CN115082132A - Promotion method and system based on point reward - Google Patents
Promotion method and system based on point reward Download PDFInfo
- Publication number
- CN115082132A CN115082132A CN202210989643.8A CN202210989643A CN115082132A CN 115082132 A CN115082132 A CN 115082132A CN 202210989643 A CN202210989643 A CN 202210989643A CN 115082132 A CN115082132 A CN 115082132A
- Authority
- CN
- China
- Prior art keywords
- target
- reward
- activity
- point
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0226—Incentive systems for frequent usage, e.g. frequent flyer miles programs or point systems
- G06Q30/0232—Frequent usage rewards other than merchandise, cash or travel
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0235—Discounts or incentives, e.g. coupons or rebates constrained by time limit or expiration date
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a promotion method and a promotion system based on point reward, and belongs to the technical field of marketing promotion. The method comprises the following steps: obtaining a corresponding target activity change vector according to the activity change vector; obtaining each target historical integral reward activity corresponding to each target user according to the representation value of the target activity change vector; obtaining the point reward types which are interesting to target users in the target historical time period according to the point reward types in the target historical point reward activities; obtaining the category of each target user according to the point reward type which is interested by each target user; and setting the bonus point types and the bonus amount of the bonus point types in the next bonus point activity according to the number of the target users in each target user category. The invention can improve the activity of the user in the next point reward activity period to the maximum extent, and realize the purpose of marketing or promotion of the merchant.
Description
Technical Field
The invention relates to the technical field of marketing promotion, in particular to a promotion method and system based on point reward.
Background
Currently, a point system is a user operation means commonly used by various merchants, and various point reward activities can be held by various large merchants in an unscheduled manner, so that the purposes of user retention, new user expansion and user activity improvement are achieved, and the purpose of merchant popularization or marketing is further achieved; in addition, under the general condition, the user can participate in the activities held by the merchants only on the premise of being interested in the rewards in the bonus point activities, namely, the user can use the bonus point system only on the premise of being interested in the rewards in the bonus point activities; therefore, the problem that how to set the reward in the bonus point activity by the merchant to attract more users to participate in the activity is solved by the promotion purpose of the merchant.
Disclosure of Invention
In order to solve the above problems, the present invention provides a promotion method and system based on point reward, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a promotion method based on bonus points, including the following steps:
acquiring historical point reward activities, target users, activity change vectors of the target users when the historical point reward activities are finished, point reward types in the historical point reward activities and reward numbers corresponding to the point reward types in the target historical time period;
normalizing the activity degree change vector to obtain a target activity degree change vector corresponding to the activity degree change vector; obtaining a representation value of the target activity degree change vector; obtaining each target historical integral reward activity corresponding to each target user according to the representation value;
obtaining the point reward types which are interesting to the target users in the target historical time period according to the point reward types in the target historical point reward activities and the reward quantity corresponding to the point reward types;
obtaining the category of each target user according to the interested integral reward type of each target user in the target historical time period; and setting the bonus point types and the bonus amount of the bonus point types in the next bonus point activity according to the number of the target users in each target user category.
In a second aspect, the present invention provides a promotion system based on bonus points, which includes a memory and a processor, wherein the processor executes a computer program stored in the memory to implement a promotion method based on bonus points as described above.
Preferably, the method for acquiring the target historical time period includes:
acquiring the starting time of the merchant for holding the next bonus point activity, and acquiring the ending time of the historical bonus point activity which is closest to the starting time of the merchant for holding the next bonus point activity, and recording the ending time as the deadline of the target historical time period;
and continuously acquiring a preset number of historical point reward activities from the deadline of the target historical time period, and recording the ending time of the historical point reward activity farthest from the starting time of the next point reward activity held by the merchant as the starting time of the target historical time period.
Preferably, the target users refer to all users participating in the historical bonus activities for each historical point during the target historical time period.
Preferably, the method for obtaining the activity change vector of each target user at the end of each historical point reward activity in the target historical time period comprises the following steps:
for any historical point reward activity and any target user:
acquiring a historical time period from the deadline of the previous historical point reward activity to the starting time of the historical point reward activity, and recording the historical time period as the historical time period before the historical point reward activity starts;
obtaining the activity vector of the target user in the historical time period before the historical integral reward activity starts;
acquiring a historical time period from the starting time of the historical point reward activity to the ending time of the historical point reward activity, and recording the historical time period as the continuous historical time period of the historical point reward activity;
obtaining the activity vector of the target user in the historical time period for which the historical integral reward activity lasts;
subtracting the activity vector of the target user in the historical time period in which the historical integral reward activity lasts from the activity vector of the target user in the historical time period before the historical integral reward activity starts, and recording the subtracted result as the activity change vector of the target user when the historical integral reward activity ends.
Preferably, the method for obtaining the target activity change vector corresponding to the activity change vector includes:
for any target user:
obtaining each activity degree change vector corresponding to the target user according to the activity degree change vector of the target user when each historical integral rewarding activity is finished;
obtaining the maximum value in the ith element value in each activity degree change vector corresponding to the target user, and recording as the characteristic value corresponding to the ith element; dividing the ith element value in each liveness change vector corresponding to the target user by the characteristic value corresponding to the ith element, and recording the division result as the normalized value of the ith element value in each liveness change vector corresponding to the target user;
and obtaining a target activity change vector corresponding to each activity change vector corresponding to the target user according to the normalized value of each element value in each activity change vector corresponding to the target user, wherein the value of each element in the target activity change vector is the normalized value of each element value in the corresponding activity change vector.
