CN111882361A - Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium - Google Patents
Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium Download PDFInfo
- Publication number
- CN111882361A CN111882361A CN202010758398.0A CN202010758398A CN111882361A CN 111882361 A CN111882361 A CN 111882361A CN 202010758398 A CN202010758398 A CN 202010758398A CN 111882361 A CN111882361 A CN 111882361A
- Authority
- CN
- China
- Prior art keywords
- user
- advertisement
- data
- audience
- artificial intelligence
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000463 material Substances 0.000 claims abstract description 25
- 230000004913 activation Effects 0.000 claims abstract description 10
- 238000007405 data analysis Methods 0.000 claims abstract description 7
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 claims description 54
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 3
- 238000000746 purification Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000012769 display material Substances 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0236—Incentive or reward received by requiring registration or ID from user
-
- 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
- H04L67/535—Tracking the activity of the user
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to an audience accurate advertisement pushing method, system and readable storage medium based on artificial intelligence, comprising the following steps: acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform; collecting user behavior information, collecting user traffic advertisement materials, establishing a feature word library and generating a user behavior log; establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement; acquiring a user scoring vector according to the user behavior information; judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not; if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
Description
Technical Field
The invention relates to an advertisement pushing method, in particular to an audience accurate advertisement pushing method and system based on artificial intelligence and a readable storage medium.
Background
In the application practice of mobile internet advertisement under the application of user-oriented thinking, the key point is that the needs and psychology of users are thoroughly known, and a large amount of manpower and time cost is consumed for accurately subdividing and judging target users, which undoubtedly also brings a practical bottleneck to large-scale advertisement delivery.
However, when a new artificial intelligence technology appears and is applied to advertisement propagation, not only can users be quickly identified to obtain information and high-standard user segmentation be realized, but also an advertisement content analyst can predict user behaviors and advertisement effects based on an algorithm model of the analyst, so that the quality and efficiency of advertisement analysis work are improved to a great extent, and the delivery cost is reduced.
The current 5G era comes, and the 5G communication technology mainly has three characteristics: the transmission speed is fast, the quality is high and the intelligence is integrated. First, in a network environment with enhanced transmission speed and quality, users will have a greater degree of dependence on the mobile internet, so their concentration on mobile terminals and usage time will increase, which undoubtedly brings a jet of east wind to mobile advertising marketing. Moreover, the existing mobile advertisement is limited by the transmission speed, the occupied ratio of the video advertisement is not high, and the concept of the product and the brand cannot be completely shown, but in the 5G era, the occupied ratio of the video advertisement may be increased, and the playing time length of the video advertisement is correspondingly adjusted. Secondly, the real intelligent integration of everything interconnection can be realized in a 5G network platform, for example, the application of unmanned technology and telemedicine needs to be based on the high-speed network environment, and an entrance is opened for realizing multi-field penetration of mobile interconnection advertisement propagation. Meanwhile, in the aspect of the expression form, the mobile internet advertisement has more space for selection and imagination, and can interact with the user in a richer form.
The traditional capturing, storing and data analyzing technology cannot be matched with the traditional capturing, storing and data analyzing technology, on one hand, a large amount of new data cannot be effectively collected, on the other hand, in the data analyzing process, due to the fact that the relevance between the captured data is not available, the data analyzing model is inaccurate, and finally the behavior characteristics of the user cannot be accurately grasped.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides an audience accurate advertisement pushing method and system based on artificial intelligence and a readable storage medium.
In order to achieve the purpose, the invention adopts the technical scheme that: an audience accurate advertisement pushing method based on artificial intelligence comprises the following steps:
acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
acquiring a user scoring vector according to the user behavior information;
judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not;
if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
Preferably, the user behavior information includes one or more of historical browsing information, historical purchased goods information, historical searched goods information, historical collected data information, and historical searched video resources.
Preferably, the user scores the advertisement preference to obtain a scoring matrix, and the user with high similarity is obtained through analysis of the scoring matrix to obtain the recommendation list.
Preferably, the scoring unit scores the user into 5 gradients, and the user marks 1 score when clicking the advertisement; the user clicks the advertisement and stays on the advertisement page for more than 10-20s and records the time for 2 minutes; the user stays on the advertisement page for more than 1 minute and is marked as 3 minutes; the user downloads and registers for 4 points; the user generated consumption behavior as 5 points.
Preferably, the building of the advertisement recommendation model specifically includes that the input data is subjected to local convolution calculation through convolution kernels in the convolution layer, convolution kernel parameters are shared, a plurality of feature maps are generated,
the nonlinear data output by the activation function is input into the pooling layer,
extracting key features and information of users and advertisements, filtering, performing feature dimension reduction,
and outputting the characteristic map to the height purification characteristics of the full connecting layer, and outputting a result.
