Discount information recommendation method and device, computer equipment and storage medium

Abstract

The invention discloses a preferential information recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a business interaction request for a target vehicle, which comprises the information of the target vehicle; determining a target vehicle type based on the target vehicle information; if the target vehicle type is the preset preferential vehicle type, obtaining at least one preferential strategy corresponding to the target vehicle; and recommending the preferential strategy to a target user corresponding to the target vehicle. And according to the preset preferential vehicle type, at least one adaptive preferential strategy is intelligently matched and accurately pushed to the target user. The preferential information recommendation accuracy can be improved, the preferential strategy and the user demand are accurately matched, the attention and acceptability of the user on preferences can be remarkably improved, the user is effectively attracted to use services such as parking or charging, the income of the parking lot is increased, the user experience is greatly optimized, and the good sensitivity of the user on the parking lot is enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of parking lot management, and in particular to a preferential information recommendation method and device, computer equipment and a storage medium. BACKGROUND

[0002] In the current mode of parking lot operation management, the means of recommending preferential information is relatively lagging. The traditional method is often based on broad time nodes or regular scenarios to push uniform preferential strategies to all parking users without distinction. Taking holidays as an example, the common preferential form is to launch a universal parking fee discount for all vehicles, such as an 80% discount on parking fees during the "May Day" period. The formulation of this strategy only focuses on the time commonality, but users often have different needs in their daily travel, for example, private cars, online car-hailing vehicles, etc. have different parking needs, so they have different needs for preferential strategies. In the face of such differentiated needs, a uniform preferential strategy cannot accurately adapt, resulting in a decrease in the attention of some users to preferential content, which not only affects user satisfaction, but also reduces parking lot revenue to some extent. SUMMARY

[0003] Therefore, it is necessary to provide a preferential information recommendation method, device, computer equipment and storage medium to solve at least one problem existing in the prior art.

[0004] In a first aspect, a preferential information recommendation method is provided, comprising:

[0005] obtaining a business interaction request for a target vehicle, the business interaction request comprising target vehicle information;

[0006] determining the target vehicle type based on the target vehicle information;

[0007] if the target vehicle type is a preset preferential vehicle type, obtaining at least one preferential strategy corresponding to the target vehicle;

[0008] recommending the preferential strategy to a target user corresponding to the target vehicle.

[0009] In an embodiment of the present application, the business interaction request comprises a recharge request, and the preferential strategy comprises a plurality of preferential strategies. The step of recommending the preferential strategy to the target user corresponding to the target vehicle comprises:

[0010] obtaining a historical recharge record of the target vehicle;

[0011] determining a recharge preference corresponding to the target user based on the historical recharge record;

[0012] Select an incentive policy that matches the charging preference from all the incentive policies, and make a recommendation.

[0013] In an embodiment of the present application, the incentive policies include a plurality of incentive policies, and the recommending the incentive policy to the target user corresponding to the target vehicle includes:

[0014] Determining an actual incentive value corresponding to each incentive policy;

[0015] Comparing the actual incentive values corresponding to each incentive policy to determine an incentive policy with the highest actual incentive value;

[0016] Recommending the incentive policy with the highest actual incentive value to the target user corresponding to the target vehicle.

[0017] In an embodiment of the present application, the incentive policies include a plurality of incentive policies, and the recommending the incentive policy to the target user corresponding to the target vehicle includes:

[0018] If the target vehicle is a regular customer vehicle, obtaining a parking frequency and / or a charging frequency of the target vehicle within a preset time range, wherein the regular customer vehicle refers to a vehicle that continuously generates an approach parking or charging behavior;

[0019] Based on the parking frequency and / or the charging frequency of the target vehicle, determining whether the target vehicle is a high-frequency vehicle;

[0020] If the target vehicle is a high-frequency vehicle, selecting an incentive policy corresponding to the high-frequency vehicle, otherwise selecting an incentive policy corresponding to a low-frequency vehicle.

[0021] In an embodiment of the present application, after the recommending the incentive policy to the target user corresponding to the target vehicle, the method further includes:

[0022] Statistically obtaining a recommendation success rate of each of the recommended incentive policies within a preset time range;

[0023] By comparing the recommendation success rates of different incentive policies, determining an acceptance degree of each of the recommended incentive policies;

[0024] Based on the acceptance degree, adjusting the incentive policies.

