CN112116202A - Network application supervision method and system based on big data - Google Patents
Network application supervision method and system based on big data Download PDFInfo
- Publication number
- CN112116202A CN112116202A CN202010813767.1A CN202010813767A CN112116202A CN 112116202 A CN112116202 A CN 112116202A CN 202010813767 A CN202010813767 A CN 202010813767A CN 112116202 A CN112116202 A CN 112116202A
- Authority
- CN
- China
- Prior art keywords
- user
- adjustment
- data
- contribution value
- value
- 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.)
- Pending
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The invention relates to a network application supervision method and system based on big data, wherein the method comprises the following steps: acquiring first index data generated when a user participates in one or more activities; obtaining a time-dependent contribution value of the user by using a contribution value model based on the first index data; and determining second data to be dispensed to the user based on the time-dependent contribution value of the user, and/or a policy to withdraw cash based on the second data. The invention relates the value brought by the user to the platform with the calculation, cash withdrawal and the like of the user income, and adjusts the relevant strategies of the user income and cash withdrawal in real time according to the value brought by the user to the platform, thereby promoting the user to actively participate in activities, forming a self-driving positive good-shape cycle and automatically completing the user cleaning.
Description
Technical Field
The invention relates to the technical field of Application (Application), in particular to a network Application supervision method and system based on big data.
Background
Based on marketing needs, many apps currently design activities that develop old users, attract new users, such as card coupons, rush purchases, commission returns, etc. The operator of the App marketing platform manually puts on shelf; carrying out cost and income evaluation according to behavior data of the user within a period of time, and determining income for the user; and (4) redeeming the income for the user at the request of the user. By the means, old users can be stimulated to create higher benefits for the platform, and more new users can be attracted to join, so that more benefits are brought to the platform.
However, the activities proposed in the prior art do not achieve the above-mentioned objects well. This is because: firstly, the existing marketing platform relies on manual work to evaluate the contribution value of a user to the platform, the manual statistics and calculation are time-consuming, labor-consuming and delayed, so that the contribution value of the user cannot be obtained in real time, the change trend of the contribution value of the user cannot be mastered, and a high-quality user and a poor-quality user cannot be distinguished in time, so that the platform adopts the same marketing strategy for the high-quality user and the poor-quality user, and neither can encourage the high-quality user to exert the activity thereof to further improve the contribution value, nor can the poor-quality user be eliminated. Secondly, when various marketing activities are implemented, the contribution value calculation and the rights and interests issue for the users are mutually split, and the contribution value calculation and the rights and interests issue are not mutually supported and supplemented, so that the users cannot be well attracted.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a network application supervision method and a network application supervision system, which are used for supervising a plurality of related aspects of activities deduced from applications to enable the aspects to be mutually supported and supplemented, so that high-quality users are fully developed, and greater benefits are brought to platforms and users.
In order to solve the above technical problem, according to an aspect of the present invention, the present invention provides a big data based network application monitoring method, including the following steps:
acquiring first index data generated when a user participates in one or more activities;
obtaining a time-dependent contribution value of the user by using a contribution value model based on the first index data; and
determining second data to dispense to a user based on the user's time-dependent contribution value, and/or a policy to withdraw cash based on the second data.
According to one aspect of the invention, the invention provides a big data-based network application supervision system, which comprises a first index data acquisition module, a contribution value calculation module and an adjustment module, wherein the first index data acquisition module is configured to acquire first index data generated when a user participates in one or more activities; the contribution value calculation module is configured to derive a time-dependent contribution value for the user using a contribution value model based on the first indicator data; and the adjustment module is configured to determine second data to dispense to the user based on the time-related contribution value of the user, and/or a policy to withdraw cash based on the second data.
The method and the system correlate the value brought by the user to the platform with the calculation, cash withdrawal and the like of the user income, adjust the relevant strategies of the user income and the cash withdrawal in real time through the value brought by the user to the platform (the value is called as a contribution value in the invention), and when the contribution value of the user to the platform is large, the income is also large. When the user participates in the interaction of the activities, the platform continuously calculates and adjusts the user benefits in real time according to the activity participation condition of the user, and the user also continuously benefits, so that the user is promoted to participate in the activities more actively, and a self-driven positive good-shape cycle is formed. And because when the activity of the user is reduced and the value brought to the platform is reduced, the income is automatically reduced, part of users with low value to the platform can be eliminated, more and more high-quality users with value brought to the platform are left, and the user cleaning is automatically finished.
Drawings
Preferred embodiments of the present invention will now be described in further detail with reference to the accompanying drawings, in which:
FIG. 1 is a flow diagram of a big data based network application policing method according to one embodiment of the invention;
FIG. 2 is a flow diagram of a method of calculating a user real-time contribution value, according to one embodiment of the present invention;
FIG. 3 is a flow diagram of a method of adjusting user revenue, according to one embodiment of the present invention;
FIG. 4 is a graph of user contribution values for two users according to one embodiment of the invention;
FIG. 5 is a functional block diagram of a big data based network application policing system according to one embodiment of the present invention; and
FIG. 6 is a functional block diagram of the operation of a system according to one embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the following detailed description, reference is made to the accompanying drawings that form a part hereof and in which is shown by way of illustration specific embodiments of the application. In the drawings, like numerals describe substantially similar components throughout the different views. Various specific embodiments of the present application are described in sufficient detail below to enable those skilled in the art to practice the teachings of the present application. It is to be understood that other embodiments may be utilized and structural, logical or electrical changes may be made to the embodiments of the present application.