Preferably, the similarity calculation is to vectorize the data features, judge the relevance of the data items by using the vector inner product, obtain higher inner products for data items which are closer,
when the similarity between two features reaches a predetermined value, the two features are associated.
The second aspect of the present invention also provides an audience accurate advertisement push system based on artificial intelligence, which includes: the system comprises a memory and a processor, wherein the memory comprises an audience accurate advertisement pushing method program based on artificial intelligence, and the audience accurate advertisement pushing method program based on artificial intelligence realizes the following steps when being executed by the processor:
acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
acquiring a user scoring vector according to the user behavior information;
judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not;
if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
Preferably, the picture recommendation system further comprises a self-editing unit, and the picture data is edited by the user through the self-editing unit and transmitted to the advertisement recommendation unit to be matched with the advertisement material with high user similarity.
Preferably, the system also comprises a reward unit, the user edits portrait data by self, the portrait data comprises basic characteristics, purchasing ability, interests and hobbies, behavior characteristics and social networks of the user, the user participates in advertisement pushing to induce the user to be in deep contact with advertisement information, the user inputs the portrait data into a user data platform and rewards the user, and the reward form comprises issuing coupons, cash red packages or small gifts.
The third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes an audience accurate advertisement pushing method program based on artificial intelligence, and when the audience accurate advertisement pushing method program based on artificial intelligence is executed by a processor, the steps of any one of the above audience accurate advertisement pushing methods based on artificial intelligence are implemented.
The invention solves the defects in the background technology, and has the following beneficial effects:
(1) this application is on the basis of a large amount of analysis user's actions, through a large amount of user's action analysis, can be accurate match user and suitable advertisement, under the holding of artificial intelligence algorithm, can also carry out continuous self-learning iteration through learning feedback module, very big improvement the precision that the advertisement was put in to can carry out specific input along with situations such as time, region, the audience matching degree obtains very big improvement.
(2) The advertisement front end is displayed under the high-speed holding of a 5G communication network, richer advertisement display materials can be used, such as video advertisements, HTML5 dynamic advertisements and the like, the interactive advertisement form can help advertisement publishers to obtain more user demands, the frequency of watching advertisements by users is greatly improved, and the media can be quickly docked by an advertisement system through an open SDK/API (software development kit/application programming interface) mode.
(3) The invention has accurate positioning of users, and applies the advanced technology of artificial intelligence to the advertising industry, so that accurate marketing based on big data becomes possible. And the precise positioning is realized by integrating data sets of various layers, types and structures. Breaking barriers of various media resources, realizing data flow, perfecting a data ecological chain and constructing a user behavior characteristic database. The user groups are subdivided, and the user groups with the most requirements are found for advertisement content pushing, so that the advertisement propagation efficiency is improved to a great extent, and the waste of resources is reduced.
(4) The invention can replace basic and repeated mechanical work in the advertising process under the addition of an artificial intelligence algorithm and big data, and the machine-based self detection, judgment and promotion realizes the artificial intelligence recognition of consumer behavior tracks, the rapid judgment and information filtration, the instant positioning of advertisement propagation target groups, the pre-judgment and analysis of data and the accurate touch of target audience groups through a programmed path through the user behavior data. On the basis of programming, algorithms and data are utilized to dynamically display advertisements for different users and carry out creative optimization, so that intelligent system identification and targeted delivery are realized.
(5) The selection of marketing propagation objects (including user interests, personal attributes, purchasing power, potential purchasing intentions and the like) is completed according to the user portrait, on the basis of deeply understanding the personalized requirements of the user, through automatic crowd tracking, artificial intelligence can accurately identify the media preference and the scene preference of a target user, a high-cost-performance delivery channel which can match the dual requirements of the user demand and the user portrait and is suitable for the creative content form is screened out, and efficient flow configuration is achieved in the modes of automatic planning, accurate orientation and the like.
(6) Driven by user benefits, the user activity is high, the user has certain purpose in the process that the user participates in advertisement interaction, the user obtains real rewards through the interaction process with the advertisement, and the advertiser induces the user to deeply contact with advertisement information through issuing coupons, cash red packages or small gifts, so that the user activity is greatly improved.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart illustrating an audience-accurate advertisement push method based on artificial intelligence according to the present invention;
FIG. 2 illustrates a flow diagram of a method of modeling advertisement recommendations;
fig. 3 illustrates a block diagram of an artificial intelligence based audience accurate ad push system.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of an audience accurate advertisement pushing method based on artificial intelligence.
