CN116757749A - Advertisement pushing effect evaluation method, system and storage medium based on big data - Google Patents
Advertisement pushing effect evaluation method, system and storage medium based on big data Download PDFInfo
- Publication number
- CN116757749A CN116757749A CN202311042162.7A CN202311042162A CN116757749A CN 116757749 A CN116757749 A CN 116757749A CN 202311042162 A CN202311042162 A CN 202311042162A CN 116757749 A CN116757749 A CN 116757749A
- Authority
- CN
- China
- Prior art keywords
- pushing
- push
- commodity
- application
- applet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000000694 effects Effects 0.000 title claims abstract description 224
- 238000011156 evaluation Methods 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000012546 transfer Methods 0.000 claims description 16
- 238000013500 data storage Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
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
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
- H04L67/306—User profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an advertisement pushing effect evaluation method, an advertisement pushing effect evaluation system and a storage medium based on big data, which relate to the technical field of advertisement pushing effect evaluation and comprise the following steps: step S1, obtaining an advertisement type of a push advertisement; s2, analyzing the applet pushing feedback to obtain an applet pushing effect; s3, analyzing the application pushing feedback to obtain an application pushing effect; s4, analyzing commodity pushing feedback to obtain commodity pushing effects; s5, analyzing age groups of best pushing audiences with different advertisement types; the invention is used for solving the problems that the existing advertisement pushing effect evaluation technology lacks special analysis on advertisements of different types and analysis on the ages of advertisement audiences, so that the pushing effect evaluation result is not accurate enough and the advertisements are difficult to be targeted.
Description
Technical Field
The invention relates to the technical field of advertisement pushing effect evaluation, in particular to an advertisement pushing effect evaluation method, an advertisement pushing effect evaluation system and a storage medium based on big data.
Background
The advertisement pushing effect evaluation technology is a technology for evaluating and analyzing advertisement pushing effects through a data analysis and statistics method, and can be used for measuring the advertisement pushing effects and benefits through collecting and processing data generated in the advertisement putting process, so that advertisers and advertisement platforms can be helped to know how the advertisement putting effects are, the advertisement putting strategy is optimized, and the advertisement effects and the return on investment rate are improved.
The prior art of evaluating the pushing effect of the advertisement generally performs unified analysis on the pushing advertisements in the platform, uses the same data type to analyze the pushing effect of the pushing advertisements of different advertisement types, ignores the analysis of factors which play a decisive role on the pushing effect in the pushing advertisements of different advertisement types, and causes that the pushing effect obtained by analysis is inconsistent with the reality, for example, in the application patent with application publication number of CN113327140A, an intelligent analysis management system for the pushing effect of the video advertisement based on big data analysis is disclosed.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides the advertisement pushing effect evaluation method based on big data, which can perform special analysis on the pushing advertisements of different advertisement types, respectively select data with decisive factors for evaluation, analyze the best pushing audience of the advertisement types aiming at the different advertisement types, find the best audience age, thereby realizing the directional delivery and solving the problems that the existing advertisement pushing effect evaluation technology lacks special analysis on the advertisements of different types and analysis on the advertisement audience ages, and leads to inaccurate pushing effect evaluation results and difficulty in carrying out the directional delivery on the advertisements.
In order to achieve the above object, in a first aspect, the present invention provides an advertisement push effect evaluation method based on big data, including the steps of:
step S1, obtaining advertisement types of push advertisements, wherein the advertisement types comprise small program game advertisements, application download advertisements and commodity push advertisements;
step S2, feedback data of a user after the operation is performed on the applet game advertisement is obtained, the feedback data is marked as applet push feedback, the applet push feedback is analyzed, and the push effect of the applet game advertisement is obtained, and the feedback data is marked as applet push effect;
Step S3, feedback data after the user executes operation on the application download advertisement is obtained, the feedback data is marked as application push feedback, the application push feedback is analyzed, a push effect of the application download advertisement is obtained, and the feedback data is marked as application push effect;
step S4, feedback data of a user after operation is performed on the commodity pushing advertisement is obtained, the feedback data is marked as commodity pushing feedback, analysis is performed on the commodity pushing feedback, a pushing effect of the commodity pushing advertisement is obtained, and the feedback data is marked as a commodity pushing effect;
and S5, acquiring the ages of the users, and analyzing the age groups of the best pushing audiences with different advertisement types.
Further, the step S1 includes the following sub-steps:
step S101, establishing data connection with a short video platform;
step S102, the advertisement type of the push advertisement is obtained.
Further, the step S2 includes the following sub-steps:
step S201, analyzing the applet game advertisement to obtain applet pushing feedback of a user, wherein the applet pushing feedback comprises applet click quantity, applet forwarding quantity and applet exposure quantity;
step S202, a game duration database is read, the applet game duration in each record is sequentially obtained, the applet game duration is compared with a first game duration threshold value, and if the applet game duration is smaller than or equal to the first game duration threshold value, a low-efficiency push signal is output; if the small program game time length is greater than the first game time length threshold value, outputting a high-efficiency push signal; recording and outputting the quantity of the low-efficiency push signals and the high-efficiency push signals, and marking the quantity as the low-efficiency push number and the high-efficiency push number respectively;
And step S203, analyzing the applet exposure amount, the applet click amount, the applet forwarding amount, the inefficient pushing number and the efficient pushing number to obtain the applet pushing effect.
Further, the step S203 includes the following sub-steps:
step S2031, analyzing and calculating the applet exposure, the applet click quantity, the applet forwarding quantity, the low-efficiency push number and the high-efficiency push number through an applet push reference value calculation formula to obtain an applet push reference value;
the applet push reference value calculation formula is configured as:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Gpv is an applet push reference value, glp is a low-efficiency push number, ghp is a high-efficiency push number, gf is an applet transfer amount, ge is an applet exposure amount, gc is an applet click amount, α1 is a low-efficiency push coefficient, β1 is a high-efficiency push coefficient, γ1 is an applet transfer coefficient, α1, β1 and γ1 are constants and are larger than zero;
step S2032, comparing the applet push reference value with the first push reference threshold and the second push reference threshold, respectively, and outputting an applet low push effect signal if the applet push reference value is less than or equal to the first push reference threshold; if the small program pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value, outputting a pushing effect signal in the small program; if the applet push reference value is larger than the second push reference threshold value, outputting an applet high push effect signal;
Step S2033, if the applet low push effect signal is output, determining that the applet push effect is a three-level push effect; if the pushing effect signal in the applet is output, judging that the pushing effect of the applet is a secondary pushing effect; if the small program high pushing effect signal is output, the small program pushing effect is judged to be the first-level pushing effect.
