CN114862432A - Target user determination method and device, electronic equipment and storage medium - Google Patents
Target user determination method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114862432A CN114862432A CN202110157881.8A CN202110157881A CN114862432A CN 114862432 A CN114862432 A CN 114862432A CN 202110157881 A CN202110157881 A CN 202110157881A CN 114862432 A CN114862432 A CN 114862432A
- Authority
- CN
- China
- Prior art keywords
- user
- reward
- live broadcast
- broadcast platform
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000008901 benefit Effects 0.000 claims abstract description 12
- 238000013145 classification model Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 14
- 230000006399 behavior Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 101100460704 Aspergillus sp. (strain MF297-2) notI gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4784—Supplemental services, e.g. displaying phone caller identification, shopping application receiving rewards
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a target user determination method, a target user determination device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform; determining the reference degree of the candidate user as the target user according to the interest index; and determining whether the candidate user is a target user according to the reference degree and a set threshold value. Through the technical scheme of the embodiment of the invention, the aim of scientifically determining the target user is achieved, the determination precision of the target user is improved, and the realization of the maximum benefit of a live broadcast platform is facilitated.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a target user determination method, a target user determination device, electronic equipment and a storage medium.
Background
In the live broadcast platform, in order to prolong the watching duration of the user, the user is usually rewarded with some valuable items after the user reaches a certain watching duration, so that the user is prompted to watch for a longer time and pay, and the benefit conversion of the live broadcast platform is realized. However, the props themselves are costly, and the live platform needs to consider how to maximize the revenue, so the cost of the effort and the revenue obtained need to be balanced.
The traditional method for solving the problems is to select suitable crowds according to labels through crowd selection and operation experience, and reward is issued to the users who select the crowds.
However, the above method needs to maintain more selection rules, is difficult to manage, and the division of the population awarded for the reward is mainly based on manual experience and is not scientific.
Disclosure of Invention
The embodiment of the invention provides a target user determination method, a target user determination device, electronic equipment and a storage medium, which achieve the aim of scientifically determining a target user, improve the determination precision of the target user and further contribute to maximizing the benefits of a live broadcast platform.
In a first aspect, an embodiment of the present invention provides a target user determination method, where the method includes:
determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
determining the reference degree of the candidate user as the target user according to the interest index;
and determining whether the candidate user is a target user according to the reference degree and a set threshold value.
In a second aspect, an embodiment of the present invention further provides a target user determination apparatus, where the apparatus includes:
the first determination module is used for determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
the second determination module is used for determining the reference degree of the candidate user as the target user according to the interest index;
and the third determining module is used for determining whether the candidate user is the target user according to the reference degree and a set threshold value.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the target user determination method steps as provided by any of the embodiments of the invention.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the target user determination method provided in any embodiment of the present invention.
The embodiment of the invention has the following advantages or beneficial effects:
the target user determination method provided by the embodiment of the invention comprises the following steps: determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform; determining the reference degree of the candidate user as the target user according to the interest index; and determining whether the candidate user is a target user according to the reference degree and a set threshold value. Whether the candidate user is the target user is determined by combining the user characteristics of the candidate user on the live broadcast platform, the aim of scientifically determining the target user is achieved, the determination accuracy of the target user is improved, and the method is further beneficial to enabling the live broadcast platform to achieve the maximum benefit.
Drawings
Fig. 1 is a flowchart of a target user determination method according to an embodiment of the present invention;
fig. 2 is a flowchart of a target user determination method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a target user determination device according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
The technical scheme of the embodiment is suitable for determining which users of the live broadcast platform to issue the rewards, so that the users can pay to watch more live broadcast videos on the live broadcast platform, and the benefit maximization of the live broadcast platform is facilitated.
Specifically, the goal of the live platform is to maximize the probability of user payment through reward measures, so that an optimization problem can be defined and solved:
e represents the loss expectation obtained by the live broadcast platform through reward measures, and U represents the user complete set of the live broadcast platform; i denotes any one platform user, x i A user characteristic representing user i; w is a i Indicating whether a prize is issued, 0 indicating no prize is issued, 1 indicating a prize is issued, E L (x i ) Indicating the expectation of loss of the live platform by the user i.