Preferably, the method for obtaining the representation value of the target activity change vector comprises:
and calculating the mean value of each element value in the target activity change vector, and recording the mean value as the representation value of each target activity change vector.
Preferably, the method for obtaining each target historical integral reward activity corresponding to each target user according to the characterization value includes:
according to the characteristic values, constructing and obtaining a characteristic value sequence corresponding to each target user in a target historical time period;
for any sequence of characterization values: calculating the characteristic value sequence by an otsu threshold segmentation method to obtain a threshold value k, eliminating the characteristic values smaller than the threshold value k in the characteristic value sequence, and recording sequences constructed by the remaining characteristic values as target characteristic value sequences;
and obtaining historical integral reward activities corresponding to the characteristic values in the target characteristic value sequence corresponding to the target users in the target historical time period according to the target characteristic value sequence corresponding to the target users in the target historical time period, and recording the historical integral reward activities as the target historical integral reward activities.
Preferably, the method for obtaining the bonus point types interested by each target user in the target historical time period comprises the following steps:
for any target user:
acquiring each point reward type in each target historical point reward activity corresponding to the target user, and recording the point reward type as a target point reward type;
according to the target point reward types in the target historical point reward activities corresponding to the target user, constructing and obtaining a target point reward type sequence corresponding to the target historical point reward activities corresponding to the target user;
according to each target point reward type corresponding to each target historical point reward activity corresponding to the target user, a comprehensive target point reward type sequence corresponding to the target user is constructed and obtained, and repeated target point reward types do not exist in the comprehensive target point reward type sequence; for any target point reward type in the comprehensive target point reward type sequence corresponding to the target user:
calculating the accumulated sum of the parameter numbers in the target point reward type sequence corresponding to each target historical point reward activity corresponding to the target user; recording the target historical point reward activity corresponding to the target point reward type sequence containing the target point reward type in each target point reward type sequence corresponding to the target user as a first target historical point reward activity corresponding to the target point reward type;
counting the number of first target historical point reward activities corresponding to the target point reward type; calculating the ratio of the number of first target historical point reward activities corresponding to the target point reward type to the number of parameters in the comprehensive target point reward type sequence corresponding to the target user, and recording the ratio as the occurrence frequency of the target point reward type;
obtaining the reward quantity corresponding to the target point reward type in each first target historical point reward activity and the reward total quantity corresponding to each first target historical point reward activity; recording the average value of the accumulated sum of the ratio of the reward quantity corresponding to the target point reward type in each first target historical point reward activity to the total reward quantity corresponding to the first target historical point reward activity as the average specific gravity value of the target point reward type;
recording the result of multiplying the occurrence frequency of the target point reward type and the average specific gravity value of the target point reward type as the interest degree of the target user in the target point reward type;
and recording the target point reward type corresponding to the maximum value in the interest degree of each target point reward type in the corresponding comprehensive target point reward type sequence as the point reward type which is interested by the target user.
Preferably, each target user category is obtained according to the point reward type in which each target user is interested in the target historical time period; the method for setting the bonus point types and the bonus number of the bonus point types in the next bonus point activity according to the number of target users in each target user category comprises the following steps:
classifying the target users with the consistent interest point reward types into one category to obtain each target user category, wherein one target user category only corresponds to one interest point reward type and is recorded as the target point reward type corresponding to each target user category;
recording the target point reward type corresponding to each target user category as each point reward type in the next point reward activity; the ratio of the reward quantity corresponding to each point reward type in the next point reward activity to the total reward quantity in the next point reward activity is the ratio of the target user quantity in the target user category corresponding to each point reward type in the next point reward activity to the target user total quantity in the target historical time period.
Firstly, acquiring various historical integral reward activities in a target historical time period, various target users, activity change vectors of the target users when the historical integral reward activities are finished, various integral reward types in the historical integral reward activities and reward quantity corresponding to the integral reward types; according to the invention, each target historical integral reward activity corresponding to each target user is obtained according to the activity change vector of the target user when each historical integral reward activity is finished, and then the integral reward type interested by each target user in the target historical time period is obtained according to each integral reward type in each target historical integral reward activity and the reward quantity corresponding to the integral reward type, so that the accurate positioning of the integral reward type interested by each target user is realized; classifying the target users based on the point reward types which are interested by the target users to obtain the target user categories; the number of the target users in each target user category can reflect the popularity of the point reward types which are interested by the target users corresponding to each target user category, namely, the more the number of the target users in each target user category is, the more popular the point reward types which are interested by the target users corresponding to each target user category are, so that the invention sets the point reward types corresponding to the next point reward activity and the reward number of each point reward type based on the number of the target users in each target user category, can maximally improve the activity of the users during the next point reward activity, and helps the merchant to realize the purposes of user retention and new user expansion, namely, the marketing or popularization of the merchant is realized; therefore, the promotion method based on the point reward can attract more users to use the point system, improve the activity of the users in the next point reward activity period to the maximum extent, and help merchants to achieve the purposes of user retention and new user expansion, namely the purpose of marketing or promotion of the merchants.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart of a promotion method based on bonus points according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by those skilled in the art based on the embodiments of the present invention belong to the protection scope of the embodiments of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment provides a promotion method based on bonus points, which is described in detail as follows:
as shown in fig. 1, the promotion method based on the bonus point includes the following steps:
and S001, acquiring each historical integral reward activity in the target historical time period, each target user, activity change vectors of each target user when each historical integral reward activity is finished, each integral reward type in each historical integral reward activity and reward quantity corresponding to each integral reward type.