Further, the step S3 includes the following sub-steps:
step S301, analyzing an application download advertisement to obtain application push feedback of a user, wherein the application push feedback comprises application advertisement click quantity, application forwarding quantity, application downloading quantity and application exposure quantity;
step S302, after the user downloads the application, acquiring a download date of the user, generating a unique identification code for the user and inputting the unique identification code into a user identification code database, and when the application is detected to be uninstalled, acquiring an uninstalled date, acquiring the unique identification code of the user for uninstalling the application, and marking the unique identification code as an uninstalled identification code;
step S303, searching and comparing the unloading identification code with a user identification code database to obtain the corresponding downloading date of the user, subtracting the downloading date from the unloading date, converting the date into a time length to obtain the use time length of the user, comparing the use time length with a first time length threshold value, and outputting a use time too short signal if the use time length is less than or equal to the first time length threshold value; outputting a normal use time signal if the use time is longer than the first time threshold;
Step S304, if the using time is too short, recording one negative pushing, obtaining the number of negative pushing, and marking as the number of negative pushing;
step S305, analyzing the application push feedback and the negative push number to obtain an application push effect.
Further, the step S305 includes the following sub-steps:
step S3051, calculating an application push feedback and a negative push number by applying a push reference value calculation formula to obtain an application push reference value;
the application push reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Apv is an application push reference value, D is an application download amount, np is a negative push number, af is an application transfer amount, ae is an application exposure amount, ac is an application click amount, α2 is an effective download coefficient, β2 is a download scaling factor, γ2 is an application transfer coefficient, and α2, β2 and γ2 are constants and are larger than zero;
step S3052, comparing the application push reference value with a first push reference threshold and a second push reference threshold respectively, and outputting an application low push effect signal if the application push reference value is smaller than or equal to the first push reference threshold; if the application push reference value is larger than the first push reference threshold value and smaller than or equal to the second push reference threshold value, outputting a push effect signal in the application; outputting an application high push effect signal if the application push reference value is larger than the second push reference threshold value;
Step S3053, if the low pushing effect signal is output, determining that the pushing effect is three-level pushing effect; if the pushing effect signal in the application is output, judging that the pushing effect of the application is a secondary pushing effect; if the application high push effect signal is output, the application push effect is judged to be the first-stage push effect.
Further, the step S4 includes the following sub-steps:
step S401, analyzing commodity pushing advertisements to obtain commodity pushing feedback, wherein the commodity pushing feedback comprises commodity exposure, commodity advertisement click quantity, commodity forwarding quantity, commodity purchasing quantity and commodity returning quantity;
step S402, after checking the commodity pushing advertisement, the user detects whether the user adds the commodity into a shopping cart or sends consultation information to customer service, if so, an effective commodity pushing signal is output; if not, outputting an invalid commodity pushing signal; recording the number of times of outputting effective commodity pushing signals, and marking the number as the effective commodity pushing number;
step S403, analyzing the commodity pushing feedback and the effective commodity pushing number to obtain a commodity pushing effect.
Further, the step S403 includes the following sub-steps:
step S4031, calculating commodity pushing feedback and effective commodity pushing number through a commodity pushing reference value calculation formula to obtain a commodity pushing reference value;
The commodity pushing reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ce is commodity exposure, cc is commodity click quantity, cf is commodity transfer quantity, cb is commodity purchase quantity, cr is commodity withdrawal quantity, cp is effective commodity pushing number, alpha 3 is effective commodity pushing coefficient, beta 3 is effective commodity purchase coefficient, gamma 3 is effective commodity transfer coefficient, alpha 3, beta 3 and gamma 3 are constants and are larger than zero;
step S4032, comparing the commodity pushing reference value with a first pushing reference threshold and a second pushing reference threshold respectively, and outputting a commodity low pushing effect signal if the commodity pushing reference value is smaller than or equal to the first pushing reference threshold; outputting a pushing effect signal in the commodity if the commodity pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value; if the commodity pushing reference value is larger than the second pushing reference threshold value, outputting a commodity high pushing effect signal;
step S4033, if the commodity low pushing effect signal is output, judging that the commodity pushing effect is three-level pushing effect; if the pushing effect signal in the commodity is output, judging that the commodity pushing effect is a secondary pushing effect; if the commodity high pushing effect signal is output, the commodity pushing effect is judged to be the first-stage pushing effect.
Further, the step S5 includes the following sub-steps:
step S501, obtaining user ages, establishing a push audience database, and recording the user ages of outputting high-efficiency push signals, outputting normal use time signals and outputting effective commodity push signals, wherein the user ages are respectively marked as applet audience ages, application audience ages and commodity audience ages;
step S502, classifying the ages of the users, and dividing the ages of the users into teenagers, young, middle-aged and elderly;
step S503, classifying the ages of the small program audience, the applied audience age and the commodity audience age, recording the proportion of the number of records of the ages of the small program audience in the teenager, the young age, the middle-aged and the elderly, respectively marking the proportion of the small program audience, the proportion of the small program young audience, the proportion of the small program middle-aged audience and the proportion of the small program elderly audience, and integrating the proportion of the small program audience;
step S504, searching the maximum value in the audience proportion of the small program, and marking the age of the small program audience corresponding to the maximum value as the best pushing audience of the small program;
step S505, the proportion of the recorded number of the application audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages is marked as the application teenager audience proportion, the application young audience proportion, the application middle-aged audience proportion and the application elderly audience proportion respectively, and the integration marks as the application audience proportion;
Step S506, searching the maximum value in the application audience proportion, and marking the application audience age corresponding to the maximum value as the application best pushing audience;
step S507, recording the proportion of the recorded quantity of the commodity audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages, respectively marking the proportion as the commodity teenagers, the commodity young audience proportion, the commodity middle-aged audience proportion and the commodity elderly audience proportion, and integrating the proportion as the commodity audience proportion;
step S508, searching the maximum value in the commodity audience proportion, and marking the commodity audience age corresponding to the maximum value as the commodity best pushing audience.
In a second aspect, the invention provides a system of the advertisement pushing effect evaluation method based on big data, which comprises a platform data acquisition module, a pushing effect analysis module and a data storage module; the platform data acquisition module and the data storage module are respectively connected with the pushing effect analysis module in a data mode;
the platform data acquisition module comprises a push advertisement acquisition unit and a user data acquisition unit; the push advertisement acquisition unit is used for acquiring advertisement types, applet push feedback, application push feedback and commodity push feedback of push advertisements; the user data acquisition unit is used for acquiring the age of a user;
The pushing effect analysis module comprises an applet pushing analysis unit, an application pushing analysis unit, a commodity pushing analysis unit and a pushing audience analysis unit; the applet pushing analysis unit is used for analyzing applet pushing feedback to obtain an applet pushing effect; the application pushing analysis unit is used for analyzing application pushing feedback to obtain an application pushing effect; the commodity pushing analysis unit is used for analyzing commodity pushing feedback to obtain commodity pushing effects; the push audience analysis unit is used for analyzing the age of the user, the pushing feedback of the small program, the pushing feedback of the application and the pushing feedback of the commodity, and obtaining the age groups of the optimal push audiences with different advertisement types;
the data storage module is used for storing user ages, applet pushing feedback, application pushing feedback and commodity pushing feedback.
In a third aspect, the application provides an electronic device comprising a processor and a memory storing computer readable instructions which, when executed by the processor, perform the steps of the method as described above.
In a fourth aspect, the application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above.
The invention has the beneficial effects that: according to the invention, the advertisement types of the push advertisements are obtained, and different advertisement types in the same platform are analyzed to judge the push effect, so that the method has the advantages that a targeted analysis method can be designed aiming at different advertisement types, the push effect is analyzed in a deeper layer, and the rationality and the accuracy of the push effect analysis are improved;
according to the method, the device and the system, the applet game duration of the user is monitored, whether the applet game duration meets the expectations is judged, the applet push reference value is calculated according to the analysis result and the applet push feedback, and the applet push effect is finally obtained through analysis;
the invention detects whether the user downloads the application or not, sets the unique code for the user, records the download date, searches the corresponding unique code to acquire the download date after detecting the user uninstallation of the application, and calculates the download date and the uninstallation date to acquire the use time of the user;
According to the invention, the user ages are obtained, the user ages are grouped, and the pushing effects of different advertisement types in different audience ages are respectively analyzed, so that the optimal audience ages of different advertisement types are obtained.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of the steps of the method of the present invention;
FIG. 2 is a schematic block diagram of the system of the present invention;
FIG. 3 is a schematic diagram of an applet best-push audience analysis of the present invention;
fig. 4 is a connection block diagram of an electronic device in a third embodiment of the present invention;
in the figure: 60. an electronic device; 601. a processor; 602. a memory.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Example 1
According to the advertisement pushing effect evaluation method based on big data, special analysis can be carried out on pushing advertisements of different advertisement types, data with decisive factors are selected for evaluation, and aiming at different advertisement types, the best pushing audience is analyzed, and the best audience age is found, so that the problem that the existing advertisement pushing effect evaluation technology is insufficient in special analysis on advertisements of different types and analysis on advertisement audience ages, and therefore the pushing effect evaluation result is inaccurate and the advertisement is difficult to directionally put is solved.
Referring to fig. 1, the advertisement pushing effect evaluation method based on big data includes steps S1, S2, S3, S4 and S5;
step S1, acquiring advertisement types of push advertisements, wherein the advertisement types comprise small program game advertisements, application download advertisements and commodity push advertisements; step S1 comprises the following sub-steps:
step S101, establishing data connection with a short video platform;
step S102, obtaining the advertisement type of the push advertisement;
in specific implementation, the advertisement type of the push advertisement 1 is obtained as an applet game advertisement, the advertisement type of the push advertisement 2 is an application download advertisement, and the advertisement type of the push advertisement 3 is a commodity push advertisement.
Step S2, feedback data of a user after the operation is performed on the applet game advertisement is obtained, the feedback data is marked as applet push feedback, the applet push feedback is analyzed, and the push effect of the applet game advertisement is obtained, and the feedback data is marked as applet push effect; step S2 comprises the following sub-steps:
step S201, analyzing the applet game advertisement to obtain applet pushing feedback of a user, wherein the applet pushing feedback comprises applet click quantity, applet forwarding quantity and applet exposure quantity; the small program exposure is specifically the pushing times of the small program, and the pushing times of the small program can be obtained from a short video platform;
step S202, a game duration database is read, the applet game duration in each record is sequentially obtained, the applet game duration is compared with a first game duration threshold value, and if the applet game duration is smaller than or equal to the first game duration threshold value, a low-efficiency push signal is output; if the small program game time length is greater than the first game time length threshold value, outputting a high-efficiency push signal; recording and outputting the quantity of the low-efficiency push signals and the high-efficiency push signals, and marking the quantity as the low-efficiency push number and the high-efficiency push number respectively;
In the implementation, the applet push feedback is recorded in a short video platform background database, and the first game duration threshold is set to be 5min; the obtained small program click quantity is 62204, the small program forwarding quantity is 9821, and the small program exposure quantity is 204834; reading a game duration database, acquiring the duration of the applet game to be 3min, and comparing to acquire that the duration of the applet game is smaller than a first game duration threshold value, and outputting a low-efficiency push signal; analyzing all data in the game duration database, and counting to obtain a low-efficiency push number 38648 and a high-efficiency push number 23556;
step S203, analyzing the applet exposure, applet click quantity, applet forwarding quantity, low-efficiency pushing number and high-efficiency pushing number to obtain applet pushing effect;
step S203 includes the following sub-steps:
step S2031, analyzing and calculating the applet exposure, the applet click quantity, the applet forwarding quantity, the low-efficiency push number and the high-efficiency push number through an applet push reference value calculation formula to obtain an applet push reference value;
the applet push reference value calculation formula is configured as:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Gpv is an applet push reference value, glp is a low-efficiency push number, ghp is a high-efficiency push number, gf is an applet transfer amount, ge is an applet exposure amount, gc is an applet click amount, α1 is a low-efficiency push coefficient, β1 is a high-efficiency push coefficient, γ1 is an applet transfer coefficient, α1, β1 and γ1 are constants and are larger than zero;
Step S2032, comparing the applet push reference value with the first push reference threshold and the second push reference threshold, respectively, and outputting an applet low push effect signal if the applet push reference value is less than or equal to the first push reference threshold; if the small program pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value, outputting a pushing effect signal in the small program; if the applet push reference value is larger than the second push reference threshold value, outputting an applet high push effect signal;
step S2033, if the applet low push effect signal is output, determining that the applet push effect is a three-level push effect; if the pushing effect signal in the applet is output, judging that the pushing effect of the applet is a secondary pushing effect; if the small program high pushing effect signal is output, judging that the small program pushing effect is a primary pushing effect;
in specific implementation, α1 is set to 1.5, β1 is set to 2, γ1 is set to 3, a first pushing reference threshold is set to 0.7, a second pushing reference threshold is set to 1, an applet pushing reference value Gpv is obtained through calculation and is 0.94, a calculation result retains two decimal places, a pushing effect signal in the applet is output through comparison, and the applet pushing effect is judged to be a secondary pushing effect; in the judging result, the third-level pushing effect does not reach the expected pushing effect standard, the second-level pushing effect reaches the expected pushing effect standard, and the first-level pushing effect is far beyond the expected pushing effect standard.
Step S3, feedback data after the user executes operation on the application download advertisement is obtained, the feedback data is marked as application push feedback, the application push feedback is analyzed, a push effect of the application download advertisement is obtained, and the feedback data is marked as application push effect; step S3 comprises the following sub-steps:
step S301, analyzing the application downloaded advertisements to obtain application pushing feedback of a user, wherein the application pushing feedback comprises application advertisement click quantity, application forwarding quantity, application downloading quantity and application exposure quantity; the application exposure is specifically the pushing times of the application, and the pushing times of the application can be obtained from a short video platform;
step S302, after the user downloads the application, acquiring a download date of the user, generating a unique identification code for the user and inputting the unique identification code into a user identification code database, and when the application is detected to be uninstalled, acquiring an uninstalled date, acquiring the unique identification code of the user for uninstalling the application, and marking the unique identification code as an uninstalled identification code;
step S303, searching and comparing the unloading identification code with a user identification code database to obtain the corresponding downloading date of the user, subtracting the downloading date from the unloading date, converting the date into a time length to obtain the use time length of the user, comparing the use time length with a first time length threshold value, and outputting a use time too short signal if the use time length is less than or equal to the first time length threshold value; outputting a normal use time signal if the use time is longer than the first time threshold;
Step S304, if the using time is too short, recording one negative pushing, obtaining the number of negative pushing, and marking as the number of negative pushing;
in the implementation, the application push feedback is recorded in a background database of a short video platform, a first time length threshold is set to 48 hours, the click rate of the obtained application advertisement is 58462, the application forwarding rate is 6643, the application downloading rate is 25689, and the application exposure rate is 186421; the downloading date of the user is 2023, 7, 23, 13:26, the generation rule of the unique identification code is that the unique identification code is started from 1000000000, and each user is downloaded by adding one to the unique identification code, so that the unique identification code of the user is 1000254856; detecting that a user uninstalls an application, acquiring an uninstallation date of 2023, 7 months, 24 days, 18:33, an uninstallation identification code of 1000254856, acquiring a download date of 2023, 7 months, 23 days, 13:26 of a corresponding user, calculating to obtain a using time of 29h7min, comparing the using time of 2023, 7 months, 23 days, 13:26 with a first time threshold value, outputting a using time too short signal, recording one negative pushing, and counting to obtain a negative pushing number of 2866;
step S305, analyzing the application push feedback and the negative push number to obtain an application push effect;
Step S305 includes the following sub-steps:
step S3051, calculating an application push feedback and a negative push number by applying a push reference value calculation formula to obtain an application push reference value;
the application push reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Apv is an application push reference value, D is an application download amount, np is a negative push number, af is an application transfer amount, ae is an application exposure amount, ac is an application click amount, α2 is an effective download coefficient, β2 is a download scaling factor, γ2 is an application transfer coefficient, and α2, β2 and γ2 are constants and are larger than zero;
step S3052, comparing the application push reference value with a first push reference threshold and a second push reference threshold respectively, and outputting an application low push effect signal if the application push reference value is smaller than or equal to the first push reference threshold; if the application push reference value is larger than the first push reference threshold value and smaller than or equal to the second push reference threshold value, outputting a push effect signal in the application; outputting an application high push effect signal if the application push reference value is larger than the second push reference threshold value;
step S3053, if the low pushing effect signal is output, determining that the pushing effect is three-level pushing effect; if the pushing effect signal in the application is output, judging that the pushing effect of the application is a secondary pushing effect; if the application high pushing effect signal is output, judging that the application pushing effect is a primary pushing effect;
In specific implementation, α2 is set to 2, β2 is set to 100000, γ2 is set to 10, an application push reference value is calculated to be 0.96, a calculated result is reserved in two decimal places, and by comparison, an application push reference value is obtained to be larger than a first push reference threshold and smaller than a second push reference threshold, a push effect signal in the application is output, and the application push effect is judged to be a secondary push effect.
Step S4, feedback data of a user after operation is performed on the commodity pushing advertisement is obtained, the feedback data is marked as commodity pushing feedback, analysis is performed on the commodity pushing feedback, a pushing effect of the commodity pushing advertisement is obtained, and the feedback data is marked as a commodity pushing effect; step S4 comprises the following sub-steps:
step S401, analyzing the commodity pushing advertisement to obtain commodity pushing feedback, wherein the commodity pushing feedback comprises commodity exposure, commodity advertisement click quantity, commodity forwarding quantity, commodity purchasing quantity and commodity returning quantity; the commodity exposure is specifically the pushing times of the commodity, and the pushing times of the commodity can be obtained from a short video platform;
step S402, after checking the commodity pushing advertisement, the user detects whether the user adds the commodity into a shopping cart or sends consultation information to customer service, if so, an effective commodity pushing signal is output; if not, outputting an invalid commodity pushing signal; recording the number of times of outputting effective commodity pushing signals, and marking the number as the effective commodity pushing number;
In the specific implementation, commodity pushing feedback is recorded in a background database of a short video platform, the obtained commodity exposure is 243821, the commodity advertisement click amount is 102368, the commodity forwarding amount is 23884, the commodity purchasing amount is 56972, the commodity returning amount is 6381, whether a user adds a commodity into a shopping cart or sends consultation information to customer service or not is detected by adopting a web crawler, the obtained user adds the commodity into the shopping cart, namely an effective commodity pushing signal is output, and the obtained effective commodity pushing signal is recorded to be 63724;
step S403, analyzing commodity pushing feedback and effective commodity pushing number to obtain commodity pushing effect;
step S403 includes the following sub-steps:
step S4031, calculating commodity pushing feedback and effective commodity pushing number through a commodity pushing reference value calculation formula to obtain a commodity pushing reference value;
the commodity pushing reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ce is commodity exposure, cc is commodity click quantity, cf is commodity transfer quantity, cb is commodity purchase quantity, cr is commodity withdrawal quantity, cp is effective commodity pushing number, alpha 3 is effective commodity pushing coefficient, beta 3 is effective commodity purchase coefficient, gamma 3 is effective commodity transfer coefficient, alpha 3, beta 3 and gamma 3 are constants and are larger than zero;
Step S4032, comparing the commodity pushing reference value with a first pushing reference threshold and a second pushing reference threshold respectively, and outputting a commodity low pushing effect signal if the commodity pushing reference value is smaller than or equal to the first pushing reference threshold; outputting a pushing effect signal in the commodity if the commodity pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value; if the commodity pushing reference value is larger than the second pushing reference threshold value, outputting a commodity high pushing effect signal;
step S4033, if the commodity low pushing effect signal is output, judging that the commodity pushing effect is three-level pushing effect; if the pushing effect signal in the commodity is output, judging that the commodity pushing effect is a secondary pushing effect; if the commodity high pushing effect signal is output, judging that the commodity pushing effect is a primary pushing effect;
in specific implementation, α3 is set to 1.1, β3 is set to 1.2, γ3 is set to 1.3, the calculated commodity pushing reference value Cpv is 1.15, the calculated result retains two decimal places, the commodity pushing reference value obtained through comparison is larger than the second pushing reference threshold, a commodity high pushing effect signal is output, and the commodity pushing effect is judged to be a primary pushing effect.
S5, obtaining the age of the user, and analyzing the age groups of the best pushing audiences with different advertisement types; step S5 comprises the following sub-steps:
step S501, obtaining user ages, establishing a push audience database, and recording the user ages of outputting high-efficiency push signals, outputting normal use time signals and outputting effective commodity push signals, wherein the user ages are respectively marked as applet audience ages, application audience ages and commodity audience ages;
step S502, classifying the ages of the users, and dividing the ages of the users into teenagers, young, middle-aged and elderly;
in particular implementations, the push audience database is shown in the following table:
dividing the user age of [0,16) into teenager segments, dividing the user age of [16, 30) into young segments, dividing the user age of [30, 60) into middle-aged segments, and dividing the user age of [60, 100) into elderly segments;
referring to fig. 3, step S503 is performed to classify the ages of the small program audience, the applied audience and the commercial audience, record the ratio of the number of records of the ages of the small program audience in the teenager, the young adult, the middle-aged and the elderly, and mark the ratio of the small program audience, the ratio of the small program young audience, the ratio of the small program middle-aged audience and the ratio of the small program elderly audience as the ratio of the small program audience, respectively;
Step S504, searching the maximum value in the audience proportion of the small program, and marking the age of the small program audience corresponding to the maximum value as the best pushing audience of the small program;
in the implementation, the proportion of the small program audience is recorded to be 43%, the proportion of the small program young audience is recorded to be 35%, the proportion of the small program middle-aged audience is recorded to be 18%, the proportion of the small program old audience is recorded to be 4%, the maximum value in the proportion of the small program audience is found to be 43%, namely the proportion of the small program young audience, and the age of the small program young audience is marked as the best small program pushing audience;
step S505, the proportion of the recorded number of the application audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages is marked as the application teenager audience proportion, the application young audience proportion, the application middle-aged audience proportion and the application elderly audience proportion respectively, and the integration marks as the application audience proportion;
step S506, searching the maximum value in the application audience proportion, and marking the application audience age corresponding to the maximum value as the application best pushing audience;
in the specific implementation, the audience proportion of the application teenagers is recorded to be 22%, the audience proportion of the application young people is recorded to be 13%, the audience proportion of the application middle-aged people is recorded to be 39%, the audience proportion of the application old people is recorded to be 26%, the maximum value in the audience proportion of the application middle-aged people is found to be 39%, and the age of the audience in the application middle-aged people is marked as the best pushing audience of the application;
Step S507, recording the proportion of the recorded quantity of the commodity audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages, respectively marking the proportion as the commodity teenagers, the commodity young audience proportion, the commodity middle-aged audience proportion and the commodity elderly audience proportion, and integrating the proportion as the commodity audience proportion;
step S508, searching the maximum value in the commodity audience proportion, and marking the commodity audience age corresponding to the maximum value as the commodity best pushing audience;
in the specific implementation, the proportion of commodity teenagers is recorded to be 12%, the proportion of commodity young people is recorded to be 25%, the proportion of commodity middle-aged people is recorded to be 43%, the proportion of commodity old people is recorded to be 20%, the maximum value in the proportion of commodity audience is found to be 43%, namely the proportion of commodity middle-aged people, and the age of commodity middle-aged people is marked as the best commodity pushing audience.
Example two
Referring to fig. 2, in a second aspect, the present invention provides a system for evaluating advertisement pushing effect based on big data, which includes a platform data acquisition module, a pushing effect analysis module, and a data storage module; the platform data acquisition module and the data storage module are respectively connected with the pushing effect analysis module in a data way;
The platform data acquisition module comprises a push advertisement acquisition unit and a user data acquisition unit; the push advertisement acquisition unit is used for acquiring advertisement types, applet push feedback, application push feedback and commodity push feedback of push advertisements; the user data acquisition unit is used for acquiring the age of the user;
the pushing effect analysis module comprises an applet pushing analysis unit, an application pushing analysis unit, a commodity pushing analysis unit and a pushing audience analysis unit; the applet pushing analysis unit is used for analyzing applet pushing feedback to obtain an applet pushing effect; the application pushing analysis unit is used for analyzing application pushing feedback to obtain an application pushing effect; the commodity pushing analysis unit is used for analyzing commodity pushing feedback to obtain commodity pushing effects; the pushing audience analysis unit is used for analyzing the age of the user, the pushing feedback of the small program, the pushing feedback of the application and the pushing feedback of the commodity, and obtaining the age groups of the optimal pushing audience with different advertisement types;
the data storage module is used for storing user ages, applet pushing feedback, application pushing feedback and commodity pushing feedback.
Example III
Referring to fig. 4, in a third aspect, the present application provides an electronic device 60, including a processor 601 and a memory 602, the memory 602 storing computer readable instructions which, when executed by the processor 601, perform the steps of any of the methods described above. Through the above technical solutions, the processor 601 and the memory 602 are interconnected and communicate with each other through a communication bus and/or other form of connection mechanism (not shown), the memory 602 stores a computer program executable by the processor 601, which when the electronic device 60 is running, is executed by the processor 601 to perform the method in any of the alternative implementations of the above embodiments, and to realize the following functions: acquiring the advertisement type of the push advertisement; analyzing the applet pushing feedback to obtain an applet pushing effect; analyzing the application pushing feedback to obtain an application pushing effect; analyzing commodity pushing feedback to obtain commodity pushing effect; the age group of the best pushing audience for the different advertisement types is analyzed.
Example IV
In a fourth aspect, the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the methods described above. By the above technical solution, the computer program, when executed by the processor, performs the method in any of the alternative implementations of the above embodiments to implement the following functions: acquiring the advertisement type of the push advertisement; analyzing the applet pushing feedback to obtain an applet pushing effect; analyzing the application pushing feedback to obtain an application pushing effect; analyzing commodity pushing feedback to obtain commodity pushing effect; the age group of the best pushing audience for the different advertisement types is analyzed.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein. The storage medium may be implemented by any type or combination of volatile or nonvolatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Red Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (12)
1. The advertisement pushing effect evaluation method based on big data is characterized by comprising the following steps:
step S1, obtaining advertisement types of push advertisements, wherein the advertisement types comprise small program game advertisements, application download advertisements and commodity push advertisements;
step S2, feedback data of a user after the operation is performed on the applet game advertisement is obtained, the feedback data is marked as applet push feedback, the applet push feedback is analyzed, and the push effect of the applet game advertisement is obtained, and the feedback data is marked as applet push effect;
Step S3, feedback data after the user executes operation on the application download advertisement is obtained, the feedback data is marked as application push feedback, the application push feedback is analyzed, a push effect of the application download advertisement is obtained, and the feedback data is marked as application push effect;
step S4, feedback data of a user after operation is performed on the commodity pushing advertisement is obtained, the feedback data is marked as commodity pushing feedback, analysis is performed on the commodity pushing feedback, a pushing effect of the commodity pushing advertisement is obtained, and the feedback data is marked as a commodity pushing effect;
and S5, acquiring the ages of the users, and analyzing the age groups of the best pushing audiences with different advertisement types.
2. The method for evaluating the pushing effect of advertisement based on big data according to claim 1, wherein the step S1 comprises the following sub-steps:
step S101, establishing data connection with a short video platform;
step S102, the advertisement type of the push advertisement is obtained.
3. The method for evaluating the pushing effect of advertisement based on big data according to claim 2, wherein the step S2 comprises the following sub-steps:
step S201, analyzing the applet game advertisement to obtain applet pushing feedback of a user, wherein the applet pushing feedback comprises applet click quantity, applet forwarding quantity and applet exposure quantity;
Step S202, a game duration database is read, the applet game duration in each record is sequentially obtained, the applet game duration is compared with a first game duration threshold value, and if the applet game duration is smaller than or equal to the first game duration threshold value, a low-efficiency push signal is output; if the small program game time length is greater than the first game time length threshold value, outputting a high-efficiency push signal; recording and outputting the quantity of the low-efficiency push signals and the high-efficiency push signals, and marking the quantity as the low-efficiency push number and the high-efficiency push number respectively;
and step S203, analyzing the applet exposure amount, the applet click amount, the applet forwarding amount, the inefficient pushing number and the efficient pushing number to obtain the applet pushing effect.
4. The advertisement push effect evaluation method based on big data as set forth in claim 3, wherein the step S203 includes the sub-steps of:
step S2031, analyzing and calculating the applet exposure, the applet click quantity, the applet forwarding quantity, the low-efficiency push number and the high-efficiency push number through an applet push reference value calculation formula to obtain an applet push reference value;
the applet push reference value calculation formula is configured as: The method comprises the steps of carrying out a first treatment on the surface of the Wherein Gpv is the applet push reference, and Glp is lowThe effective pushing number Ghp is the high-efficiency pushing number, gf is the applet forwarding amount, ge is the applet exposure amount, gc is the applet click amount, α1 is the low-efficiency pushing coefficient, β1 is the high-efficiency pushing coefficient, γ1 is the applet forwarding coefficient, α1, β1 and γ1 are constants and larger than zero;
step S2032, comparing the applet push reference value with the first push reference threshold and the second push reference threshold, respectively, and outputting an applet low push effect signal if the applet push reference value is less than or equal to the first push reference threshold; if the small program pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value, outputting a pushing effect signal in the small program; if the applet push reference value is larger than the second push reference threshold value, outputting an applet high push effect signal;
step S2033, if the applet low push effect signal is output, determining that the applet push effect is a three-level push effect; if the pushing effect signal in the applet is output, judging that the pushing effect of the applet is a secondary pushing effect; if the small program high pushing effect signal is output, the small program pushing effect is judged to be the first-level pushing effect.
5. The method for evaluating the pushing effect of advertisement based on big data according to claim 4, wherein the step S3 comprises the following sub-steps:
step S301, analyzing an application download advertisement to obtain application push feedback of a user, wherein the application push feedback comprises application advertisement click quantity, application forwarding quantity, application downloading quantity and application exposure quantity;
step S302, after the user downloads the application, acquiring a download date of the user, generating a unique identification code for the user and inputting the unique identification code into a user identification code database, and when the application is detected to be uninstalled, acquiring an uninstalled date, acquiring the unique identification code of the user for uninstalling the application, and marking the unique identification code as an uninstalled identification code;
step S303, searching and comparing the unloading identification code with a user identification code database to obtain the corresponding downloading date of the user, subtracting the downloading date from the unloading date, converting the date into a time length to obtain the use time length of the user, comparing the use time length with a first time length threshold value, and outputting a use time too short signal if the use time length is less than or equal to the first time length threshold value; outputting a normal use time signal if the use time is longer than the first time threshold;
Step S304, if the using time is too short, recording one negative pushing, obtaining the number of negative pushing, and marking as the number of negative pushing;
step S305, analyzing the application push feedback and the negative push number to obtain an application push effect.
6. The method for evaluating the pushing effect of advertisement based on big data as set forth in claim 5, wherein said step S305 comprises the sub-steps of:
step S3051, calculating an application push feedback and a negative push number by applying a push reference value calculation formula to obtain an application push reference value;
the application push reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Apv is an application push reference value, D is an application download amount, np is a negative push number, af is an application transfer amount, ae is an application exposure amount, ac is an application click amount, α2 is an effective download coefficient, β2 is a download scaling factor, γ2 is an application transfer coefficient, and α2, β2 and γ2 are constants and are larger than zero;
step S3052, comparing the application push reference value with a first push reference threshold and a second push reference threshold respectively, and outputting an application low push effect signal if the application push reference value is smaller than or equal to the first push reference threshold; if the application push reference value is larger than the first push reference threshold value and smaller than or equal to the second push reference threshold value, outputting a push effect signal in the application; outputting an application high push effect signal if the application push reference value is larger than the second push reference threshold value;
Step S3053, if the low pushing effect signal is output, determining that the pushing effect is three-level pushing effect; if the pushing effect signal in the application is output, judging that the pushing effect of the application is a secondary pushing effect; if the application high push effect signal is output, the application push effect is judged to be the first-stage push effect.
7. The method for evaluating the pushing effect of advertisement based on big data according to claim 6, wherein the step S4 comprises the following sub-steps:
step S401, analyzing commodity pushing advertisements to obtain commodity pushing feedback, wherein the commodity pushing feedback comprises commodity exposure, commodity advertisement click quantity, commodity forwarding quantity, commodity purchasing quantity and commodity returning quantity;
step S402, after checking the commodity pushing advertisement, the user detects whether the user adds the commodity into a shopping cart or sends consultation information to customer service, if so, an effective commodity pushing signal is output; if not, outputting an invalid commodity pushing signal; recording the number of times of outputting effective commodity pushing signals, and marking the number as the effective commodity pushing number;
step S403, analyzing the commodity pushing feedback and the effective commodity pushing number to obtain a commodity pushing effect.
8. The method for evaluating the pushing effect of advertisement based on big data according to claim 7, wherein the step S403 comprises the following sub-steps:
step S4031, calculating commodity pushing feedback and effective commodity pushing number through a commodity pushing reference value calculation formula to obtain a commodity pushing reference value;
the commodity pushing reference value calculation formula is configured as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein Ce is commodity exposure, cc is commodity click quantity, cf is commodity transfer quantity, cb is commodity purchase quantity, cr is commodity withdrawal quantity, cp is effective commodity pushing number, alpha 3 is effective commodity pushing coefficient, beta 3 is effective commodity purchase coefficient, gamma 3 is effective commodity transfer coefficient, alpha 3, beta 3 and gamma 3 are constants and are larger than zero;
step S4032, comparing the commodity pushing reference value with a first pushing reference threshold and a second pushing reference threshold respectively, and outputting a commodity low pushing effect signal if the commodity pushing reference value is smaller than or equal to the first pushing reference threshold; outputting a pushing effect signal in the commodity if the commodity pushing reference value is larger than the first pushing reference threshold value and smaller than or equal to the second pushing reference threshold value; if the commodity pushing reference value is larger than the second pushing reference threshold value, outputting a commodity high pushing effect signal;
Step S4033, if the commodity low pushing effect signal is output, judging that the commodity pushing effect is three-level pushing effect; if the pushing effect signal in the commodity is output, judging that the commodity pushing effect is a secondary pushing effect; if the commodity high pushing effect signal is output, the commodity pushing effect is judged to be the first-stage pushing effect.
9. The method for evaluating the pushing effect of advertisement based on big data according to claim 8, wherein the step S5 comprises the following sub-steps:
step S501, obtaining user ages, establishing a push audience database, and recording the user ages of outputting high-efficiency push signals, outputting normal use time signals and outputting effective commodity push signals, wherein the user ages are respectively marked as applet audience ages, application audience ages and commodity audience ages;
step S502, classifying the ages of the users, and dividing the ages of the users into teenagers, young, middle-aged and elderly;
step S503, classifying the ages of the small program audience, the applied audience age and the commodity audience age, recording the proportion of the number of records of the ages of the small program audience in the teenager, the young age, the middle-aged and the elderly, respectively marking the proportion of the small program audience, the proportion of the small program young audience, the proportion of the small program middle-aged audience and the proportion of the small program elderly audience, and integrating the proportion of the small program audience;
Step S504, searching the maximum value in the audience proportion of the small program, and marking the age of the small program audience corresponding to the maximum value as the best pushing audience of the small program;
step S505, the proportion of the recorded number of the application audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages is marked as the application teenager audience proportion, the application young audience proportion, the application middle-aged audience proportion and the application elderly audience proportion respectively, and the integration marks as the application audience proportion;
step S506, searching the maximum value in the application audience proportion, and marking the application audience age corresponding to the maximum value as the application best pushing audience;
step S507, recording the proportion of the recorded quantity of the commodity audience ages belonging to the teenagers, the young ages, the middle-aged and the elderly ages, respectively marking the proportion as the commodity teenagers, the commodity young audience proportion, the commodity middle-aged audience proportion and the commodity elderly audience proportion, and integrating the proportion as the commodity audience proportion;
step S508, searching the maximum value in the commodity audience proportion, and marking the commodity audience age corresponding to the maximum value as the commodity best pushing audience.
10. The advertisement pushing effect evaluation system based on big data is characterized in that the advertisement pushing effect evaluation method based on the big data is realized according to any one of claims 1-9, and comprises a platform data acquisition module, a pushing effect analysis module and a data storage module; the platform data acquisition module and the data storage module are respectively connected with the pushing effect analysis module in a data mode;
The platform data acquisition module comprises a push advertisement acquisition unit and a user data acquisition unit; the push advertisement acquisition unit is used for acquiring advertisement types, applet push feedback, application push feedback and commodity push feedback of push advertisements; the user data acquisition unit is used for acquiring the age of a user;
the pushing effect analysis module comprises an applet pushing analysis unit, an application pushing analysis unit, a commodity pushing analysis unit and a pushing audience analysis unit; the applet pushing analysis unit is used for analyzing applet pushing feedback to obtain an applet pushing effect; the application pushing analysis unit is used for analyzing application pushing feedback to obtain an application pushing effect; the commodity pushing analysis unit is used for analyzing commodity pushing feedback to obtain commodity pushing effects; the push audience analysis unit is used for analyzing the age of the user, the pushing feedback of the small program, the pushing feedback of the application and the pushing feedback of the commodity, and obtaining the age groups of the optimal push audiences with different advertisement types;
the data storage module is used for storing user ages, applet pushing feedback, application pushing feedback and commodity pushing feedback.
11. An electronic device comprising a processor and a memory storing computer readable instructions that, when executed by the processor, perform the steps in the method of any of claims 1-9.
12. A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311042162.7A CN116757749B (en) | 2023-08-18 | 2023-08-18 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311042162.7A CN116757749B (en) | 2023-08-18 | 2023-08-18 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116757749A true CN116757749A (en) | 2023-09-15 |
| CN116757749B CN116757749B (en) | 2023-11-10 |
Family
ID=87948295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311042162.7A Active CN116757749B (en) | 2023-08-18 | 2023-08-18 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116757749B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117311166A (en) * | 2023-11-08 | 2023-12-29 | 杭州大仁科技有限公司 | Self-adaptive control method and system for full-automatic integrated sock turning device |
| CN118710335A (en) * | 2024-08-27 | 2024-09-27 | 深圳市创致联创科技有限公司 | Optimization analysis method, system and medium based on webpage advertisement feedback data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018018279A1 (en) * | 2016-07-24 | 2018-02-01 | 金蕾 | Method for pushing information when feeding back ad serving object and data collecting device |
| WO2018023656A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting advertisement push according to usage conditions of other users, and push system |
| WO2018027775A1 (en) * | 2016-08-11 | 2018-02-15 | 王志远 | Method for feeding back usage data of advertisement pushing technology, and pushing system |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN114092144A (en) * | 2021-11-22 | 2022-02-25 | 上海途零信息科技有限公司 | Advertisement pushing method and system based on big data internet platform |
| CN116051191A (en) * | 2023-02-01 | 2023-05-02 | 上海风芃信息科技有限公司 | New media advertisement putting recommendation system based on data analysis |
| CN116308537A (en) * | 2023-02-21 | 2023-06-23 | 欢聚时代文化传媒（北京）有限公司 | Advertisement targeted delivery management system based on information flow big data |
-
2023
- 2023-08-18 CN CN202311042162.7A patent/CN116757749B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018018279A1 (en) * | 2016-07-24 | 2018-02-01 | 金蕾 | Method for pushing information when feeding back ad serving object and data collecting device |
| WO2018023656A1 (en) * | 2016-08-05 | 2018-02-08 | 汤隆初 | Method for adjusting advertisement push according to usage conditions of other users, and push system |
| WO2018027775A1 (en) * | 2016-08-11 | 2018-02-15 | 王志远 | Method for feeding back usage data of advertisement pushing technology, and pushing system |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN114092144A (en) * | 2021-11-22 | 2022-02-25 | 上海途零信息科技有限公司 | Advertisement pushing method and system based on big data internet platform |
| CN116051191A (en) * | 2023-02-01 | 2023-05-02 | 上海风芃信息科技有限公司 | New media advertisement putting recommendation system based on data analysis |
| CN116308537A (en) * | 2023-02-21 | 2023-06-23 | 欢聚时代文化传媒（北京）有限公司 | Advertisement targeted delivery management system based on information flow big data |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117311166A (en) * | 2023-11-08 | 2023-12-29 | 杭州大仁科技有限公司 | Self-adaptive control method and system for full-automatic integrated sock turning device |
| CN117311166B (en) * | 2023-11-08 | 2024-04-30 | 杭州大仁科技有限公司 | Self-adaptive control method and system for full-automatic integrated sock turning device |
| CN118710335A (en) * | 2024-08-27 | 2024-09-27 | 深圳市创致联创科技有限公司 | Optimization analysis method, system and medium based on webpage advertisement feedback data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116757749B (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116757749B (en) | Advertisement pushing effect evaluation method, system and storage medium based on big data | |
| CN109040844B (en) | Method and device for acquiring video heat and electronic equipment | |
| CN107330459B (en) | Data processing method and device and electronic equipment | |
| US20160285672A1 (en) | Method and system for processing network media information | |
| CN109657138A (en) | A kind of video recommendation method, device, electronic equipment and storage medium | |
| WO2019127981A1 (en) | H5 activity page propagation based marketing method, electronic apparatus and storage medium | |
| JP2015060331A (en) | Posterior probability calculation device, posterior probability calculation method, and program | |
| CN116823409B (en) | Intelligent screening method and system based on target search data | |
| US20180039766A1 (en) | Method and system for identifying a unique mobile device based on mobile device attribute changes over time | |
| CN107592346A (en) | User classification method based on user behavior analysis | |
| CN111461778A (en) | Advertisement pushing method and device | |
| CN106355450B (en) | User behavior analysis system and method | |
| CN104123303B (en) | A kind of method and device that data are provided | |
| CN114331521A (en) | Business data monitoring, analyzing and managing method, system, equipment and storage medium | |
| CN106919609B (en) | Product information pushing method and device | |
| WO2019161718A1 (en) | Attribution method and apparatus | |
| CN116342353B (en) | Method and system for realizing economic forest carbon sink analysis based on deep learning | |
| CN116934418B (en) | Abnormal order detection and early warning method, system, equipment and storage medium | |
| KR20120136503A (en) | System of advertisement and method for evaluation of advertisement result | |
| CN115860820A (en) | Intelligent encryption putting and destroying method and device for electronic coupons | |
| CN105868252A (en) | User behavior data processing method and apparatus | |
| CN114285848A (en) | Scalable method, system, electronic device and readable medium for blockchain resources | |
| CN109165238B (en) | Data processing method and device for generating period index data | |
| CN111368201A (en) | Hot event detection method and device, electronic equipment and storage medium | |
| CN117708183B (en) | Potential user mining method and system based on user consumption habit |
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 |