CN120235659B - Directional marketing method and system for parking users - Google Patents
Directional marketing method and system for parking usersInfo
- Publication number
- CN120235659B CN120235659B CN202510716648.7A CN202510716648A CN120235659B CN 120235659 B CN120235659 B CN 120235659B CN 202510716648 A CN202510716648 A CN 202510716648A CN 120235659 B CN120235659 B CN 120235659B
- Authority
- CN
- China
- Prior art keywords
- parking
- time
- information
- time interval
- acquiring
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明属于营销领域，公开了停车用户的定向营销方法及系统，方法包括：S1，获取停车场用户的车辆信息和停车信息；S2，对停车信息进行数据预处理，获得经过处理的停车信息；S3，对经过处理的停车信息进行数据特征识别，获得停车信息特征；S4，基于车辆信息和停车信息特征获取用户标签集合；S5，基于用户标签集合计算待推送的广告的推送值；S6，基于推送值确定向停车场用户推送的广告。在无法获得基本属性数据和线上数据时，与随机推送广告的方向相比，本发明的广告的推送的精准度得到了有效的提升。
The present invention belongs to the field of marketing and discloses a method and system for targeted marketing of parking users. The method comprises: S1, obtaining vehicle information and parking information of parking lot users; S2, performing data preprocessing on the parking information to obtain processed parking information; S3, performing data feature recognition on the processed parking information to obtain parking information features; S4, obtaining a user tag set based on the vehicle information and parking information features; S5, calculating a push value of an advertisement to be pushed based on the user tag set; and S6, determining an advertisement to be pushed to the parking lot user based on the push value. When basic attribute data and online data are unavailable, the accuracy of advertisement push in the present invention is effectively improved compared to randomly pushing advertisements.
Description
Technical Field
The invention relates to the marketing field, in particular to a method and a system for targeted marketing of parking users.
Background
In the prior art, a similar technology is generally disclosed in a patent with application number CN201910260628.8, in which a user figure is constructed based on basic attribute data (such as gender, age, etc.) of a parking lot user and on-line data (such as browsing records, purchasing records, etc.) and advertisement pushing is performed based on the user figure. However, the acquisition of these data is often difficult, because the online data system and the parking management system are mostly independent, and the parking management system is difficult to obtain these data, which results in insufficient marketing accuracy when marketing to the parking users through the parking management system.
Disclosure of Invention
The invention aims to disclose a directional marketing method and a directional marketing system for a parking user, and solve the technical problems pointed out in the background technology.
In order to achieve the above purpose, the invention adopts the following technical scheme:
In one aspect, the present invention provides a method for targeted marketing of parking users, comprising:
s1, acquiring vehicle information and parking information of a parking lot user;
s2, carrying out data preprocessing on the parking information to obtain processed parking information;
S3, carrying out data feature recognition on the processed parking information to obtain parking information features;
s4, acquiring a user tag set based on the characteristics of the vehicle information and the parking information;
S5, calculating a pushing value of the advertisement to be pushed based on the user tag set;
and S6, determining advertisements pushed to the parking lot users based on the push values.
Further, the vehicle information includes a make and a model;
the parking information includes a parking place and a parking duration.
Further, the process of obtaining parking information includes:
and acquiring parking information of N time intervals closest to the current time, wherein N is an adaptive control coefficient.
Further, the determining process of the N time intervals includes:
the current time is expressed as tn, and the N-th time interval is T is the set time interval length;
The nth time interval is ,n∈[1,N-1]。
Further, the data preprocessing is performed on the parking information to obtain processed parking information, including:
and carrying out data cleaning processing on the parking information to obtain processed parking information.
Further, the data feature recognition is performed on the processed parking information to obtain the parking information feature, which comprises the following steps:
The first step, for the parking place contained in the parking information, the characteristic acquisition process is as follows:
respectively acquiring a set of parking places in each time interval;
respectively calculating a clustering center of a set of each parking place;
calculating an activity range based on the clustering center;
secondly, for the parking time length contained in the parking information, the acquiring process of the characteristics is as follows:
respectively calculating the influence coefficient of each time interval;
Calculating an average value of parking time lengths of each parking place of each time interval respectively;
calculating a corrected parking time length of each parking place in the Nth time interval based on the influence coefficient and the average value of the parking time respectively;
and thirdly, taking the movable range and the corrected parking time length as parking characteristic information.