The method realizes the purpose of promotion of merchants by setting rewards corresponding to various point reward types in the point reward activities; under the general condition, in order to realize the purpose of marketing or popularization, each large merchant can hold various point reward activities irregularly, namely using points to exchange rewards or using points to extract rewards and the like, so that the purposes of keeping users, expanding new users and improving the liveness of the users are realized; the merchant in this embodiment refers to a platform that interacts with a user, such as a game platform, an e-commerce platform, a social platform, and the like, where the game platform includes Tencent, snowstorm, and the like, the e-commerce platform includes Jingdong, Taobao, and the like, and the social platform includes trembler, fast hand, and the like; however, if the merchant wants to achieve the purpose of promotion, more users are attracted to use the point system, that is, the user activity of the point system is improved, and one key factor attracting the users to use the point system is the reward set by the merchant, so the embodiment provides the promotion method based on the point reward, and the method obtains the point reward types interested by the target users in the target history time period by analyzing the activity change vectors of the target users when the history point reward activities are finished, that is, the point reward types interested by the users can be accurately positioned; classifying the users based on the point reward types which are interested by the target users to obtain the target user categories, and setting the point reward types corresponding to the next point reward activity and the reward quantity of the point reward types based on the quantity of the users in the target user categories; the method achieves the purpose of attracting more users to use the point system by setting the point reward types and the reward quantity of the point reward types in the next point reward activity, namely, the activity of the users in the next point reward activity is improved to the maximum extent, the merchants are helped to achieve the purposes of user retention and new user expansion, namely, the marketing or popularization of the merchants are achieved, and if the activity of a certain category of users in the point reward activity is reduced, the activity of the category of users can be increased by adjusting the reward quantity corresponding to the point reward types which the category of users are interested in, and the loss of the users is avoided.
In this embodiment, a merchant who performs the following process analysis is a game platform, and first needs to acquire a target historical time period, where the specific process of acquiring the target historical time period is as follows: acquiring the starting time of the merchant for holding the next bonus point activity, acquiring the ending time of the historical bonus point activity which is closest to the starting time of the merchant for holding the next bonus point activity from the database, and recording the ending time as the deadline of the target historical time period; then, starting from the deadline of the target historical time period, a preset number of historical point reward activities are continuously acquired, the ending time of the historical point reward activity farthest from the starting time of the next point reward activity held by the merchant is recorded as the starting time of the target historical time period, and the historical data in the embodiment is acquired from the database.
In this embodiment, if the preset number is recorded as a, the number of the historical integral reward activities in the target historical time is a-1; acquiring each point reward type in each historical point reward activity, reward quantity corresponding to each point reward type in each historical point reward activity and reward total quantity corresponding to each historical point reward activity in a target historical time period from a database; for example, a royal glory game proposes to draw points by completing tasks in the game in a certain point reward activity, the set point reward types in the point reward activity comprise a point reward type 1 and a point reward type 2, the point reward type 1 is skin, the point reward type 2 is hero, the total number of rewards in the point reward activity is set to be 100, the reward number corresponding to the point reward type 1 is set to be 40, and the reward number corresponding to the point reward type 2 is set to be 60; the user may then receive rewards corresponding to bonus point reward type 1 and bonus point reward 2 by points.
In the embodiment, the bonus point reward type which is interested by the user is determined by analyzing the activity change vector of the user, and all users participating in each historical bonus point reward activity in the target historical time period are obtained from the database and marked as target users; next, activity change vectors of target users in a target historical time period need to be acquired, but parameter data reflecting user activity by different merchants are different, and because the embodiment is analyzed by a game platform, the parameter data reflecting user activity comprise user login frequency, login times, daily average online time, consumption amount, check-in rate and the like, so the activity vector in the embodiment is constructed by the user login frequency, the login times, the daily average online time, the consumption amount and the check-in rate; as other embodiments, activity vectors can be constructed by using different numbers of parameters according to different requirements, for example, activity vectors can be constructed by only using login frequency and check-in rate. If the embodiment is analyzed by the e-commerce platform, the parameter data capable of reflecting the user activity comprises user browsing frequency, collection quantity, consumption amount, purchase frequency and the like; if the embodiment is analyzed by the social platform, the parameter data capable of reflecting the user activity includes the user browsing frequency, the check-in rate, the consumption amount, the approval rate, and the like.