The limitation condition of the above-mentioned optimal problem is that the loss expectation E obtained by the rewarding measure live broadcast platform cannot be greater than 0, otherwise the profit of the live broadcast platform will be damaged, so E is less than or equal to 0. According to the above optimization problem, it is necessary to determine which users are awarded prizes and not which users are awarded prizes, i.e. it is necessary to solve w for which users i Value of 1, for which users w i The value is 0. For the user who issues the reward, the larger the expectation that the user will bring the benefit to the live platform, so that the live platform can be guaranteed to be finally profitable.
Based on the above optimization problem, the present embodiment provides a target user determination method, whichThe target user may be the user for whom the reward is issued, i.e. w i A user with a value of 1.
Fig. 1 is a flowchart of a target user determination method according to an embodiment of the present invention, where the target user determination method may be performed by a target user determination apparatus, and the apparatus may be implemented by software and/or hardware, and is generally integrated in a server of a live platform.
As shown in fig. 1, the method specifically includes the following steps:
and step 110, determining interest indexes corresponding to the candidate users according to the user characteristics of the candidate users on the live broadcast platform.
The candidate users can be any users who log in the live broadcast platform.
The user characteristics include at least one of: effective watching time ratio, active days, watching payment conversion rate and recharging amount. The effective watching duration ratio is specifically the effective watching duration/the total watching duration, and the effective watching duration may refer to a duration when the continuous watching duration reaches the duration threshold, and generally, when the continuous watching duration reaches 5 minutes, the 5 minutes is considered as the effective watching duration. The number of active days specifically refers to the number of days that the user logs in the live platform, for example, if the user continuously or intermittently logs in the live platform for 30 days, the number of active days of the user may be considered to be 30 days. The viewing payment conversion rate may refer to a payment amount/total viewing duration.
The ratio of the effective watching time duration represents the proportion of the user to effectively watch the live video, and if the ratio is not high, the effective watching time duration can be improved by a certain rewarding means. The number of active days represents the activity of the user and the stickiness of the user to the live broadcast platform, and the higher the activity is, the higher the probability that the user pays further is. The view payment conversion rate represents the capability of converting the user's view behavior into the payment behavior, and the higher the view payment conversion rate of the user is, the stronger the capability of converting the user into the payment behavior is. The recharging amount represents the payment capability of the user, and the larger the recharging amount is, the larger the probability of subsequent payment is.
The interest indexes comprise the probability of paying on the live broadcast platform after the reward is obtained, the expected cost under the condition that the reward is issued and the user pays, the first expected income brought to the live broadcast platform after the reward is obtained, and the second expected income brought to the live broadcast platform when the reward is not obtained. Where the reward is issued and the expected cost for the user to pay may refer to the cost expended in issuing the reward to the user. The first expected benefit brought to the live platform after the reward is obtained may refer to the cost paid by the user on the live platform after the reward is obtained minus the cost consumed by issuing the reward to the user on the live platform.
The method and the device determine which users are specifically issued with the rewards by combining the user characteristics of the candidate users, improve the scientificity and accuracy of the determination of the target users, and are favorable for realizing the maximum income of the live broadcast platform.
And step 120, determining the reference degree of the candidate user as the target user according to the interest index.
The direct solution of the optimization problem is complicated, but each user can be considered independently because the contribution ratio of each user is very small relative to the whole user population. If a user has a higher probability of paying the fee and the expected revenue it would bring to the live platform is as large as possible (with as small losses), it is more advantageous to distribute the reward to the user to the live platform. The reference degree θ can then be set to:
where θ represents a reference for awarding a reward to a user having a user characteristic x, E Y (x) Representing the probability of payment of a user with a user characteristic x, E L (x) The expectation of loss brought to the live platform by the user with the user characteristic x is obviously shown to the user i, E Y (x i ) The larger, E L (x i ) The smaller the size of the tube is,
the smaller the contribution to the forward revenue of the live platform. Then if x is for a feature i If the calculated reference degree is not the same as the reference degree
Below a certain threshold, a prize is awarded, otherwise no prize is awarded.
And step 130, determining whether the candidate user is the target user according to the reference degree and a set threshold value.
Optionally, if the reference degree of the candidate user is lower than a set threshold, the candidate user is determined as a target user, that is, a reward is issued to the candidate user.
According to the technical scheme, the specific awards are determined to which users by combining the user characteristics of the candidate users, the scientificity and the accuracy of target user determination are improved, and the realization of the maximum profit of the live broadcast platform is facilitated.
