CN116664196A - Internet-based data processing system - Google Patents
Internet-based data processing system Download PDFInfo
- Publication number
- CN116664196A CN116664196A CN202310621985.9A CN202310621985A CN116664196A CN 116664196 A CN116664196 A CN 116664196A CN 202310621985 A CN202310621985 A CN 202310621985A CN 116664196 A CN116664196 A CN 116664196A
- Authority
- CN
- China
- Prior art keywords
- marketing
- app
- calculating
- benefit
- audience
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 43
- 238000011835 investigation Methods 0.000 claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 9
- 230000008901 benefit Effects 0.000 claims description 136
- 230000006872 improvement Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 11
- 230000001737 promoting effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 235000019633 pungent taste Nutrition 0.000 claims description 3
- 238000011160 research Methods 0.000 claims 1
- 238000012552 review Methods 0.000 claims 1
- 238000012546 transfer Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000007480 spreading 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
- G06Q30/0244—Optimization
-
- 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
- G06Q30/0271—Personalized advertisement
-
- 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
Abstract
The invention discloses a data processing system based on the Internet, in particular to the technical field of data processing, wherein a target product audience information investigation module is arranged to investigate the active condition of target product audiences in different APP, register rate, usage and creation user attention are calculated, an advertisement marketing fund distribution module is arranged to calculate the activity index of the target product audiences in different software according to the APP register rate and the APP usage, influence indexes of creation users on the target product audiences are calculated according to the APP register rate and the creation user attention, meanwhile, matching degree of works of the creation users and target products is calculated, advertisement marketing fund invested by different APP is determined according to the APP activity indexes, and popularization fund of different creation users is distributed according to the influence indexes and the matching degree of the creation users.
Description
Technical Field
The present invention relates to the field of data processing technology, and more particularly, to an internet-based data processing system.
Background
With the vigorous development of new media technology in China, internet advertising has become the dominant force of the current advertising industry gradually, and is the main stream direction of brand popularization.
In the existing advertisement marketing data processing system based on the Internet, brand marketers purchase advertisement putting qualification on recommended pages and access interfaces of different platforms, so that omnibearing advertisement putting is realized, audience and advertisement spreading range are expanded, one-to-one consultation service is carried out after user information is counted for potential users of products for users browsing advertisements, consumer satisfaction is improved, sales before and after advertisement marketing are calculated according to sales conditions before and after advertisement marketing, marketing benefits are calculated according to sales benefits and consumer satisfaction, advertisement marketing quality is calculated according to marketing benefits, and the higher corresponding advertisement marketing quality indicates higher advertisement marketing effect.
However, the existing system still has some problems, the cost of advertisement putting in all directions on the recommendation interface and the access interface of different platforms is high, the accuracy of advertisement putting needs to be improved, in the use process of actual software, the user always directly ignores the coming advertisements, and how to improve the attraction of the advertisements is still a problem to be solved.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, embodiments of the present invention provide an internet-based data processing system to solve the above-mentioned problems.
In order to achieve the above purpose, the present invention provides the following technical solutions: an internet-based data processing system, comprising:
the target product audience determination module: the method comprises the steps of determining corresponding target product audiences according to functions, prices and product concepts of target products, and estimating the total number of the target product audiences through the Internet;
the audience information investigation module of the target product; the system comprises an APP registration information collection unit, an APP use time information statistics unit, an APP use condition recording unit, an APP registration rate calculation unit, an APP use degree calculation unit, an authored work browsing heat calculation unit and an authored user attention calculation unit, wherein the APP use degree calculation unit is used for calculating the activity of a confirmed target product audience in different APP;
advertisement marketing fund distribution module: the advertisement marketing fund distribution unit is used for distributing advertisement marketing fund according to the active conditions of target audience in different APP, and comprises a target product audience activity degree calculation unit, an authored user influence calculation unit, an APP marketing fund distribution unit and an authored user popularization fund distribution unit;
marketing benefit promotion prediction module: the method comprises the steps of predicting marketing benefits brought by different authoring users in different APP according to liveness indexes of the different APP, influence indexes of the different authoring users in the APP and matching degrees of corresponding authoring styles, and calculating expected marketing benefit improvement indexes;
advertisement marketing data acquisition module: the method is used for collecting browsing amount, purchasing price and actual ordering amount of target products before and after advertisement marketing;
advertisement marketing data processing module: the system is used for processing the acquired product purchase data information and comprises a data source tracing unit, a data summarizing and counting unit and a benefit improving index calculating unit;
marketing benefit judging module: the method comprises the steps of comparing a marketing benefit promotion index with an expected marketing benefit promotion index to judge whether a corresponding marketing means meets the marketing purpose, and screening out a corresponding marketing scheme which does not meet the marketing purpose;
marketing benefit data processing module: the method comprises the steps of calculating marketing cost performance according to marketing benefits and costs of different marketing channels meeting marketing purposes;
marketing scheme selection module: the marketing method comprises the steps of ranking marketing cost performance, and selecting a marketing scheme with top three of the cost performance values to continue to be executed;
database: for storing all data information in the system.
Preferably, the APP registration information collection unit in the target product audience information investigation module is used for collecting real name registration information of target product audiences in different APP; the APP using time information statistics unit is used for counting time consumed by the target product audience on different APPs every month; the APP use condition statistics unit is used for counting the history browsing record, the history comment record, the history praise record, the history attention record, the history collection record and the history forwarding record of the last month of the target product audience on different APP; the APP registration rate calculation unit is used for calculating the APP registration rate according to the ratio situation of the registration number of the target product audience in the APP registration information in the whole target product audience; the APP usage calculating unit is used for calculating APP usage according to the time occupation ratio condition of each month of the target audience on each APP; the authored work browsing heat calculating unit is used for calculating the browsing rate, comment heat, praise rate, forwarding rate and collection rate of a certain authored work by target product audiences in different APP, and calculating the browsing heat of the authored work according to the browsing heat; the attention calculating unit of the authoring user is used for calculating attention rate of target product audiences in different APP to a certain authoring user and average browsing heat of the authored content, and calculating attention of the authoring user.
Preferably, the specific calculation process in the audience information investigation module of the target product is as follows:
a1, calculating APP registration rate alpha c The specific calculation formula is as follows:wherein alpha is a Alpha is the registration number of target audience in APP registration information 0 The number of target audience members as a whole;
a2, calculating APP usage degree beta c The specific calculation formula is as follows:wherein beta is a For each software, the foreground occupies a long time, beta 0 The total duration is occupied for the foreground of each month of different software;
a3, calculating a certain creation of the target product audienceBrowsing rate a of works c Comment heat b c Praise rate c a Rate e of forwarding c And collection rate f c The specific calculation formula is as follows: browsing rateWherein a is i For browsing times of each target product audience who browses the same authored work, comment hotness +.>Wherein b a The number of comments posted for the audience of the target product, a e To browse the number of target audience of a certain authored work, praise rate +.>Wherein c e Praise amount for the target audience for the same authored work, forwarding rate +.>Wherein e a Forwarding times for the same authored work e b To forward the audience quantity of the target product of the work, collection rate +.>Wherein f a The collection of the same authored work for the target product audience;
a4, calculating browsing heat gamma of authored works c The specific calculation formula is as follows:wherein x is 1 、x 2 、x 3 、x 4 、x 5 For the proportionality coefficient of the corresponding factor, calculating the browsing heat of the authored works corresponding to all the authored works of the authored user, summarizing, screening out the data with larger deviation, and calculating the average value gamma e The specific calculation formula is as follows: />
A5, calculating the attention rate d of target product audiences in different APP to a certain authoring user c The specific calculation formula is as follows:wherein d is a For the number of target audiences focusing on the content creator, db is the total number of target audiences who have browsed the content creator work;
a6, calculating the attention delta of the creation user c The specific calculation formula is as follows:wherein y is 1 、y 2 For the corresponding constant coefficient, y 1 >0,y 2 >0。
Preferably, the specific process of funds distribution in the advertising marketing funds distribution module is as follows:
the audience liveness calculation unit of the target product: calculating the liveness index X of the audience of the target product in different software according to the APP registration rate and the APP usage a The specific calculation formula is as follows: x is X a ＝a e1 *(α c ) 3 +a e2 *β c Wherein a is e1 、a e2 Is a corresponding constant coefficient;
an authoring user influence calculation unit: calculating influence index Y of authoring user on target product audience according to APP registration rate and interest degree of authoring user a The specific calculation formula is as follows:wherein b e1 、b e2 An index adjustment factor that is a corresponding factor;
APP marketing funds allocation unit: calculating liveness indexes of audience of different APP target products, ranking, and calculating the proximity degree h of the difference value of liveness corresponding to adjacent ranking and the software liveness value after ranking a The specific calculation formula is as follows:wherein X is ai 、X aj For adjacent ranked APP liveness, i-j=1, the first APP of rank invests advertising marketing funds W ta 30% of the second ranked APP invested advertising marketing funds W t2 ＝W t1 *(1-h a1 ) According to the method, funds are distributed, and advertising marketing funds W corresponding to the j-th APP investment are ranked tj ＝W ti *(1-h ai ) Wherein i-j=1;
the creation user promotes the fund distribution unit: calculating influence indexes of different authoring users in APP, ranking, classifying the authoring contents of the users, setting keywords of different hierarchical categories, matching the keywords with target products, counting the coincidence condition of the keywords, and calculating the matching degree Z a The post ranking, the specific calculation formula is: z is Z a ＝c b1 *ξ 1 +c b2 *ξ 2 +......+c bn *ξ n Wherein c bi For the scaling factor of each level, ζ i For the ratio of the number of the key words to the number of the key words in each level, when xi i When the calculated result is 0, namely the target matching degree, the difference epsilon between the two ranks is calculated, and the specific calculation formula is as follows:wherein F is i To author user' S impact index ranking, S j For ranking the superposition of the creation user works and the target products, phi is a constant adjustment parameter, and the corresponding creation users are ranked according to the degree of difference and distributed according to 30%, 25%, 20%, 15% and 10% of APP advertising marketing funds.
Preferably, the marketing benefit improvement prediction module calculates the expected marketing benefit improvement index Q according to the liveness index of different APP, the influence index of different authoring users in the APP and the authoring style matching degree c The specific calculation formula of (2) is as follows:wherein j is 1 、j 2 、j 3 For the scale factors corresponding to different factors, the expected marketing benefit improvement indexes corresponding to different authoring users in the selected APP are summarized, and the overall expected marketing benefit improvement index Q is calculated e The specific calculation formula is as follows: q (Q) e ＝∑Q ci 。
Preferably, a data source tracing stage in the advertisement marketing data processing module is used for tracing the purchase information of the target product after marketing to confirm a purchase link reloading platform and a reloading user; the data summarizing and counting unit is used for summarizing the purchase information from the same reloading platform and the same reloading user; the benefit promoting index calculating unit is used for calculating normal sales benefit and marketing benefit according to the browsing amount, the purchasing price and the actual purchasing amount of the target product before and after marketing, and calculating the marketing benefit promoting index according to the normal sales benefit and the marketing benefit.
Preferably, the specific calculation process in the advertising marketing data processing module is as follows:
b1, counting the browsing quantity f of the product in the previous month of marketing a Quantity g of product a Different selling prices p of products a Corresponding actual product quantity v a Calculating sales income W of product a The specific calculation formula is as follows:
b2, counting the browsing quantity f of the products generated by different marketing sources within one month after marketing b Quantity g of product b Price p for selling product b Corresponding actual product quantity v b Calculating marketing benefit W of product b The specific calculation formula is as follows:
b3, calculating sales benefit W ac And marketing benefit W bc The specific calculation formula is as follows: w (W) ac ＝W a -W a0 Wherein W is a0 For the total cost of the sold product, W bc ＝W b -W t -W b0 Wherein W is t Marketing funds for corresponding advertisements, W b0 Cost of the product sold for marketing;
b4, calculating a marketing benefit improvement index Q corresponding to each marketing source a The specific calculation formula is as follows:
b5, calculating marketing benefit improvement indexes Q corresponding to all marketing sources t The specific calculation formula is as follows: q (Q) t ＝∑Q ai 。
Preferably, the marketing benefit judging module judges the overall marketing benefit improving index first, if the actual marketing benefit improving index is larger than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to meet the current marketing purpose, if the actual marketing benefit improving index is smaller than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to not meet the current marketing purpose, the specific situation is analyzed, the marketing benefit improving index brought by the corresponding creation user in each selected APP is compared with the corresponding expected marketing benefit improving index, whether the marketing scheme which does not meet the current marketing purpose exists is judged, and the subsequent marketing fund distribution mode is adjusted.
Preferably, the marketing benefit data processing module calculates the marketing cost performance w according to the marketing benefits and the costs corresponding to different marketing sources v The specific formula of (2) is:
the invention has the technical effects and advantages that:
1. according to the invention, the advertisement marketing fund distribution module is arranged, the liveness indexes of the target product audience in different software are calculated according to the APP registration rate and the APP usage, and the advertisement marketing fund corresponding to the selected users is determined according to the difference value of the corresponding liveness of adjacent ranks and the proximity of the software liveness value after ranking, so that the additional economic loss caused by omnibearing advertisement investment is avoided, the centralized investment of advertisement fund is realized, the influence index of an authoring user on the target product audience is calculated according to the APP registration rate and the focus of the authoring user, the influence degree of the authoring user on the target product audience is reflected, meanwhile, the matching degree of the authoring user and the target product is calculated, and the advertisement marketing fund corresponding to the selected users is input according to the difference between the two ranks.
2. The invention sets up marketing benefit and promotes the prediction module, according to the liveness index of different APP, influence index and correspondent creation style matching degree of different creation users in APP, predict the marketing benefit brought by different creation users in different APP, calculate the correspondent expected marketing benefit and overall expected marketing benefit sign index of each advertising marketing channel, the invention sets up the data acquisition module of advertising marketing, advertising marketing data processing module gather, process the sales information of the goal products before marketing, after marketing, calculate the correspondent marketing benefit promotion index of each marketing source and gather and calculate the marketing benefit promotion index respectively, the invention sets up marketing benefit judgement module judges whether the marketing scheme selected accords with the marketing purpose, the invention sets up marketing benefit data processing module calculates the cost performance of the marketing scheme which accords with the marketing purpose, set up marketing scheme selection module to select marketing scheme of three before the numerical value ranking of the cost performance continues to be implemented, further optimize the marketing scheme, help to improve the marketing benefit.
Drawings
Fig. 1 is a block diagram of a system architecture of the present invention.
Fig. 2 is a flow chart of the operation of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment shown in fig. 1 provides an internet-based data processing system, which comprises a target product audience determining module, a target product audience information investigation module, an advertisement marketing fund distribution module, a marketing benefit promotion prediction module, an advertisement marketing data acquisition module, an advertisement marketing data processing module, a marketing benefit judging module, a marketing benefit data processing module, a marketing scheme selection module and a database.
The system comprises a target product audience determination module, a target product audience information investigation module and an advertisement marketing fund distribution module, wherein the advertisement marketing fund distribution module is connected with a marketing benefit promotion prediction module and an advertisement marketing data acquisition module respectively, the advertisement marketing data acquisition module is connected with an advertisement marketing data processing module, the marketing benefit promotion prediction module and the advertisement marketing data processing module are connected with a marketing benefit judgment module respectively, the marketing benefit judgment module, the marketing benefit data processing module and a marketing scheme selection module are connected in sequence, and the database is connected with all modules in the system.
The target product audience determining module is used for determining the corresponding target product audience according to the function, price and product concept of the target product, and estimating the total number of the target product audience through the Internet.
The target product audience information investigation module is used for investigating the active conditions of confirmed target product audience in different APP, and comprises an APP registration information collection unit, an APP use time information statistics unit, an APP use condition recording unit, an APP registration rate calculation unit, an APP use degree calculation unit, an authored work browsing heat calculation unit and an authored user attention calculation unit.
Further, the APP registration information collection unit in the target product audience information investigation module is used for collecting real name registration information of target product audiences in different APPs; the APP using time information statistics unit is used for counting time consumed by the target product audience on different APPs every month; the APP use condition statistics unit is used for counting the history browsing record, the history comment record, the history praise record, the history attention record, the history collection record and the history forwarding record of the last month of the target product audience on different APP; the APP registration rate calculation unit is used for calculating the APP registration rate according to the ratio situation of the registration number of the target product audience in the APP registration information in the whole target product audience; the APP usage calculating unit is used for calculating APP usage according to the time occupation ratio condition of each month of the target audience on each APP; the authored work browsing heat calculating unit is used for calculating the browsing rate, comment heat, praise rate, forwarding rate and collection rate of a certain authored work by target product audiences in different APP, and calculating the browsing heat of the authored work according to the browsing heat; the attention calculating unit of the authoring user is used for calculating attention rate of target product audiences in different APP to a certain authoring user and average browsing heat of the authored content, and calculating attention of the authoring user.
Further, the specific calculation process in the audience information investigation module of the target product is as follows:
a1, calculating APP registration rate alpha c The specific calculation formula is as follows:wherein alpha is a Alpha is the registration number of target audience in APP registration information 0 The number of target audience members as a whole;
a2, calculating APP usage degree beta c The specific calculation formula is as follows:wherein beta is a For each software, the foreground occupies a long time, beta 0 The total duration is occupied for the foreground of each month of different software;
a3, calculating the browsing rate a of the target product audience to a certain authored work c Comment heat b c Praise rate c a Rate e of forwarding c And collection rate f c The specific calculation formula is as follows: browsing rateWherein a is i For browsing times of each target product audience who browses the same authored work, comment hotness +.>Wherein b a The number of comments posted for the audience of the target product, a e To browse the number of target audience of a certain authored work, praise rate +.>Wherein c e Praise amount for the target audience for the same authored work, forwarding rate +.>Wherein e a Forwarding times for the same authored work e b To forward the audience quantity of the target product of the work, collection rate +.>Wherein f a The collection of the same authored work for the target product audience;
a4, calculating browsing heat gamma of authored works c The specific calculation formula is as follows:wherein x is 1 、x 2 、x 3 、x 4 、x 5 For the proportionality coefficient of the corresponding factor, calculating the browsing heat of the authored works corresponding to all the authored works of the authored user, summarizing, screening out the data with larger deviation, and calculating the average value gamma e Concrete meterThe calculation formula is as follows: />
A5, calculating the attention rate d of target product audiences in different APP to a certain authoring user c The specific calculation formula is as follows:wherein d is a For the number of target audiences focusing on the content creator, db is the total number of target audiences who have browsed the content creator work;
a6, calculating the attention delta of the creation user c The specific calculation formula is as follows:wherein y is 1 、y 2 For the corresponding constant coefficient, y 1 >0,y 2 >0。
The advertising marketing fund distribution module is used for distributing advertising marketing fund according to the active conditions of target audiences in different APP, and comprises a target product audience activity degree calculation unit, an authoritative user influence calculation unit, an APP marketing fund distribution unit and an authoritative user popularization fund distribution unit.
Further, the specific process of funds distribution in the advertising marketing funds distribution module is as follows:
the audience liveness calculation unit of the target product: calculating the liveness index X of the audience of the target product in different software according to the APP registration rate and the APP usage a The specific calculation formula is as follows: x is X a ＝a e1 *(α c ) 3 +a e2 *β c Wherein a is e1 、a e2 Is a corresponding constant coefficient;
an authoring user influence calculation unit: calculating influence index Y of authoring user on target product audience according to APP registration rate and interest degree of authoring user a The specific calculation formula is as follows:wherein b e1 、b e2 An index adjustment factor that is a corresponding factor;
APP marketing funds allocation unit: calculating liveness indexes of audience of different APP target products, ranking, and calculating the proximity degree h of the difference value of liveness corresponding to adjacent ranking and the software liveness value after ranking a The specific calculation formula is as follows:wherein X is ai 、X aj For adjacent ranked APP liveness, i-j=1, the first APP of rank invests advertising marketing funds W ta 30% of the second ranked APP invested advertising marketing funds W t2 ＝W t1 *(1-h a1 ) According to the method, funds are distributed, and advertising marketing funds W corresponding to the j-th APP investment are ranked tj ＝W ti *(1-h ai ) Wherein i-j=1;
the creation user promotes the fund distribution unit: calculating influence indexes of different authoring users in APP, ranking, classifying the authoring contents of the users, setting keywords of different hierarchical categories, matching the keywords with target products, counting the coincidence condition of the keywords, and calculating the matching degree Z a The post ranking, the specific calculation formula is: z is Z a ＝c b1 *ξ 1 +c b2 *ξ 2 +......+c bn *ξ n Wherein c bi For the scaling factor of each level, ζ i For the ratio of the number of the key words to the number of the key words in each level, when xi i When the calculated result is 0, namely the target matching degree, the difference epsilon between the two ranks is calculated, and the specific calculation formula is as follows:wherein F is i To author user' S impact index ranking, S j For ranking the superposition condition of the creation user works and the target products, phi is a constant adjustment parameter, the corresponding creation users are ranked according to the degree of difference, and the corresponding creation users are respectively divided according to 30%, 25%, 20%, 15% and 10% of APP advertising marketing fundsMatching.
The marketing benefit promotion prediction module is used for predicting marketing benefits brought by different authoring users in different APP according to liveness indexes of the different APP, influence indexes of the different authoring users in the APP and corresponding authoring style matching degrees, and calculating expected marketing benefit promotion indexes.
Further, the marketing benefit improvement prediction module calculates an expected marketing benefit improvement index Q according to the liveness index of different APP, the influence index of different authoring users in the APP and the authoring style matching degree c The specific calculation formula of (2) is as follows:wherein j is 1 、j 2 、j 3 For the scale factors corresponding to different factors, the expected marketing benefit improvement indexes corresponding to different authoring users in the selected APP are summarized, and the overall expected marketing benefit improvement index Q is calculated e The specific calculation formula is as follows: q (Q) e ＝∑Q ci 。
The advertisement marketing data acquisition module is used for acquiring browsing amount, purchasing price and actual ordering amount of target products before and after advertisement marketing.
The advertising marketing data processing module is used for processing the acquired product purchase data information and comprises a data source tracing unit, a data summarizing and counting unit and a benefit improving index calculating unit.
Further, the data source tracing stage in the advertisement marketing data processing module is used for tracing the purchase information of the target product after marketing to confirm the purchase link reloading platform and the reloading user; the data summarizing and counting unit is used for summarizing the purchase information from the same reloading platform and the same reloading user; the benefit promoting index calculating unit is used for calculating normal sales benefit and marketing benefit according to the browsing amount, the purchasing price and the actual purchasing amount of the target product before and after marketing, and calculating the marketing benefit promoting index according to the normal sales benefit and the marketing benefit.
Further, the specific calculation process in the advertisement marketing data processing module is as follows:
b1, counting the browsing quantity f of the product in the previous month of marketing a Quantity g of product a Different selling prices p of products a Corresponding actual product quantity v a Calculating sales income W of product a The specific calculation formula is as follows:
b2, counting the browsing quantity f of the products generated by different marketing sources within one month after marketing b Quantity g of product b Price p for selling product b Corresponding actual product quantity v b Calculating marketing benefit W of product b The specific calculation formula is as follows:
b3, calculating sales benefit W ac And marketing benefit W bc The specific calculation formula is as follows: w (W) ac ＝W a -W a0 Wherein W is a0 For the total cost of the sold product, W bc ＝W b -W t -W b0 Wherein W is t Marketing funds for corresponding advertisements, W b0 Cost of the product sold for marketing;
b4, calculating a marketing benefit improvement index Q corresponding to each marketing source a The specific calculation formula is as follows:
b5, calculating marketing benefit improvement indexes Q corresponding to all marketing sources t The specific calculation formula is as follows: q (Q) t ＝∑Q ai 。
The marketing benefit judging module is used for comparing the marketing benefit improving index with the expected marketing benefit improving index to judge whether the corresponding marketing means meets the marketing purpose or not, and screening out the corresponding marketing scheme which does not meet the marketing purpose.
Further, the marketing benefit judging module judges the overall marketing benefit improving index first, if the actual marketing benefit improving index is larger than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to meet the current marketing purpose, if the actual marketing benefit improving index is smaller than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to not meet the current marketing purpose, the specific situation is analyzed, the marketing benefit improving index brought by the corresponding creation user in each selected APP is compared with the corresponding expected marketing benefit improving index, and whether the marketing scheme which does not meet the current marketing purpose exists is judged, and the subsequent marketing fund distribution mode is adjusted.
The marketing benefit data processing module is used for calculating marketing cost performance according to marketing benefits and costs of different marketing channels conforming to marketing purposes.
Further, the marketing cost performance w is calculated according to the marketing benefits and the costs corresponding to different marketing sources in the marketing benefit data processing module v The specific formula of (2) is:
the marketing scheme selection module is used for ranking the marketing cost performance, and selecting the marketing scheme with the top three of the cost performance values to continue to be executed.
The database is used for storing all data information in the system.
As shown in fig. 2, the present embodiment provides an operation flow of an internet-based data processing system, which includes the following steps:
s1: determining corresponding target product audiences according to the functions, prices and product concepts of the target products, and estimating the total number of the target product audiences through the Internet;
s2: investigation of the active condition of the confirmed target product audience in different APP, calculation of APP registration rate according to real name registration information of the target product audience in different APP, calculation of APP usage degree according to time consumed by the target product audience in different APP in each month, calculation of browsing heat of the target product audience to a certain authored work according to historical browsing record, historical comment record, historical praise record, historical collection record and historical forwarding record of the target product audience in the last month of different APP, calculation of attention rate according to historical attention record of the target product audience in the last month of different APP, and calculation of authored user attention degree according to attention rate and average browsing heat of authored content;
s3: calculating liveness indexes of target product audiences in different software according to the APP registration rate and the APP usage, determining advertisement marketing funds put into different APP by the APP liveness ranking and the proximity degree of the difference value of the liveness corresponding to the adjacent ranking and the software liveness value after ranking, calculating influence indexes of the authoring users on the target product audiences according to the APP registration rate and the focus of the authoring users, calculating matching degree of the work styles of the authoring users and the target products, selecting the authoring users for product popularization according to the difference degree of the influence ranking and the matching degree ranking, and distributing product popularization funds;
s4: predicting marketing benefits brought by different authoring users in different APP according to liveness indexes of the different APP, influence indexes of the different authoring users in the APP and matching degree of corresponding authoring styles, and calculating expected marketing benefit improvement indexes;
s5: collecting browsing amount, purchasing price and actual ordering amount of target products before advertisement marketing, and browsing amount, purchasing price and actual ordering amount of target products corresponding to different marketing sources after marketing;
s6: tracing the purchase information of the target product after marketing to confirm a purchase link transfer platform and a transfer user, summarizing the purchase information from the same transfer platform and the same transfer user, calculating normal sales benefits and marketing benefits according to the browsing amount, the purchase adding amount, the purchase price and the actual reduction amount of the target product before and after marketing, and calculating a marketing benefit improvement index;
s7: judging the overall marketing benefit improvement index, if the actual marketing benefit improvement index is larger than the expected marketing benefit improvement index, indicating that the corresponding marketing scheme meets the current marketing purpose, if the actual marketing benefit improvement index is smaller than the expected marketing benefit improvement index, indicating that the corresponding marketing scheme does not meet the current marketing purpose, analyzing specific conditions, comparing data of the marketing benefit improvement index brought by the corresponding creation user in each selected APP with the corresponding expected marketing benefit improvement index, judging whether a marketing scheme which does not meet the current marketing purpose exists or not, and adjusting a subsequent marketing fund distribution mode;
s8: calculating marketing cost performance according to marketing benefits and costs of different marketing channels meeting marketing purposes;
s9: ranking the marketing cost performance, and selecting the marketing scheme with the top three of the cost performance values to continue to execute.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. An internet-based data processing system, characterized by: comprising the following steps:
the target product audience determination module: the method comprises the steps of determining corresponding target product audiences according to functions, prices and product concepts of target products, and estimating the total number of the target product audiences through the Internet;
the audience information investigation module of the target product; the system comprises an APP registration information collection unit, an APP use time information statistics unit, an APP use condition recording unit, an APP registration rate calculation unit, an APP use degree calculation unit, an authored work browsing heat calculation unit and an authored user attention calculation unit, wherein the APP use degree calculation unit is used for calculating the activity of a confirmed target product audience in different APP;
advertisement marketing fund distribution module: the advertisement marketing fund distribution unit is used for distributing advertisement marketing fund according to the active conditions of target audience in different APP, and comprises a target product audience activity degree calculation unit, an authored user influence calculation unit, an APP marketing fund distribution unit and an authored user popularization fund distribution unit;
marketing benefit promotion prediction module: the method comprises the steps of predicting marketing benefits brought by different authoring users in different APP according to liveness indexes of the different APP, influence indexes of the different authoring users in the APP and matching degrees of corresponding authoring styles, and calculating expected marketing benefit improvement indexes;
advertisement marketing data acquisition module: the method is used for collecting browsing amount, purchasing price and actual ordering amount of target products before and after advertisement marketing;
advertisement marketing data processing module: the system is used for processing the acquired product purchase data information and comprises a data source tracing unit, a data summarizing and counting unit and a benefit improving index calculating unit;
marketing benefit judging module: the method comprises the steps of comparing a marketing benefit promotion index with an expected marketing benefit promotion index to judge whether a corresponding marketing means meets the marketing purpose, and screening out a corresponding marketing scheme which does not meet the marketing purpose;
marketing benefit data processing module: the method comprises the steps of calculating marketing cost performance according to marketing benefits and costs of different marketing channels meeting marketing purposes;
marketing scheme selection module: and the marketing cost performance is ranked, and the marketing scheme with the top three of the cost performance values is selected to continue to be executed.
2. The internet-based data processing system of claim 1, wherein: the APP registration information collection unit in the target product audience information investigation module is used for collecting real name registration information of target product audiences in different APP; the APP using time information statistics unit is used for counting time consumed by the target product audience on different APPs every month; the APP use condition statistics unit is used for counting the history browsing record, the history comment record, the history praise record, the history attention record, the history collection record and the history forwarding record of the last month of the target product audience on different APP; the APP registration rate calculation unit is used for calculating the APP registration rate according to the ratio situation of the registration number of the target product audience in the APP registration information in the whole target product audience; the APP usage calculating unit is used for calculating APP usage according to the time occupation ratio condition of each month of the target audience on each APP; the authored work browsing heat calculating unit is used for calculating the browsing rate, comment heat, praise rate, forwarding rate and collection rate of a certain authored work by target product audiences in different APP, and calculating the browsing heat of the authored work according to the browsing heat; the attention calculating unit of the authoring user is used for calculating attention rate of target product audiences in different APP to a certain authoring user and average browsing heat of the authored content, and calculating attention of the authoring user.
3. The audience information research module of claim 2 wherein: the specific calculation process of the module is as follows:
a1, calculating APP registration rate alpha c The specific calculation formula is as follows:wherein alpha is a Alpha is the registration number of target audience in APP registration information 0 The number of target audience members as a whole;
a2, calculating APP usage degree beta c The specific calculation formula is as follows:wherein beta is a For each software, the foreground occupies a long time, beta 0 The total duration is occupied for the foreground of each month of different software;
a3, calculating the browsing rate a of the target product audience to a certain authored work c Comment heat b c Praise rate c a Rate e of forwarding c And collection rate f c The specific calculation formula is as follows: browsing rateWherein a is i For browsing times of each target product audience who browses the same authored work, comment hotness +.>Wherein b a For the purpose ofThe number of reviews posted by the audience of the target product, a e To browse the number of target audience of a certain authored work, praise rate +.>Wherein c e Praise amount for the target audience for the same authored work, forwarding rate +.>Wherein e a Forwarding times for the same authored work e b To forward the audience quantity of the target product of the work, collection rate +.>Wherein f a The collection of the same authored work for the target product audience;
a4, calculating browsing heat gamma of authored works c The specific calculation formula is as follows:wherein x is 1 、x 2 、x 3 、x 4 、x 5 For the proportionality coefficient of the corresponding factor, calculating the browsing heat of the authored works corresponding to all the authored works of the authored user, summarizing, screening out the data with larger deviation, and calculating the average value gamma e The specific calculation formula is as follows:
a5, calculating the attention rate d of target product audiences in different APP to a certain authoring user c The specific calculation formula is as follows:wherein d is a For the number of target audiences focusing on the content creator, db is the total number of target audiences who have browsed the content creator work；
A6, calculating the attention delta of the creation user c The specific calculation formula is as follows:wherein y is 1 、y 2 For the corresponding constant coefficient, y 1 >0,y 2 >0。
4. The internet-based data processing system of claim 1, wherein: the specific process of fund distribution in the advertising marketing fund distribution module is as follows:
the audience liveness calculation unit of the target product: calculating the liveness index X of the audience of the target product in different software according to the APP registration rate and the APP usage a The specific calculation formula is as follows: x is X a ＝a e1 *(α c ) 3 +a e2 *β c Wherein a is e1 、a e2 Is a corresponding constant coefficient;
an authoring user influence calculation unit: calculating influence index Y of authoring user on target product audience according to APP registration rate and interest degree of authoring user a The specific calculation formula is as follows:wherein b e1 、b e2 An index adjustment factor that is a corresponding factor;
APP marketing funds allocation unit: calculating liveness indexes of audience of different APP target products, ranking, and calculating the proximity degree h of the difference value of liveness corresponding to adjacent ranking and the software liveness value after ranking a The specific calculation formula is as follows:wherein X is ai 、X aj For adjacent ranked APP liveness, i-j=1, the first APP of rank invests advertising marketing funds W ta 30% of the second ranked APP invested advertising marketing funds W t2 ＝W t1 *(1-h a1 ) According to the method, funds are distributed, and advertising marketing funds W corresponding to the j-th APP investment are ranked tj ＝W ti *(1-h ai ) Wherein i-j=1;
the creation user promotes the fund distribution unit: calculating influence indexes of different authoring users in APP, ranking, classifying the authoring contents of the users, setting keywords of different hierarchical categories, matching the keywords with target products, counting the coincidence condition of the keywords, and calculating the matching degree Z a The post ranking, the specific calculation formula is: z is Z a ＝c b1 *ξ 1 +c b2 *ξ 2 +......+c bn *ξ n Wherein c bi For the scaling factor of each level, ζ i For the ratio of the number of the key words to the number of the key words in each level, when xi i When the calculated result is 0, namely the target matching degree, the difference epsilon between the two ranks is calculated, and the specific calculation formula is as follows:wherein F is i To author user' S impact index ranking, S j For ranking the superposition of the creation user works and the target products, phi is a constant adjustment parameter, and the corresponding creation users are ranked according to the degree of difference and distributed according to 30%, 25%, 20%, 15% and 10% of APP advertising marketing funds.
5. The internet-based data processing system of claim 1, wherein: the marketing benefit improvement prediction module calculates an expected marketing benefit improvement index Q according to the liveness indexes of different APP, the influence indexes of different authoring users in the APP and the authoring style matching degree c The specific calculation formula of (2) is as follows:wherein j is 1 、j 2 、j 3 Summarizing expected marketing benefit promotion indexes corresponding to different authoring users in the selected APP for the scale factors corresponding to different factors, and calculating the whole pre-preparationPhase marketing benefit boost index Q e The specific calculation formula is as follows: q (Q) e ＝∑Q ci 。
6. The internet-based data processing system of claim 1, wherein: the data source tracing stage in the advertising marketing data processing module is used for tracing the purchase information of the target product after marketing to confirm the purchase link reloading platform and the reloading user; the data summarizing and counting unit is used for summarizing the purchase information from the same reloading platform and the same reloading user; the benefit promoting index calculating unit is used for calculating normal sales benefit and marketing benefit according to the browsing amount, the purchasing price and the actual purchasing amount of the target product before and after marketing, and calculating the marketing benefit promoting index according to the normal sales benefit and the marketing benefit.
7. The advertising marketing data processing module of claim 6, wherein: the specific calculation process of the module is as follows:
b1, counting the browsing quantity f of the product in the previous month of marketing a Quantity g of product a Different selling prices p of products a Corresponding actual product quantity v a Calculating sales income W of product a The specific calculation formula is as follows:
b2, counting the browsing quantity f of the products generated by different marketing sources within one month after marketing b Quantity g of product b Price p for selling product b Corresponding actual product quantity v b Calculating marketing benefit W of product b The specific calculation formula is as follows:
b3, calculating sales benefit W ac And marketing benefit W bc The specific calculation formula is as follows: w (W) ac ＝W a -W a0 Wherein W is a0 Sold for saleTotal cost of product, W bc ＝W b -W t -W b0 Wherein W is t Marketing funds for corresponding advertisements, W b0 Cost of the product sold for marketing;
b4, calculating a marketing benefit improvement index Q corresponding to each marketing source a The specific calculation formula is as follows:
b5, calculating marketing benefit improvement indexes Q corresponding to all marketing sources t The specific calculation formula is as follows: q (Q) t ＝∑Q ai 。
8. The internet-based data processing system of claim 1, wherein: the marketing benefit judging module judges the whole marketing benefit improving index firstly, if the actual marketing benefit improving index is larger than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to meet the current marketing purpose, if the actual marketing benefit improving index is smaller than the expected marketing benefit improving index, the corresponding marketing scheme is indicated to not meet the current marketing purpose, the specific situation is analyzed, the marketing benefit improving index brought by the corresponding creation user in each selected APP is compared with the corresponding expected marketing benefit improving index, whether the marketing scheme which does not meet the current marketing purpose exists is judged, and the subsequent marketing fund distribution mode is adjusted.
9. The internet-based data processing system of claim 1, wherein: the marketing cost performance w is calculated according to the marketing benefits and the costs corresponding to different marketing sources in the marketing benefit data processing module v The specific formula of (2) is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310621985.9A CN116664196A (en) | 2023-05-29 | 2023-05-29 | Internet-based data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310621985.9A CN116664196A (en) | 2023-05-29 | 2023-05-29 | Internet-based data processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116664196A true CN116664196A (en) | 2023-08-29 |
Family
ID=87721859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310621985.9A Pending CN116664196A (en) | 2023-05-29 | 2023-05-29 | Internet-based data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116664196A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106611344A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Method and device for mining potential customers |
| US20170308926A1 (en) * | 2010-12-23 | 2017-10-26 | Michael R. Wofford | ARRANGEMENTS FOR FACILITATING e-COMMERCE VIA A MESSAGING SERVICE WITH SEEMLESS TRANSITION TO AN IP BASED SERVICE |
| CN108446927A (en) * | 2011-06-06 | 2018-08-24 | 恩弗伦斯媒体公司 | Consumer drives ad system |
| CN114926199A (en) * | 2022-05-05 | 2022-08-19 | 上海天擎天拓软件技术有限公司 | Internet marketing audience accurate analysis method and system |
| CN115222461A (en) * | 2022-09-19 | 2022-10-21 | 杭州数立信息技术有限公司 | Intelligent marketing accurate recommendation method |
| CN115686445A (en) * | 2022-11-29 | 2023-02-03 | 深圳市云客派科技有限公司 | SaaS (software as a service) system and service method based on digital marketing data service |
-
2023
- 2023-05-29 CN CN202310621985.9A patent/CN116664196A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170308926A1 (en) * | 2010-12-23 | 2017-10-26 | Michael R. Wofford | ARRANGEMENTS FOR FACILITATING e-COMMERCE VIA A MESSAGING SERVICE WITH SEEMLESS TRANSITION TO AN IP BASED SERVICE |
| CN108446927A (en) * | 2011-06-06 | 2018-08-24 | 恩弗伦斯媒体公司 | Consumer drives ad system |
| CN106611344A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Method and device for mining potential customers |
| CN114926199A (en) * | 2022-05-05 | 2022-08-19 | 上海天擎天拓软件技术有限公司 | Internet marketing audience accurate analysis method and system |
| CN115222461A (en) * | 2022-09-19 | 2022-10-21 | 杭州数立信息技术有限公司 | Intelligent marketing accurate recommendation method |
| CN115686445A (en) * | 2022-11-29 | 2023-02-03 | 深圳市云客派科技有限公司 | SaaS (software as a service) system and service method based on digital marketing data service |
Non-Patent Citations (5)
| Title |
|---|
| @卓战科技: "论抖音APP的广告营销策略", Retrieved from the Internet <URL:《https://www.admin5.com/article/20191011/928148.shtml》> * |
| @春天适合放牛: "怎么选择合适的平台投放广告？盘点各平台投放广告优势点", Retrieved from the Internet <URL:《https://baijiahao.baidu.com/s?id=1762860664736502365&wfr=spider&for=pc》> * |
| 代文承: "基于用户画像的新媒体广告投放策略研究——以S公司为例", 《中国优秀硕士学位论文全文数据库经济与管理科学辑》, no. 2, 15 February 2021 (2021-02-15), pages 157 - 22 * |
| 王潇仪 等: "浅析自媒体平台上Vlog形式的营销广告——以小红书APP为例", 《营销界》, no. 2, 25 January 2023 (2023-01-25), pages 152 - 154 * |
| 肖媛媛: "自媒体环境下的微博广告探析", 《新闻战线》, no. 14, 23 July 2017 (2017-07-23), pages 67 - 68 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Choi et al. | Online display advertising markets: A literature review and future directions | |
| JP4927863B2 (en) | Advertising campaign optimization | |
| Lahaie et al. | Revenue analysis of a family of ranking rules for keyword auctions | |
| JP4937962B2 (en) | Display a paid search table proportional to advertising spend | |
| AU2009225273B2 (en) | Method And System For Providing Advertising Listing Variance In Distribution Feeds | |
| JP5975875B2 (en) | Computer-implemented method and system for generating bids for a multi-channel advertising environment | |
| RU2431194C2 (en) | Distributed architecture for network advertisement | |
| Zimmermann et al. | Decomposing the variance of consumer ratings and the impact on price and demand | |
| US20110119136A1 (en) | Advertising Forecast and Revenue Systems and Methods | |
| US20070027865A1 (en) | System and method for determining semantically related term | |
| US20060106670A1 (en) | System and method for interactively and progressively determining customer satisfaction within a networked community | |
| US20090198684A1 (en) | System and Method for Determining Semantically Related Terms | |
| US20080052278A1 (en) | System and method for modeling value of an on-line advertisement campaign | |
| Reinsdorf et al. | Measuring consumer inflation in a digital economy | |
| WO2009046434A1 (en) | Collaborative production of rich media content | |
| BRPI0807017A2 (en) | DETERMINATION AND COMMUNICATION OF EXCESS INFORMATION FROM ADVERTISER DEMAND TO USERS AS PARTICIPATING, OR EXPECTED TO PARTICIPATE IN, AN ADVERTISING NETWORK | |
| JP2009169699A (en) | Sales information analysis device | |
| WO2022095701A1 (en) | Method and device for recommending objects, equipment, and storage medium | |
| TWI629604B (en) | Data set transaction and computing resource integration method | |
| JP2009169698A (en) | Sales information analysis device | |
| US20120130828A1 (en) | Source of decision considerations for managing advertising pricing | |
| CN116452261A (en) | Advertisement delivery data processing method based on cross-border E-commerce service platform | |
| Pandiangan et al. | Implementation of Operational Competitiveness Rating Analysis (OCRA) and Rank Order Centroid (ROC) to Determination of Minimarket Location | |
| Cannon | Addressing new media with conventional media planning | |
| JP5442011B2 (en) | Method, system, and computer-readable recording medium for billing for online advertising |
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 |