Further, obtaining a set of user tags based on the vehicle information and the parking information features includes:
acquiring a first tag set according to vehicle information;
Acquiring a second label set according to the parking information characteristics;
And taking the union set of the first tag set and the second tag set as a user tag set.
Further, calculating a push value of the advertisement to be pushed based on the user tag set includes:
Acquiring an advertisement tag set of an advertisement to be pushed;
a push value for an advertisement to be pushed is calculated based on the set of user tags and the set of advertisement tags.
Further, determining advertisements pushed to the parking lot user based on the push values includes:
and taking the advertisement to be pushed corresponding to the maximum pushing value as the advertisement pushed to the parking lot user.
On the other hand, the invention provides a directional marketing system of a parking user, which comprises an information acquisition module, a preprocessing module, a feature recognition module, a label acquisition module, a calculation module and a determination module;
the information acquisition module is used for acquiring vehicle information and parking information of a parking lot user;
The preprocessing module is used for preprocessing the data of the parking information to obtain the processed parking information;
the feature recognition module is used for carrying out data feature recognition on the processed parking information to obtain parking information features;
the tag acquisition module is used for acquiring a user tag set based on the characteristics of the vehicle information and the parking information;
the computing module is used for computing the pushing value of the advertisement to be pushed based on the user tag set;
The determining module is used for determining advertisements pushed to the parking lot users based on the push values.
The beneficial effects are that:
The present invention does not perform construction of a user image based on conventional basic attribute data and on-line data, but performs selection of advertisements for pushing by acquiring vehicle information and parking information using a parking lot management system and then based on the vehicle information and the parking information. The brand and model of the vehicle directly reflect the consumption capability of the user, and the parking place attribute (such as a high-grade district and school) can infer the life scene and the demand of the user. When the basic attribute data and the online data cannot be obtained, compared with the direction of randomly pushing the advertisement, the advertisement pushing accuracy is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a method for targeted marketing of parking users according to the present invention.
FIG. 2 is a schematic diagram of a targeted marketing system of a parking user of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
In one embodiment as shown in fig. 1, the present invention provides a method for targeted marketing of parking users, comprising:
S1, acquiring vehicle information and parking information of a parking lot user.
Further, the vehicle information includes a make and a model;
the parking information includes a parking place and a parking duration.
Specifically, when the vehicle enters and exits the gate of the parking lot, the vehicle may be photographed to obtain a vehicle appearance image (e.g., a vehicle tail image), and then the vehicle appearance image is identified to obtain vehicle information.
For example, the vehicle information may be:
brand: baox;
Model number xxxLi.
The parking information can be obtained through a database of the parking lot management system, and when a plurality of parking lots belong to the same property company for management, the plurality of parking lots use the same management system, so that the invention can conduct directional marketing on parking lot users based on the parking information of the plurality of parking lots.
In addition, the authorization of the parking information can be obtained from the property company managing other parking lots so as to enlarge the coverage range of the parking lot, thereby obtaining more accurate marketing results.
Further, the parking place is the position of the parking lot, not the position of the vehicle.
Further, the process of obtaining parking information includes:
and acquiring parking information of N time intervals closest to the current time, wherein N is an adaptive control coefficient.
In the present invention, the value of N is not fixed, but can be changed according to the actual situation of the parking lot user.
When the user drives out of the parking lot, the parking information is generated and put into the database for storage, so that the time interval in which each piece of parking information falls can be determined according to the stored time.
Specifically, the acquisition process of N includes:
acquiring the first two time intervals L1 and L2 closest to the current time;
parking information C1 and C1 of L1 and L2 acquired respectively;
Respectively acquiring sets P1 and P2 of parking places in C1 and C2, and respectively acquiring sets TM1 and TM2 of parking time lengths in C1 and C2;
Calculating a coefficient of variation based on P1, P2, TM1 and TM 2;
N is calculated based on the coefficient of variation.
In calculating N, the present invention is based on the first two time intervals closest to the current time, L1 may be one of the first two time intervals closest to the current time, and L2 may be the other. By acquiring the set of parking places, whether the parking places have larger changes in the two time intervals or not can be judged, and by acquiring the set of parking times, whether the parking time of the same parking place has larger changes in the two time intervals or not can be compared, so that the value of N can be more accurately determined to reduce the calculation amount of subsequent feature recognition, and the efficiency of acquiring the advertisements pushed by each parking place user can be still maintained when more parking place users need to be determined to push the advertisements.
Further, calculating the coefficient of variation based on P1, P2, TM1, and TM2, includes:
Acquiring an intersection P3 of P1 and P2;
the coefficient of variation was calculated using the following function:
The coefficient of variation is represented by a coefficient of variation, 、AndRepresenting the total number of parking places contained in P1, P2 and P3 respectively,AndThe average value of the parking time lengths of the parking places i in the time zone L1 and the time zone L2 are respectively indicated,Representing the weight, max represents the acquisition of a larger value in brackets,Represents the median of the collection tlen, tlen is i ε P3A set of calculation results of (a).
For example max (1, 2) has a value of 2.
The average value is the average value of all parking time lengths of the same parking place in the same time interval.
The change coefficient of the invention is calculated from the number of identical parking places in the two time intervals and the average value of the parking time length of the identical parking place in the two time intervals, so that when the number of identical parking places in the two time intervals is larger, the average value of the parking time length of the identical parking place in the two time intervals is changed to be smaller, the life habit of a parking lot user is more stable, and at the moment, the sufficiently accurate parking information feature can be obtained by only relying on a small amount of historical parking information, so that the efficiency of subsequently acquiring the parking information feature can be improved.
Further, the weight may have a value of 0.5.
Further, calculating N based on the coefficient of variation includes:
N is calculated using the following function:
represents a preset reference value, PN represents a preset number, To round up the symbol, for example,Has a value of 3.
In the invention, the value of N changes along with the change of the change coefficient, when the change coefficient is larger, the parking habit of a user is changed more, so that more historical parking information is required to be introduced to calculate the parking characteristic information, the degree of reducing the interference of suddenly changed parking behaviors as noise on the parking characteristic information is achieved, and a more accurate label set can be obtained.
Further, PN may be 10.
Further, the method comprises the steps of,May have a value of 0.6.
Further, the determining process of the N time intervals includes:
the current time is expressed as tn, and the N-th time interval is T is the set time interval length;
The nth time interval is ,n∈[1,N-1]。
Further, T may be 1 week.
Further, the current time may be the time when the parking lot user left the parking lot last time.
S2, data preprocessing is carried out on the parking information, and the processed parking information is obtained.
Further, the data preprocessing is performed on the parking information to obtain processed parking information, including:
and carrying out data cleaning processing on the parking information to obtain processed parking information.
The data cleaning refers to a process of identifying and correcting errors, inconsistencies, repeated or invalid information in data by a technical means, and aims to improve the accuracy, the integrity and the consistency of the data. Its core tasks include processing missing values, correcting erroneous data, eliminating duplicate records, unifying data formats, and processing outliers, etc.
Cleaning a parking place:
Address normalization:
And converting the parking place text (such as an xx road xxx number) into longitude and latitude coordinates or a unified administrative division format, so that subsequent map visualization or space analysis is facilitated. For example, the text address is converted to latitude and longitude by a geocoding tool (e.g., the geocoder library of Python).
Error address correction:
checking address validity using external data sources (e.g., map APIs), correcting misspellings or ambiguous expressions (e.g., "mall parking lot" requires replenishment of specific names)
Missing value processing:
if the parking place is missing, other data sources (such as parking lot management system logs) can be associated according to the vehicle entering and exiting time to complete, and if the parking place cannot be completed, the record is marked as unknown or removed.
Cleaning the parking time period:
Abnormal value detection:
The logical range check parking duration needs to be greater than 0 and less than a reasonable upper limit (e.g., 72 hours), and out of range is considered abnormal.
Statistical method identification, outliers are detected by box plot or Z score. For example, a parking duration with a Z score exceeding ±3 may be erroneous data.
Correcting error duration:
If the parking time is abnormal (such as negative value) due to equipment failure, the parking time is corrected according to the record or manual verification of the adjacent time period.
Treatment of the missing duration:
The missing records are deleted directly or by adopting an interpolation method (such as front-back record average filling), and the data integrity and accuracy are required to be weighed according to the service scene.
And S3, carrying out data feature recognition on the processed parking information to obtain the parking information features.
The method comprises the steps of extracting features through comprehensive historical parking information, so that the obtained parking information features not only can contain the parking features of the current time, but also can contain the previous parking features, and the influence of accidental parking behaviors of a parking lot user and large differences between the accidental parking behaviors and the parking habits on the accuracy of judgment of labels of the parking lot user can be reduced.