Example two
Fig. 2 is a flowchart of a target user determination method provided in the second embodiment of the present invention, and this embodiment further optimizes the implementation of determining the reference degree on the basis of the foregoing embodiment, so as to improve the determination accuracy of the reference degree, and further improve the determination accuracy of the target user. Wherein explanations of the same or corresponding terms as those of the above-described embodiments are omitted.
Referring to fig. 2, the target user determination method provided in this embodiment specifically includes the following steps:
And step 230, determining the candidate users with the reference degrees lower than a set threshold value as target users.
Specifically, the following two parameters are defined:
c (x) and Ri (x); wherein: c (x) represents the expected cost of issuing the reward and the user paying the fee; ri (x) represents the expected profit of the user on payment or not, wherein i ═ 0 represents no award, i ═ 1 represents award, specifically, R1(x) represents the first expected profit to the live platform after the award is received, and R0(x) represents the second expected profit to the live platform when the award is not received.
Then, the set reference degree θ can be expressed as:
where p (Y ═ 1| x, T ═ 1) represents the probability of payment on the live broadcast platform after receiving the bonus, and p (Y ═ 1| x, T ═ 0) represents the probability of payment on the live broadcast platform without receiving the bonus.
Defining s (x) to represent the probability of paying on the live platform after receiving the reward, then:
thus:
where s (x) represents the probability of paying on the live platform after receiving the award, R1(x) represents the first expected revenue to the live platform after receiving the award, R0(x) represents the second expected revenue to the live platform when not receiving the award, and c (x) represents the expected cost of the award and user for paying.
The above-mentioned each of the indices of interest(s), (x), R 1 (x)、R 0 (x) C (x)) can be estimated by sampling experimental data. Randomly sampling a part of users to perform online experiments, giving rewards when the watching time meets a certain condition, and calculating the interested indexes according to the following method.
(1) Selecting positive and negative samples, wherein the positive sample is a user who has paid behavior after being rewarded, the negative sample is a user who has no paid behavior after being rewarded, training a classification model CM (x), and taking the output of the classification model CM (x) as the probability s (x) of paying on a live broadcast platform after being rewarded.
(2) Selecting users who pay after reward, and training regression model RM by taking user characteristics x and cost c of rewarding the users as samples 1 (x) The expected cost c (x) for the case where the output of the regression model is taken as the award for delivery and the user pays a fee.
(3) Selecting users who pay after reward, and training a regression model RM by taking the user characteristics x and the payment amount r of the users as samples 2 (x) Taking the output of the regression model as a first expected profit R brought to the live broadcast platform after the reward is obtained 1 (x)。
(4) Selecting users without rewards but with payment behaviors, and training a regression model RM by taking the user characteristics x and the payment amount r of the users as samples 3 (x) Taking the output of the regression model as a second expected profit R brought to the live broadcast platform when no reward is obtained 0 (x)。
Illustratively, the determining the interest indicator corresponding to the candidate user according to the user characteristic of the candidate user on the live platform includes:
inputting the user characteristics into a classification model, and obtaining the probability of paying on a live broadcast platform after the reward is obtained; the classification model is obtained by training based on the user characteristics of paid users on the live broadcast platform after awarding and the user characteristics of unpaid users on the live broadcast platform after awarding;
inputting the user characteristics into a first regression model, and obtaining the expected cost under the conditions of issuing the reward and paying by the user; the first regression model is trained and obtained based on the user characteristics of the paid users on the live broadcast platform after the users are rewarded and the cost of rewarding the users;
inputting the user characteristics into a second regression model, and obtaining a first expected income brought to a live broadcast platform after the reward is obtained; the second regression model is obtained by training based on the user characteristics of the paid users on the live broadcast platform after the rewards and the payment amount of the users;
inputting the user characteristics into a third regression model to obtain a second expected income brought to the live broadcast platform when the reward is not obtained; wherein the third regression model is obtained by training based on the user characteristics of the user who does not obtain the reward but has the payment behavior on the live broadcast platform and the payment amount of the user.
Furthermore, since each of the above-mentioned interested indexes is obtained based on a trained model, there is a certain deviation, and in order to further improve the calculation accuracy of the reference degree, a step of calibrating each of the interested indexes may be added. Specifically, the calibration method will be described by taking the probability s (x) of paying on the live platform after receiving the reward as an example.