For any historical point reward activity and any target user, the specific process of obtaining the activity change vector of the target user when the historical point reward activity is finished in the target time period is as follows:
acquiring a historical time period from the ending time of the previous historical point reward activity to the starting time of the historical point reward activity, and recording the historical time period as the historical time period before the historical point reward activity starts; according to the login frequency, login times, daily average online time length, consumption amount and sign-in rate of the target user in the historical time period before the historical integral reward activity starts, constructing and obtaining an activity vector of the target user in the historical time period before the historical integral reward activity starts; then obtaining the historical time period from the starting time of the historical point reward activity to the ending time of the historical point reward activity, and recording the historical time period as the continuous historical time period of the historical point reward activity; according to the login frequency, login times, daily average online time length, consumption amount and sign-in rate of the target user in the historical time period in which the historical integral reward activity lasts, constructing and obtaining an activity vector of the target user in the historical time period in which the historical integral reward activity lasts; in this embodiment, the 1 st element in each activity vector is the login frequency, and so on, the 5 th element in each activity vector is the sign-in rate; therefore, the activity vector of the target user in the historical time period before the historical integral reward activity is started and the activity vector of the target user in the historical time period when the historical integral reward activity is continued are obtained through the process; and subtracting the activity vector of the target user in the historical time period in which the historical integral reward activity lasts from the activity vector of the target user in the historical time period before the historical integral reward activity starts, and recording the subtracted result as the activity change vector of the target user when the historical integral reward activity ends.
Therefore, through the process, the activity change vectors of all target users at the end of all historical integral reward activities in the target time period can be obtained, namely all activity change vectors of all target users in the target time period are obtained, and one user corresponds to A-1 activity change vectors.
Step S002, normalizing the activity degree change vector to obtain a target activity degree change vector corresponding to the activity degree change vector; obtaining a representation value of the target activity degree change vector; and obtaining the historical integral reward activities of each target corresponding to each target user according to the characterization values.
Because the interest degrees of different users for different point reward types are different, and the interest degrees of the users for different point reward types can be reflected by the activity change vectors of the users, namely after a certain activity is finished, the activity of some users is greatly improved relative to the activity before the activity is started, which shows that the interest degrees of the users for the point reward types corresponding to the activity are possibly larger; if the user wants to know which point reward types are interested by the user, firstly, a representation value of an activity change vector of each target user when each historical point reward activity is finished in a target historical time period needs to be calculated, the representation value is used for representing the change degree of the activity of each target user when each historical point reward activity is finished, the greater the representation value is, the higher the activity of each target user in the activity period is than the activity before the activity is started, namely, the representation value can reflect the interest degree of each target user in each historical point reward activity; the bonus point types of interest to each target user are subsequently derived by analyzing the bonus point types in each historical bonus point activity of interest to each target user. The specific process is as follows:
in this embodiment, because the dimensions of each element value in the activity change vector are different, the sum or the average of all the element values in the activity change vector cannot be directly calculated as the representation value of the activity change vector; therefore, normalization processing needs to be performed on the liveness change vector to remove dimensions, and the specific process of the normalization processing is as follows: for any target user, in a target historical time period, obtaining a-1 activity change vector corresponding to the target user, obtaining a maximum value of the ith element value in each activity change vector corresponding to the target user, recording the maximum value as a characteristic value corresponding to the ith element, dividing the ith element value in each activity change vector corresponding to the target user by the characteristic value corresponding to the ith element, and recording the division result as a normalized value of the ith element value in each activity change vector corresponding to the target user. Therefore, through the above process, normalization processing can be performed on each liveness change vector corresponding to each target user, so as to obtain each target liveness change vector corresponding to each target user in a target historical time period, and the value of each element in the target liveness change vector is the normalized value of each element value in the corresponding liveness change vector.
Then calculating the mean value of each element value in each target activity change vector corresponding to each target user in the target historical time period, and recording the mean value as the representation value of each target activity change vector; the larger the characterization value is, the more interested the target user is in the point reward type in the corresponding historical point reward activity; according to the representation values of the target activity change vectors corresponding to the target users in the target historical time period, constructing and obtaining a representation value sequence corresponding to the target users in the target historical time period; calculating any characteristic value sequence by using an otsu threshold segmentation method to obtain a threshold k, then eliminating the characteristic values smaller than the threshold k in the characteristic value sequence, and recording sequences constructed by the remaining characteristic values as target characteristic value sequences, wherein each characteristic value in the target characteristic value sequences is greater than or equal to the threshold k; therefore, a target characteristic value sequence corresponding to each target user in the target historical time period is obtained through the process; one representation value corresponding to any target user corresponds to one historical point reward activity; therefore, according to the target characteristic value sequence corresponding to each target user in the target history time period, obtaining a historical integral reward activity corresponding to each characteristic value in the target characteristic value sequence corresponding to each target user in the target history time period, and recording the historical integral reward activity as a target historical integral reward activity, wherein the target historical integral reward activity is an activity which is interested by the target user; and obtaining the point reward types corresponding to the target historical point reward activities corresponding to the target users in the target historical time period. Since users generally participate in the corresponding point reward activities on the premise that the users are interested in the rewards, the point reward types which are interested in the users exist in the target historical point reward activities corresponding to the users, and the point reward types which are interested in different users may be different, so the point reward activities which are interested in different users may also be different, for example, the target user a is interested in activities of obtaining monkey hero by using the points in royal glory or obtaining prayer skin by using the grandfather, and the target user B is interested in activities of obtaining martian hero by using the points in the royal glory or phoenix skin by using the points.
And S003, obtaining the point reward types which are interesting to the target users in the target history time period according to the point reward types in the target history point reward activities and the reward quantity corresponding to the point reward types.
Because the users can participate in the corresponding point reward activities on the premise that the users are interested in the reward, the point reward types which are interested by the target users exist in the target historical point reward activities corresponding to the target users; therefore, the point reward types which are interesting to the target users in the target history time period are obtained by analyzing the point reward types in the target history point reward activities corresponding to the target users; the method specifically comprises the following steps:
for any target user:
acquiring each point reward type in each target historical point reward activity corresponding to the target user, and recording the point reward type as a target point reward type; and constructing a target point reward type sequence corresponding to each target historical point reward activity corresponding to the target user according to each target point reward type in each target historical point reward activity corresponding to the target user, for example, if the point reward types in any target historical point reward activity corresponding to the target user are a target point reward type 1 and a target point reward type 3 respectively, then the target point reward type sequence W1= { target point reward type 1, target point reward type 3} corresponding to the target historical point reward activity. Different point reward activities may correspond to the same point reward types, so that a comprehensive target point reward type sequence corresponding to the target user in a target history time period is constructed according to each target point reward type corresponding to each target history point reward activity corresponding to the target user, and repeated target point reward types do not exist in the target point reward type sequence of the comprehensive target point reward type sequence; for example, each target historical point reward activity corresponding to the target user is a target historical point reward activity 1 and a target historical point reward activity 2, point reward types in the target historical point reward activity 1 are a target point reward type 1, a target point reward type 2 and a target point reward type 4 respectively, point reward types in the target historical point reward activity 2 are a target point reward type 2 and a target point reward type 3 respectively, and then a comprehensive target point reward type sequence W2= { target point reward type 1, target point reward type 2, target point reward type 3 and target point reward type 4} corresponding to the target user. For any target point reward type in the comprehensive target point reward type sequence corresponding to the target user:
calculating the accumulated sum of the parameter numbers in the target point reward type sequence corresponding to each target historical point reward activity corresponding to the target user; then target historical point reward activities corresponding to the target point reward type sequences containing the target point reward type in each target point reward type sequence corresponding to the target user are recorded as first target historical point reward activities corresponding to the target point reward type; counting the number of first target historical point reward activities corresponding to the target point reward type; calculating the ratio of the number of first target historical point reward activities corresponding to the target point reward type to the number of parameters in the comprehensive target point reward type sequence corresponding to the target user, and recording the ratio as the occurrence frequency of the target point reward type; because the target point reward types in each first target historical point reward activity all contain the target point reward type, the reward quantity corresponding to the target point reward type in each first target historical point reward activity and the reward total quantity corresponding to each first target historical point reward activity can be obtained in the step S001; and recording the average value of the accumulated sum of the ratios of the reward quantity corresponding to the target point reward type in each first target historical point reward activity and the reward total quantity corresponding to the first target historical point reward activity as the average specific gravity value of the target point reward type.
Because the greater the frequency of occurrence of the bonus target type is, the greater the number of occurrences of the bonus target type in the sequence of the comprehensive bonus target type corresponding to the target user is, and because the frequency of occurrence of the bonus target type is obtained based on each historical bonus reward activity that the target user is interested in, the greater the frequency of occurrence of the bonus target type is, the greater the degree of interest of the target user in the bonus target type may be; when the average specific gravity value of the target point reward type is larger, the fact that the reward quantity of the target point reward type in each first target point reward type corresponding to the target user is larger is indicated, and the fact that the interest degree of the target user in the target point reward type is possibly larger is indicated.
Therefore, the present embodiment records the result of multiplying the frequency of occurrence of the target bonus point type by the average specific gravity value of the target bonus point type as the interest level of the target user in the target bonus point type. For example, each target historical integral reward activity corresponding to any target user is a target historical integral reward activity 1 and a target historical integral reward activity 2, the integral reward types corresponding to the target historical integral reward activity 1 are respectively a target integral reward type 1, a target integral reward type 2 and a target integral reward type 3, and the integral reward types corresponding to the target historical integral reward activity 2 are respectively a target integral reward type 2 and a target integral reward type 2Bonus point type 3; the total number of rewards corresponding to the target historical point reward activity 1 is 10, wherein the reward number of the target point reward type 1 is 3, the reward number of the target point reward type 2 is 3, the reward number of the target point reward type 3 is 4, the total number of rewards corresponding to the target historical point reward activity 2 is 10, the reward number of the target point reward type 2 is 3, and the reward number of the target point reward type 3 is 7; the occurrence frequency of the target bonus point type 1 is thus
The occurrence frequency of the target point bonus type 2 is
And the occurrence frequency of the target point bonus type 3 is
5 is the number of parameters in the comprehensive target point reward type sequence corresponding to the target user, and the average specific gravity value of the target point reward type 1 is
The target point reward type 2 has an average specific gravity value of
And the average specific gravity value of the point reward type 3 is
Then the interest level of the target user in the target bonus point type 1 is
The interest level for the type 2 of the target bonus point is
And a degree of interest in the type 2 of the target point award
。
Therefore, the interest degree of each target user in each target point reward type in the corresponding comprehensive target point reward type sequence is obtained through the process; for any target user, recording the target point reward type corresponding to the maximum value in the interest degree of each target point reward type in the corresponding comprehensive target point reward type sequence as the point reward type which is interested by the target user; thus, the bonus point types of interest to each target user in the target history time period are obtained.