Further, the data feature recognition is performed on the processed parking information to obtain the parking information feature, which comprises the following steps:
The first step, for the parking place contained in the parking information, the characteristic acquisition process is as follows:
respectively acquiring a set of parking places in each time interval;
respectively calculating a clustering center of a set of each parking place;
calculating an activity range based on the clustering center;
secondly, for the parking time length contained in the parking information, the acquiring process of the characteristics is as follows:
respectively calculating the influence coefficient of each time interval;
Calculating an average value of parking time lengths of each parking place of each time interval respectively;
calculating a corrected parking time length of each parking place in the Nth time interval based on the influence coefficient and the average value of the parking time respectively;
and thirdly, taking the movable range and the corrected parking time length as parking characteristic information.
According to the invention, the characteristics are acquired based on the parking place and the parking time, so that the parking information characteristics are more comprehensive.
Specifically, by determining the activity range, advertisements of merchants near the activity range can be matched based on the activity range in a subsequent process, so that more accurate advertisement pushing can be realized.
By calculating the corrected parking time length, the influence of behaviors deviating from parking habits, which are happened occasionally, on the determining process of the label can be reduced, and the accuracy of the label is further improved.
Further, calculating a cluster center of each set of parking places, respectively, includes:
the number of cluster centers is set to 1 by using a clustering algorithm, and the cluster centers of the set of each parking place are calculated respectively.
For example, a clustering center may be obtained using an algorithm such as K-means clustering.
Further, calculating the activity range based on the cluster center includes:
The range with the cluster center as the center and the radius of R is used as the movable range.
In the present invention, the value of R may be 5 km.
Further, calculating the influence coefficient of each time interval respectively includes:
The influence coefficient of the time interval is calculated using the following function:
The influence coefficient representing the mth time interval, when m epsilon 1, N-1, Indicating the start time of the mth time interval, when m is equal to N,Indicating the end time of the N-1 th time interval; Indicating the start time of the 1 st time interval, Representing a set of parking places comprised in an mth time interval, tn being the current time,Representation ofStandard deviation of parking time length of parking place j in (2):
Indicating the total number of parks of parking place j in the mth time interval, Representing a parking duration at the kth parking in the mth time interval;
Indicating the total number of parking places included in the mth time interval, A median value representing a standard deviation of parking time periods of all parking places included in the mth time zone; The weights are influenced for time.
In the process of calculating the influence coefficient, the method introduces the sum of the time length of the interval between the mth time interval and the 1 st time interval and the standard deviation of the parking time length of each parking place in the mth time interval, so that the influence coefficient can be calculated by integrating two different types of data, and the calculated influence coefficient is more accurate. If the longer the time length between the mth time interval and the 1 st time interval is, the smaller the sum of the standard deviations of the parking time durations of each parking place is, the larger the influence coefficient is, the larger the reference force of the data representing the mth time interval to the subsequent calculation of the corrected parking time duration is, so that on one hand, the historical parking information can be introduced to calculate the parking information characteristics, and on the other hand, the same reference force can be prevented from being reserved for the parking time durations in all the time intervals, so that the invention can adapt to the change of the parking time durations more timely.
Further, the time-dependent weight is 0.6.
Further, calculating a corrected parking duration for each parking place in the nth time interval based on the influence coefficient and the average value of the parking times, respectively, includes:
storing all parking places in the Nth time interval into a set ;
For the followingThe z-th parking place in (a),The calculation formula of the corrected parking time length is as follows:
Representation of Is provided with a correction of the parking time period,As the influence coefficient of the q-th time interval,For parking places in the q-th time intervalIs a mean value of the parking time period of (a).
The corrected parking time length is calculated based on the influence coefficient, and for the same parking place, if the influence coefficient of the time interval in which the corresponding parking time length is located is larger, the influence degree of the parking time length on the final corrected parking time length is larger, so that different nonlinear influence degrees are set for different time intervals, and the finally obtained corrected parking time length can more accurately represent the parking habit of a parking lot user.
And S4, acquiring a user tag set based on the vehicle information and the parking information characteristics.
In this step, the user tag of the parking lot user is obtained mainly based on the tag classification standard set in advance. Further, obtaining a set of user tags based on the vehicle information and the parking information features includes:
acquiring a first tag set according to vehicle information;
Acquiring a second label set according to the parking information characteristics;
and taking the union set of the first tag set and the second tag set as a user tag set. Further, acquiring the first tag set according to the vehicle information includes:
acquiring the price of the vehicle in the second-hand vehicle market according to the vehicle information;
Acquiring a user tag based on the price;
Acquiring the type of the vehicle according to the vehicle information;
Acquiring a user tag based on the type of the vehicle;
the user tag obtained based on the price and the user tag obtained based on the type of the vehicle are stored into the first tag set.