Illustratively, the probability of paying at the live platform after the reward is calibrated based on the following algorithm:
wherein, N (x) represents N sample sets in which the similarity between the model training samples and the user characteristic x reaches a set threshold, s is a user characteristic corresponding to any one sample in the sample sets, cm(s) represents a probability estimation value paid on the live broadcast platform after the user characteristic s is rewarded through the classification model, and r(s) represents a probability truth value paid on the live broadcast platform after the user characteristic s is rewarded. It should be noted that, in the following description,
the meaning expressed is: if it is not
Is established, then
Is-1, otherwise
Is 1.
The principle of the idea of the calibration algorithm is as follows: predicting the prediction deviation of the sample x according to the sample x 'by finding the sample x' closest to the sample x, wherein the prediction deviation can be measured by the error between the prediction value CM(s) and the actual value r(s) of the classification model, and the evolution of the mean square sum of errors is adopted because the error can be positive or negative
And (6) measuring. By passing
Determining whether to increase or decrease the adjustment value based on the original value (i.e. the value to be calibrated s (x)) or the value before calibration, if the average predicted value is higher than the average actual value, it indicates that the predicted result is higher, and it needs to decrease the adjustment value based on the original value and decrease the predicted result; otherwise, it means that the prediction result is low, and the adjustment value needs to be added on the basis of the original value. And finally, adding the original value and the calculation result to obtain a calibrated calibration value.
According to the method, the expected cost C (x) when the reward is issued and the user pays the fee, and the first expected income R brought to the live broadcast platform after the reward is obtained 1 (x) And a second expected profit R brought to the live broadcast platform when no reward is obtained 0 (x) Calibration is carried out to obtain C ' (x), R ' after calibration ' 1 (x) And R 0 ′(x)。
Further, the determining the reference degree of the candidate user as the target user according to the interest indicator includes:
determining the reference degree based on the following algorithm:
wherein T represents the reference, s '(x) represents a calibrated value of the probability of paying at the live platform after the award, and C' (x) represents the award deliveryAnd a calibrated value of expected cost, R ', at customer payment' 1 (x) Calibration value, R, representing a first expected revenue for a live broadcast platform after a reward is received 0 ' (x) indicates a second desired benefit to the live platform when no prize is awarded. The method comprises the steps of determining a reference degree through the probability paid by a live broadcast platform after awarding, the expected cost under the condition of issuing the awards and paying by a user, the first expected income brought to the live broadcast platform after the awards are obtained and the second expected income brought to the live broadcast platform when the awards are not obtained, converting the problems into the solution of the probability, the expected cost, the first expected income and the second expected income, and achieving the purpose and the advantage that the variables are all related to the crowd issuing the awards when Y is 1, so that follow-up behaviors of the crowd issuing the awards can be tracked, different positive and negative samples are constructed, and the purpose of solving the variables by using a regression model or a classification model to determine the reference degree is achieved.
If the reference degree is larger than the set threshold value, the current candidate user is not issued with the reward, namely, the current candidate user is not the target user needing to issue the reward; if the reference degree is smaller than the set threshold value, the reward can be issued to the current candidate user, namely, the current candidate user is the target user needing to issue the reward. The influence factors for setting the threshold value may include: the budget of the live broadcast platform for the reward activity is high, and the budget indicates that more rewards can be issued, and the set threshold value can be properly increased at the moment, so that more candidate users become target users needing to be rewarded by the method; otherwise, the set threshold is appropriately lowered.
The following describes the method for determining the reference degree and the method for determining the target user with specific data:
assuming that the calibration values of the above-mentioned interest indicators corresponding to the candidate user with the user characteristic x are respectively:
s′(x)＝0.1 C′(x)＝10 R′ 1 (x)＝12 R′ 0 (x)＝2
thus:
assuming that the threshold is set to-0.3, since-0.5 is smaller than-0.3, the current candidate user is the target user, and it is recommended to issue a reward to the current candidate user.
In the technical solution of this embodiment, on the basis of the above embodiment, the implementation of determining the reference degree is further optimized, specifically, a prediction deviation is determined by a model prediction value of another user feature x' closest to the user feature x, and if the average prediction value is higher than the average actual value, it indicates that the prediction result is higher, and it is necessary to reduce an adjustment value on the basis of the original value and reduce the prediction result of the prediction; on the contrary, the prediction result is low, an adjustment value needs to be added on the basis of the original value, and finally the original value and the calculation result are added to obtain a calibrated calibration value, so that the reference degree is determined based on the calibration value, the determination accuracy of the reference degree is improved, and the determination accuracy of the target user is improved; by combining the user characteristics and a specific algorithm, the scientificity of determining the target user is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a target user determining apparatus according to a third embodiment of the present invention, where the apparatus specifically includes: a first determination module 310, a second determination module 320, and a third determination module 330.