The invention provides a network application supervision method and system based on big data. The web application may be a separate application associated with the online application, or may be an activity introduced into the online application, such as an activity introduced into a reading application to read earn reading coins, which may be used to purchase paid reading material provided in the application, or exchanged into current currency. The benefits, revenues, etc. that a user gains from using a web application, or engaging in an activity that the application proposes, are referred to herein as user revenue. The platform that launched the application or activity sets up user revenue calculation rules so that user revenue can be calculated and placed into the user revenue account for use by the user or for exchange into current currency. The method and the system provided by the invention are used for monitoring the application or the activity so as to promote the application or the activity to achieve the aim of platform promotion, namely simultaneously improving the benefits of the platform and the user. The user gains correspond to different data according to different stages in the data system, in the invention, the user gains calculated according to the original rule are marked as first data, and the user gains finally distributed to the user are marked as second data.
Fig. 1 is a flowchart of a big data-based network application supervision method according to an embodiment of the present invention. In this embodiment, taking the application-derived activity as an example, the method includes the following steps:
and step S100, collecting behavior data of the user participating in the activity in real time. The behavior data includes, but is not limited to, data generated when the advertisement is browsed, such as the number of clicks of clicking the advertisement, time, advertisement playing time, and the like, data of downloading a propaganda object in the advertisement, and the like, and also includes data of specific business related to the campaign, such as reading content, single reading time, reading quantity, and the like for reading the campaign, or data generated when the user invites, downloads, shares, and the like when the campaign task is completed, such as the remaining time of a new user invited. The activity attended may be one or more.
And S101, analyzing the behavior data to obtain real-time first index data. The first index is some index that represents the user value, and for the sake of understanding, the first index data will be referred to as value index data in the following description. The user value corresponds to the amount of income brought to the platform by the user. In order to evaluate the contribution of the user to the platform, the embodiment sets different quantifiable value indexes which can reflect the profit brought to the platform by the user aiming at different activities. Such as general advertisement click rate, reading duration, advertisement conversion rate, etc., and the page forwarding amount, secondary retention (retention rate of day 1), long retention (retention rate of user remaining from recording new user to present), check-in rate, reading times, ARPU (average income), etc., for some businesses, or for customer order price, repurchase rate, refund rate, white bar (installment) rate, cash payment rate, sales promotion deduction rate, etc., for e-commerce business.
Step S102, based on the value index data, calculating a time-related contribution value of the user by using a contribution value model, in this embodiment, calculating a real-time contribution value. In the present invention, a number of different types of contribution value models are provided for calculating the contribution value of a user to a platform. Although the types of the contribution value models may be various, the principle is the same, that is, the user contribution value is finally calculated by formula one:
formula one of R-C
Wherein V is a user contribution value during the user participation in the activity, R is revenue brought to the platform during the user participation in the activity, and C is an expenditure of the platform to the user during the user participation in the activity, which may be embodied as a cash amount that the user can pay up, for example. For an advertisement type campaign, revenue for the platform for the user to view the advertisement corresponding to R in the user contribution value model; for activities requiring users to complete the invitation task type, R in the contribution value model is the income brought to the platform by the invited users; for activities requiring user sharing, R in the contribution value model is revenue and the like for the platform due to the user sharing. In order to calculate these revenues, it is necessary to calculate the revenues using the corresponding value index data, for example, in an advertisement service, according to an agreement with an advertisement publisher, according to an advertisement click rate, a conversion rate, and the like. Therefore, the invention sets the value indexes of corresponding types according to the business income needs of different types. The user value indicator data obtained in step S101 relates to different types of value indicators, since revenue is derived from different types of services, e.g. advertisements, new user invitations, reading tasks, etc., when launching an activity. Thus, as shown in fig. 2, a flowchart of a method for calculating a real-time contribution value of a user according to an embodiment of the present invention is shown, where the method includes:
step S200, determining the type of the obtained value index data, for example, the advertisement click rate is an advertisement service type, the sharing link is an expansion service type, and the like.
In step S201, a user contribution value is calculated using a user contribution value model corresponding to the type of the value index data. For example to obtainA plurality of contribution values V1、V2、V3……。
Step S202, calculating the total end user contribution value according to the calculation strategy. For example, the weighted value of each user contribution value is calculated according to a preset weighted value, so as to obtain a final user contribution value. For example, the total user contribution value is calculated according to formula two.
ViFor the ith single type contribution value, aiN is the total number of the contribution values of a single type. The proportion of the type in the whole user contribution value can be flexibly adjusted by adjusting the weight value, so that the method is suitable for the continuously changing market.
And step S103, adjusting the user income and the cash withdrawal strategy issued to the user based on the real-time contribution value of the user. And after the real-time contribution value of the user is obtained, the user income and the cash withdrawal strategy which are issued to the user are adjusted on the basis of the real-time contribution value of the user. The principle of adjustment is that the contribution of the user is large, the obtained income is increased, and more convenient presentation conditions are provided. Therefore, different adjustment modes are provided according to the real-time contribution value of the user. In one embodiment of the invention, two-stage adjustment is included, one is to perform one-stage adjustment according to the current real-time contribution value, and then perform two-stage adjustment according to the variation trend of the user contribution value, so that the adjustment is more reasonable. Fig. 3 is a flowchart illustrating adjustment of the user profits according to this embodiment.
And step S300, performing primary adjustment according to the current user real-time contribution value. Wherein, the primary adjustment is different according to the positive and negative of the real-time contribution value of the user. And when the real-time contribution value of the user is a positive value, increasing the user income with a preset proportion on the basis of the user basic income obtained by calculating based on the user income rule so as to obtain the user income after primary adjustment. And when the real-time contribution value of the user is a negative value, deducting the user income with a preset proportion from the user income obtained by real-time calculation to obtain the user income after primary adjustment. Wherein the added or subtracted preset proportion corresponds to a range of preset levels in which the real-time contribution value of the user is located. For example, different level ranges and corresponding adjustment ratios are set for the real-time contribution values, and the adjustment ratio is higher as the level is higher. As shown in table 1 below.
TABLE 1
| Range of | Adjusting the ratio |
| ～-20 | -50％ |
| -20 to-10 | -30％ |
| -10 to-5 | -20％ |
| -5 to 0 | -10％ |
| 0 to 5 | 10％ |
| 5 to 10 | 20％ |
| …… | …… |
The adjusted proportion may be determined by determining the range in which the real-time contribution value of the current user lies. When the ratio value is positive, it means that the profit of the corresponding ratio is increased on the user's basis profit, and when the ratio is negative, the profit calculated from the ratio is subtracted on the user's basis profit. For example, taking the gold coins issued by the platform to the user to represent the user income as an example, the current basic gold coin quantity is 2000 according to the participation degree of the user in the activity and the calculation rule. If the currently calculated real-time contribution value of the user is 3, the proportion of the adjustment is 10% as can be seen from the above table, and 2000 × 10% — 200 coins are issued to the user's coin account as a primary adjustment amount. Thus the current monetary account value is 2000+200 2200. The 200 coins are used as the encouragement of the user for bringing income to the platform, and the user can be effectively encouraged to participate in the activity more actively. If the current calculated real-time contribution value of the user is-12, the proportion of the adjustment to the real-time contribution value is-30%, namely the adjustment amount is 2000-30% — 600. The current adjustment amount is subtracted from the current amount of the money account issued for the user, i.e., the current amount of the money account of the user is 2000-600-1400.
Step S301, counting the historical trend of the user contribution value. Namely, the trend of the user contribution value is obtained according to the historical real-time contribution value of the user, wherein the previously obtained real-time contribution value of the user is included. Since the real-time contribution value of the user only represents the current state, the present embodiment refers to the long-term value of the user in order to balance and reasonably adjust the user profit.
And step S302, performing secondary adjustment according to the trend change rate of the user contribution value. The present embodiment performs the secondary adjustment based on the primary adjustment. For example, when the current real-time contribution value of the user is in an ascending trend within a period of time, even if the real-time contribution value of the current user is a negative value, the user should be encouraged, i.e., the adjustment amount is increased. Conversely, if the user handles a downward trend, a corresponding deduction is made. The addition and subtraction can also be adjusted by setting corresponding proportions according to the primary adjustment strategy. And in the secondary adjustment, the change rate is used as a reference index. And determining the change rate of the trend of the current user contribution value according to the previous user real-time contribution value and the current user real-time contribution value, and determining a specific two-stage adjustment proportion according to the proportion corresponding to the multi-stage change rate range set in the system. For example as shown in table 2 below:
TABLE 2
| Rate of change | Two-stage adjustment of the ratio |
| ～10 | 20％ |
| 5～10 | 10％ |
| 0～5 | 5％ |
| -5～0 | -5％ |
| …… | …… |
As shown in fig. 4, a graph of user contribution values for two users a and B. Where the horizontal axis represents time in hours, the vertical axis represents user contribution values, the solid line represents user a, and the dashed line represents user B. The adjustment when the profit adjustment amounts for the user a and the user B are calculated at times T1, T2, and T3, respectively, is as follows:
for user A: at time T1, the user real-time contribution is positive and therefore the first positive adjustment, and the second negative adjustment, since the trend at time T1 is decreasing. At time T2, the first positive adjustment and the second negative adjustment are performed in the same manner. At time T3, the first adjustment is positive and the second adjustment is positive.
For user B: at time T1, the user real-time contribution is positive and therefore the first positive adjustment, and the second negative adjustment, since the trend at time T1 is decreasing. At time T2, the user real-time contribution is negative and therefore the first negative adjustment, and the second negative adjustment is still due to the decreasing trend at time T2. At time T3, the user real-time contribution is negative and therefore the first negative adjustment, and the second positive adjustment, since the trend at time T3 is rising.
As for the proportions used in the adjustment, tables 1 and 2 can be referred to, so that specific adjustment amounts can be obtained. And increasing the adjustment amount on the basis of the user basic income obtained according to the user activity behavior to obtain the final income of the user. Through the adjustment, the current situation that the user income is obtained only according to the activity rule of the user is changed, and according to the value of the user to the platform, the user is encouraged to actively participate in the activity by greatly contributing to create higher value for the platform through increasing the income of the user. Moreover, the more valuable the user is to create, the more revenue it will receive, and the more aggressive it will be, thus creating a benign forward cycle. Moreover, the method of the invention can automatically adjust the user income in real time by the system, thereby having no hysteresis. On the other hand, the method of the invention can gradually eliminate the inferior users which create little value for the platform and even need to consume the platform, so that after a period of time, the superior users are more and more, and the inferior users are less and less, thereby effectively improving the platform benefit.
In addition, the invention can calculate the user income adjustment amount and adjust the user income issuing time. For example, for a new user, such as a user within 1 month from the date of registration referred to as a new user, a second check-in is conducted. For old users, the user can be delayed to be charged for a period of time, such as 1 hour, and when the user income reaches a preset limit, the user income is checked to prevent the cheating behavior of the user, so that for the large user income, the user income is delayed for a certain period of time, such as 10 hours and 12 hours, and is released into the user income charging account when no problem exists.
In another embodiment, the invention also adjusts the withdrawal strategy based on the real-time contribution value of the user, wherein the withdrawal strategy comprises various withdrawal indexes, withdrawal qualification/day, withdrawal frequency, withdrawal amount/day and the like. Wherein, in the original cash-out strategy, corresponding values are set for the cash-out indexes. For example, for a new user, the last three days worth/day of withdrawal is unavailable, i.e., the new user cannot be renewed in the first three days, and from the fourth day, considered as an old user, the worth/day of withdrawal is: the income account amount is not less than one amount X on the same day, the withdrawal frequency is n times/day, and the withdrawal amount/day is an amount Y. In the prior art, these cash-out indicators are essentially unchanged after the order, and if changed, also require platform services to modify. The present invention can adjust these cash-out indicators according to the real-time contribution values. For example, for different performance-promoting indexes, the system sets an adjustment condition and a corresponding adjustment amount that the real-time contribution value should satisfy. For example, when the real-time contribution value of the user is positive and reaches a certain value, the increasing and presenting frequency is 2/day from the original 1/day, the presenting amount/day is increased from the original 10 yuan/day to 20 yuan/day, etc., while if the real-time contribution value of the user is negative and reaches a preset value, the decreasing and presenting frequency is 1/2 day from the original 1 yuan/day, the presenting amount/day is decreased from the original 10 yuan/day to 5 yuan/day, etc.
Through the modification of the cash withdrawal strategy, the requirements on cash withdrawal of high-quality users can be relaxed, and the user income can be timely and accurately converted into currency.
Fig. 5 is a schematic block diagram of a method and a system for monitoring a network application based on big data according to an embodiment of the present invention, which includes a value index data obtaining module 51, a contribution value calculating module 52, and an adjusting module 53, where the value index data obtaining module 51 is configured to obtain, in real time, value index data generated when a user participates in an activity. In one embodiment, the value indicator data acquisition module 51 comprises a behavior data acquisition unit 510 and an analysis unit 512. The behavior data acquiring unit 510 is configured to collect behavior data of the user participating in the activity in real time. For example by burying the spot in a particular location to monitor whether there is data generation required, such as whether the user has clicked on an advertisement, the time of the click, the duration of the browsing, whether there is a download, etc. The data can be obtained by real-time monitoring of the invention, and can also be data collected by other modules, such as an applied monitoring module and the like. If the monitoring module collects the data according to the embodiment, the data can be directly read for use. The analysis unit 512 analyzes the behavior data according to the value index requirement to obtain real-time value index data. In order to evaluate the contribution of the user to the platform, the quantifiable value indexes which can reflect the profit brought to the platform by the user are set differently aiming at different activities. Such as general advertisement click rate, reading time, advertisement conversion rate, forwarding amount, etc., the analysis unit 512 analyzes, calculates, etc. the behavior data of the user, thereby obtaining value index data. Such as specific advertisement click-through rate, reading duration, advertisement conversion rate, forwarding amount, secondary stay, long stay, etc.
The contribution value calculation module 52 is configured to calculate a real-time contribution value for the user using a contribution value model based on the value indicator data. Wherein the contribution value model adopts formula one to calculate the user contribution value:
formula one of R-C
Wherein, V is a user contribution value during the user participation activity, R is income brought to the platform during the user participation activity, and C is expenditure of the platform user for the user during the user participation activity, which can be embodied as cash amount that the user can withdraw.
Since revenue from different types of services is considered when an activity is introduced, R in the formula is calculated differently, and thus, the contribution value calculation module 52 includes: a classification unit 521, a contribution value model calculation unit 522, and a contribution value calculation unit 523. The classifying unit 521 classifies the value index data generated by the user in real time according to the service type, so as to obtain one or more different types of value index data. The contribution value model calculation unit 522 selects a corresponding contribution value model to calculate the contribution value of the user according to different types. If there is only one type, the contribution value model calculation unit 522 calculates a contribution value, which is a real-time contribution value of the user. When there are a plurality of different types of value index data, the contribution value model calculation unit 522 performs parallel calculation using the corresponding contribution value model to obtain a plurality of corresponding contribution values, and therefore, the contribution value calculation unit 523 calculates the plurality of contribution values using a corresponding calculation strategy to obtain a real-time user contribution value. For example, the contribution value calculating unit 523 calculates two or more contribution values using the formula:
Vifor the ith single type contribution value, aiN is the total number of the contribution values of a single type.
The adjusting module 53 is configured to adjust the user revenue and the cash withdrawal policy issued to the user based on the real-time contribution value of the user. In one embodiment, the adjustment module 53 includes a user profit primary adjustment unit 530, a statistics unit 531 and a user profit secondary adjustment unit 532. The user profit primary adjusting unit 530 compares the real-time user contribution value with a preset adjusting range to determine an adjusting ratio, calculates an adjusting amount by using the adjusting ratio and the current user basic profit calculated according to the user profit calculating rule, and superimposes the adjusting amount on the user basic profit. And if the real-time contribution value of the user is a negative value, adjusting the proportion to be the negative value, and after superposition, deducting a part of income with a certain proportion from the user income calculated according to the income calculation rule. And if the real-time contribution value of the user is a positive value, adjusting the proportion to be the positive value, and adding a certain proportion of income in the basic income of the user after superposition.
The statistic unit 531 is configured to count a variation trend of the user contribution value. For example, real-time contribution values for a certain period of time, such as 1 hour, 1 day, or 1 week, will be collected, so that trends in the current user real-time contribution value versus user long-term contribution value curve can be obtained. As shown in fig. 4 as an example, at time T1, the current real-time contribution value of user a is smaller than the previous real-time contribution value, so that it can be determined that the current trend of change is decreasing. At time T3, the current real-time contribution value of user a is greater than the previous real-time contribution value, so that it can be determined that the current trend of change is rising.
The user income secondary adjustment unit 532 performs secondary adjustment on the basis of the primary adjustment according to the change trend of the current contribution value of the user. And similarly, setting the adjustment ratios of different levels, and determining the adjustment ratio of the corresponding level according to the change rate of the real-time contribution value of the current user. When the change rate is a positive value, the change trend of the real-time contribution value of the user is indicated to be increased, the user needs to be encouraged, so that the adjustment proportion is positive, and the user income is increased by adding a secondary adjustment amount to the user income after primary adjustment. If the change rate is a negative value, the change trend of the real-time contribution value of the user is reduced, and the user income is reduced by adding a secondary adjustment amount to the user income after the primary adjustment.
In addition, the module 53 further includes a dispensing time adjusting unit 533. For example, a second check-in may be implemented for a new user, such as a user within 1 month from the date of registration, called the new user, while a delay of a period of time, such as 1 hour, may be implemented for an old user.
The platform and the user are prevented from being lost due to abnormal user income caused by various reasons such as user cheating behaviors and system faults. The system of the present invention further includes a monitoring module 54 for monitoring the status of the user's revenue. For example, when the user income suddenly increases in a short time, that is, the increase rate exceeds the normal amount set by the system, or the user income reaches a preset limit, it may be considered that the user income is abnormal, at this time, the issuing time adjusting unit 533 is notified, suspended or delayed for a certain time, for example, 10 hours or 12 hours, the related personnel is notified or submitted to the related module to perform an audit on the user income, and when it is determined that there is no problem, the user income is issued to the user income account.
The adjustment module 53 includes an evaluation unit 534 and a modification unit 535 for adjusting the presentation policy. Wherein the evaluation unit 534 is to evaluate a condition that satisfies one or more presentation indicators based on the user real-time contribution value. For example, the withdrawal frequency, the adjustment range of withdrawal amount/day, and the adjustment amount. The evaluation unit 534 evaluates the adjustment range that the real-time contribution value of the user satisfies, thereby determining the specific adjustment amount. The presentation index value for the user is then modified by the modification unit 535 by the adjustment amount. For example, when the real-time contribution value of the user is a positive value and a preset adjustment range value is reached, the modification unit 535 increases the current increase frequency from the original 1/day to 2/day, the current increase amount/day is increased from the original 10 yuan/day to 20 yuan/day, and the like, and if the real-time contribution value of the user is a negative value and a preset adjustment range value is reached, the current decrease frequency is increased from the original 1/day to 1/2 day, and the current increase amount/day is decreased from the original 10 yuan/day to 5 yuan/day, and the like.
FIG. 6 is a functional block diagram of a system according to an embodiment of the present invention. In this embodiment, the user engages in some activity that the platform pushes out using the App. And a user income calculating module 10a in the platform calculates the user basic income obtained by the participation of the user in the activity according to the user income calculating rule. The income calculation rule comprises value income, tax rate, wind control conditions and the like.
The value index data acquisition module 60 calculates the value index data according to the behavior data generated by the interaction between the App and the platform in the user participation activity. The contribution value calculating module 61 calculates the final real-time contribution value of the user by using different contribution value models according to the value index data.
The user income adjusting module 62 calculates the user adjusting amount according to the user real-time contribution value and the user income adjusting rule, and obtains the adjusted user basic income after overlapping with the user income calculating module 10 a; and simultaneously, adjusting the user income issuing conditions according to the real-time contribution value of the user. The user revenue adjustment module 62 places the adjusted user revenue into the user revenue account C1 according to the adjusted distribution conditions. The user benefit is a virtual asset, such as gold coins.
And the cash withdrawal strategy adjusting module 63 adjusts the cash withdrawal strategy according to the real-time contribution value of the user and the cash withdrawal adjusting rule, and modifies the cash withdrawal indexes.
The user is entitled to a cash-out through the App participating in the activity, such as reading, sharing, forwarding, continuous login, etc., and if the user is entitled to a cash-out entitlement, a cash-out request is made, which is sent to the cash-out engine 20 a. When the cash-withdrawal engine 20a determines the security through a series of security checks, it queries each cash-withdrawal index in the cash-withdrawal policy, and checks whether the credit is met, such as credit, cash-withdrawal frequency, etc., and after the checking is passed, the credit in the corresponding user request is stored in the user bank account C2.
In the above flow, the invention associates the value brought by the user to the platform with the calculation, cash withdrawal and the like of the user income, adjusts the relevant strategies of the user income and cash withdrawal in real time through the value brought by the user to the platform, which is called contribution value in the invention, and the income is also large when the contribution value of the user to the platform is large. When the user participates in the interaction of the activities, the platform continuously calculates and adjusts the user benefits in real time according to the activities, and the user also continuously benefits, so that the user is promoted to participate in the activities more actively, and a self-driving positive good-shape cycle is formed. And because when the activity of the user is reduced and the value brought to the platform is reduced, the income is automatically reduced, part of users with low value to the platform can be eliminated, more and more users with high value brought to the platform are left, and the user cleaning is automatically finished.
The above embodiments are provided only for illustrating the present invention and not for limiting the present invention, and those skilled in the art can make various changes and modifications without departing from the scope of the present invention, and therefore, all equivalent technical solutions should fall within the scope of the present invention.
Claims (29)
1. A big data-based network application supervision method comprises the following steps:
acquiring first index data generated when a user participates in one or more activities;
obtaining a time-dependent contribution value of the user by using a contribution value model based on the first index data; and
determining second data to dispense to a user based on the user's time-dependent contribution value, and/or a policy to withdraw cash based on the second data.
2. The method of claim 1, further comprising:
collecting behavior data of a user participating in an activity in real time; and
and analyzing the behavior data to obtain first index data.
3. The method of claim 1 or 2, the first indicator data comprising one or more of a length of reading time, a number of readings, a click-through rate, a conversion rate, a check-in rate, a secondary stay, a long stay, ARPU, a unit price for a guest, a repurchase rate, a refund rate, a white bar rate, a cash payment rate, a promotional deduction rate.
4. The method of claim 1, further comprising:
and selecting one or more corresponding contribution value models to obtain the contribution value of the user according to the type of the first index data generated by the user in real time.
5. The method of claim 4, further comprising: in response to a plurality of different types of contribution values computed by the plurality of contribution value models, a user's final time-dependent contribution value is derived based on the plurality of different types of contribution values in accordance with a computation policy.
6. The method of claim 5, further comprising: and calculating the final time-related contribution value of the user according to the weight values corresponding to the plurality of different types of contribution values.
7. The method of claim 1, wherein the time-dependent contribution is a real-time contribution.
8. The method of claim 1, wherein the step of determining the second data to assign to the user based on the time-dependent contribution value comprises:
determining a primary adjustment proportion based on the current user contribution value;
obtaining a primary adjustment amount based on the primary adjustment proportion and first data obtained by calculation based on an original rule; and
and combining the first data and the first adjustment amount to obtain second data after the first adjustment.
9. The method of claim 8, further comprising:
querying a preset multi-level adjustment range based on the current user contribution value to determine a current adjustment level; and
and determining the adjustment proportion corresponding to the adjustment level as a primary adjustment proportion.
10. The method of claim 9, wherein the adjustment range comprises a multi-level positive adjustment range and a multi-level negative adjustment range; correspondingly, the positive adjustment range corresponds to the positive adjustment ratio, and the negative adjustment range includes the negative adjustment ratio.
11. The method of claim 9, wherein the absolute value of the adjustment ratio is stepped up.
12. The method of claim 8, further comprising:
determining the change rate of the trend of the current user contribution value according to the previous user contribution value and the current user contribution value;
determining a secondary adjustment proportion according to the change rate of the current user contribution value trend;
obtaining a secondary adjustment amount based on the secondary adjustment proportion and the second data after the primary adjustment; and
and combining the second data after the first-stage adjustment and the second adjustment to obtain second data after the second-stage adjustment.
13. The method of claim 12, further comprising:
inquiring a preset multi-stage adjustment range based on the change rate of the user contribution value trend to determine the current adjustment level; and
and determining the adjustment proportion corresponding to the adjustment level as a two-stage adjustment proportion.
14. The method of claim 13, wherein the adjustment range comprises a multi-level positive adjustment range and a multi-level negative adjustment range; correspondingly, the positive adjustment range corresponds to the positive adjustment ratio, and the negative adjustment range includes the negative adjustment ratio.
15. The method of claim 14, wherein the absolute value of the adjustment ratio is stepped up.
16. The method of claim 12, further comprising: and counting the user contribution value to obtain a user contribution value historical trend, wherein the user contribution value of the previous time is included.
17. The method of claim 12, further comprising: and in response to the value of the second data reaching a preset value, auditing the second data.
18. The method of claim 12, further comprising: and updating the corresponding data of the current user account by adopting the second data after the second-stage adjustment.
19. The method of claim 1, wherein adjusting the policy for withdrawing cash based on the second data based on the time-based contribution value of the user comprises:
evaluating a condition that satisfies one or more cash-out indicators based on the user contribution value; and
and modifying the withdrawal index value in response to the condition that one or more withdrawal indexes are met meets a preset condition.
20. A big data based network application supervision system, comprising:
a first index data acquisition module configured to acquire first index data generated when a user participates in one or more activities;
a contribution value calculation module configured to obtain a time-dependent contribution value of the user using a contribution value model based on the first indicator data; and
an adjustment module configured to determine second data to dispense to a user based on a time-related contribution value of the user, and/or a policy to withdraw cash based on the second data.
21. The system of claim 20, the first metric data acquisition module further comprising:
a behavior data acquisition unit configured to collect behavior data of a user while participating in an activity in real time; and
an analysis unit configured to analyze the behavior data to obtain real-time first index data.
22. The system of claim 20, the contribution value calculation module comprising:
the classification unit is configured to classify first index data generated by a user in real time according to the service type; and
a contribution value model calculation unit configured to select a corresponding contribution value model to calculate a contribution value of the user according to the first index data type.
23. The system of claim 22, the contribution value calculation module further comprising:
a contribution value calculation unit configured to, in response to a plurality of different types of contribution values, derive a user-final time-dependent real-time contribution value based on the plurality of different types of contribution values in accordance with a calculation policy.
24. The system of claim 20, the adjustment module comprising:
and the primary adjusting unit is configured to calculate a primary adjusting proportion determined based on the current user contribution value to obtain the primary adjusted second data.
25. The system of claim 24, the adjustment module further comprising:
and the secondary adjustment unit is configured to calculate secondary adjusted second data according to a secondary adjustment proportion determined based on the change rate of the current user contribution value trend.
26. The system of claim 25, the adjustment module further comprising:
and the statistical unit is configured to count the user contribution values to obtain a historical trend of the user contribution values, wherein the change rate of the trend of the current user contribution values is calculated according to the current user contribution values and the previous user contribution values.
27. The system of claim 20, further comprising:
a monitoring module configured to monitor the second data, suspend or delay the allocation to the user when the second data is abnormal.
28. The system of claim 20, the adjustment module further comprising:
an evaluation unit configured to evaluate a condition that satisfies one or more performance indicators based on a time-related contribution value of a user;
a modification unit configured to modify a cash-out index value for the user in response to a condition satisfying one or more cash-out indexes meeting a preset condition.
29. The system of claim 25, further comprising:
and the updating module is configured to update the corresponding data of the current user account according to the second data after the second-level adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010813767.1A CN112116202A (en) | 2020-08-13 | 2020-08-13 | Network application supervision method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010813767.1A CN112116202A (en) | 2020-08-13 | 2020-08-13 | Network application supervision method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116202A true CN112116202A (en) | 2020-12-22 |
Family
ID=73803945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010813767.1A Pending CN112116202A (en) | 2020-08-13 | 2020-08-13 | Network application supervision method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116202A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102130949A (en) * | 2011-03-10 | 2011-07-20 | 肖智刚 | User contribution-based method and system for sharing personalized digital resources |
| CN102819806A (en) * | 2012-07-08 | 2012-12-12 | 辜进荣 | Mobile phone advertising cost distribution method |
| CN102833347A (en) * | 2012-09-10 | 2012-12-19 | 辜进荣 | Cloud platform-based mobile terminal advertisement |
| CN105631708A (en) * | 2015-12-25 | 2016-06-01 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN105897770A (en) * | 2016-06-20 | 2016-08-24 | 武汉斗鱼网络科技有限公司 | Virtual gift display method and device based on live broadcasting |
| CN105992057A (en) * | 2015-03-04 | 2016-10-05 | 王筱娜 | Video playing data monitoring method, system and application |
| CN106973360A (en) * | 2017-03-22 | 2017-07-21 | 中国科学院上海微系统与信息技术研究所 | The cache policy and motivational techniques of a kind of D2D communication networks |
| CN107516240A (en) * | 2017-07-31 | 2017-12-26 | 广州点升信息技术有限公司 | The method giveed training by training system to user |
| CN107749000A (en) * | 2017-10-18 | 2018-03-02 | 天脉聚源（北京）科技有限公司 | Platform returns the instant processing method and processing device of existing information |
| CN110070422A (en) * | 2019-04-30 | 2019-07-30 | 德德市界(深圳)科技有限公司 | Data processing system, method and relevant device based on flat framework |
| CN110490658A (en) * | 2019-08-21 | 2019-11-22 | 北京字节跳动网络技术有限公司 | User's motivational techniques, device, electronic equipment and the readable medium of application program |
-
2020
- 2020-08-13 CN CN202010813767.1A patent/CN112116202A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102130949A (en) * | 2011-03-10 | 2011-07-20 | 肖智刚 | User contribution-based method and system for sharing personalized digital resources |
| CN102819806A (en) * | 2012-07-08 | 2012-12-12 | 辜进荣 | Mobile phone advertising cost distribution method |
| CN102833347A (en) * | 2012-09-10 | 2012-12-19 | 辜进荣 | Cloud platform-based mobile terminal advertisement |
| CN105992057A (en) * | 2015-03-04 | 2016-10-05 | 王筱娜 | Video playing data monitoring method, system and application |
| CN105631708A (en) * | 2015-12-25 | 2016-06-01 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| CN105897770A (en) * | 2016-06-20 | 2016-08-24 | 武汉斗鱼网络科技有限公司 | Virtual gift display method and device based on live broadcasting |
| CN106973360A (en) * | 2017-03-22 | 2017-07-21 | 中国科学院上海微系统与信息技术研究所 | The cache policy and motivational techniques of a kind of D2D communication networks |
| CN107516240A (en) * | 2017-07-31 | 2017-12-26 | 广州点升信息技术有限公司 | The method giveed training by training system to user |
| CN107749000A (en) * | 2017-10-18 | 2018-03-02 | 天脉聚源（北京）科技有限公司 | Platform returns the instant processing method and processing device of existing information |
| CN110070422A (en) * | 2019-04-30 | 2019-07-30 | 德德市界(深圳)科技有限公司 | Data processing system, method and relevant device based on flat framework |
| CN110490658A (en) * | 2019-08-21 | 2019-11-22 | 北京字节跳动网络技术有限公司 | User's motivational techniques, device, electronic equipment and the readable medium of application program |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Optimized cost per click in taobao display advertising | |
| Zhang et al. | Optimal real-time bidding for display advertising | |
| Han et al. | Segmentation of telecom customers based on customer value by decision tree model | |
| US20190019213A1 (en) | Predicting the effectiveness of a marketing campaign prior to deployment | |
| US20090186689A1 (en) | Systems and methods for providing investment opportunities | |
| CN107103548A (en) | The monitoring method and system and risk monitoring and control method and system of network behavior data | |
| Costain | Unemployment insurance with endogenous search intensity and precautionary saving | |
| CN104252680B (en) | Keyword automatic pricing method and search engine marketing system | |
| Drozd et al. | Competing for customers: A search model of the market for unsecured credit | |
| Dullaghan et al. | Integration of machine learning techniques to evaluate dynamic customer segmentation analysis for mobile customers | |
| KR102384322B1 (en) | Platform System for Matching between Bidding Expert and Bidding Participant and Method thereof | |
| JP6978551B2 (en) | Patent evaluation system | |
| Ngai et al. | Moving house | |
| CN110827149A (en) | Method for constructing distributed economic system Deco based on block chain | |
| Collings et al. | Valuing customers | |
| Hanspach | The home bias in procurement. Cross-border procurement of medical supplies during the Covid-19 pandemic. | |
| Forró et al. | When games meet reality: is Zynga overvalued? | |
| Zhang | Optimal real-time bidding for display advertising | |
| Bonacchi et al. | Measuring and managing customer lifetime value: A CLV scorecard and cohort analysis in a subscription-based enterprise | |
| CN112116202A (en) | Network application supervision method and system based on big data | |
| WO2011109690A2 (en) | Consumption engine | |
| KR20150096569A (en) | Funding system for social funding service | |
| Steinberg et al. | State Energy Efficiency Resource Standards: Design, Status, and Impacts | |
| Lhoest-Snoeck et al. | Customer value modelling in the energy market and a practical application for marketing decision making | |
| Choi et al. | Optimizing reserve prices in display advertising auctions |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201222 |