Step S004, obtaining categories of all target users according to the types of the point rewards which are interested by all target users in the target historical time period; and setting the bonus point types and the bonus amount of the bonus point types in the next bonus point activity according to the number of the target users in each target user category.
Classifying the target users according to the point reward types which are interesting to the target users in the target historical time period obtained in the process, namely classifying the target users with the consistent point reward types which are interesting into one category, so that each target user category is obtained, one target user category only corresponds to one point reward type which is interesting and is marked as the target point reward type corresponding to each target user category, and the number of the target users in each target user category can reflect the popularity of the point reward types which are interesting to the target users corresponding to each target user category, namely the more the number of the target users in each target user category is, the more the point reward type which is interesting to the target users corresponding to each target user category is popular; recording the target point reward type corresponding to each target user category as each point reward type in the next point reward activity; setting the ratio of the reward quantity corresponding to each point reward type in the next point reward activity to the total reward quantity in the next point reward activity as the ratio of the target user quantity in the target user category corresponding to each point reward type in the next point reward activity to the total target user quantity in the target historical time period, namely, the reward quantity of the point reward type with high popularity accounts for a large ratio; therefore, the setting of the point reward types and the reward quantity corresponding to the point reward types in the next point reward activity is realized through the process, the setting rules of the point reward types and the reward quantity corresponding to the point reward types can attract more users to use the point system, namely, the activity of the users in the next point reward activity is improved to the maximum extent, the merchant is helped to achieve the purposes of user retention and new user expansion, namely, the marketing or promotion purpose of the merchant is achieved, and if the activity of a certain category of users in the point reward activity is reduced, the activity of the category of users can be increased by adjusting the reward quantity corresponding to the point reward types which the category of users are interested in, and the loss of the users is avoided.
The method comprises the steps of firstly, acquiring historical integral reward activities, target users, activity change vectors of the target users when the historical integral reward activities are finished, integral reward types in the historical integral reward activities and reward numbers corresponding to the integral reward types in the target historical time period; next, obtaining each target historical integral reward activity corresponding to each target user according to the activity change vector of the target user when each historical integral reward activity is finished, and then obtaining the integral reward type interested by each target user in the target historical time period according to each integral reward type in each target historical integral reward activity and the reward quantity corresponding to the integral reward type, so that the accurate positioning of the integral reward type interested by each target user is realized; classifying the target users based on the point reward types which are interested by the target users to obtain the target user categories; because the number of the target users in each target user category can reflect the popularity of the bonus point types which are interested by the target users corresponding to each target user category, namely, the more the number of the target users in each target user category, the more popular the bonus point types which are interested by the target users corresponding to each target user category, the embodiment sets the bonus point types corresponding to the next bonus point activity and the bonus number of each bonus point type based on the number of the target users in each target user category, can maximally improve the activity of the users during the next bonus point activity, and helps the merchant to realize the purposes of user retention and new user expansion, namely, the purpose of marketing or popularization of the merchant; therefore, the promotion method based on the point reward provided by the embodiment can attract more users to use the point system, maximally improve the activity of the users during the next point reward activity, and help the merchant to realize the purposes of user retention and new user expansion, namely, the purpose of marketing or promotion of the merchant is realized.
The promotion system based on the point reward of the embodiment comprises a memory and a processor, and the processor executes a computer program stored in the memory to realize the promotion system method based on the point reward.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A promotion method based on point reward is characterized by comprising the following steps:
acquiring historical integral reward activities, target users, activity change vectors of the target users when the historical integral reward activities are finished, integral reward types in the historical integral reward activities and reward quantity corresponding to the integral reward types in the target historical time period;
normalizing the activity degree change vector to obtain a target activity degree change vector corresponding to the activity degree change vector; obtaining a representation value of the target activity degree change vector; obtaining each target historical integral reward activity corresponding to each target user according to the representation value;
obtaining the point reward types which are interesting to the target users in the target historical time period according to the point reward types in the target historical point reward activities and the reward quantity corresponding to the point reward types;
obtaining the category of each target user according to the interested integral reward type of each target user in the target historical time period; and setting the bonus point types and the bonus amount of the bonus point types in the next bonus point activity according to the number of the target users in each target user category.
2. The promotion method based on the bonus point, according to claim 1, wherein the method for obtaining the target historical time period comprises:
acquiring the starting time of the merchant for holding the next bonus point activity, and acquiring the ending time of the historical bonus point activity which is closest to the starting time of the merchant for holding the next bonus point activity, and recording the ending time as the deadline of the target historical time period;
and continuously acquiring a preset number of historical point reward activities from the deadline of the target historical time period, and recording the ending time of the historical point reward activity farthest from the starting time of the next point reward activity held by the merchant as the starting time of the target historical time period.
3. The method for promoting based on the bonus points as claimed in claim 1, wherein the target users are all users who participated in the historical bonus point activities in the target historical time period.
4. The promotion method based on bonus point, according to claim 2, wherein the method for obtaining the activity change vector of each target user at the end of each historical bonus point activity in the target historical time period comprises:
reward the activity and any target user for any historical points:
acquiring a historical time period from the ending time of the previous historical point reward activity to the starting time of the historical point reward activity, and recording the historical time period as the historical time period before the historical point reward activity starts;
obtaining the activity vector of the target user in the historical time period before the historical integral reward activity starts;
acquiring a historical time period from the starting time of the historical point reward activity to the ending time of the historical point reward activity, and recording the historical time period as the continuous historical time period of the historical point reward activity;
obtaining the activity vector of the target user in the historical time period for which the historical integral reward activity lasts;
subtracting the activity vector of the target user in the historical time period in which the historical integral reward activity lasts from the activity vector of the target user in the historical time period before the historical integral reward activity starts, and recording the subtracted result as the activity change vector of the target user when the historical integral reward activity ends.
5. The promotion method based on bonus point, according to claim 1, wherein the method for obtaining the target liveness change vector corresponding to the liveness change vector comprises:
for any target user:
obtaining each activity degree change vector corresponding to the target user according to the activity degree change vector of the target user when each historical integral rewarding activity is finished;
obtaining the maximum value in the ith element value in each activity degree change vector corresponding to the target user, and recording as the characteristic value corresponding to the ith element; dividing the ith element value in each activity degree change vector corresponding to the target user by the characteristic value corresponding to the ith element, and recording the division result as the normalized value of the ith element value in each activity degree change vector corresponding to the target user;
and obtaining a target activity change vector corresponding to each activity change vector corresponding to the target user according to the normalized value of each element value in each activity change vector corresponding to the target user, wherein the value of each element in the target activity change vector is the normalized value of each element value in the corresponding activity change vector.
6. The bonus point-based promotion method of claim 1, wherein the method of obtaining the token value of the target activity change vector comprises:
and calculating the mean value of each element value in the target activity change vector, and recording the mean value as the representation value of each target activity change vector.
7. The promotion method based on bonus point, according to claim 1, characterized in that, the method for obtaining historical bonus point activity of each target corresponding to each target user according to the characterization value comprises:
according to the characteristic values, constructing and obtaining a characteristic value sequence corresponding to each target user in a target historical time period;
for any sequence of characterization values: calculating the characteristic value sequence by an otsu threshold segmentation method to obtain a threshold value k, eliminating the characteristic values smaller than the threshold value k in the characteristic value sequence, and recording sequences constructed by the remaining characteristic values as target characteristic value sequences;
and obtaining historical integral reward activities corresponding to the characteristic values in the target characteristic value sequence corresponding to the target users in the target historical time period according to the target characteristic value sequence corresponding to the target users in the target historical time period, and recording the historical integral reward activities as the target historical integral reward activities.
8. The promotion method based on bonus points, according to claim 1, wherein the method for obtaining bonus point types which are interesting to each target user in the target historical time period comprises:
for any target user:
acquiring each point reward type in each target historical point reward activity corresponding to the target user, and recording the point reward type as a target point reward type;
according to the target point reward types in the target historical point reward activities corresponding to the target user, constructing and obtaining a target point reward type sequence corresponding to the target historical point reward activities corresponding to the target user;
according to the target point reward types corresponding to the target historical point reward activities of the target user, constructing and obtaining a comprehensive target point reward type sequence corresponding to the target user, wherein repeated target point reward types do not exist in the comprehensive target point reward type sequence; for any target point reward type in the comprehensive target point reward type sequence corresponding to the target user:
calculating the accumulated sum of the parameter numbers in the target point reward type sequence corresponding to each target historical point reward activity corresponding to the target user; recording the target historical point reward activity corresponding to the target point reward type sequence containing the target point reward type in each target point reward type sequence corresponding to the target user as a first target historical point reward activity corresponding to the target point reward type;
counting the number of first target historical point reward activities corresponding to the target point reward type; calculating the ratio of the number of first target historical point reward activities corresponding to the target point reward type to the number of parameters in the comprehensive target point reward type sequence corresponding to the target user, and recording the ratio as the occurrence frequency of the target point reward type;
obtaining the reward quantity corresponding to the target point reward type in each first target historical point reward activity and the reward total quantity corresponding to each first target historical point reward activity; recording the average value of the accumulated sum of the ratio of the reward quantity corresponding to the target point reward type in each first target historical point reward activity to the reward total quantity corresponding to the first target historical point reward activity as the average specific gravity value of the target point reward type;
recording the result of multiplying the occurrence frequency of the target point reward type by the average specific gravity value of the target point reward type as the interest degree of the target user in the target point reward type;
and recording the target point reward type corresponding to the maximum value in the interest degree of each target point reward type in the corresponding comprehensive target point reward type sequence as the point reward type which is interested by the target user.
9. The promotion method based on the bonus point, as claimed in claim 1, wherein the categories of target users are obtained according to the bonus point types in which the target users are interested in the target historical time period; the method for setting the bonus point types and the bonus number of the bonus point types in the next bonus point activity according to the number of target users in each target user category comprises the following steps:
classifying the target users with the consistent interest point reward types into one category to obtain each target user category, wherein one target user category only corresponds to one interest point reward type and is recorded as the target point reward type corresponding to each target user category;
recording the target point reward type corresponding to each target user category as each point reward type in the next point reward activity; the ratio of the reward quantity corresponding to each point reward type in the next point reward activity to the total reward quantity in the next point reward activity is the ratio of the target user quantity in the target user category corresponding to each point reward type in the next point reward activity to the target user total quantity in the target historical time period.
10. A bonus point based promotion system comprising a memory and a processor, wherein said processor executes a computer program stored in said memory to implement a bonus point based promotion method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210989643.8A CN115082132B (en) | 2022-08-18 | 2022-08-18 | Promotion method and system based on point reward |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210989643.8A CN115082132B (en) | 2022-08-18 | 2022-08-18 | Promotion method and system based on point reward |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115082132A true CN115082132A (en) | 2022-09-20 |
| CN115082132B CN115082132B (en) | 2022-11-04 |
Family
ID=83244876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210989643.8A Active CN115082132B (en) | 2022-08-18 | 2022-08-18 | Promotion method and system based on point reward |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115082132B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060195325A1 (en) * | 2003-03-27 | 2006-08-31 | Tateson Richard E | Data retrieval system |
| JP2012168653A (en) * | 2011-02-10 | 2012-09-06 | M-Warp Inc | Information providing system |
| US20160191450A1 (en) * | 2014-12-31 | 2016-06-30 | Socialtopias, Llc | Recommendations Engine in a Layered Social Media Webpage |
| WO2017172967A1 (en) * | 2016-03-31 | 2017-10-05 | Square, Inc. | Customer groups and sales promotions |
| US20170286989A1 (en) * | 2016-03-31 | 2017-10-05 | Square, Inc. | Customer groups and sales promotions |
| CN110148012A (en) * | 2019-04-15 | 2019-08-20 | 中国平安人寿保险股份有限公司 | User's motivational techniques, device, computer equipment and storage medium |
| CN110910036A (en) * | 2019-12-02 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Resource share distribution method and device for guiding user behavior |
| CN111714897A (en) * | 2020-06-15 | 2020-09-29 | 北京智明星通科技股份有限公司 | Method, system and server for distributing game rewards based on game activity |
| CN112148973A (en) * | 2020-09-04 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for information push |
-
2022
- 2022-08-18 CN CN202210989643.8A patent/CN115082132B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060195325A1 (en) * | 2003-03-27 | 2006-08-31 | Tateson Richard E | Data retrieval system |
| JP2012168653A (en) * | 2011-02-10 | 2012-09-06 | M-Warp Inc | Information providing system |
| US20160191450A1 (en) * | 2014-12-31 | 2016-06-30 | Socialtopias, Llc | Recommendations Engine in a Layered Social Media Webpage |
| WO2017172967A1 (en) * | 2016-03-31 | 2017-10-05 | Square, Inc. | Customer groups and sales promotions |
| US20170286989A1 (en) * | 2016-03-31 | 2017-10-05 | Square, Inc. | Customer groups and sales promotions |
| CN110148012A (en) * | 2019-04-15 | 2019-08-20 | 中国平安人寿保险股份有限公司 | User's motivational techniques, device, computer equipment and storage medium |
| CN110910036A (en) * | 2019-12-02 | 2020-03-24 | 支付宝(杭州)信息技术有限公司 | Resource share distribution method and device for guiding user behavior |
| CN111714897A (en) * | 2020-06-15 | 2020-09-29 | 北京智明星通科技股份有限公司 | Method, system and server for distributing game rewards based on game activity |
| CN112148973A (en) * | 2020-09-04 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for information push |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115082132B (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Slivkins et al. | Online decision making in crowdsourcing markets: Theoretical challenges | |
| CN104778173B (en) | Target user determination method, device and equipment | |
| CN111177538B (en) | User interest label construction method based on unsupervised weight calculation | |
| Sheng et al. | Incentivized actions in freemium games | |
| WO2020221022A1 (en) | Service object recommendation method | |
| CN112232852A (en) | Automatic marketing system implementation method based on big data calculation | |
| CN111461793B (en) | Integration chain consensus method based on liveness probability selection | |
| CN111798310A (en) | Rejection inference method based on Cox regression and logistic regression and electronic equipment | |
| CN115082132B (en) | Promotion method and system based on point reward | |
| CN111881365A (en) | Content recommendation method and device | |
| Gonen et al. | Increased efficiency through pricing in online labor markets | |
| CN112288478A (en) | Edge computing service incentive method based on reinforcement learning | |
| US20190164453A1 (en) | Virtual stock market environment | |
| CN114676324B (en) | Data processing method, device and equipment | |
| CN114418609A (en) | Deal probability estimation method, storage medium, and program product | |
| Foutz et al. | The wisdom of crowds: pre-release forecasting via functional shape analysis of the online virtual stock market | |
| Zhang et al. | Autor3: Au tomated R eal-time R anking with R einforcement Learning in E-commerce Sponsored Search Advertising | |
| Qin et al. | On adaptivity and confounding in contextual bandit experiments | |
| CN116860833B (en) | Main body information service system of multi-domain data | |
| Xu et al. | Optimal crowds contest model for crowdsourcing | |
| US11361252B1 (en) | Methods and systems for using reinforcement learning | |
| CN108154409A (en) | A kind of method and system of internet shopping evaluation | |
| CN109886596B (en) | Method for improving cooperative rate of crowd sensing system based on psychological account theory | |
| Ryan et al. | Incentivized actions in freemium games | |
| Jaillet | Real-Time Bidding with Side Information |
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 | ||
| GR01 | Patent grant |