For example, if the price is 20 ten thousand or less, the user tag is the entrance-level car owner, if the price is 20 ten thousand or more and less than 50 ten thousand, the user tag is the middle-level car owner, and if the price is 50 ten thousand or more, the user tag is the luxury car owner.
The price of the second-hand car market can be obtained from the platform of xx emperor, xx home and the like.
The types of vehicles comprise cars, SUVs, MPVs and the like, and user labels corresponding to the cars, SUVs and MPVs can be car owners, SUV owners and MPV owners respectively.
In addition, in addition to the vehicle price and the vehicle type, the user tag may be acquired from data of the type such as the vehicle color.
Further, obtaining the second tag set according to the parking information feature includes:
And acquiring the user labels according to the movable range and the parking correction time length respectively, and storing the acquired user labels into a second label set.
Specifically, when the user tag is obtained according to the activity range, the average price in the activity range can be used as a judgment standard of the user tag, for example, when the average price is 10 ten thousand or more, the user tag is a CBD person, when the average price is 10 ten thousand or less and 7 ten thousand or more, the user tag is a study area room person, when the average price is 7 ten thousand or less and 4 ten thousand or more, the user tag is an emerging city fusion area person, and other average prices are suburban living area persons.
When a user label is acquired according to the parking correction time length, firstly calculating an average value of the correction parking time length of each parking place in the N-th time interval;
Setting corresponding place weights for each parking place according to the type of the area to which the parking place belongs;
For example, the zone types are divided into CBD, school district rooms, emerging city fusion zones, and suburban residential zones, and the site weights are set to 0.65, 0.2, 0.1, and 0.05, respectively.
The average value of the corrected parking time lengths of different parking places is weighted and summed according to the place weight, so that a parking time length judgment value is obtained:
a parking time period judgment value is indicated, The location weight for the c-th parking location in the nth time interval,A normalization value corresponding to the average value of the corrected parking time length of the c-th parking place; cN represents a set of parking places in the nth time interval;
And obtaining the user tag according to the parking time length judgment value.
For example, the relationship between the parking time period judgment value and the user tag may be:
The judging value of the parking time length is more than or equal to 0.8, and the user labels are high-consumption-capability groups;
The judging value of the parking time length is more than or equal to 0.4 and less than 0.8, and the user label is a middle consumption capability group;
the judging value of the parking time length is smaller than 0.4, and the user label is a low-consumption-capability group.
S5, calculating the pushing value of the advertisement to be pushed based on the user tag set.
In this step, the calculation of the push value is mainly performed by comparing the degree of association between the tags in the user tag set and the advertisement to be pushed.
Further, calculating a push value of the advertisement to be pushed based on the user tag set includes:
Acquiring an advertisement tag set of an advertisement to be pushed;
a push value for an advertisement to be pushed is calculated based on the set of user tags and the set of advertisement tags.
In the invention, the advertisement label of the advertisement to be pushed is a label which is manually set in advance and stored in a database, and the advertisement label of the advertisement to be pushed can be obtained from the database, for example, for high-end brand advertisements, the advertisement label can comprise luxury car owners, CBD personnel, high-consumption capability groups and the like.
Further, calculating a push value of an advertisement to be pushed based on the user tag set and the advertisement tag set includes:
Calculating a push value for an advertisement to be pushed using the following function:
Representation of AndAnd centralizing the total number of tags contained; Representation of The total number of tags contained in the label set,AndThe user tag set and the advertisement tag set of the advertisement b to be pushed respectively,Is the push value of advertisement b to be pushed.
In another embodiment, calculating a push value for an advertisement to be pushed based on a set of user tags includes:
and S6, determining advertisements pushed to the parking lot users based on the push values.
This step can be performed according to the push value, and in general, advertisements can be pushed to terminals such as applets and APP, which can be installed with clients of the parking lot management system, and popup pushing can be performed when a user opens a client.
Further, determining advertisements pushed to the parking lot user based on the push values includes:
and taking the advertisement to be pushed corresponding to the maximum pushing value as the advertisement pushed to the parking lot user.
On the other hand, as shown in fig. 2, the invention provides a directional marketing system of a parking user, which comprises an information acquisition module, a preprocessing module, a feature recognition module, a label acquisition module, a calculation module and a determination module;
the information acquisition module is used for acquiring vehicle information and parking information of a parking lot user;
The preprocessing module is used for preprocessing the data of the parking information to obtain the processed parking information;
the feature recognition module is used for carrying out data feature recognition on the processed parking information to obtain parking information features;
the tag acquisition module is used for acquiring a user tag set based on the characteristics of the vehicle information and the parking information;
the computing module is used for computing the pushing value of the advertisement to be pushed based on the user tag set;
The determining module is used for determining advertisements pushed to the parking lot users based on the push values.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. The directional marketing method of the parking user is characterized by comprising the following steps:
s1, acquiring vehicle information and parking information of a parking lot user;
s2, carrying out data preprocessing on the parking information to obtain processed parking information;
s3, carrying out data feature recognition on the processed parking information to obtain parking information features, wherein the method comprises the following steps:
The first step, for the parking place contained in the parking information, the characteristic acquisition process is as follows:
respectively acquiring a set of parking places in each time interval;
respectively calculating a clustering center of a set of each parking place;
calculating an activity range based on the clustering center;
secondly, for the parking time length contained in the parking information, the acquiring process of the characteristics is as follows:
calculating the influence coefficient of each time interval respectively, including:
The influence coefficient of the time interval is calculated using the following function:
;
The influence coefficient representing the mth time interval, when m epsilon 1, N-1, Indicating the start time of the mth time interval, when m is equal to N,Indicating the end time of the N-1 th time interval; Indicating the start time of the 1 st time interval, Representing a set of parking places comprised in an mth time interval, tn being the current time,Representation ofStandard deviation of parking time length of parking place j in (2):
;
Indicating the total number of parks of parking place j in the mth time interval, Representing a parking duration at the kth parking in the mth time interval;
Indicating the total number of parking places included in the mth time interval, A median value representing a standard deviation of parking time periods of all parking places included in the mth time zone; the weight is influenced by time;
If the longer the time length between the mth time interval and the 1 st time interval is, the smaller the sum of the standard deviations of the parking time durations of each parking place is, the larger the influence coefficient is, and the larger the reference force of the data representing the mth time interval to the subsequent calculation of the corrected parking time duration is;
Calculating an average value of parking time lengths of each parking place of each time interval respectively;
calculating a corrected parking time length of each parking place in the Nth time interval based on the influence coefficient and the average value of the parking time respectively;
Thirdly, taking the movable range and the corrected parking time length as parking characteristic information;
s4, acquiring a user tag set based on the characteristics of the vehicle information and the parking information;
S5, calculating a pushing value of the advertisement to be pushed based on the user tag set;
s6, determining advertisements pushed to parking lot users based on the pushing values;
The vehicle information includes a brand and a model;
The parking information comprises a parking place and a parking duration;
The process of obtaining parking information includes:
acquiring parking information of N time intervals closest to the current time;
the acquisition process of N comprises the following steps:
acquiring the first two time intervals L1 and L2 closest to the current time;
parking information C1 and C1 of L1 and L2 acquired respectively;
Respectively acquiring sets P1 and P2 of parking places in C1 and C2, and respectively acquiring sets TM1 and TM2 of parking time lengths in C1 and C2;
Calculating a coefficient of variation based on P1, P2, TM1 and TM 2;
calculating the change of the values of N and N along with the change of the change coefficient based on the change coefficient, when the change coefficient is larger, indicating that the parking habit of a user is changed more, and introducing more historical parking information to calculate parking characteristic information;
Calculating the coefficient of variation based on P1, P2, TM1, and TM2, comprising:
Acquiring an intersection P3 of P1 and P2;
the coefficient of variation was calculated using the following function:
;
The coefficient of variation is represented by a coefficient of variation, 、AndRepresenting the total number of parking places contained in P1, P2 and P3 respectively,AndThe average value of the parking time lengths of the parking places i in the time zone L1 and the time zone L2 are respectively indicated,Representing the weight, max represents the acquisition of a larger value in brackets,Represents the median of the collection tlen, tlen is i ε P3A set of calculation results of (a).
2. The method of targeted marketing of a parking user according to claim 1, wherein the determining of the N time intervals comprises:
the current time is expressed as tn, and the N-th time interval is T is the set time interval length;
The nth time interval is ,n∈[1,N-1]。
3. The method of targeted marketing of a parking user according to claim 2, wherein the data preprocessing of the parking information to obtain processed parking information comprises:
and carrying out data cleaning processing on the parking information to obtain processed parking information.
4. The method of targeted marketing of a parking user of claim 1, wherein obtaining a set of user tags based on vehicle information and parking information characteristics comprises:
acquiring a first tag set according to vehicle information;
Acquiring a second label set according to the parking information characteristics;
And taking the union set of the first tag set and the second tag set as a user tag set.
5. The method of targeted marketing of parking users according to claim 1, wherein calculating a push value of an advertisement to be pushed based on a set of user tags comprises:
Acquiring an advertisement tag set of an advertisement to be pushed;
a push value for an advertisement to be pushed is calculated based on the set of user tags and the set of advertisement tags.
6. The method of targeted marketing of parking users of claim 1, wherein determining advertisements to push to parking users based on push values comprises:
and taking the advertisement to be pushed corresponding to the maximum pushing value as the advertisement pushed to the parking lot user.
7. The directional marketing system of the parking user is characterized by comprising an information acquisition module, a preprocessing module, a characteristic identification module, a label acquisition module, a calculation module and a determination module;
the information acquisition module is used for acquiring vehicle information and parking information of a parking lot user;
The preprocessing module is used for preprocessing the data of the parking information to obtain the processed parking information;
The feature recognition module is used for carrying out data feature recognition on the processed parking information to obtain parking information features, and comprises the following steps:
The first step, for the parking place contained in the parking information, the characteristic acquisition process is as follows:
respectively acquiring a set of parking places in each time interval;
respectively calculating a clustering center of a set of each parking place;
calculating an activity range based on the clustering center;
secondly, for the parking time length contained in the parking information, the acquiring process of the characteristics is as follows:
calculating the influence coefficient of each time interval respectively, including:
The influence coefficient of the time interval is calculated using the following function:
;
The influence coefficient representing the mth time interval, when m epsilon 1, N-1, Indicating the start time of the mth time interval, when m is equal to N,Indicating the end time of the N-1 th time interval; Indicating the start time of the 1 st time interval, Representing a set of parking places comprised in an mth time interval, tn being the current time,Representation ofStandard deviation of parking time length of parking place j in (2):
;
Indicating the total number of parks of parking place j in the mth time interval, Representing a parking duration at the kth parking in the mth time interval;
Indicating the total number of parking places included in the mth time interval, A median value representing a standard deviation of parking time periods of all parking places included in the mth time zone; the weight is influenced by time;
If the longer the time length between the mth time interval and the 1 st time interval is, the smaller the sum of the standard deviations of the parking time durations of each parking place is, the larger the influence coefficient is, and the larger the reference force of the data representing the mth time interval to the subsequent calculation of the corrected parking time duration is;
Calculating an average value of parking time lengths of each parking place of each time interval respectively;
calculating a corrected parking time length of each parking place in the Nth time interval based on the influence coefficient and the average value of the parking time respectively;
Thirdly, taking the movable range and the corrected parking time length as parking characteristic information;
the tag acquisition module is used for acquiring a user tag set based on the characteristics of the vehicle information and the parking information;
the computing module is used for computing the pushing value of the advertisement to be pushed based on the user tag set;
the determining module is used for determining advertisements pushed to the parking lot users based on the pushing values;
The vehicle information includes a brand and a model;
The parking information comprises a parking place and a parking duration;
The process of obtaining parking information includes:
acquiring parking information of N time intervals closest to the current time;
the acquisition process of N comprises the following steps:
acquiring the first two time intervals L1 and L2 closest to the current time;
parking information C1 and C1 of L1 and L2 acquired respectively;
Respectively acquiring sets P1 and P2 of parking places in C1 and C2, and respectively acquiring sets TM1 and TM2 of parking time lengths in C1 and C2;
Calculating a coefficient of variation based on P1, P2, TM1 and TM 2;
calculating the change of the values of N and N along with the change of the change coefficient based on the change coefficient, when the change coefficient is larger, indicating that the parking habit of a user is changed more, and introducing more historical parking information to calculate parking characteristic information;
Calculating the coefficient of variation based on P1, P2, TM1, and TM2, comprising:
Acquiring an intersection P3 of P1 and P2;
the coefficient of variation was calculated using the following function:
;
The coefficient of variation is represented by a coefficient of variation, 、AndRepresenting the total number of parking places contained in P1, P2 and P3 respectively,AndThe average value of the parking time lengths of the parking places i in the time zone L1 and the time zone L2 are respectively indicated,Representing the weight, max represents the acquisition of a larger value in brackets,Represents the median of the collection tlen, tlen is i ε P3A set of calculation results of (a).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510716648.7A CN120235659B (en) | 2025-05-30 | 2025-05-30 | Directional marketing method and system for parking users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510716648.7A CN120235659B (en) | 2025-05-30 | 2025-05-30 | Directional marketing method and system for parking users |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120235659A CN120235659A (en) | 2025-07-01 |
| CN120235659B true CN120235659B (en) | 2025-09-26 |
Family
ID=96161282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510716648.7A Active CN120235659B (en) | 2025-05-30 | 2025-05-30 | Directional marketing method and system for parking users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120235659B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669071A (en) * | 2020-12-30 | 2021-04-16 | 中兴智能交通股份有限公司 | System and method for analyzing targeted advertisement marketing based on vehicle parking data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170262887A1 (en) * | 2016-03-11 | 2017-09-14 | Anand Vaidyanathan | Method and system for delivering targeted advertisements associated with a payment parking system |
| CN110062030A (en) * | 2019-03-25 | 2019-07-26 | 智慧互通科技有限公司 | A kind of parking advertisement pushing method and system |
| CN110619539A (en) * | 2019-08-08 | 2019-12-27 | 横琴善泊投资管理有限公司 | Big data analysis method and system based on parking lot aggregation information |
| CN116959288A (en) * | 2023-08-23 | 2023-10-27 | 昭通亮风台信息科技有限公司 | A parking lot recommendation method, device and distributed system based on historical data |
| CN118132126A (en) * | 2024-02-20 | 2024-06-04 | 重庆赛力斯凤凰智创科技有限公司 | OTA pushing method and device based on historical data |
-
2025
- 2025-05-30 CN CN202510716648.7A patent/CN120235659B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669071A (en) * | 2020-12-30 | 2021-04-16 | 中兴智能交通股份有限公司 | System and method for analyzing targeted advertisement marketing based on vehicle parking data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120235659A (en) | 2025-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12288230B2 (en) | System and method for analysis and presentation of used vehicle pricing data | |
| Baburajan et al. | Open-ended versus closed-ended responses: A comparison study using topic modeling and factor analysis | |
| Richardson et al. | Survey methods for transport planning | |
| Yavorsky et al. | Consumer search in the US auto industry: The role of dealership visits | |
| Anas | The estimation of multinomial logit models of joint location and travel mode choice from aggregated data | |
| Wielinski et al. | Electric and hybrid car use in a free-floating carsharing system | |
| Lindenthal et al. | Machine learning, architectural styles and property values | |
| US10685363B2 (en) | System, method and computer program for forecasting residual values of a durable good over time | |
| Bhat et al. | Accommodating immigration status and self-selection effects in a joint model of household auto ownership and residential location choice | |
| US20100174657A1 (en) | System and method for appraisal information services | |
| US9116964B2 (en) | System, method and computer program product for decoding vehicle identification numbers | |
| CN115456442B (en) | Site selection method for emergency shuttle bus parking points based on GIS and fuzzy comprehensive evaluation | |
| CN119359360A (en) | A car owner rights marketing management system and platform based on big data | |
| CN112507207A (en) | Travel recommendation method and device | |
| CN112258029B (en) | Demand prediction method for sharing bicycles around subway station | |
| CN113282842A (en) | Travel purpose identification method based on travel survey of smart phone and artificial neural network particle swarm optimization algorithm | |
| CN112612934A (en) | User charging behavior portrait processing method and device | |
| CN115860790A (en) | Method for predicting place passenger flow, method and device for training model | |
| CN120235659B (en) | Directional marketing method and system for parking users | |
| CN114912717A (en) | Smart city guarantee housing application risk assessment method and system based on Internet of things | |
| US20110251750A1 (en) | Vehicle emission manager and credits bank | |
| Wells et al. | Targeting carbon reduction in UK households: A new segmentation model using financial transaction data | |
| Nguyen | Automotive Service Quality Investigation Using a Grey-DEMATEL Model. | |
| US20230274336A1 (en) | Apparatus and method for generating positioning indicator | |
| CN114283003B (en) | A method, medium and device for identifying second-hand car transaction behavior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |