CN109121006B - Marketing method and platform based on live broadcast watching user - Google Patents
Marketing method and platform based on live broadcast watching user Download PDFInfo
- Publication number
- CN109121006B CN109121006B CN201810871105.2A CN201810871105A CN109121006B CN 109121006 B CN109121006 B CN 109121006B CN 201810871105 A CN201810871105 A CN 201810871105A CN 109121006 B CN109121006 B CN 109121006B
- Authority
- CN
- China
- Prior art keywords
- user
- live broadcast
- live
- watching
- record
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004891 communication Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000003796 beauty Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2543—Billing, e.g. for subscription services
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a marketing method and a marketing platform based on a live watching user, wherein the method comprises the following steps: judging whether the live broadcast watching user is a target marketing user or not according to the live broadcast watching record and the live broadcast payment record of the live broadcast watching user in a preset historical time period; if the live broadcast watching user is judged to be the target marketing user, predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record; and recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user. The invention can combine the live broadcast service with the mobile service of the operator and promote the product marketing of the operator and the third-party partner thereof.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a marketing method and a marketing platform based on live broadcast watching users.
Background
The development of the live broadcast service drives the consumption of live broadcast watching users, and based on the characteristics of the live broadcast service, the consumption points of the live broadcast watching users mainly include flow consumption and payment consumption.
How to combine the live broadcast service with the mobile service of the operator and promote the product marketing of the operator and the third party partner thereof becomes an urgent problem to be solved.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides a marketing method and a marketing platform based on a live broadcast watching user, which can combine live broadcast services with mobile services of operators and promote product marketing of the operators and third-party partners.
In order to achieve the above object, the present invention provides a marketing method based on live viewing users, comprising:
judging whether the live broadcast watching user is a target marketing user or not according to the live broadcast watching record and the live broadcast payment record of the live broadcast watching user in a preset historical time period;
if the live broadcast watching user is judged to be the target marketing user, predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record;
and recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user.
Optionally, before the determining whether the live viewing user is the targeted marketing user according to the live viewing record and the live payment record of the live viewing user in the preset historical time period, the method further includes:
judging whether user data meet preset conditions or not, wherein the user data comprise a transport layer protocol, a target IP address, a transmission rate and continuous communication time;
if the user data meet the preset conditions, judging whether the user is a live broadcast watching user or not according to a mirror image data packet of the user data and a user identifier corresponding to the user data;
and if the user is judged to be a live broadcast watching user, generating a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and storing the live broadcast watching record of the live broadcast watching user, wherein the live broadcast watching record comprises live broadcast watching flow and live broadcast watching duration.
Optionally, before the determining whether the live viewing user is the targeted marketing user according to the live viewing record and the live payment record of the live viewing user in the preset historical time period, the method further includes:
judging whether the user data comprises a target IP address corresponding to the payment website;
if the user data comprises a target IP address corresponding to the payment website, judging whether a mirror image data packet corresponding to the target IP address comprises two-dimension code information of a live broadcast platform;
and if the mirror image data packet corresponding to the target IP address corresponding to the payment website comprises live broadcast platform two-dimension code information, storing live broadcast payment records of the live broadcast watching user, wherein the live broadcast payment records comprise live broadcast payment times.
Optionally, the determining, according to the mirror image data packet of the user data and the user identifier corresponding to the user data, whether the user is a live broadcast watching user specifically includes:
generating a picture to be identified according to the mirror image data packet of the user data;
and judging whether the picture to be recognized comprises a live broadcast identification or not, if so, judging that the picture to be recognized comprises the live broadcast identification, and judging that the user is a live broadcast watching user, wherein the live broadcast identification comprises a live broadcast rectangular frame and a live broadcast room identification.
Optionally, the determining, according to the live viewing record and the live payment record of the live viewing user in the preset historical time period, whether the live viewing user is a targeted marketing user specifically includes:
generating a first conditional probability value of the live broadcast watching user in a first type state and a second conditional probability value of the live broadcast watching user in a second type state according to a preset classification set;
selecting the higher one of the first conditional probability value and the second conditional probability value as the user value of the live broadcast watching user;
and judging whether the user value is greater than a preset user value threshold value or not, and if so, judging that the live watching user is a target marketing user.
In order to achieve the above object, the present invention further provides a marketing platform based on live viewing users, including:
the system comprises a first judging module, a second judging module and a third judging module, wherein the first judging module is used for judging whether a live watching user is a target marketing user or not according to a live watching record and a live paying record of the live watching user in a preset historical time period;
the prediction module is used for predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record when the live broadcast watching user is judged to be the target marketing user;
and the recommending module is used for recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user.
Optionally, the method further comprises:
the second judgment module is used for judging whether user data meet preset conditions or not, wherein the user data comprise a transport layer protocol, a target IP address, a transmission rate and continuous communication time;
the third judgment module is used for judging whether the user is a live broadcast watching user or not according to the mirror image data packet of the user data and the user identification corresponding to the user data when the user data is judged to meet the preset condition;
and the generation and storage module is used for generating a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and storing the live broadcast watching record of the live broadcast watching user when the user is judged to be the live broadcast watching user, wherein the live broadcast watching record comprises live broadcast watching flow and live broadcast watching duration.
Optionally, the system further comprises a fourth judging module;
the second judgment module is also used for judging whether the user data comprises a target IP address corresponding to the payment website;
the fourth judging module is used for judging whether a mirror image data packet corresponding to a target IP address comprises two-dimension code information of a live broadcast platform or not when the user data is judged to comprise the target IP address corresponding to the payment website;
and the generation and storage module is also used for storing the live broadcast payment record of the live broadcast watching user when judging that the mirror image data packet corresponding to the target IP address corresponding to the payment website comprises live broadcast platform two-dimensional code information, wherein the live broadcast payment record comprises live broadcast payment times.
Optionally, the third determining module specifically includes:
the third generation submodule is used for generating a picture to be identified according to the mirror image data packet of the user data;
and the third judgment submodule is used for judging whether the picture to be recognized comprises a live broadcast identification or not, if so, judging that the picture to be recognized comprises the live broadcast identification, and judging that the user is a live broadcast watching user, wherein the live broadcast identification comprises a live broadcast rectangular frame and a live broadcast room identification.
Optionally, the first determining module specifically includes:
the first generation submodule is used for generating a first conditional probability value of the live broadcast watching user in a first type state and a second conditional probability value of the live broadcast watching user in a second type state according to a preset classification set;
the first selection submodule is used for selecting the higher one of the first conditional probability value and the second conditional probability value as the user value of the live broadcast watching user;
and the first judgment submodule is used for judging whether the user value is greater than a preset user value threshold value or not, and judging that the live broadcast watching user is a target marketing user if the user value is greater than the preset user value threshold value.
The invention has the following beneficial effects:
according to the marketing method based on the live broadcast watching user, provided by the invention, products are recommended to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user. The method can combine the live broadcast service with the mobile service of the operator and promote the product marketing of the operator and the third-party partner thereof.
Drawings
Fig. 1 is a schematic flowchart of a marketing method based on a live viewing user according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a marketing method based on a live viewing user according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a marketing platform based on a live viewing user according to a third embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following clear and complete description of the technical solution of the present invention is made with reference to the accompanying drawings, and it is obvious that the described embodiments are a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Fig. 1 is a schematic flow chart of a marketing method based on a live viewing user according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
And step 102, predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record.
And 103, recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user.
According to the marketing method based on the live broadcast watching user, provided by the embodiment, products are recommended to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user. The method can combine the live broadcast service with the mobile service of the operator and promote the product marketing of the operator and the third-party partner thereof.
Fig. 2 is a schematic flow chart of a marketing method based on a live viewing user according to a second embodiment of the present invention, and as shown in fig. 2, the method includes the following steps:
Preferably, the steps in this embodiment are performed by a marketing platform based on live viewing users.
Such as: the intelligent base station monitors the data field of the IMSI code attached to the intelligent base station and judges whether a plurality of user data corresponding to the IMSI codes meet preset conditions. Preferably, the preset conditions are: the transport layer Protocol is UDP (User Datagram Protocol) and the target IP addresses are continuously the same and the transmission rate is higher than 128kbps and the continuous communication time is longer than 200 seconds.
Preferably, the subscriber identity is an IMSI number.
Such as: and the intelligent base station sends the mirror image data packet and the IMSI code corresponding to the user data to the high-value user list device so as to judge whether the user is a live broadcast watching user or not by the high-value user list device.
Step 202 specifically includes:
The process of generating the picture to be recognized specifically includes: identifying an application layer protocol I frame (I frame, intra-coded frame) of an imaged data packet, denoted as I1And (5) frame. Identify and1i frame adjacent to frame and marked as I1' frame and I1"frame, wherein1' frame is AND1Frame-adjacent previous I frame, I1"frame is AND1The frame is the next I frame adjacent. Statistics I1Frame and I1All B frames (Bframe, bidirectionally predictive coded frame), P frames (P frame, interframe predictive coded frame) and total frames C and I within the timestamp interval of a frame1Frame and I1"all B frames, P frames, and total number of frames C' within the timestamp interval of a frame. And when the result shows that C is equal to C', recombining the I/B/P frames to restore and generate the picture to be identified.
And calculating the contrast of adjacent pixels of the picture to be recognized, and judging whether the picture to be recognized comprises a live broadcast identifier or not according to the contrast. The live room identification may be a room number of the live room.
And 203, generating a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and storing the live broadcast watching record of the live broadcast watching user, wherein the live broadcast watching record comprises live broadcast watching flow and live broadcast watching duration.
Optionally, the live viewing record further includes an IMSI number, and the IMSI number corresponds to the live viewing user.
Such as: the stored live viewing records may be as shown in table one below:
watch 1
The table one shown above is only an example, and in practice the table one may also include live room identification.
Optionally, a target IP address corresponding to the live viewing record is obtained according to the mirror image data packet, the target IP address corresponding to the live viewing record is a live platform, and the target IP address is stored in a live platform database. The live broadcast platform database stores data of a plurality of live broadcast platforms, and whether a certain IP address is a live broadcast platform can be judged according to the live broadcast platform database.
Such as: when the intelligent base station judges that the user data comprises a target IP address corresponding to the payment website, the intelligent base station sends a mirror image data packet corresponding to the target IP address and the IMSI code to a high-value user list device, so that the high-value user list device judges whether the mirror image data packet corresponding to the target IP address comprises two-dimension code information of a live broadcast platform.
Alternatively, step 204 and step 202 may be performed simultaneously.
Specifically, two-dimension code information included in a mirror image data packet corresponding to the target IP address is acquired, and whether the two-dimension code information is live broadcast platform two-dimension code information or not is judged. Optionally, whether the two-dimension code information is live broadcast platform two-dimension code information is judged according to a live broadcast platform database, and live broadcast platform two-dimension code information corresponding to each live broadcast platform is stored in live broadcast platform data.
And step 206, storing the live broadcast payment record of the live broadcast watching user, wherein the live broadcast payment record comprises live broadcast payment times.
Optionally, the live payment record further comprises an IMSI number. Further optionally, the live pay record further comprises a pay live platform identification.
Such as: the stored live payment records may be as shown in table two below:
watch two
| Live broadcast payment | IMSI code | Time stamp |
| 100******* | yyyy-mm-dd hh:mm:ss |
It should be noted that table two only shows the record that the live viewing user corresponding to the IMSI number paid for the live platform once.
Alternatively, the preset historical time period may be within the last month. And generating a live broadcast statistical table according to the live broadcast watching records and the live broadcast payment records of a plurality of live broadcast watching users in a month, and judging whether a certain live broadcast watching user is a target marketing user or not according to the live broadcast statistical table. Such as: the live broadcast statistical table generated according to the live broadcast viewing record and the live broadcast payment record of the live broadcast viewing user in the last month can be as shown in the following table three:
watch III
Step 207 specifically comprises the following steps:
and generating a first conditional probability value of the live broadcast watching user in a first type state and a second conditional probability value of the live broadcast watching user in a second type state according to a preset classification set.
And selecting the higher one of the first conditional probability value and the second conditional probability value as the user value of the live watching user.
And judging whether the user value is greater than a preset user value threshold value or not, and if so, judging that the live watching user is a target marketing user.
By the formula P (y)k|x)＝max{P(y1|x)，P(y2|x)，…P(yn| x) } generates the user value of the live viewing user, where P (y)k| x) is the user value of the live viewing user, x ═ a1，a2，…amIs the set of characteristic attributes of the live viewing user, amRepresenting live viewing usersThe mth feature attribute, in this embodiment, the feature attribute set of the live viewing user includes live viewing traffic, live viewing duration, and live payment times, where C ═ y1，y2，…ymThe classification set is a preset classification set, and in this embodiment, the classification set includes a high value class and a low value class, P (y)n| x) represents the conditional probability value of the live viewing user in the nth state, P (y)n| x) is calculated and generated according to a Bayesian formula. Specifically, a first conditional probability value of the live viewing user in a first type state (namely, in a low value class) and a second conditional probability value of the live viewing user in a second type state (namely, in a high value class) are calculated and generated according to a preset low value class table and a preset high value class table.
In an actual application scenario, a user value threshold may be generated according to user values of all live viewing users, such as: and designating live watching users with the first 60% of user values as target marketing users, and taking the lowest user value of all the target marketing users as a user value threshold.
And step 208, predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record.
In this embodiment, the personal information prestored in the operator network is obtained through the IMSI number corresponding to the live viewing user.
The personal information may include gender and age, and the live preference may include three categories of game category, beauty category and travel category. And respectively weighting and adding the gender and age of the live broadcast watching user, the live broadcast watching flow and the live broadcast watching time length, the live broadcast payment times and the live broadcast content type according to a weighting system to generate three total scores of three kinds of live broadcast preferences of games, beauty and tourism, and selecting the live broadcast preference corresponding to the highest total score in the three total scores as the live broadcast preference of the live broadcast watching user. The weighting system can weight the gender and age of the live broadcast watching user, the live broadcast watching flow, the live broadcast watching time length, the live broadcast payment times and the live broadcast content type according to a pre-generated statistical model.
Such as: if the live broadcast watching flow, the live broadcast watching time length and the payment times of a certain game type live broadcast watching user with the age of 20 and the gender of a man are all larger than the average value in the statistical model, the total game type score is generated to be 10 (age) +10 (gender) +30 (live broadcast watching flow) +20 (live broadcast watching time length) +20 (live broadcast payment times) +10 (game type): 100. In this embodiment, the total score is a percentage, the game category total score of the live viewing user is a full score, and the live viewing preference of the live viewing user is predicted to be a game category when the total score of other beauty categories and the total score of travel categories of the live viewing user are lower than the game category total score.
And 209, recommending products to the live watching user according to the live watching preference, the live watching record and the live paying record of the live watching user.
The recommended product may be an operator product or a product of a third party partner who cooperates with the operator. Such as: and recommending the operator cooperation package of the live broadcast platform, or recommending an operator flow card (such as a king card), or recommending a travel product/beauty product/game product to the live broadcast watching user.
Optionally, the way to recommend the product to the live viewing user may be short message, or WeChat, or a cell phone business hall.
According to the marketing method based on the live broadcast watching user, provided by the embodiment, products are recommended to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user. The method can combine live broadcast service with mobile service of an operator, excavate potential requirements and values of live broadcast watching users by analyzing behaviors of the live broadcast watching users, recommend proper communication products and information services for the live broadcast watching users, effectively promote product marketing of the operator and third-party partners of the operator, and promote service expansion of the operator and cooperation depth of the operator and the third-party partners.
Fig. 3 is a schematic structural diagram of a marketing platform based on a live viewing user according to a third embodiment of the present invention, and as shown in fig. 3, the marketing platform includes: a first judgment module 11, a prediction module 12 and a recommendation module 13.
The first judging module 11 is configured to judge whether the live viewing user is a target marketing user according to a live viewing record and a live payment record of the live viewing user within a preset historical time period.
The prediction module 12 is configured to predict a live preference of the live viewing user according to pre-acquired personal information of the live viewing user, the live viewing record, and the live payment record when it is determined that the live viewing user is the targeted marketing user.
And the recommending module 13 is used for recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user.
Further, the platform further comprises: a second judging module 14, a third judging module 15 and a generating and storing module 16.
The second determining module 14 is configured to determine whether user data meets a preset condition, where the user data includes a transport layer protocol, a target IP address, a transmission rate, and a continuous communication duration. The third judging module 15 is configured to, when it is judged that the user data meets the preset condition, judge whether the user is a live broadcast watching user according to the mirror image data packet of the user data and the user identifier corresponding to the user data. The generation storage module 16 is configured to generate a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and store the live broadcast watching record of the live broadcast watching user when it is determined that the user is the live broadcast watching user, where the live broadcast watching record includes live broadcast watching flow and live broadcast watching duration.
Further, the platform further comprises a fourth judging module 17.
The second determining module 14 is further configured to determine whether the user data includes a target IP address corresponding to the payment website. The fourth judging module 17 is configured to, when it is judged that the user data includes a target IP address corresponding to the payment website, judge whether a mirror image data packet corresponding to the target IP address includes live broadcast platform two-dimensional code information. The generation storage module 16 is further configured to store a live broadcast payment record of the live broadcast watching user when it is determined that the mirror image data packet corresponding to the target IP address corresponding to the payment website includes live broadcast platform two-dimensional code information, where the live broadcast payment record includes live broadcast payment times.
Further, the third determining module 15 specifically includes: a third generation submodule 151 and a third determination submodule 152.
The third generating sub-module 151 is configured to generate a picture to be identified according to the mirror image data packet of the user data. The third determining submodule 152 is configured to determine whether the picture to be recognized includes a live broadcast identifier, and if the picture to be recognized includes the live broadcast identifier, determine that the user is a live broadcast watching user, where the live broadcast identifier includes a live broadcast rectangular frame and a live broadcast room identifier.
Further, the first determining module 11 specifically includes: a first generation submodule 111, a first selection submodule 112 and a first judgment submodule 113.
The first generation submodule 111 is configured to generate a first conditional probability value of the live viewing user in a first type state and a second conditional probability value of the live viewing user in a second type state according to a preset classification set. The first selecting submodule 112 is configured to select a higher one of the first conditional probability value and the second conditional probability value as the user value of the live viewing user. The first determining sub-module 113 is configured to determine whether the user value is greater than a preset user value threshold, and if it is determined that the user value is greater than the preset user value threshold, determine that the live viewing user is a target marketing user.
The marketing platform based on the live viewing user provided by the third embodiment is used for realizing the marketing method based on the live viewing user provided by the first embodiment or the second embodiment.
It should be noted that the intelligent base station in the second embodiment carries the function of the second determination module in this embodiment, and the high-value user list device in the second embodiment carries the functions of the first determination module, the third determination module and the fourth determination module in this embodiment.
According to the marketing platform based on the live broadcast watching user, the recommending module recommends products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user. The platform can combine live broadcast services with the mobile services of operators and promote product marketing of the operators and their third-party partners.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (8)
1. A marketing method based on a live viewing user is characterized by comprising the following steps:
judging whether the live broadcast watching user is a target marketing user or not according to the live broadcast watching record and the live broadcast payment record of the live broadcast watching user in a preset historical time period;
if the live broadcast watching user is judged to be the target marketing user, predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record;
recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user;
the judging whether the live broadcast watching user is a target marketing user according to the live broadcast watching record and the live broadcast payment record of the live broadcast watching user in the preset historical time period specifically comprises the following steps:
generating a first conditional probability value of the live broadcast watching user in a first type state and a second conditional probability value of the live broadcast watching user in a second type state according to a preset classification set;
selecting the higher one of the first conditional probability value and the second conditional probability value as the user value of the live broadcast watching user; the user value is determined according to a formula P (yk | x) ═ max { P (y1| x), P (y2| x), … P (yn | x) }, wherein P (yk | x) is the user value of the live viewing user, x ═ { a1, a2, … am } is a set of characteristic attributes of the live viewing user, am is the mth characteristic attribute of the live viewing user, the set of characteristic attributes of the live viewing user comprises live viewing flow, live viewing duration and live viewing payment times, C ═ y1, y2, … ym } is a preset classification set, the classification set comprises a high value class and a low value class, P (yn | x) represents a conditional probability value of the live viewing user in the nth class state, and P (yn | x) is calculated according to a bayesian formula;
judging whether the user value is greater than a preset user value threshold value or not, and if so, judging that the live broadcast watching user is a target marketing user;
the predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record specifically comprises the following steps:
and respectively weighting and adding the personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record according to a weighting system to generate a total score, and predicting the live broadcast preference of the live broadcast watching user according to the total score.
2. The marketing method based on the live viewing user according to claim 1, wherein before the determining whether the live viewing user is the target marketing user according to the live viewing record and the live payment record of the live viewing user in the preset historical time period, the marketing method further comprises:
judging whether user data meet preset conditions or not, wherein the user data comprise a transport layer protocol, a target IP address, a transmission rate and continuous communication time;
if the user data meet the preset conditions, judging whether the user is a live broadcast watching user or not according to a mirror image data packet of the user data and a user identifier corresponding to the user data;
and if the user is judged to be a live broadcast watching user, generating a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and storing the live broadcast watching record of the live broadcast watching user, wherein the live broadcast watching record comprises live broadcast watching flow and live broadcast watching duration.
3. The marketing method based on the live viewing user according to claim 2, wherein before the determining whether the live viewing user is the target marketing user according to the live viewing record and the live payment record of the live viewing user in the preset historical time period, the marketing method further comprises:
judging whether the user data comprises a target IP address corresponding to the payment website;
if the user data comprises a target IP address corresponding to the payment website, judging whether a mirror image data packet corresponding to the target IP address comprises two-dimension code information of a live broadcast platform;
and if the mirror image data packet corresponding to the target IP address corresponding to the payment website comprises live broadcast platform two-dimension code information, storing live broadcast payment records of the live broadcast watching user, wherein the live broadcast payment records comprise live broadcast payment times.
4. The marketing method based on the live viewing user according to claim 2, wherein the determining whether the user is a live viewing user according to the mirror image data package of the user data and the user identifier corresponding to the user data specifically includes:
generating a picture to be identified according to the mirror image data packet of the user data;
and judging whether the picture to be recognized comprises a live broadcast identification or not, if so, judging that the picture to be recognized comprises the live broadcast identification, and judging that the user is a live broadcast watching user, wherein the live broadcast identification comprises a live broadcast rectangular frame and a live broadcast room identification.
5. A marketing platform based on live viewing users, comprising:
the system comprises a first judging module, a second judging module and a third judging module, wherein the first judging module is used for judging whether a live watching user is a target marketing user or not according to a live watching record and a live paying record of the live watching user in a preset historical time period;
the prediction module is used for predicting the live broadcast preference of the live broadcast watching user according to the pre-acquired personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record when the live broadcast watching user is judged to be the target marketing user;
the recommendation module is used for recommending products to the live broadcast watching user according to the live broadcast preference, the live broadcast watching record and the live broadcast payment record of the live broadcast watching user;
the first judging module specifically comprises:
the first generation submodule is used for generating a first conditional probability value of the live broadcast watching user in a first type state and a second conditional probability value of the live broadcast watching user in a second type state according to a preset classification set;
the first selection submodule is used for selecting the higher one of the first conditional probability value and the second conditional probability value as the user value of the live broadcast watching user; the user value is determined according to a formula P (yk | x) ═ max { P (y1| x), P (y2| x), … P (yn | x) }, wherein P (yk | x) is the user value of the live viewing user, x ═ { a1, a2, … am } is a set of characteristic attributes of the live viewing user, am is the mth characteristic attribute of the live viewing user, the set of characteristic attributes of the live viewing user comprises live viewing flow, live viewing duration and live viewing payment times, C ═ y1, y2, … ym } is a preset classification set, the classification set comprises a high value class and a low value class, P (yn | x) represents a conditional probability value of the live viewing user in the nth class state, and P (yn | x) is calculated according to a bayesian formula;
the first judgment submodule is used for judging whether the user value is greater than a preset user value threshold value or not, and judging that the live broadcast watching user is a target marketing user if the user value is greater than the preset user value threshold value;
the prediction module is specifically configured to:
and respectively weighting and adding the personal information of the live broadcast watching user, the live broadcast watching record and the live broadcast payment record according to a weighting system to generate a total score, and predicting the live broadcast preference of the live broadcast watching user according to the total score.
6. The live viewing user-based marketing platform of claim 5, further comprising:
the second judgment module is used for judging whether user data meet preset conditions or not, wherein the user data comprise a transport layer protocol, a target IP address, a transmission rate and continuous communication time;
the third judgment module is used for judging whether the user is a live broadcast watching user or not according to the mirror image data packet of the user data and the user identification corresponding to the user data when the user data is judged to meet the preset condition;
and the generation and storage module is used for generating a live broadcast watching record of the live broadcast watching user according to the mirror image data packet of the user data and storing the live broadcast watching record of the live broadcast watching user when the user is judged to be the live broadcast watching user, wherein the live broadcast watching record comprises live broadcast watching flow and live broadcast watching duration.
7. The live-viewing user-based marketing platform of claim 6, further comprising a fourth determination module;
the second judgment module is also used for judging whether the user data comprises a target IP address corresponding to the payment website;
the fourth judging module is used for judging whether a mirror image data packet corresponding to a target IP address comprises two-dimension code information of a live broadcast platform or not when the user data is judged to comprise the target IP address corresponding to the payment website;
and the generation and storage module is also used for storing the live broadcast payment record of the live broadcast watching user when judging that the mirror image data packet corresponding to the target IP address corresponding to the payment website comprises live broadcast platform two-dimensional code information, wherein the live broadcast payment record comprises live broadcast payment times.
8. The marketing platform based on live viewing users of claim 6, wherein the third determination module specifically comprises:
the third generation submodule is used for generating a picture to be identified according to the mirror image data packet of the user data;
and the third judgment submodule is used for judging whether the picture to be recognized comprises a live broadcast identification or not, if so, judging that the picture to be recognized comprises the live broadcast identification, and judging that the user is a live broadcast watching user, wherein the live broadcast identification comprises a live broadcast rectangular frame and a live broadcast room identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810871105.2A CN109121006B (en) | 2018-08-02 | 2018-08-02 | Marketing method and platform based on live broadcast watching user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810871105.2A CN109121006B (en) | 2018-08-02 | 2018-08-02 | Marketing method and platform based on live broadcast watching user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109121006A CN109121006A (en) | 2019-01-01 |
| CN109121006B true CN109121006B (en) | 2021-02-02 |
Family
ID=64851722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810871105.2A Active CN109121006B (en) | 2018-08-02 | 2018-08-02 | Marketing method and platform based on live broadcast watching user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109121006B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110996110B (en) * | 2019-12-02 | 2022-02-18 | 深圳市云积分科技有限公司 | Commodity adjusting method and device in live broadcast process |
| CN113313506B (en) * | 2020-02-27 | 2023-04-07 | 中国电信股份有限公司 | Method and system for realizing user management of operator |
| CN111918076A (en) * | 2020-07-20 | 2020-11-10 | 北京达佳互联信息技术有限公司 | Payment method, device, server, terminal and storage medium for live video |
| CN112702631A (en) * | 2020-11-27 | 2021-04-23 | 苏州宇讯科技信息有限公司 | Operation management system and method for network training |
| CN116415977B (en) * | 2023-03-24 | 2023-10-03 | 广州市原象信息科技有限公司 | Target crowd consumption data analysis method and system for live broadcasting room |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385601A (en) * | 2010-09-03 | 2012-03-21 | 阿里巴巴集团控股有限公司 | Product information recommendation method and system |
| CN102681999A (en) * | 2011-03-08 | 2012-09-19 | 阿里巴巴集团控股有限公司 | Method and device for collecting and sending user action information |
| CN105160008A (en) * | 2015-09-21 | 2015-12-16 | 合一网络技术(北京)有限公司 | Method and device for locating suggested users |
| CN105955994A (en) * | 2016-04-19 | 2016-09-21 | 乐视控股（北京）有限公司 | Information recommend method and information recommend device based on gallery |
| CN106326441A (en) * | 2016-08-26 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN106612461A (en) * | 2015-10-23 | 2017-05-03 | 中兴通讯股份有限公司 | A recommendation method, apparatus and system for a product package |
| CN107016589A (en) * | 2016-08-10 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The determination method and device of recommended products |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7062510B1 (en) * | 1999-12-02 | 2006-06-13 | Prime Research Alliance E., Inc. | Consumer profiling and advertisement selection system |
| US8732739B2 (en) * | 2011-07-18 | 2014-05-20 | Viggle Inc. | System and method for tracking and rewarding media and entertainment usage including substantially real time rewards |
| US8966525B2 (en) * | 2011-11-08 | 2015-02-24 | Verizon Patent And Licensing Inc. | Contextual information between television and user device |
-
2018
- 2018-08-02 CN CN201810871105.2A patent/CN109121006B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385601A (en) * | 2010-09-03 | 2012-03-21 | 阿里巴巴集团控股有限公司 | Product information recommendation method and system |
| CN102681999A (en) * | 2011-03-08 | 2012-09-19 | 阿里巴巴集团控股有限公司 | Method and device for collecting and sending user action information |
| CN105160008A (en) * | 2015-09-21 | 2015-12-16 | 合一网络技术(北京)有限公司 | Method and device for locating suggested users |
| CN106612461A (en) * | 2015-10-23 | 2017-05-03 | 中兴通讯股份有限公司 | A recommendation method, apparatus and system for a product package |
| CN105955994A (en) * | 2016-04-19 | 2016-09-21 | 乐视控股（北京）有限公司 | Information recommend method and information recommend device based on gallery |
| CN107016589A (en) * | 2016-08-10 | 2017-08-04 | 阿里巴巴集团控股有限公司 | The determination method and device of recommended products |
| CN106326441A (en) * | 2016-08-26 | 2017-01-11 | 乐视控股（北京）有限公司 | Information recommendation method and device |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109121006A (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109121006B (en) | Marketing method and platform based on live broadcast watching user | |
| US11507867B2 (en) | Systems and methods for managing interactions between an individual and an entity | |
| US8626818B2 (en) | System and method for generating user contexts for targeted advertising | |
| US7921036B1 (en) | Method and system for dynamically targeting content based on automatic demographics and behavior analysis | |
| CN111741336B (en) | Video content recommendation method, device, equipment and storage medium | |
| RU2482539C2 (en) | System and method of sending information over mobile communication network | |
| US20030208754A1 (en) | System and method for selective transmission of multimedia based on subscriber behavioral model | |
| US20100223641A1 (en) | System and method for predicting the optimum delivery of multimedia content based on human behavior patterns | |
| US20090048905A1 (en) | Methods for Grouping, Targeting and Meeting Objectives for an Advertisement Campaign | |
| Molnar et al. | Cost-oriented adaptive multimedia delivery | |
| CN110362751B (en) | Service recommendation method, device, computer equipment and storage medium | |
| US20240338730A1 (en) | Methods and systems for online to offline conversion tracking an optimization | |
| CN111492664B (en) | Controlling playback of advertising content during real-time video streaming at an end-user terminal | |
| US20230410144A1 (en) | Methods and systems for automatic call routing with no caller intervention using anonymous online user behavior | |
| CN109168043B (en) | Method, equipment and system for displaying recommendation information | |
| US10755313B2 (en) | System and method for distribution of targeted content between mobile communication devices | |
| US20210142366A1 (en) | Method and system to run targeted marketing campaigns through one or more telecommunication channels | |
| Moltchanov et al. | Context-aware content sharing and casting | |
| CN117407592A (en) | Information recommendation method, equipment and computer-readable storage medium | |
| US20210194985A1 (en) | Timing content presentation based on predicted recipient mental state | |
| CN113722633A (en) | Method and device for determining message publishing strategy, electronic equipment and storage medium | |
| EP4002254A1 (en) | Interconnection method for users and data and related system | |
| Sachar | An Empirical Study on Customer Satisfaction Related to Telecommunication Services-(A Comparative Analysis of Airtel & Jio Services) | |
| Fox et al. | Online stalking of Instagram influencers. | |
| Fox et al. | Journal of Threat Assessment and Management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |