
  • the adjustment coefficient less than 1 is determined according to the working life.
  • the working life is short, it means that the income and expenditure between the years have not changed much, and the adjustment coefficient is set to be close to 1.
  • the time limit is longer, it means that the income and expenditures between the years have changed greatly, and the adjustment coefficient is set to be smaller than 1. Multiply the adjustment coefficient and the accumulation data to obtain the adjusted accumulation data; determine the adjusted accumulation data as the user's accumulation information to reflect the user's current disposable amount.
  • the user's savings information is compared with the price information of each preferred car model one by one, and the comparison result between the savings information and each price information is obtained, and the matching degree between the savings information and each price is reflected through each comparison result;
  • Step S35 sorting the preferred car models according to the comparison results to generate a car model sequence.
  • the comparison results generated represent the degree of matching between the accumulated information and the price information.
  • the higher the degree of matching the stronger the user's ability to purchase the vehicle that generates the price information of the matching degree; thus, the comparison result shows that
  • sort the various preferred car models and arrange the preferred car models corresponding to the price information with high matching degree in the front row, and arrange the preferred car models corresponding to the price information with low matching degree in the back column.
  • a car model sequence that characterizes the user's purchasing power can be generated, and the car model series are all preferred car models that the user has paid attention to many times.
  • the vehicle type information of the preferred vehicle type is acquired according to the sequence of each preferred vehicle type in the vehicle type sequence, so that the acquired vehicle type information corresponds to each of the favorite vehicle types in the vehicle type sequence.
  • the acquired model information includes manufacturer, vehicle model, engine model, price, horsepower, etc.; the acquired model information is used as target model information to recommend the vehicle from which it originated.
  • step S40 the target vehicle type information is output to the terminal held by the user based on the arrangement sequence.
  • the order in the car model series represents the user’s preference or purchasing power;
  • This arrangement sequence outputs the information of each target vehicle type to a terminal such as a computer and a mobile phone held by the user, so as to recommend the vehicle corresponding to the information of each target vehicle type.
  • the number can be numbered according to the sequence of the recommendation to represent the strength of the recommendation, which corresponds to the user's preference or purchasing power.
  • the vehicle information push method of this embodiment collects operation data generated by the user browsing various preset vehicle information based on the network, and filters the collected operation data to determine the vehicle type information that the user browses;
  • the number of operations and operation duration corresponding to the information of each vehicle type in the operation data, and the user's preferred car model is determined according to the number of operations and each operation duration; after that, the preferred car models are sorted to generate a car model sequence, and according to each preference in the car model sequence
  • the order of the car models is to obtain the target car model information; and then the target car model information is output to the terminal held by the user based on the order of arrangement, so as to realize the recommendation to the user of the vehicle corresponding to the target car model information.
  • the preferred car model is generated based on the number of operations and operating time the user browses, and the car model sequence is arranged according to the preferred car model; the target car model information obtained according to the car model sequence is the car model information that meets the user's preference, and the target car model information is output to the user
  • the recommendation by the terminal can enable the recommended vehicle to accurately meet the user's preference requirements and improve the accuracy of pushing vehicle information.
  • the step of screening the operation data includes before:
  • Step S50 Read the identity information of the user, and determine whether the user has a user vehicle according to the identity information;
  • the purpose of browsing various preset vehicle information on the network platform where the user sells the vehicle may be to purchase vehicle value-added services, but not to purchase a vehicle.
  • the prerequisite for purchasing vehicle value-added services is that the user has already purchased the vehicle and has the user vehicle; therefore, in order to distinguish the user for browsing the preset vehicle information, it is necessary to determine whether the user already has the user vehicle.
  • Read the user's identity information and apply to the vehicle management agency for inquiries based on the user's identity information to determine whether the identity information is associated with a vehicle. When it is determined by query that the identity information is associated with a vehicle, it means that the user already has a user vehicle; and when it is determined that the identity information is not associated with a vehicle, it means that the user does not have a user vehicle.
  • Step S60 if the user has a user vehicle, read the auto insurance information of the user vehicle, and recommend auto insurance to the user according to each of the auto insurance information;
  • the vehicle value-added service in this embodiment mainly involves compulsory traffic insurance, vehicle loss insurance, and third party liability insurance.
  • the auto insurance can be recommended to the user based on the auto insurance information corresponding to the user's vehicle that the user already has.
  • the auto insurance information of the user's vehicle is read, and the auto insurance information includes various types of auto insurance, time limits corresponding to various types of auto insurance, and insurance records and other information related to auto insurance.
  • the steps of recommending auto insurance to the user include:
  • Step S61 comparing the time limit information in each of the auto insurance information with a preset time limit, and judge whether there is target time limit information less than the preset time limit in each of the time limit information;
  • Step S62 if there is target time limit information less than the preset time limit, determine the type of car insurance corresponding to the target time limit information
  • a preset time limit indicating that it is about to expire is preset, for example, a time one month away from the deadline is set as the preset time limit, and the time limit information in the car insurance information is compared with the preset time limit.
  • the time limit information in the auto insurance information is the length of time between the respective expiration dates of the various auto insurances purchased by the user's vehicle; for example, the auto insurance purchased by the user's vehicle includes p1, p2, and p3, where the expiration period of p1 is q1, p2 The expiration period of q2, p3 is q3, and the time length information of the current time from q1, q2, and q3 is d1, d2, and d3 respectively; the d1, d2, and d3 are the time limit information in the car insurance information .
  • the car insurance from which the target time limit information originates determines the type of car insurance corresponding to the target time limit information to query the car insurance corresponding to the car insurance type for recommendation.
  • Step S63 Read the risk information corresponding to the user's vehicle, and recommend the car insurance corresponding to the type of car insurance to the user according to the risk information.
  • the user’s vehicle may have an insurance that corresponds to the auto insurance that is about to expire.
  • the auto insurance that is about to expire is a vehicle loss insurance
  • the user’s vehicle has suffered hail during use, which is carried out by the insurance agency.
  • the claim; the claim caused by the hail is the risk situation corresponding to the auto insurance that is about to expire.
  • the car insurance corresponding to the type of car insurance that different institutions can provide is different in price or time limit.
  • the insurance information corresponding to the user’s vehicle is read.
  • the insurance information includes the number of times of insurance, the time of each insurance and the main responsible party; according to the information of the insurance, each car insurance to be recommended is determined, which should be recommended Auto insurance comes from different agencies, and they all correspond to the type of auto insurance recommended. Compare the information of each car insurance to be recommended to determine the car insurance to be recommended with the greatest relative discount; or determine the car insurance to be recommended with the most user views among the car insurances to be recommended; the car insurance to be recommended with the greatest discount or the most viewed The auto insurance to be recommended as the auto insurance corresponding to the auto insurance type is recommended to the user.
  • the user can also purchase other vehicles; therefore, when it is determined that the user has a vehicle and it is determined that there is no target time limit information less than the preset time limit in the time limit information, it means that the user browses The purpose of preset vehicle information is to need to purchase other vehicles.
  • the collected operating data is screened to determine the preferred car model that meets the user's needs and preferences, and each preferred car model is generated into a car model sequence for recommendation; the specific recommendation method is similar to the recommendation method in the first embodiment above, here Do not repeat it.
  • Step S70 If the user does not have a user vehicle, perform the step of screening the operation data.
  • each preset vehicle information is to purchase a vehicle, so as to filter the collected operating data to determine the preferred car model that meets the user’s needs and preferences, and Each preferred car model generates a car model sequence for recommendation; the specific recommendation method is similar to the recommendation method in the first embodiment described above, and will not be repeated here.
  • this application provides a device for pushing vehicle information.
  • the device for pushing vehicle information includes:
  • the collection module 10 is configured to collect operation data generated by users browsing various preset vehicle information based on the network, and filter the operation data to determine the vehicle type information that the user browses;
  • the determining module 20 is configured to read the operation times and operation durations corresponding to each of the vehicle type information in the operation data, and determine the user's preferred vehicle type according to each of the operation times and each of the operation durations;
  • the sorting module 30 is used to sort each of the preferred car models to generate a car model sequence, and obtain information of each target car model according to the order of the preferred car models in the car model sequence;
  • the recommendation module 40 is configured to output the target vehicle type information to the terminal held by the user based on the arrangement sequence.
  • the vehicle information pushing device of this embodiment collects the operation data generated by the user from browsing various preset vehicle information based on the network through the collection module 10, and filters the collected operation data to determine the vehicle type information that the user browses;
  • the determination module 20 then reads the number of operations and operation duration corresponding to the information of each vehicle model in the operation data, and determines the user's preferred car model according to the number of operations and each operation duration; after that, the sorting module 30 sorts the preferred car models.
  • the recommendation module 40 outputs the target car model information to the terminal held by the user based on the order of arrangement, so as to realize the recommendation to the user and the target car model The vehicle corresponding to the information.
  • the preferred car model is generated based on the number of operations and operating time the user browses, and the car model sequence is arranged according to the preferred car model; the target car model information obtained according to the car model sequence is the car model information that meets the user's preference, and the target car model information is output to the user
  • the recommendation by the terminal can enable the recommended vehicle to accurately meet the user's preference requirements and improve the accuracy of pushing vehicle information.
  • the determining module further includes:
  • a first comparison unit configured to compare each of the number of operations with a first preset threshold, and determine a target number of operations that is greater than the first preset threshold among the number of operations;
  • a second comparison unit configured to compare each of the operation durations with a second preset threshold, and determine a target operation duration of each of the operation durations that is greater than the second preset threshold;
  • the determining unit is configured to determine the preferred car model information corresponding to the target operation times and/or target operation duration in each of the car model information, and determine the car model corresponding to each of the preferred car model information as the user's preferred car model .
  • the sorting module further includes:
  • the reading unit is configured to read the loan data in the operation data, generate a loan attention ratio based on the loan data and the operation data, compare the loan attention ratio with a preset ratio, and determine Whether the loan interest ratio is greater than the preset ratio;
  • the sorting unit is configured to, if it is greater than the preset ratio, integrate the target operation times and/or target operation duration corresponding to each of the preferred car models to generate the preference coefficients of each of the preferred car models, and according to the respective The size relationship between the preference coefficients is used to sort the preferred car models to generate a car model sequence.
  • the sorting unit is further configured to:
  • the weighting process generates the preference coefficient of each of the preferred car models.
  • the sorting module further includes:
  • a collection unit configured to read the price information of each of the preferred car models if it is not greater than the preset ratio, and collect basic information corresponding to the user's economic status;
  • the first generating unit is configured to determine the user's savings information according to the basic information, and compare the savings information with each of the price information to generate each comparison result;
  • the second generating unit is configured to sort the preferred car models according to the comparison results to generate a car model sequence.
  • the collection module is further used for:
  • the step of screening the operation data is performed.
  • the collection module is further used for:
  • the virtual function modules of the aforementioned vehicle information pushing device are stored in the memory 1005 of the vehicle information pushing device shown in FIG. 3.
  • the processor 1001 executes the readable instructions for pushing vehicle information, the implementation shown in the embodiment shown in FIG. The function of each module.
  • FIG. 3 is a schematic diagram of the device structure of the hardware operating environment involved in the method of the embodiment of the present application.
  • the device for pushing vehicle information in the embodiment of this application may be a PC (personal computer, personal computer ), it can also be terminal devices such as smart phones, tablet computers, e-book readers, and portable computers.
  • PC personal computer, personal computer
  • terminal devices such as smart phones, tablet computers, e-book readers, and portable computers.
  • the vehicle information pushing device may include: a processor 1001, such as a CPU (Central Processing Unit, central processing unit), memory 1005, communication bus 1002. Among them, the communication bus 1002 is used to implement connection and communication between the processor 1001 and the memory 1005.
  • the memory 1005 may be a high-speed RAM (random access memory, random access memory), or stable memory (non-volatile memory), such as disk storage.
  • the memory 1005 may also be a storage device independent of the foregoing processor 1001.
  • the vehicle information push device may also include user interface, network interface, camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio circuit, WiFi (Wireless Fidelity, wireless broadband) module and so on.
  • the user interface may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface.
  • the optional network interface can include standard wired interface and wireless interface (such as WI-FI interface).
  • the structure of the vehicle information pushing device shown in FIG. 3 does not constitute a limitation on the vehicle information pushing device, and may include more or less components than shown in the figure, or a combination of certain components, Or different component arrangements.
  • the memory 1005 which is a computer-readable storage medium, may include an operating system, a network communication module, and push readable instructions for vehicle information.
  • the operating system is a readable instruction that manages and controls the hardware and software resources of the push device of vehicle information, and supports the operation of push readable instructions of vehicle information and other software and/or readable instructions.
  • the network communication module is used to implement communication between various components in the memory 1005 and communication with other hardware and software in the vehicle information push device.
  • the processor 1001 is configured to execute the readable instructions for pushing the vehicle information stored in the memory 1005 to implement the steps in each embodiment of the aforementioned vehicle information pushing method.
  • the present application provides a computer-readable storage medium
  • the computer-readable storage medium may be a non-volatile storage medium
  • the computer-readable storage medium stores one or more readable instructions, the one or one
  • the above readable instructions may also be executed by one or more processors to implement the steps in each embodiment of the foregoing method for pushing vehicle information.

Landscapes

  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种车辆信息的推送方法、装置、设备及计算机可读存储介质，所述方法包括：采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对操作数据进行筛选，确定用户进行浏览的车型信息（S10）；读取操作数据中与各车型信息对应的操作次数和操作时长，并根据各操作次数和各操作时长，确定用户的偏好车型(S20)；对各偏好车型进行排序，生成车型序列，并根据车型序列中各偏好车型的排列顺序，获取各目标车型信息(S30)；将各目标车型信息基于排列顺序输出到用户所持有的终端（S40）。本推送方法基于大数据分析技术所生成的车型序列表征了用户的需求，使得依据其所推荐的车辆，满足了用户的偏好需求，提高了车辆信息的推送的准确性。

Description

车辆信息的推送方法、装置、设备及计算机可读存储介质
本申请要求于2019年08月14日提交中国专利局、申请号为201910762719.1、发明名称为“车辆信息的推送方法、装置、设备及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请主要涉及数据处理技术领域，具体地说，涉及一种车辆信息的推送方法、装置、设备及计算机可读存储介质。
背景技术
随着互联网技术的发展，通过网络平台所提供的咨询和资源越来越丰富，如通过网络查看新闻、公告、通知、购买各种各样的物品等；用户在对物品进行购买时，一方面可通过网络平台直接购买，另一方面也可以先在网络平台上查看物品信息，再在现场进行试用购买等。如用户在对车辆进行购买时，则先在车辆销售平台浏览各种车辆相关的信息，当浏览到满足其需求的车辆时，则进行线下试驾等。
但车辆销售平台所提供的车辆信息众多且不断更新，为了便于用户快速浏览到满足其需求的车辆，汽车销售平台通常设置有推荐机制；根据用户针对汽车所浏览的近期历史信息，向用户推荐车辆。但因近期历史信息可能由用户的误操作而生成，具有不准确性；使得向用户推荐的车辆也不准确，不能满足用户需求。
发明内容
本申请的主要目的是提供一种车辆信息的推送方法、装置、设备及计算机可读存储介质，旨在解决现有技术中向用户推荐的车辆不准确，不能满足用户需求的问题。
为实现上述目的，本申请提供一种车辆信息的推送方法，所述车辆信息的推送方法包括以下步骤：
采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
此外，为实现上述目的，本申请还提出一种车辆信息的推送装置，所述车辆信息的推送装置包括：
采集模块，用于采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
确定模块，用于读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
排序模块，用于对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
推荐模块，用于将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
其中，所述确定模块还包括：
第一对比单元，用于将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
第二对比单元，用于将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
确定单元，用于确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
此外，为实现上述目的，本申请还提出一种车辆信息的推送设备，所述车辆信息的推送设备包括：存储器、处理器、通信总线以及存储在所述存储器上的车辆信息的推送可读指令；
所述通信总线用于实现处理器和存储器之间的连接通信；
所述处理器用于执行所述车辆信息的推送可读指令，以实现以下步骤：
采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质存储有一个或者一个以上可读指令，所述一个或者一个以上可读指令可被一个或者一个以上的处理器执行以用于：
采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
本实施例的车辆信息的推送方法，通过对用户基于网络对各预设车辆信息进行浏览所生成的操作数据采集，并对该采集的操作数据进行筛选，确定用户浏览的车型信息；再读取操作数据中与各车型信息对应的操作次数和操作时长，并根据各操作次数和各操作时长，确定用户的偏好车型；此后对各偏好车型进行排序，生成车型序列，并根据车型序列中各偏好车型的排列顺序，获取目标车型信息；进而将各目标车型信息基于排列顺序输出到用户所持有的终端，实现向用户推荐与各目标车型信息对应的车辆。本方案中偏好车型依据用户浏览的操作次数和操作时长生成，而车型序列依据偏好车型排列；使得依据车型序列所获取的目标车型信息为满足用户偏好的车型信息，将该目标车型信息输出到用户终端进行推荐，可使得所推荐的车辆准确的满足了用户的偏好需求，提高了车辆信息的推送的准确性。
附图说明
图1是本申请的车辆信息的推送方法第一实施例的流程示意图；
图2是本申请的车辆信息的推送装置第一实施例的功能模块示意图；
图3是本申请实施例方法涉及的硬件运行环境的设备结构示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供一种车辆信息的推送方法。
请参照图1，图1为本申请车辆信息的推送方法第一实施例的流程示意图。在本实施例中，所述车辆信息的推送方法包括：
步骤S10，采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
本申请的车辆信息的推送方法应用于服务器，适用于通过服务器依据用户在网络上对车辆进行浏览所生成的操作数据，向用户推荐满足其偏好的车辆。用户在有车辆购买需求时，通常会在对车辆进行销售的网络平台上，对各个车辆信息进行浏览，以查找满足其购买需求的车辆。浏览操作会生成各种类型的操作数据，如各次浏览所针对车辆的车型，各车型的浏览次数等数据，或者对车辆配置信息、价格、是否支持贷款、贷款额度等进行查看的查看数据等。操作数据中的车型、浏览次数等表征了用户的需求偏好，对某一车型的浏览次数越多，浏览时长越长，则表征用户对该车型的偏好程度越高。从而对用户基于网络对各预设车辆信息进行浏览所生成的操作数据进行采集，其中预设车辆信息为网络平台上可支持查看的车辆各类信息，且所采集的操作数据为一段预设时间内所生成；如以当前时间往前的一个月内，以确保所采集的操作数据准确反映用户当前需求。此后对操作数据进行筛选，确定用户所浏览的车型信息，该车型信息为用户在对各预设车辆信息进行浏览过程中所涉及到的车型，表征用户可能所需要购买的车型。预设车辆信息中所涉及到的车辆各类信息由不同的标识进行区分，在获取到操作数据后，相应的操作数据中的各类信息也携带有表征其类型的标识，从而可依据标识从操作数据中筛选出车型信息。
步骤S20，读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
进一步地，用户在浏览过程中针对不同车型所浏览的次数以及浏览的时长不一样，将针对各车型所浏览的次数作为与各车型信息对应的操作次数，而将针对各车型所浏览的时长作为与各车型信息对应的操作时长。其中用户对车型信息进行点击，对车型信息进行查看的操作作为该车型的一次操作次数；对在预设时间内所生成的操作数据中，用户各次对各车型信息进行查看的次数进行统计，生成操作数据中的各操作次数。同时将用户对车型信息一次查看操作的查看时长，作为对车型的单次查看时长；对在预设时间内所生成的操作数据中，用户对各车型信息进行查看的各单次查看时长进行统计，生成操作数据中的各操作时长。依据与操作次数和操作时长相关的标识，从操作数据中读取与各车型信息对应的操作次数和操作时长，即用户对与各车型信息对应车型进行浏览，所生成的各车型的操作次数和操作时长；进而依据各操作次数和各操作时长，确定用户的偏好车型。因对车型的浏览次数越多、浏览时长越长，即车型信息所对应的操作次数越多、浏览时长越长，所表征的偏好程度越高；从而可依据各车型信息所对应的操作次数和浏览时长之间的数值大小关系，来确定用户的偏好车型。具体地，根据各操作次数和各操作时长，确定用户的偏好车型的步骤包括：
步骤S21，将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
步骤S22，将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
为了表征各车型信息所对应操作次数的多少以及操作时长的长短，预先设置有第一预设阈值和第二预设阈值。将各操作次数逐一和该第一预设阈值进行对比，确定各操作次数中大于第一预设阈值的操作次数；同时将各操作时长逐一和第二预设阈值进行对比，确定各操作时长中大于第二预设阈值的操作时长。进而将大于第一预设阈值的操作次数确定为目标操作次数，而将大于第二预设阈值的操作时长确定为目标操作时长；表征用户所浏览的各车型中，浏览次数较多或浏览时长较长的车型。
步骤S23，确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
可理解地，用户在对各车型进行浏览的过程中，存在浏览次数较多、而浏览时长较短的车型，或者浏览次数较少、而浏览时长较长的车型，或者浏览次数较多、且浏览时长较长的车型；该三类车型为用户关注度较高的车型，表征了用户的偏好。在经对比确定目标操作次数和目标操作时长后，可依据该目标操作次数和目标操作时长，从车型信息中确定偏好车型信息。操作次数和操作时长均与某一车型信息对应，与目标操作次数对应的车型信息为用户浏览次数多的车型信息，而将其确定为偏好车型信息；与目标操作时长对应的车型信息为用户浏览时间长的车型信息，同样的也将其确定为偏好车型信息。当目标操作次数和目标操作时长对应同一车型信息时，则表征用户对该车型信息的浏览次数多，且浏览时间长，为用户着重关注的车型信息，而需要将该车型信息确定为偏好车型信息。因各车型偏好车型信息来源于各车型，从而可将与各偏好车型信息所对应的车型确定为用户的偏好车型，以表征用户所需求偏好的车型。
步骤S30，对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
考虑到不同的目标操作次数和目标操作时长，表征了用户对各偏好车型的偏好程度不一样；当偏好车型所对应的目标操作次数越多，且目标操作时长越长，则表征用户对该偏好车型的偏好程度越高。为了表征用户对个偏好车型的偏好程度，对各偏好车型进行排序，生成车型序列；且偏好程度越高的偏好车型排列在前列，而偏好程度越低的偏好车型排列在后列；通过车型序列，表征用户的偏好程度从高到低下降。因偏好程度与目标操作次数以及目标操作时长相关，从而在对各偏好车型进行排序时，依据各偏好车型所对应的目标操作次数和/或目标操作时长进行；具体地，对各偏好车型进行排序，生成车型序列的步骤包括：
步骤S31，读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
进一步地，为了促进用户对车辆的购买，车辆销售方通常设置有贷款机制，即用户可通过贷款对其偏好的车辆进行购买。若用户有通过贷款购买车辆的需求时，则在对车辆信息进行浏览的过程中，会对各车辆所对应的贷款信息进行浏览，查看各车辆所支持的贷款额度、贷款时限等。将对贷款信息查看所生成的数据作为操作数据中的贷款数据，根据与贷款相关的标识，从操作数据中读取该贷款数据，通过贷款数据来表征用户通过贷款的方式对车辆进行购买的需求强弱。若需求强，则可预测用户对车辆价格的因素考虑较少，可在大程度上购买其偏好程度高的车型；在对偏好车型进行排序时，直接依据偏好程度高低进行排序。而若需求弱，则在对偏好车型进行排序时，则需要考虑各偏好车型的价格因素，而依据价格因素进行排序。为了通过贷款数据来表征贷款购车需求的强弱，预先设定有预设比例，并将根据贷款数据和操作数据所生成的贷款关注度比值和该预设比例进行对比，通过贷款关注度比值和预设比例之间的大小关系，来确定贷款购车需求的强弱。
贷款数据中包括用户对各车型对应贷款信息进行浏览的浏览次数，且不同车型所对应的浏览次数不相同，对各浏览次数进行相加，得到操作数据中所涉及到的与贷款相关的浏览总次数。同时对操作数据中的各项操作次数进行相加，得到对各车型进行查看的操作总次数；进而用浏览总次数和操作总次数做比值，所得到的比值结果即为贷款关注度比值，表征用户对各车辆信息进行查看过程中对贷款信息进行查看的次数。当贷款关注度比值越大，表征用户对贷款信息进行查看的次数越多，用户贷款购车的需求越强；反之则说明用户贷款购车的需求越弱。
步骤S32，若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
进一步地，当将贷款关注度比值和预设比例进行对比，判断出贷款关注度比值大于预设比例时，则说明用户贷款购车的需求越强；在对各偏好车型进行排序时，按照各偏好车型的偏好程度高低进行。而为了表征偏好程度高度，则对各偏好车型对应的目标操作次数和/或目标操作时长整合，生成各偏好车型的偏好系数；其中偏好系数的数值越大，所表征偏好程度越高，反之则越低。因各偏好车型由目标操作次数和目标操作时长中的任意一项决定，即当某一车型所具有车型信息对应的操作次数为或操作时长中存在任意一项为目标操作次数或目标操作时长，则该车型即为偏好车型；从而在生成各偏好车型的偏好系数时，依据各偏好车型实际所对应的目标操作次数和/或目标操作时长进行。如对于偏好车型A、B、C，其中A所对应的操作次数a1是目标操作次数，而其所对应的操作时长a2不是目标操作时长；B所对应的操作次数b1不是目标操作次数，而其所对应的操作时长b2是目标操作时长；C所对应的操作次数c1是目标操作次数，且其所对应的操作时长c2是目标操作时长。则在生成偏好车型A的偏好系数时，则对a1进行整合；在生成偏好车型B的偏好系数时，则对b2进行整合；在生成偏好车型C的偏好系数时，则对c1和c2进行整合。具体地，对各偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各偏好车型的偏好系数的步骤包括：
步骤S321，将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
为了通过目标操作次数体现偏好程度的高低，预先设定有多个预设次数区间，且各个预设次数区间对应设置有不同的系数；如设定预设次数区间[50~100]对应的系数为0.7，预设次数区间[100~150]对应的系数为0.8等。通过不同的系数表征不同的偏好程度，当预设次数区间所对应的数值越大，用户的查看次数越多，则对应的偏好程度越高，反之则对应的偏好程度越低。将各偏好车型所对应的目标操作次数和各个预设次数区间对比，确定各偏好车型对应的目标操作次数所在的预设次数区间；该所在的预设次数区间所对应的系数，即为各偏好车型的次数系数，表征对各偏好车型的查看次数多少。
步骤S322，将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
同样地，为了通过目标操作时长体现偏好程度的高低，预先设定有多个预设时长区间，且各个预设时长区间对应设置有不同的系数；如设定预设时长区间[5h~8h]对应的系数为0.7，预设时长区间[8h~12h]对应的系数为0.8等。通过不同的系数表征不同的偏好程度，当预设时长区间所对应的数值越大，用户的查看时长越长，则对应的偏好程度越高，反之则对应的偏好程度越低。将各偏好车型所对应的目标操作时长和各个预设时长区间对比，确定各偏好车型对应的目标操作时长所在的预设时长区间；该所在的预设时长区间所对应的系数，即为各偏好车型的时长系数，表征对各偏好车型的查看时长长短。
步骤S323，读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
可理解地，目标操作次数和目标操作时长对整体偏好程度高低的影响不一样，为了体现两者对整体偏好程度高低的影响，预先针对操作次数和操作时长分别设定有第一权重值和第二权重值。在确定次数系数和时长系数后，对该第一权重值和第二权重值进行读取，并用该读取的第一权重值和第二权重值分别对次数系数和时长系数进行加权处理，生成各偏好车型的偏好系数。因各偏好车型中存在只对应目标操作次数和目标操作时长中任一项的情况，即只存在次数系数和时长系数中某一项的情况；从而在进行加权处理的过程中，依据各偏好车型所具有次数系数和时长系数的情况进行。当偏好车型仅具有次数系数或仅具有时长系数，则由第一权重值对次数系数进行加权，或由第二权重值对时长系数进行加权；当偏好车型具有次数系数和时长系数时，则用第一权重值和第二权重值分别对两者进行加权。如对于上述偏好车型A、B、C，若第一权重值为k1，第二权重值为k2；则对于A所生成的偏好系数为k1*a1，对于B所生成的偏好系数为k2*b2，对于C所生成的偏好系数为（k1*c1+k2*c2）。通过加权处理所得到的各偏好车型的偏好系数来表征用户对各偏好车型的偏好程度高低，其中所得到的偏好系数越大，则对应的偏好程度越高，反之则越低。
进一步地，在生成各偏好车型的偏好系数之后，可依据各偏好系数所表征的偏好程度高低，对各偏好车型进行排序，生成车型序列。具体地，在各偏好系数之间进行对比，确定各偏好系数之间的大小关系；依据该大小关系，对各偏好车型进行排序，将偏好系数大的偏好车型排列在前列，而将偏好系数小的偏好车型排列在后列；在各偏好车型排列完成后，即可生成表征用户偏好程度高低的车型序列。
更进一步地，对于在将贷款关注度比值和预设比例对比，所得到的对比结果为贷款关注度比值不大于预设比例的情形，则说明用户贷款购车的需求较弱，在对各偏好车型进行排序时，需要结合各偏好车型的价格因素进行。具体地，判断贷款关注度比值是否大于预设比例的步骤之后包括：
步骤S33，若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
当经对比确定贷款关注度比值不大于预设比例时，则对各偏好车型的价格信息进行读取，同时采集用户的基础信息。该基础信息包括用户的性别、年龄、学历、工作性质、工作行业、居住地址等，以用该类信息对用户的经济状况进行反映。
步骤S34，根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
进一步地，因用户的基础信息反映了用户的经济状况，从而可依据基础信息对用户的收入信息进行预测；其中基础信息中的居住地址表征了用户所工作的城市，而可得到该城市的城市平均收入；而工作行业和工作性质表征了用户所在行业相对于其所在城市的收入，即可用工作行业和工作性质对城市平均收入进行优化。当工作行业和性质相对为热门高薪行业，则优化为对城市平均收入乘以一个大于1的系数，而当工作行业和性质相对为冷门基础行业，则优化为对城市平均收入乘以一个小于1的系数；通过优化以得到用户的基本收入。同时对用户的基本支出进行预测，通过读取用户所在城市中与其性别和年龄相同人员的平均支出作为用户的基本支出。进而用所预测的基本收入和基本支出即可得到用户的收入数据，依据基础信息中的年龄和学历推测用户的工作年限，用工作年限和收入数据相乘，生成用户的积蓄数据。
考虑到每年度经济的变化因素以及用户本身工作经验的因素，距离当前年限时间越远的年限中的收入数据与当前年限中的收入数据差别越大；从而使得所生成的积蓄数据可能高于用户实际的积蓄数据，为了提高积蓄数据的准确性，依据工作年限对积蓄数据进行调整。调整时依据工作年限确定小于1的调整系数，在工作年限较短时，则说明各年度之间的收入以及支出之间的变化不大，而将调整系数设定为接近于1；而在工作年限较长时，则说明各年度之间的收入以及支出之间的变化较大，而将调整系数设定为较小于1。用调整系数和积蓄数据相乘，得到调整后的积蓄数据；将该调整后的积蓄数据确定为用户的积蓄信息，来反映用户当前的可支配金额。
更进一步地，用用户的积蓄信息逐一和各偏好车型的价格信息做对比，得到积蓄信息和各个价格信息之间的对比结果，通过各个对比结果来反映积蓄信息和各个价格之间的匹配程度；其中价格信息低于积蓄信息的程度越多，则表征该价格信息与积蓄信息之间的匹配程度越高，反之则越低。
步骤S35，根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
进一步地，所生成的各对比结果表征了积蓄信息和各价格信息之间的匹配程度，匹配程度越高说明用户对生成该匹配程度的价格信息的车辆的购买能力越强；从而以及对比结果所表征的匹配程度高度，对各个偏好车型进行排序，将匹配程度高的价格信息所对应的偏好车型排列在前列，而将匹配程度低的价格信息所对应的偏好车型排列在后列。在各偏好车型排列完成后，即可生成表征用户购买能力强弱的车型序列，且该车型序列中均为用户多次关注的偏好车型。
在对各车型排列生成车型序列后，则根据车型序列中各偏好车型的排列顺序，对其中偏好车型的车型信息进行获取，使得所获取的各车型信息和车型序列中各偏好车型对应。所获取的车型信息包括厂商、车辆型号、发动机型号、价格、马力等；将该获取的车型信息作为目标车型信息，以对其所来源的车辆进行推荐。
步骤S40，将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端。
更进一步地，在按照车型序列中各偏好车型的排列顺序，获取到各偏好车型的目标车型信息后，因车型序列中的排列顺序表征了用户的偏好强弱或购买能力强弱；从而可依据该排列顺序将各目标车型信息输出到用户所持有诸如电脑、手机的终端，以对于各目标车型信息对应的车辆进行推荐。在推荐的过程中可依据排列顺序进行编号，以表征推荐的力度大小，该力度大小与用户的偏好强弱或购买能力强弱对应。
本实施例的车辆信息的推送方法，通过对用户基于网络对各预设车辆信息进行浏览所生成的操作数据采集，并对该采集的操作数据进行筛选，确定用户浏览的车型信息；再读取操作数据中与各车型信息对应的操作次数和操作时长，并根据各操作次数和各操作时长，确定用户的偏好车型；此后对各偏好车型进行排序，生成车型序列，并根据车型序列中各偏好车型的排列顺序，获取目标车型信息；进而将各目标车型信息基于排列顺序输出到用户所持有的终端，实现向用户推荐与各目标车型信息对应的车辆。本方案中偏好车型依据用户浏览的操作次数和操作时长生成，而车型序列依据偏好车型排列；使得依据车型序列所获取的目标车型信息为满足用户偏好的车型信息，将该目标车型信息输出到用户终端进行推荐，可使得所推荐的车辆准确的满足了用户的偏好需求，提高了车辆信息的推送的准确性。
进一步地，在本申请车辆信息的推送方法另一实施例中，所述对所述操作数据进行筛选的步骤之前包括：
步骤S50，读取所述用户的身份信息，并根据所述身份信息，确定所述用户是否具有用户车辆；
可理解地，用户在对车辆进行销售的网络平台上，对各预设车辆信息进行浏览的目的，可能是具有购买车辆增值服务的需求，而并非具有购车需求。购买车辆增值服务的前提是用户已经购买了车辆，而具有用户车辆；从而为了对用户浏览预设车辆信息的目的进行区分，需要确定用户是否已经具有用户车辆。对用户的身份信息进行读取，并依据用户的身份信息向车辆管理机构申请进行查询，以确定该身份信息是否关联有车辆。当经查询确定身份信息关联有车辆，则说明用户已经具有用户车辆；而当经查询确定身份信息没有关联车辆，则说明用户没有用户车辆。
步骤S60，若所述用户具有用户车辆，则读取所述用户车辆的车险信息，并根据各所述车险信息，对所述用户推荐车险；
进一步地，本实施例中的车辆增值服务主要涉及到交强险、车辆损失险、第三者责任险等车险，当经确定用户具有车辆时，则说明用户浏览各预设车辆信息的目的是需要购买车险，此时可依据用户已经具有的用户车辆所对应的车险信息，向用户推荐车险。具体地，对用户车辆的车险信息进行读取，该车险信息包括车险种类、各类型车险对应的时限、出险记录等各种与车险相关的信息。进而依据各车险信息，向用户推荐车险；其中推荐可依据各类型车险对应的时限进行，即针对即将到期的车险进行推荐。具体地，根据各车险信息，对用户推荐车险的步骤包括：
步骤S61，将各所述车险信息中的时限信息和预设时限对比，判断各所述时限信息中是否存在小于预设时限的目标时限信息；
步骤S62，若存在小于预设时限的目标时限信息，则确定与所述目标时限信息对应的车险类型；
更进一步地，预先设定表征即将到期的预设时限，如设定距离最后期限一个月的时间作为预设时限，并将车险信息中的时限信息和该预设时限对比。该车险信息中的时限信息为用户车辆所购买各项车险中距离各自到期期限的时间长短信息；如用户车辆所购买的车险包括p1、p2和p3，其中p1的到期期限为q1、p2的到期期限为q2、p3的到期期限为q3，而当前时间距离q1、q2、q3的时间长度信息分别为d1、d2和d3；该d1、d2和d3则为车险信息中的时限信息。将各个时限信息和预设时限对比，生成各时限信息和预设时限信息之间的大小关系；当大小关系为时限信息小于预设时限信息时，则说明时限信息所对应的车险即将到期，而当大小关系为时限信息不小于预设时限信息时，则说明时限信息所对应的车险激励到期期限较长。通过判断各个大小关系中是否存在时限信息小于预设时限信息的大小关系，来确定时限信息中是否存在小于预设时限的目标时限信息；该目标时限信息所对应的车险即将到期。当经确定各时限信息中存在小于预设时限的目标时限信息，则由目标时限信息所来源的车险，确定与目标时限信息对应的车险类型，以查询与该车险类型对应的车险进行推荐。
步骤S63，读取与所述用户车辆对应的出险信息，并根据所述出险信息，向所述用户推荐与所述车险类型对应的车险。
可理解地，用户车辆在使用过程中可能存在与即将到期的车险对应的出险情况，如即将到期的车险为车辆损失险，而用户车辆在使用过程中遭受过冰雹，并由保险机构进行了理赔；该冰雹所导致的理赔即为与即将到期的车险对应的出险情况。针对该出险情况，不同的机构所能提供的与车险类型对应的车险在价格上或者时限上不一样。为了推荐满足用户需求的车险，对用户车辆对应的出险信息进行读取，其中出险信息包括出险次数、各次出险的时间以及主要责任方等；依据该出险信息确定各待推荐车险，该待推荐车险来自于不同的机构，且均与所需要推荐的车险类型对应。将各个待推荐车险所具有的信息进行对比，确定相对优惠最大的待推荐车险；或者确定各待推荐车险中，用户查看次数最多的待推荐车险；将该优惠最大的待推荐车险或查看次数最多的待推荐车险作为与车险类型对应的车险，向用户进行推荐。
需要说明的是，即便用户具有用户车辆时，用户也可以购买其他车辆；从而当经确定用户具有车辆，并判断出各时限信息中不存在小于预设时限的目标时限信息时，则说明用户浏览预设车辆信息的目的是需要需要购买其他车辆。此时对所采集的操作数据进行筛选，以确定满足用户需求偏好的偏好车型，并将各偏好车型生成车型序列进行推荐；该具体的推荐方式和上述第一实施例的推荐方式相似，在此不做赘述。
步骤S70，若所述用户不具有用户车辆，则执行对所述操作数据进行筛选的步骤。
进一步地，当经确定用户没有用户车辆时，则说明用户浏览各预设车辆信息的目的是需要购买车辆，从而对所采集的操作数据进行筛选，以确定满足用户需求偏好的偏好车型，并将各偏好车型生成车型序列进行推荐；该具体的推荐方式和上述第一实施例的推荐方式相似，在此不做赘述。
此外，请参照图2，本申请提供一种车辆信息的推送装置，在本申请车辆信息的推送装置第一实施例中，所述车辆信息的推送装置包括：
采集模块10，用于采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
确定模块20，用于读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
排序模块30，用于对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
推荐模块40，用于将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端。
本实施例的车辆信息的推送装置，通过采集模块10对用户基于网络对各预设车辆信息进行浏览所生成的操作数据采集，并对该采集的操作数据进行筛选，确定用户浏览的车型信息；再由确定模块20读取操作数据中与各车型信息对应的操作次数和操作时长，并根据各操作次数和各操作时长，确定用户的偏好车型；此后由排序模块30对各偏好车型进行排序，生成车型序列，并根据车型序列中各偏好车型的排列顺序，获取目标车型信息；进而推荐模块40将各目标车型信息基于排列顺序输出到用户所持有的终端，实现向用户推荐与各目标车型信息对应的车辆。本方案中偏好车型依据用户浏览的操作次数和操作时长生成，而车型序列依据偏好车型排列；使得依据车型序列所获取的目标车型信息为满足用户偏好的车型信息，将该目标车型信息输出到用户终端进行推荐，可使得所推荐的车辆准确的满足了用户的偏好需求，提高了车辆信息的推送的准确性。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述确定模块还包括：
第一对比单元，用于将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
第二对比单元，用于将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
确定单元，用于确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述排序模块还包括：
读取单元，用于读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
排序单元，用于若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述排序单元还用于：
将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述排序模块还包括：
采集单元，用于若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
第一生成单元，用于根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
第二生成单元，用于根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述采集模块还用于：
读取所述用户的身份信息，并根据所述身份信息，确定所述用户是否具有用户车辆；
若所述用户具有用户车辆，则读取所述用户车辆的车险信息，并根据各所述车险信息，对所述用户推荐车险；
若所述用户不具有用户车辆，则执行对所述操作数据进行筛选的步骤。
进一步地，在本申请车辆信息的推送装置另一实施例中，所述采集模块还用于：
将各所述车险信息中的时限信息和预设时限对比，判断各所述时限信息中是否存在小于预设时限的目标时限信息；
若存在小于预设时限的目标时限信息，则确定与所述目标时限信息对应的车险类型；
读取与所述用户车辆对应的出险信息，并根据所述出险信息，向所述用户推荐与所述车险类型对应的车险。
其中，上述车辆信息的推送装置的各虚拟功能模块存储于图3所示车辆信息的推送设备的存储器1005中，处理器1001执行车辆信息的推送可读指令时，实现图2所示实施例中各个模块的功能。
参照图3，图3是本申请实施例方法涉及的硬件运行环境的设备结构示意图。
本申请实施例车辆信息的推送设备可以是PC( personal computer，个人计算机 )，也可以是智能手机、平板电脑、电子书阅读器、便携计算机等终端设备。
如图3所示，该车辆信息的推送设备可以包括：处理器1001，例如CPU（Central Processing Unit，中央处理器），存储器1005，通信总线1002。其中，通信总线1002用于实现处理器1001和存储器1005之间的连接通信。存储器1005可以是高速RAM（random access memory，随机存取存储器），也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
可选地，该车辆信息的推送设备还可以包括用户接口、网络接口、摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi（Wireless Fidelity，无线宽带）模块等等。用户接口可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口还可以包括标准的有线接口、无线接口。网络接口可选的可以包括标准的有线接口、无线接口（如WI-FI接口）。
本领域技术人员可以理解，图3中示出的车辆信息的推送设备结构并不构成对车辆信息的推送设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图3所示，作为一种计算机可读存储介质的存储器1005中可以包括操作系统、网络通信模块以及车辆信息的推送可读指令。操作系统是管理和控制车辆信息的推送设备硬件和软件资源的可读指令，支持车辆信息的推送可读指令以及其它软件和/或可读指令的运行。网络通信模块用于实现存储器1005内部各组件之间的通信，以及与车辆信息的推送设备中其它硬件和软件之间通信。
在图3所示的车辆信息的推送设备中，处理器1001用于执行存储器1005中存储的车辆信息的推送可读指令，实现上述车辆信息的推送方法各实施例中的步骤。
本申请提供了一种计算机可读存储介质，所述计算机可读存储介质可为非易失性存储介质，所述计算机可读存储介质存储有一个或者一个以上可读指令，所述一个或者一个以上可读指令还可被一个或者一个以上的处理器执行以用于实现上述车辆信息的推送方法各实施例中的步骤。
还需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个计算机可读存储介质（如ROM/RAM、磁碟、光盘）中，包括若干指令用以使得一台终端设备（可以是手机，计算机，服务器，或者网络设备等）执行本申请各个实施例所述的方法。
以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是在本申请的构思下，利用本申请说明书及附图内容所作的等效结构变换，或直接/间接运用在其他相关的技术领域均包括在本申请的专利保护范围内。

Claims (20)

  1. 一种车辆信息的推送方法，其特征在于，所述车辆信息的推送方法包括以下步骤：
    采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
    读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
    对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
    将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
    其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
    将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
    将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
    确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
  2. 如权利要求1所述的车辆信息的推送方法，其特征在于，所述对各所述偏好车型进行排序，生成车型序列的步骤包括：
    读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
    若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
  3. 如权利要求2所述的车辆信息的推送方法，其特征在于，所述对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数的步骤包括：
    将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
    将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
    读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
  4. 如权利要求2所述的车辆信息的推送方法，其特征在于，所述判断所述贷款关注度比值是否大于所述预设比例的步骤之后包括：
    若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
    根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
    根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
  5. 如权利要求1任一项所述的车辆信息的推送方法，其特征在于，所述对所述操作数据进行筛选的步骤之前包括：
    读取所述用户的身份信息，并根据所述身份信息，确定所述用户是否具有用户车辆；
    若所述用户具有用户车辆，则读取所述用户车辆的车险信息，并根据各所述车险信息，对所述用户推荐车险；
    若所述用户不具有用户车辆，则执行对所述操作数据进行筛选的步骤。
  6. 如权利要求5所述的车辆信息的推送方法，其特征在于，所述根据各所述车险信息，对所述用户推荐车险的步骤包括：
    将各所述车险信息中的时限信息和预设时限对比，判断各所述时限信息中是否存在小于预设时限的目标时限信息；
    若存在小于预设时限的目标时限信息，则确定与所述目标时限信息对应的车险类型；
    读取与所述用户车辆对应的出险信息，并根据所述出险信息，向所述用户推荐与所述车险类型对应的车险。
  7. 一种车辆信息的推送装置，其特征在于，所述车辆信息的推送装置包括：
    采集模块，用于采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
    确定模块，用于读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
    排序模块，用于对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
    推荐模块，用于将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
    其中，所述确定模块还包括：
    第一对比单元，用于将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
    第二对比单元，用于将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
    确定单元，用于确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
  8. 如权利要求7所述的车辆信息的推送装置，其特征在于，所述排序模块还包括：
    读取单元，用于读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
    排序单元，用于若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
  9. 如权利要求8所述的车辆信息的推送装置，其特征在于，所述排序单元还用于：
    将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
    将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
    读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
  10. 如权利要求8所述的车辆信息的推送装置，其特征在于，所述排序模块还包括：
    采集单元，用于若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
    第一生成单元，用于根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
    第二生成单元，用于根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
  11. 如权利要求7所述的车辆信息的推送装置，其特征在于，所述采集模块还用于：
    读取所述用户的身份信息，并根据所述身份信息，确定所述用户是否具有用户车辆；
    若所述用户具有用户车辆，则读取所述用户车辆的车险信息，并根据各所述车险信息，对所述用户推荐车险；
    若所述用户不具有用户车辆，则执行对所述操作数据进行筛选的步骤。
  12. 如权利要求11所述的车辆信息的推送装置，其特征在于，所述采集模块还用于：
    将各所述车险信息中的时限信息和预设时限对比，判断各所述时限信息中是否存在小于预设时限的目标时限信息；
    若存在小于预设时限的目标时限信息，则确定与所述目标时限信息对应的车险类型；
    读取与所述用户车辆对应的出险信息，并根据所述出险信息，向所述用户推荐与所述车险类型对应的车险。
  13. 一种车辆信息的推送设备，其特征在于，所述车辆信息的推送设备包括：存储器、处理器、通信总线以及存储在所述存储器上的车辆信息的推送可读指令；
    所述通信总线用于实现处理器和存储器之间的连接通信；
    所述处理器用于执行所述车辆信息的推送可读指令，以实现以下步骤：
    采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
    读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
    对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
    将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
    其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
    将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
    将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
    确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
  14. 如权利要求13所述的车辆信息的推送设备，其特征在于，所述对各所述偏好车型进行排序，生成车型序列的步骤包括：
    读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
    若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
  15. 如权利要求14所述的车辆信息的推送设备，其特征在于，所述对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数的步骤包括：
    将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
    将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
    读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
  16. 如权利要求14所述的车辆信息的推送设备，其特征在于，所述判断所述贷款关注度比值是否大于所述预设比例的步骤之后，所述处理器用于执行所述车辆信息的推送可读指令，以实现以下步骤：
    若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
    根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
    根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有车辆信息的推送可读指令，所述车辆信息的推送可读指令被处理器执行时实现以下步骤：
    采集用户基于网络对各预设车辆信息进行浏览所生成的操作数据，并对所述操作数据进行筛选，确定所述用户进行浏览的车型信息；
    读取所述操作数据中与各所述车型信息对应的操作次数和操作时长，并根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型；
    对各所述偏好车型进行排序，生成车型序列，并根据所述车型序列中各所述偏好车型的排列顺序，获取各目标车型信息；
    将各所述目标车型信息基于所述排列顺序输出到所述用户所持有的终端；
    其中，所述根据各所述操作次数和各所述操作时长，确定所述用户的偏好车型的步骤包括：
    将各所述操作次数和第一预设阈值对比，确定各所述操作次数中大于所述第一预设阈值的目标操作次数；
    将各所述操作时长和第二预设阈值对比，确定各所述操作时长中大于所述第二预设阈值的目标操作时长；
    确定各所述车型信息中与所述目标操作次数和/或目标操作时长对应的偏好车型信息，并将与各所述偏好车型信息对应的车型确定为所述用户的偏好车型。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，所述对各所述偏好车型进行排序，生成车型序列的步骤包括：
    读取所述操作数据中的贷款数据，并根据所述贷款数据和所述操作数据，生成贷款关注度比值，将所述贷款关注度比值和预设比例对比，判断所述贷款关注度比值是否大于所述预设比例；
    若大于所述预设比例，则对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数，并根据各所述偏好系数之间的大小关系，对各所述偏好车型进行排序，生成车型序列。
  19. 如权利要求18所述的计算机可读存储介质，其特征在于，所述对各所述偏好车型所对应的目标操作次数和/或目标操作时长进行整合，生成各所述偏好车型的偏好系数的步骤包括：
    将各所述偏好车型所对应的目标操作次数和预设次数区间对比，确定各所述偏好车型的次数系数；
    将各所述偏好车型所对应的目标操作时长和预设时长区间对比，确定各所述偏好车型的时长系数；
    读取与所述操作次数和所述操作时长分别对应的第一权重值和第二权重值，并用所述第一权重值以及第二权重值分别对各所述偏好车型的次数系数和时长系数加权处理，生成各所述偏好车型的偏好系数。
  20. 如权利要求18所述的计算机可读存储介质，其特征在于，所述判断所述贷款关注度比值是否大于所述预设比例的步骤之后，所述车辆信息的推送可读指令被处理器执行时实现以下步骤：
    若不大于所述预设比例，则读取各所述偏好车型的价格信息，并采集与所述用户的经济状况对应的基础信息；
    根据所述基础信息，确定所述用户的积蓄信息，并将所述积蓄信息和各所述价格信息对比，生成各对比结果；
    根据各所述对比结果，对各所述偏好车型进行排序，生成车型序列。
PCT/CN2019/118364 2019-08-14 2019-11-14 车辆信息的推送方法、装置、设备及计算机可读存储介质 WO2021027158A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910762719.1 2019-08-14
CN201910762719.1A CN110517072A (zh) 2019-08-14 2019-08-14 车辆信息的推送方法、装置、设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2021027158A1 true WO2021027158A1 (zh) 2021-02-18

Family

ID=68626404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/118364 WO2021027158A1 (zh) 2019-08-14 2019-11-14 车辆信息的推送方法、装置、设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN110517072A (zh)
WO (1) WO2021027158A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112800306A (zh) * 2021-01-22 2021-05-14 武汉芳华杰出科技有限公司 一种用户信息采集分析系统
CN113449002A (zh) * 2021-06-28 2021-09-28 平安银行股份有限公司 车辆推荐方法、装置、电子设备及存储介质
CN115062231A (zh) * 2022-08-18 2022-09-16 南京三百云信息科技有限公司 适用于车源推荐的数据处理方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975483A (zh) * 2016-04-25 2016-09-28 北京三快在线科技有限公司 一种基于用户偏好的消息推送方法和平台
CN108960914A (zh) * 2018-06-28 2018-12-07 宇宙世代信息技术（深圳）有限公司 信息精准推送方法、系统及设备
CN109033171A (zh) * 2018-06-21 2018-12-18 蔚来汽车有限公司 信息推送方法及装置
CN109561132A (zh) * 2018-10-23 2019-04-02 平安医疗健康管理股份有限公司 一种信息推送方法、装置、服务器及终端

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105912550A (zh) * 2015-12-15 2016-08-31 乐视网信息技术（北京）股份有限公司 一种移动终端的信息推荐方法及装置
WO2017124381A1 (zh) * 2016-01-21 2017-07-27 阮元 根据车型推荐资源时的信息推送方法以及推荐系统
CN106296368A (zh) * 2016-08-19 2017-01-04 北京好车轰轰电子商务有限公司 一种车型推荐系统和方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975483A (zh) * 2016-04-25 2016-09-28 北京三快在线科技有限公司 一种基于用户偏好的消息推送方法和平台
CN109033171A (zh) * 2018-06-21 2018-12-18 蔚来汽车有限公司 信息推送方法及装置
CN108960914A (zh) * 2018-06-28 2018-12-07 宇宙世代信息技术（深圳）有限公司 信息精准推送方法、系统及设备
CN109561132A (zh) * 2018-10-23 2019-04-02 平安医疗健康管理股份有限公司 一种信息推送方法、装置、服务器及终端

Also Published As

Publication number Publication date
CN110517072A (zh) 2019-11-29

Similar Documents

Publication Publication Date Title
WO2021027158A1 (zh) 车辆信息的推送方法、装置、设备及计算机可读存储介质
WO2020116985A1 (ko) 이커머스 플랫폼 평가 시스템 및 방법
WO2017073848A1 (ko) 사용자의 소셜 네트워크 서비스 활동을 기반으로 한 상품 광고 또는 판매 방법
WO2017157146A1 (zh) 基于用户画像的个性化推荐方法、装置、服务器及存储介质
WO2020113959A1 (zh) 医疗机构透析水平的考核方法、装置、设备及存储介质
EP3583524A1 (en) Method for providing information and electronic device supporting the same
WO2011007935A1 (ko) 홈페이지 통합 서비스 제공 시스템 및 방법
WO2018166315A1 (zh) 购房资格预评估方法、装置、系统以及可读存储介质
WO2019144585A1 (zh) 虚拟机器人的控制方法、装置、设备及可读存储介质
WO2020147385A1 (zh) 数据录入方法、装置、终端及计算机可读存储介质
WO2021027143A1 (zh) 信息推送方法、装置、设备及计算机可读存储介质
WO2019024485A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2020253115A1 (zh) 基于语音识别的产品推荐方法、装置、设备和存储介质
WO2017111195A1 (ko) 신뢰도 평가기반의 차량 직거래 인터페이스 제공 방법 및 이를 운용하는 서버
WO2021003956A1 (zh) 产品信息的管理方法、装置、设备及存储介质
WO2010027225A2 (ko) 광고 제공 방법, 시스템 및 컴퓨터 판독 가능한 기록 매체
WO2018043859A1 (ko) 사용자 이미지를 이용한 대여 아이템 선호도 자동 분석 장치 및 이를 이용한 방법
WO2010095852A4 (ko) 전자창고를 이용한 오픈마켓형 전자 상거래 방법
WO2019033511A1 (zh) 基于数据库的数据透视方法、装置和计算机存储介质
WO2022080701A1 (ko) 노출지수를 이용한 검색어 추천 방법 및 이를 위한 장치
WO2021010706A1 (en) Method and apparatus for generating structured relation information based on a text input
WO2018043860A1 (ko) 유사 성향 그룹을 이용한 대여 아이템 추천 장치 및 이를 이용한 방법
WO2019039665A1 (ko) 대화 기능을 구비한 채팅 시스템 및 채팅 서비스를 제공하는 방법
WO2016036050A1 (ko) 컨텐츠를 이용한 고객 확보 및 확장을 위한 광고방법
WO2016117818A1 (ko) 효율적인 리타겟팅을 제공하는 방법 및 장치

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19941368

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19941368

Country of ref document: EP

Kind code of ref document: A1