The first determining module 310 is configured to determine an interest indicator corresponding to a candidate user according to a user characteristic of the candidate user on a live platform; a second determining module 320, configured to determine, according to the interest indicator, a reference degree of the candidate user as a target user; a third determining module 330, configured to determine whether the candidate user is the target user according to the reference degree and a set threshold.
On the basis of the technical scheme, the user characteristics comprise at least one of the following: effective watching time ratio, active days, watching payment conversion rate and recharging amount.
On the basis of the technical scheme, the interested indexes comprise the probability of paying on the live broadcast platform after the reward is obtained, the expected cost under the condition of issuing the reward and paying by the user, the first expected income brought to the live broadcast platform after the reward is obtained and the second expected income brought to the live broadcast platform when the reward is not obtained.
On the basis of the above technical solution, the first determining module 310 includes:
the first determining unit is used for inputting the user characteristics into a classification model and obtaining the probability of paying on a live broadcast platform after the reward is obtained; the classification model is trained and obtained based on the user characteristics of the pay users on the live broadcast platform after the reward and the user characteristics of the pay-free users on the live broadcast platform after the reward.
On the basis of the above technical solution, the apparatus further includes: a calibration module, configured to calibrate the probability of paying on the live broadcast platform after the reward based on the following algorithm:
wherein s' (x) represents a calibration value obtained after calibrating a to-be-calibrated value s (x), N (x) represents N sample sets in which the similarity between model training samples and a user feature x reaches a set threshold, s is a user feature corresponding to any sample in the sample sets, cm(s) represents a probability estimation value paid on a live broadcast platform after a reward obtained through the classification model according to the user feature s, and r(s) represents a probability true value paid on the live broadcast platform after the reward corresponding to the user feature s.
On the basis of the above technical solution, the first determining module 310 further includes:
a second determining unit, configured to input the user characteristics into a first regression model, and obtain an expected cost of the issuance reward and the user payment; the first regression model is trained and obtained based on the user characteristics of the paid users on the live broadcast platform after the users are rewarded and the cost of rewarding the users;
the third determining unit is used for inputting the user characteristics to a second regression model to obtain the first expected income brought to the live broadcast platform after the reward is obtained; the second regression model is obtained by training based on the user characteristics of the paid users on the live broadcast platform after the rewarding and the payment amount of the users;
the fourth determining unit is used for inputting the user characteristics into a third regression model to obtain a second expected income brought to the live broadcast platform when the reward is not obtained; wherein the third regression model is obtained by training based on the user characteristics of the user who does not obtain the reward but has the payment behavior on the live broadcast platform and the payment amount of the user.
On the basis of the foregoing technical solution, the second determining module 320 is specifically configured to:
determining the reference degree based on the following algorithm:
wherein T represents the reference degree, s ' (x) represents a calibration value of probability of paying at the live platform after the reward, C ' (x) represents a calibration value of expected cost in case of issuing the reward and paying by the user, R ' 1 (x) Calibration value, R, representing a first expected revenue for a live broadcast platform after a reward is received 0 ' (x) indicates a second desired benefit to the live platform when no prize is awarded.
According to the technical scheme, the specific awards are determined to which users by combining the user characteristics of the candidate users, the scientificity and the accuracy of target user determination are improved, and the realization of the maximum profit of the live broadcast platform is facilitated.
The target user determination device provided by the embodiment of the invention can execute the target user determination method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the target user determination method.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 4 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 4, electronic device 12 is embodied in the form of a general purpose computing electronic device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and region-of-interest determination by executing programs stored in the system memory 28, for example, to implement a target user determination method provided by the embodiment of the present invention, the method includes:
determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
determining the reference degree of the candidate user as the target user according to the interest index;
and determining whether the candidate user is a target user according to the reference degree and a set threshold value.
Of course, those skilled in the art will understand that the processor may also implement the technical solution of the target user determination method provided in any embodiment of the present invention.
EXAMPLE five
This fifth embodiment provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the target user determination method provided by any of the embodiments of the present invention, the method comprising:
determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
determining the reference degree of the candidate user as the target user according to the interest index;
and determining whether the candidate user is a target user according to the reference degree and a set threshold value.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for target user determination, comprising:
determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
determining the reference degree of the candidate user as the target user according to the interest index;
determining whether the candidate user is a target user according to the reference degree and a set threshold;
the interest indexes comprise the probability of paying on the live broadcast platform after the reward is obtained, the expected cost under the condition of issuing the reward and paying by the user, the first expected income brought to the live broadcast platform after the reward is obtained and the second expected income brought to the live broadcast platform when the reward is not obtained.
2. The method of claim 1, wherein the user characteristics comprise at least one of: effective watching time ratio, active days, watching payment conversion rate and recharging amount.
3. The method of claim 1, wherein the determining the interest indicator corresponding to the candidate user according to the user characteristic of the candidate user on the live platform comprises:
inputting the user characteristics into a classification model, and obtaining the probability of paying on a live broadcast platform after the reward is obtained; the classification model is trained and obtained based on the user characteristics of the pay users on the live broadcast platform after the reward and the user characteristics of the pay-free users on the live broadcast platform after the reward.
4. The method of claim 3, wherein the probability of paying on a live platform after the reward is calibrated based on the following algorithm:
wherein s' (x) represents a calibration value obtained after calibrating a to-be-calibrated value s (x), N (x) represents N sample sets in which the similarity between model training samples and a user feature x reaches a set threshold, s is a user feature corresponding to any sample in the sample sets, cm(s) represents a probability estimation value paid on a live broadcast platform after a reward obtained through the classification model according to the user feature s, and r(s) represents a probability true value paid on the live broadcast platform after the reward corresponding to the user feature s.
5. The method of claim 1, wherein the determining the interest indicator corresponding to the candidate user according to the user characteristic of the candidate user on the live platform comprises:
inputting the user characteristics into a first regression model, and obtaining the expected cost under the conditions of issuing the reward and paying by the user; and the first regression model is trained and obtained based on the user characteristics of the paid user on the live broadcast platform after the reward and the cost of rewarding the user.
6. The method of claim 1, wherein the determining the interest indicator corresponding to the candidate user according to the user characteristic of the candidate user on the live platform comprises:
inputting the user characteristics into a second regression model, and obtaining a first expected income brought to a live broadcast platform after the reward is obtained; and the second regression model is obtained by training based on the user characteristics of the paid users on the live broadcast platform after the reward and the payment amount of the users.
7. The method of claim 1, wherein the determining the interest indicator corresponding to the candidate user according to the user characteristic of the candidate user on the live platform comprises:
inputting the user characteristics into a third regression model to obtain a second expected income brought to the live broadcast platform when the reward is not obtained; wherein the third regression model is obtained by training based on the user characteristics of the user who does not obtain the reward but has the payment behavior on the live broadcast platform and the payment amount of the user.
8. The method according to any one of claims 1 to 7, wherein the determining the reference degree of the candidate user as the target user according to the interest indicator comprises:
determining the reference degree based on the following algorithm:
wherein T represents the reference degree, s ' (x) represents a calibration value of probability of paying at the live platform after the reward, C ' (x) represents a calibration value of expected cost in case of issuing the reward and paying by the user, R ' 1 (x) Calibration value, R, representing a first expected revenue for a live broadcast platform after a reward is received 0 ' (x) indicates a second desired benefit to the live platform when no prize is awarded.
9. A target user determination apparatus, comprising:
the first determination module is used for determining an interest index corresponding to a candidate user according to the user characteristics of the candidate user on a live broadcast platform;
the second determination module is used for determining the reference degree of the candidate user as the target user according to the interest index;
and the third determining module is used for determining whether the candidate user is the target user according to the reference degree and a set threshold value.
10. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the target user determination method steps of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157881.8A CN114862432A (en) | 2021-02-04 | 2021-02-04 | Target user determination method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157881.8A CN114862432A (en) | 2021-02-04 | 2021-02-04 | Target user determination method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114862432A true CN114862432A (en) | 2022-08-05 |
Family
ID=82622718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110157881.8A Pending CN114862432A (en) | 2021-02-04 | 2021-02-04 | Target user determination method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114862432A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130104574A (en) * | 2012-03-14 | 2013-09-25 | (주)네오위즈게임즈 | Method and server for compensattion according to buying charged-item |
| CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
| CN109376310A (en) * | 2018-09-28 | 2019-02-22 | 乐蜜有限公司 | User's recommended method, device, electronic equipment and computer readable storage medium |
| US20190347675A1 (en) * | 2018-05-14 | 2019-11-14 | Cognant Llc | System and method for user cohort value prediction |
| CN110634010A (en) * | 2018-06-25 | 2019-12-31 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining coupon issuing strategy |
| CN110991875A (en) * | 2019-11-29 | 2020-04-10 | 广州市百果园信息技术有限公司 | Platform user quality evaluation system |
| CN111209478A (en) * | 2020-01-03 | 2020-05-29 | 京东数字科技控股有限公司 | Task pushing method and device, storage medium and electronic equipment |
| CN111353800A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | User future value prediction method, system, device and storage medium |
| CN112132634A (en) * | 2020-10-09 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Virtual gift resource distribution method and device, computer equipment and storage medium |
-
2021
- 2021-02-04 CN CN202110157881.8A patent/CN114862432A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130104574A (en) * | 2012-03-14 | 2013-09-25 | (주)네오위즈게임즈 | Method and server for compensattion according to buying charged-item |
| CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
| US20190347675A1 (en) * | 2018-05-14 | 2019-11-14 | Cognant Llc | System and method for user cohort value prediction |
| CN110634010A (en) * | 2018-06-25 | 2019-12-31 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining coupon issuing strategy |
| CN109376310A (en) * | 2018-09-28 | 2019-02-22 | 乐蜜有限公司 | User's recommended method, device, electronic equipment and computer readable storage medium |
| CN111353800A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | User future value prediction method, system, device and storage medium |
| CN110991875A (en) * | 2019-11-29 | 2020-04-10 | 广州市百果园信息技术有限公司 | Platform user quality evaluation system |
| CN111209478A (en) * | 2020-01-03 | 2020-05-29 | 京东数字科技控股有限公司 | Task pushing method and device, storage medium and electronic equipment |
| CN112132634A (en) * | 2020-10-09 | 2020-12-25 | 腾讯科技（深圳）有限公司 | Virtual gift resource distribution method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵慧;刘颖慧;崔羽飞;张第;: "机器学习在运营商用户流失预警中的运用", 信息通信技术, no. 01, 15 February 2018 (2018-02-15), pages 16 - 23 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461023B (en) | Loss user retrieval method and device, electronic equipment and storage medium | |
| CN109272348B (en) | Method and device for determining number of active users, storage medium and electronic equipment | |
| US20140149174A1 (en) | Financial Risk Analytics for Service Contracts | |
| CN111400600A (en) | Message pushing method, device, equipment and storage medium | |
| CN110598183A (en) | Flow distribution method, device, equipment and storage medium | |
| CN115578138A (en) | Marketing method, marketing device, marketing medium and computing equipment | |
| CN113344647B (en) | Information recommendation method and device | |
| CN117370065B (en) | Abnormal task determining method, electronic equipment and storage medium | |
| CN113255999B (en) | Crop yield evaluation method, device, equipment and medium based on multiple models | |
| CN113393166A (en) | Integrated energy scheduling service system, method, computer device and medium | |
| CN111695967A (en) | Method, device, equipment and storage medium for determining quotation | |
| CN114862432A (en) | Target user determination method and device, electronic equipment and storage medium | |
| CN109523296B (en) | User behavior probability analysis method and device, electronic equipment and storage medium | |
| CN116128135A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112905435B (en) | Workload assessment method, device, equipment and storage medium based on big data | |
| CN113592263A (en) | Resource return increment prediction method and device based on dynamic resource return increase ratio | |
| CN114782170A (en) | Method, apparatus, device and medium for evaluating model risk level | |
| CN111415066A (en) | Risk assessment method and device | |
| CN113934894A (en) | Data display method based on index tree and terminal equipment | |
| CN114697711B (en) | Method and device for recommending anchor, electronic equipment and storage medium | |
| CN114567788B (en) | Exposure position distribution method and device, electronic equipment and storage medium | |
| US11973576B2 (en) | Methods, systems and apparatus to determine panel attrition | |
| CN111681115B (en) | Payday identification method, system, equipment and storage medium | |
| US20230259403A1 (en) | Cloud-Based Resource Allocation Using Meters | |
| US20230281495A1 (en) | Equilibrium solution search method and information processing apparatus |
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 |