[0025] In an embodiment of the present application, after the recommending the incentive policy to the target user corresponding to the target vehicle, the method further includes:

[0026] Obtaining evaluation information and an incentive demand of the target user on the incentive policy;

[0027] Based on the evaluation information and the incentive demand, adjusting the incentive policy.

[0028] In an embodiment of the present application, the method further comprises:

[0029] When the target vehicle approaches, departs or drives into a parking space, it is determined whether the target vehicle has un-redeemed preferential benefits;

[0030] If the target vehicle has un-redeemed preferential benefits, prompt information is output.

[0031] In a second aspect, a preferential information recommendation device is provided, comprising:

[0032] A service interaction request acquisition unit is configured to acquire a service interaction request for a target vehicle, the service interaction request comprising target vehicle information;

[0033] A target vehicle type determination unit is configured to determine the target vehicle type based on the target vehicle information;

[0034] A preferential strategy determination unit is configured to acquire at least one preferential strategy corresponding to the target vehicle if the target vehicle type is a preset preferential vehicle type;

[0035] A preferential strategy recommendation unit is configured to recommend the preferential strategy to a target user corresponding to the target vehicle.

[0036] In a third aspect, a computer device is provided, comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer readable instructions to implement the steps of the preferential information recommendation method as described above.

[0037] In a fourth aspect, a readable storage medium is provided, which stores computer readable instructions, wherein the computer readable instructions are executed by a processor to implement the steps of the preferential information recommendation method as described above.

[0038] The above-mentioned preferential information recommendation method, device, computer equipment and storage medium, the method of which is implemented, includes: obtaining a business interaction request for a target vehicle, the business interaction request including target vehicle information; determining the target vehicle type based on the target vehicle information; if the target vehicle type is a preset preferential vehicle type, obtaining at least one preferential policy corresponding to the target vehicle; and recommending the preferential policy to the target user corresponding to the target vehicle. In an embodiment of the present application, for the preset preferential vehicle type, at least one adapted preferential policy is intelligently matched and accurately pushed to the target user. The accuracy of preferential information recommendation can be improved. By accurately matching preferential policies with user needs, it can not only significantly improve users' attention and acceptance of preferential treatment, effectively attract users to engage in parking, charging, recharging, card opening and other services, drive the growth of parking lot revenue, but also greatly optimize the user experience and enhance users' favorability towards parking lots. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 1 ;

[0041] Figure 2 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 2 ;

[0042] Figure 3 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 3 ;

[0043] Figure 4 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 4 ;

[0044] Figure 5 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 5 ;

[0045] Figure 6 This is a flow chart of a method for recommending preferential information in one embodiment of the present invention. Figure 6 ;

[0046] Figure 7 This is a structural diagram of a device for recommending preferential information according to an embodiment of the present invention;

[0047] Figure 8 FIG. 1 is a schematic diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0049] In one embodiment, if Figure 1 As shown, a method for recommending preferential information is provided, comprising the following steps:

[0050] In step S110, a service interaction request for a target vehicle is obtained, where the service interaction request includes target vehicle information;

[0051] Optionally, when a user is detected performing a service interaction such as card activation, renewal, top-up, exit, or entry, a service interaction request may be generated. For example, taking the top-up service as an example, the user may access the top-up page through a pre-installed parking-related application, mini-program, or official account, and enter or automatically add pre-stored vehicle information to be topped up to generate a service interaction request for the target vehicle.

[0052] Among them, the target vehicle information may include license plate number, whether the vehicle is a new energy vehicle, vehicle model, vehicle brand and other information.

[0053] In step S120, the target vehicle type is determined based on the target vehicle information;

[0054] Optionally, the vehicle type can be determined and classified based on the acquired target vehicle information. The determination of vehicle type can be based on a variety of factors, such as the vehicle's power source (fuel, electric, hybrid), vehicle usage (family sedan, SUV, truck, bus, etc.), vehicle brand positioning (luxury car, standard car, etc.), and whether the vehicle is a fixed vehicle (such as a monthly pass). Different types of vehicles differ in terms of user needs, market positioning, operating costs, etc., and corresponding preferential policies will also vary.

[0055] In step S130, if the target vehicle type is a preset preferential vehicle type, at least one preferential policy corresponding to the target vehicle is obtained;

[0056] Optionally, the vehicle types that meet the preferential conditions can be set in advance according to the business needs of the current parking lot, service promotion, etc., such as the power type of the vehicle (gasoline vehicle, pure electric vehicle, hybrid vehicle), the use of the vehicle (private car, operating vehicle, official car, etc.), the brand or grade of the vehicle, etc. For example, in order to promote the use of new energy vehicles, pure electric vehicles can be set as the preset preferential vehicle type; or if it is to improve the use of online car-hailing vehicles that often operate in a specific area, it can be set as the preset preferential vehicle type.

[0057] It should be noted that a rich preferential policy library can be established for each business interaction request, which stores various preferential policies for different preset preferential vehicle types, such as a preferential policy library corresponding to the charging business, a preferential policy library corresponding to the parking business, a preferential policy library corresponding to the charging business, and a preferential policy library corresponding to the card opening business. Different businesses can correspond to different preferential policies.

[0058] The preferential policy can cover multiple aspects, such as charging preferential (cashback, service or item gift, etc.), use preferential (fee reduction, free service, etc. during use), specific scene preferential (such as preferential in specific time period, specific location, etc.). For example, for regular customers, when the cumulative card opening or refilling reaches 500 yuan, a 50 yuan charging coupon is given; for pure electric vehicles, the preferential policy library can include policies such as "recharge 500 yuan, give 100 yuan charging quota" and "enjoy 80% discount when charging at designated fast charging stations on Tuesday every week". For operating online car-hailing vehicles, the preferential policy can be "recharge 1000 yuan, give a month of vehicle violation query service" and "operate during peak hours, complete 10 orders to get 5 yuan charging subsidy".

[0059] When the target vehicle type is determined to be a preset preferential vehicle type, a search and matching can be performed in the corresponding preferential policy library to find at least one preferential policy corresponding to the target vehicle type. For example, the most suitable preferential policy can be selected comprehensively according to multiple factors such as vehicle type, vehicle historical behavior data, and current market activities. If the target vehicle is a pure electric vehicle that often charges at night, and the user has a high refilling frequency in the past, the policy of "recharge 800 yuan, enjoy 70% discount on night charging from Monday to Friday in the next two months, and additionally give 50 yuan charging red envelope" can be matched from the preferential policy library.

[0060] In step S140, the preferential policy is recommended to the target user corresponding to the target vehicle.

[0061] It should be noted that one vehicle type can correspond to one or more preferential policies, if a single preferential policy is matched, the preferential policy can be directly pushed to the user for selection. If multiple preferential policies that meet the conditions are matched, the strategies can be sorted according to preset filtering rules, such as the size of the preferential strength, the degree of fit with the user's historical behavior, etc., and then the sorted preferential policies are pushed to the user for selection, or the most preferred preferential policy is directly recommended to the user.

[0062] The preferential policy can include preferential parking time, preferential amount, preferential charging time, optimal recharge amount, etc. Information can be personalized according to different business interactions and different types of vehicles.

[0063] In the embodiments of the present application, a preferential information recommendation method is provided, including: obtaining a business interaction request for a target vehicle, the business interaction request including target vehicle information; determining a target vehicle type based on the target vehicle information; if the target vehicle type is a preset preferential vehicle type, obtaining at least one preferential policy corresponding to the target vehicle; recommending the preferential policy to a target user corresponding to the target vehicle to guide the target user to recharge an amount corresponding to the preferential policy. In the embodiments of the present application, at least one adapted preferential policy is intelligently matched and accurately pushed to the target user for the preset preferential vehicle type. The accuracy of preferential information recommendation can be improved, and by accurately matching the preferential policy and the user demand, not only can the user's attention and acceptance of the preferential policy be significantly improved, but also the user can be effectively attracted to carry out parking, charging, recharging, card opening and other businesses, driving the parking lot income growth, and the user experience can be greatly optimized, and the user's favorability to the parking lot can be enhanced.

[0064] Referring to Figure 2 In an embodiment of the present application, the business interaction request includes a recharge request, and the preferential policy includes multiple, recommending the preferential policy to the target user corresponding to the target vehicle, including:

[0065] In step S210, the historical recharge record of the target vehicle is obtained;

[0066] In step S220, the recharge preference corresponding to the target user is determined based on the historical recharge record;

[0067] In step S230, the preferential policy that meets the recharge preference is selected from all preferential policies and is recommended.

[0068] Optionally, when the target vehicle's preferential policy includes multiple, the recharge data associated with the target vehicle can be extracted from the data repository. The recharge data can be stored in a mapping table of the data repository, which can include the correspondence between the vehicle identification, user identification and recharge data, such as the mapping relationship between the vehicle identification (such as the license plate number, vehicle identification number VIN), user identification (such as user ID), and recharge time, recharge amount, recharge channel and other information related to recharge (such as whether to use a coupon, the corresponding preferential activity of recharge, etc.). For example, the unique identification of the target vehicle can be obtained through vehicle information, and then all historical recharge records corresponding to the target vehicle in the mapping table can be filtered based on the unique identification.

[0069] Then, according to all the historical recharge records obtained, the recharge amount preference, recharge frequency and preference for using preferential can be analyzed in multiple dimensions. For example, for the recharge amount preference, the recharge amount corresponding to each recharge record can be determined, and based on the recharge amount, the recharge range can be determined. If the recharge range belongs to the small amount recharge range, it indicates that the recharge preference is small amount recharge, and if the recharge range belongs to the large amount recharge range, it indicates that the recharge preference is large amount recharge. For the recharge frequency, the recharge time interval between each recharge operation and the last recharge operation can be viewed, and based on the recharge time interval, the average recharge frequency can be determined. If a recharge is performed every week or so, the recharge frequency is high; while a recharge is performed once every few months, the recharge frequency is low. High recharge frequency is more inclined to frequent small amount preferential, while low recharge frequency is more interested in large amount but long term effective preferential. For the preference for using preferential, the user's historical parking records, historical charging records, etc. can be queried to determine whether the user often uses coupons when paying, whether the user participates in specific preferential activities, if the user often uses coupons, it indicates that the user prefers discount preferential, if the user often participates in gift preferential, it indicates that the user prefers service or physical gift preferential, and if the user often forgets to use coupons, it indicates that the user prefers cash return or discount preferential.

[0070] It can be understood that the preferential policy can include various preferential forms, such as coupons, discounts, gifts, cash return, etc., and the effective period and applicable conditions are different. According to the determined user recharge preference, all preferential policies are screened. For example, for a user who prefers small amount recharge and likes cash return, a preferential policy such as “recharge 200 yuan, return 20 yuan” can be selected.

[0071] It should be noted that the discount strategy and the recharging preference can also be matched in multiple dimensions, and the recharging amount that meets the user's preference and the favorite form of the discount can be selected, and other conditions such as the time and regional applicability of the discount strategy can also be considered. If there are multiple discount strategies that meet the conditions, they can be sorted according to factors such as the discount strength and the degree of agreement with the user's preference, for example, the weighted sum can be calculated respectively, and then the obtained scores are sorted according to the high and low, and the discount strategy with the highest score, that is, the one that best meets the user's recharging preference and has the highest comprehensive benefit, is recommended to the target user. For example, the recommended discount strategy can be ensured to be received by the user in time and clearly through the pop-up window of the application program, short message notification, etc.

[0072] Referring to Figure 3 In an embodiment of the present application, the discount strategy includes multiple, and the discount strategy is recommended to the target user corresponding to the target vehicle, including:

[0073] In step S310, the actual discount value corresponding to each discount strategy is determined;

[0074] In step S320, the actual discount value corresponding to each discount strategy is compared, and the discount strategy with the highest actual discount value is determined;

[0075] In step S330, the discount strategy with the highest actual discount value is recommended to the target user corresponding to the target vehicle.

[0076] Optionally, different discount strategies can have different discount forms, and different discount forms have different actual discount values. For discount forms such as direct cash return and coupons, such as "recharge 500 yuan and return 80 yuan", the actual discount value is the return amount 80 yuan, and the calculation is relatively intuitive. For service or goods gift type discounts, such as "recharge 700 yuan and give a car maintenance service worth 150 yuan", the actual discount value can be determined according to the actual charge standard of the service or the actual price of the given goods. Then the actual discount value corresponding to each discount strategy can be compared, and the discount strategy with the highest actual discount value is selected for recommendation.

[0077] It should be noted that some discount strategies include usage conditions, such as the need to consume in a designated store or consume within a specified time, etc. Taking the consumption in a designated store as an example, it can be determined whether the user going to the designated store will generate additional transportation costs, if so, the generated costs can be deducted, and then the actual discount value is determined.

[0078] It should be noted that if the actual discount values of multiple discount strategies are the same, further screening can be performed, for example, the scope of application of each discount strategy can be determined, such as the time limit for use, the region, and the like. Taking the time limit for use as an example, if the short-term discount of the discount strategy A is large in discount strength, and the long-term discount of the discount strategy B is slightly small in discount strength, for the user who needs to use the discount in urgency, the discount strategy of the short-term discount can be recommended.

[0079] Referring to Figure 4 In an embodiment of the present application, the discount strategies include multiple, and the discount strategy is recommended to the target user corresponding to the target vehicle, comprising:

[0080] In step S410, if the target vehicle is a regular customer vehicle, the parking frequency and / or charging frequency of the target vehicle in a preset time range are obtained;

[0081] In step S420, based on the parking frequency and / or charging frequency of the target vehicle, it is determined whether the target vehicle is a high-frequency vehicle;

[0082] In step S430, if the target vehicle is a high-frequency vehicle, the discount strategy corresponding to the high-frequency vehicle is selected, otherwise the discount strategy corresponding to the low-frequency vehicle is selected.

[0083] The regular customer vehicle refers to a vehicle that continuously generates parking or charging behaviors, and such a vehicle usually realizes high-frequency use by purchasing a monthly card, an annual card, or the like. For example, a vehicle that has opened a monthly card / annual card service.

[0084] Alternatively, the parking and / or charging records of the target vehicle in a preset time period, for example, in the past half year or 3 months, can be queried in the database, and based on the parking or charging records, the parking frequency and / or charging frequency can be counted. The parking frequency and / or charging frequency can be compared with the pre-set high-frequency threshold and low-frequency threshold, if greater than or equal to the high-frequency threshold, the vehicle is a high-frequency vehicle, if less than or equal to the low-frequency threshold, the vehicle is a low-frequency vehicle. It should be noted that if the parking frequency and the charging frequency are obtained at the same time, different weights can be given to the parking frequency and the charging frequency respectively, and then a comprehensive frequency index is calculated by weighting. For example, the parking frequency weight is set to 0.4, and the charging frequency weight is set to 0.6. If the target vehicle has parked 15 times in the past 3 months, which is converted into a monthly parking frequency of 5 times (assuming an average parking time of 1 day per month, and 30 days per month), and the average charging frequency is 4 times per week, which is converted into a monthly charging frequency of 16 times (assuming 4 weeks per month). The comprehensive frequency index = 5x0.4+16x0.6 = 11.6 times. The comprehensive frequency index is compared with the set high-frequency threshold and low-frequency threshold respectively, if greater than or equal to the high-frequency threshold, it is determined as a high-frequency vehicle; if less than or equal to the low-frequency threshold, it is a low-frequency vehicle.

[0085] It should be noted that, taking top-up services as an example, high-frequency vehicles, due to their frequent use, receive larger discounts, longer discount periods, and higher amounts. Therefore, a high top-up amount and longer discount period can be selected. Low-frequency users, due to their infrequent use, tend to require short-term discounts for smaller amounts. Therefore, a low top-up amount and shorter discount period can be selected.

[0086] See also Figure 5 In one embodiment of the present application, after recommending a preferential policy to a target user corresponding to a target vehicle, the method includes:

[0087] In step S510, the success rate of each recommended preferential strategy within a preset time range is counted;

[0088] In step S520, the acceptance level of each recommended preferential strategy is determined by comparing the recommendation success rates of different preferential strategies;

[0089] In step S530, the preferential policy is adjusted based on the acceptance level.

[0090] Optionally, the number of users who recommended the preferential policy and the number of users who accepted and used the preferential policy within a preset time range, for example, 3 months, can be obtained. The recommendation success rate = (number of users who accepted and used the preferential policy ÷ number of users who recommended the preferential policy) × 100%. For example, a preferential policy is recommended to 1,000 target users, and within the preset time range, 200 users enjoy the relevant preferential services in accordance with the preferential policy. The recommendation success rate of the preferential policy is (200 ÷ 1,000) × 100% = 20%. Then, the recommendation success rates of each preferential policy obtained by statistics can be compared. For example, if the recommendation success rate of preferential policy A is 20%, the recommendation success rate of preferential policy B is 15%, and the recommendation success rate of preferential policy C is 30%, then preferential policy C has the highest recommendation success rate. The higher the recommendation success rate, the higher the acceptance of the preferential policy among users. Therefore, the recommendation priority of preferential policies with high acceptance can be increased so that they can be pushed first.

[0091] See also Figure 6 In one embodiment of the present application, after recommending a preferential policy to a target user corresponding to a target vehicle, the method includes:

[0092] In step S610, the target user's evaluation information on the preferential policy and preferential demand are obtained;

[0093] In step S620, the preferential policy is adjusted based on the evaluation information and preferential demand.

[0094] Optionally, a special feedback page can be set in the application, applet or public number of the charging or parking platform. After viewing or using the preferential policy, the user can enter the page to make an evaluation. At the same time, the feedback page can also set a feedback column related to preferential demand, for example, the user can input "hope to increase the exclusive preferential policy for night charging" and the like, so as to obtain the preferential demand of the user, or the potential preferential demand can also be mined by analyzing the behavior data of the user. For example, if the user often parks at a specific time period (such as on weekends in the afternoon) and the parking time is long, it is possible to have a demand for long-time parking preferential policy in the time period. Then, based on the evaluation information and the preferential demand, the preferential policy can be adjusted, for example, if the user feedbacks that the preferential strength is insufficient, the preferential strength can be increased. If the user feedbacks that the preferential limitation conditions are too many, such as the use place and use time cannot be adapted, the use place and use time can be adjusted.

[0095] In an embodiment of the present application, the method further comprises:

[0096] When the target vehicle enters, exits or drives into a parking space, it is determined whether the target vehicle has unredemption preferential benefits;

[0097] If the target vehicle has unredemption preferential benefits, a prompt information is output.

[0098] The unredemption preferential benefits can include coupons, preferential discounts, gifts and the like.

[0099] Optionally, when the target vehicle drives into or drives away from the parking lot, the target vehicle information such as the license plate number can be recognized, and based on the license plate number, the recharge record is queried to determine whether the target vehicle has unredemption preferential benefits such as coupons, if yes, the user can be prompted that there are coupons not used through voice, short message, application pop-up window and the like, for example, "welcome home, there are charging piles at xx position, you have several charging coupons / parking coupons not used"; "have a good journey, you have several charging coupons / parking coupons not used", so that the user can use them in the current parking or charging process. Similarly, when the target vehicle drives into a parking space for parking, it can also be detected whether the vehicle has unredemption preferential benefits such as coupons, if yes, the user can be prompted that there are coupons not used through voice, short message, application pop-up window and the like, for example, "there are charging piles at xx position, you have several charging coupons / parking coupons not used", so that the user can use them in the current parking or charging process.

[0100] In the embodiments of the present application, at least one adaptive preferential policy is intelligently matched and accurately pushed to the target user for the preset preferential vehicle type. The accuracy of preferential information recommendation can be improved, the preferential policy and the user demand are accurately matched, the user's attention and acceptance to the preferential policy can be significantly improved, the user is effectively attracted to carry out parking, charging, recharging, card opening and other businesses, the parking lot income growth is driven, the user experience is greatly optimized, and the user's favorability to the parking lot is enhanced.

[0101] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] In an embodiment, a preferential information recommendation device is provided, which corresponds to the preferential information recommendation method in the above embodiments. As shown in the figure, the preferential information recommendation device includes a service interaction request acquisition unit 10, a target vehicle type determination unit 20, a preferential policy determination unit 30 and a preferential policy recommendation unit 40. The functions of each module are described in detail as follows: Figure 7

[0103] The service interaction request acquisition unit 10 is configured to acquire a service interaction request for a target vehicle, and the service interaction request includes target vehicle information.

[0104] The target vehicle type determination unit 20 is configured to determine a target vehicle type based on the target vehicle information.

[0105] The preferential policy determination unit 30 is configured to acquire at least one preferential policy corresponding to the target vehicle if the target vehicle type is a preset preferential vehicle type.

[0106] The preferential policy recommendation unit 40 is configured to recommend the preferential policy to a target user corresponding to the target vehicle.

[0107] In an embodiment of the present application, the service interaction request includes a recharging request, the preferential policy includes a plurality of preferential policies, and the preferential policy recommendation unit 40 is further configured to:

[0108] acquire a historical recharging record of the target vehicle;

[0109] determine a recharging preference corresponding to the target user based on the historical recharging record;

[0110] select a preferential policy that meets the recharging preference from all preferential policies and recommend the preferential policy.

[0111] In an embodiment of the present application, the preferential policy includes a plurality of preferential policies, and the preferential policy recommendation unit 40 is further configured to:

[0112] ​determine actual discount values corresponding to each discount strategy;

[0113] compare the actual discount values corresponding to each discount strategy, and determine a discount strategy with the highest actual discount value;

[0114] recommend the discount strategy with the highest actual discount value to a target user corresponding to a target vehicle.

[0115] In an embodiment of the present application, the discount strategies include a plurality of discount strategies, and the discount strategy recommendation unit 40 is further configured to:

[0116] If the target vehicle is a regular vehicle, the parking frequency and / or charging frequency of the target vehicle within a preset time range are obtained, wherein the regular vehicle refers to a vehicle that continuously generates parking or charging behaviors;

[0117] Based on the parking frequency and / or charging frequency of the target vehicle, it is determined whether the target vehicle is a high-frequency vehicle;

[0118] If the target vehicle is a high-frequency vehicle, a discount strategy corresponding to the high-frequency vehicle is selected, otherwise a discount strategy corresponding to a low-frequency vehicle is selected.

[0119] In an embodiment of the present application, the device further includes a first discount strategy adjustment unit configured to:

[0120] statistically obtain a recommendation success rate of each discount strategy within a preset time range;

[0121] By comparing the recommendation success rates of different discount strategies, an acceptance degree of each discount strategy is determined;

[0122] Based on the acceptance degree, the discount strategy is adjusted.

[0123] In an embodiment of the present application, the device further includes a second discount strategy adjustment unit configured to:

[0124] obtain evaluation information of the target user on the discount strategy and a discount demand;

[0125] Based on the evaluation information and the discount demand, the discount strategy is adjusted.

[0126] In an embodiment of the present application, the device further includes a discount prompt adjustment unit configured to:

[0127] When the target vehicle enters, exits or drives into a parking space, it is determined whether the target vehicle has an unredemption discount benefit;

[0128] If the target vehicle has an unredemption discount benefit, a prompt information is outputted.

[0129] In the embodiments of the present application, for the preset preferential vehicle type, at least one adapted preferential strategy is intelligently matched and accurately pushed to the target user. The accuracy of preferential information recommendation can be improved, the preferential strategy is accurately matched with the user demand, the user's attention and acceptance to the preferential information can be significantly improved, the user is effectively attracted to carry out parking, charging, recharging, card opening and other businesses, the parking lot income growth is driven, the user experience is greatly optimized, and the user's favorability to the parking lot is enhanced.

[0130] The specific limitation of the preferential information recommendation device can be referred to the limitation of the preferential information recommendation method in the foregoing, and will not be described here. Each module in the above preferential information recommendation device can be realized by software, hardware and combination thereof in whole or in part. The above each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operation corresponding to each module.

[0131] In one embodiment, a computer device is provided, which can be a terminal device, and an internal structure diagram thereof can be as shown in Figure 8 The computer device includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer readable instructions. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer readable instructions are executed by the processor to implement a preferential information recommendation method. The readable storage medium provided in the embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0132] In the embodiments of the present application, a computer device is provided, which includes a memory, a processor and computer readable instructions stored in the memory and executable on the processor, and the processor executes the computer readable instructions to implement the steps of the above preferential information recommendation method.

[0133] In the embodiments of the present application, a readable storage medium is provided, which stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the steps of the above preferential information recommendation method.

[0134] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware through computer readable instructions, and the computer readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer readable instructions are executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0136] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for recommending preferential information, characterized in that: The method comprises: Obtaining a service interaction request for a target vehicle, wherein the service interaction request includes target vehicle information; Determine the target vehicle type based on the target vehicle information; If the target vehicle type is a preset preferential vehicle type, obtaining at least one preferential policy corresponding to the target vehicle; The preferential policy is recommended to the target user corresponding to the target vehicle.

2. The preferential information recommendation method according to claim 1, wherein: The service interaction request includes a recharge request, the preferential policies include a plurality of preferential policies, and the recommending of the preferential policies to a target user corresponding to the target vehicle includes: Obtaining historical recharge records of the target vehicle; Determining a recharge preference corresponding to the target user based on the historical recharge records; Select the preferential policies that meet the recharge preference from all preferential policies and recommend them.

3. The preferential information recommendation method according to claim 1, wherein: The preferential policies include a plurality of preferential policies, and the preferential policies are recommended to the target user corresponding to the target vehicle, including: Determine the actual discount value corresponding to each discount strategy; Compare the actual discount values ​​corresponding to each discount strategy and determine the discount strategy with the highest actual discount value; The preferential policy with the highest actual preferential value is recommended to the target user corresponding to the target vehicle.

4. The preferential information recommendation method according to claim 1, wherein: The preferential policies include a plurality of preferential policies, and the preferential policies are recommended to the target user corresponding to the target vehicle, including: If the target vehicle is a regular customer vehicle, obtain the parking frequency and / or charging frequency of the target vehicle within a preset time range, wherein the regular customer vehicle refers to a vehicle that continuously enters the parking lot for parking or charging; Determining whether the target vehicle is a high-frequency vehicle based on the parking frequency and / or charging frequency of the target vehicle; If the target vehicle is a high-frequency vehicle, the preferential policy corresponding to the high-frequency vehicle is selected; otherwise, the preferential policy corresponding to the low-frequency vehicle is selected.

5. The preferential information recommendation method according to claim 1, wherein: After recommending the preferential policy to the target user corresponding to the target vehicle, the method further includes: Statistics on the success rate of each recommended discount strategy within the preset time range; By comparing the recommendation success rates of different preferential strategies, the acceptance level of each recommended preferential strategy is determined; Based on the acceptance level, the preferential policy is adjusted.

6. The preferential information recommendation method according to claim 1, wherein: After recommending the preferential policy to the target user corresponding to the target vehicle, the method further includes: Obtaining the target user's evaluation information on the preferential policy and preferential demand; Based on the evaluation information and preferential demand, the preferential policy is adjusted.

7. The preferential information recommendation method according to any one of claims 1 to 6, characterized in that: The method further comprises: When the target vehicle enters, exits, or drives into a parking space, determining whether the target vehicle has unredeemed preferential rights; If the target vehicle has any unredeemed preferential rights, a prompt message is output.

8. A device for recommending preferential information, characterized in that: The device comprises: A service interaction request acquiring unit, configured to acquire a service interaction request for a target vehicle, wherein the service interaction request includes target vehicle information; a target vehicle type determination unit, configured to determine the target vehicle type based on the target vehicle information; a preferential policy determining unit, configured to obtain at least one preferential policy corresponding to the target vehicle if the target vehicle type is a preset preferential vehicle type; The preferential policy recommendation unit is used to recommend the preferential policy to the target user corresponding to the target vehicle.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein: When the processor executes the computer-readable instructions, the steps of the preferential information recommendation method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the steps of the preferential information recommendation method according to any one of claims 1 to 7 are implemented.

Images