As shown in fig. 1, a first aspect of the present invention provides an audience accurate advertisement pushing method based on artificial intelligence, including:
s102, acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
s104, collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
s106, establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
s108, obtaining a user scoring vector according to the user behavior information, and judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not;
and S110, if the similarity between the advertisement materials and the user interest set is smaller than a preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
It should be noted that the user data platform focuses on collecting, storing, managing and analyzing user data. The user data platform has the characteristics of large data size, large scale and diversified types, can realize data integration and processing of multiple channels and different sources, and can accurately portray for the subsequent analysis of the behavior characteristics of users.
According to the embodiment of the invention, the user behavior information comprises one or more combinations of historical browsing information, historical purchased commodity information, historical searched commodity information, historical collected data information and historical searched video resources.
According to the embodiment of the invention, the user scores the favor of the advertisement to obtain the scoring matrix, and the user with high similarity is obtained through the analysis of the scoring matrix to obtain the recommendation list.
According to the embodiment of the invention, the scoring unit is used for grading the user into 5 gradients, and the user marks 1 score when clicking the advertisement; the user clicks the advertisement and stays on the advertisement page for more than 10-20s and records the time for 2 minutes; the user stays on the advertisement page for more than 1 minute and is marked as 3 minutes; the user downloads and registers for 4 points; the user generated consumption behavior as 5 points.
As shown in FIG. 2, the present invention discloses a flow chart of a method for establishing an advertisement recommendation model;
according to the embodiment of the invention, the establishment of the advertisement recommendation model specifically comprises the steps of carrying out local convolution calculation on input data through convolution kernels in the convolution layer, sharing parameters of the convolution kernels, generating a plurality of characteristic maps,
the nonlinear data output by the activation function is input into the pooling layer,
extracting key features and information of users and advertisements, filtering, performing feature dimension reduction,
and outputting the characteristic map to the height purification characteristics of the full connecting layer, and outputting a result.
According to the embodiment of the invention, the similarity is calculated by vectorizing the data characteristics, judging the relevance of the data items by utilizing the vector inner product, obtaining higher inner products for more similar data items,
when the similarity between two features reaches a predetermined value, the two features are associated.
As shown in FIG. 3, the present invention discloses a block diagram of an audience accurate advertisement delivery system based on artificial intelligence;
the second aspect of the present invention also provides an audience accurate advertisement push system based on artificial intelligence, which includes: the storage comprises an audience accurate advertisement pushing method program based on artificial intelligence, and the audience accurate advertisement pushing method program based on artificial intelligence realizes the following steps when being executed by the processor:
acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
acquiring a user scoring vector according to the user behavior information;
judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not;
if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
According to the embodiment of the invention, the self-editing unit is further included, and a user edits the image data by himself through the self-editing unit and transmits the image data to the advertisement recommending unit to match with the advertisement material with high user similarity.
According to the embodiment of the invention, the system also comprises a reward unit, the user can induce the user to deeply contact with the advertisement information by editing the portrait data by self, wherein the portrait data comprises the basic characteristics, purchasing ability, interests and hobbies, behavior characteristics and social network of the user, the user participates in advertisement pushing, the user inputs the portrait data into a user data platform, and then the user is rewarded, and the reward form comprises the issue of coupons, cash packages or small gifts.
The third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes an audience accurate advertisement pushing method program based on artificial intelligence, and when the audience accurate advertisement pushing method program based on artificial intelligence is executed by a processor, the steps of any one of the above audience accurate advertisement pushing methods based on artificial intelligence are implemented.
This application is on the basis of a large amount of analysis user's actions, through a large amount of user's action analysis, can be accurate match user and suitable advertisement, under the holding of artificial intelligence algorithm, can also carry out continuous self-learning iteration through learning feedback module, very big improvement the precision that the advertisement was put in to can carry out specific input along with situations such as time, region, the audience matching degree obtains very big improvement.
The advertisement front end is displayed under the high-speed holding of a 5G communication network, richer advertisement display materials can be used, such as video advertisements, HTML5 dynamic advertisements and the like, the interactive advertisement form can help advertisement publishers to obtain more user demands, the frequency of watching advertisements by users is greatly improved, and the media can be quickly docked by an advertisement system through an open SDK/API (software development kit/application programming interface) mode.
The invention has accurate positioning of users, and applies the advanced technology of artificial intelligence to the advertising industry, so that accurate marketing based on big data becomes possible. And the precise positioning is realized by integrating data sets of various layers, types and structures. Breaking barriers of various media resources, realizing data flow, perfecting a data ecological chain and constructing a user behavior characteristic database. The user groups are subdivided, and the user groups with the most requirements are found for advertisement content pushing, so that the advertisement propagation efficiency is improved to a great extent, and the waste of resources is reduced.
The invention can replace basic and repeated mechanical work in the advertising process under the addition of an artificial intelligence algorithm and big data, and the machine-based self detection, judgment and promotion realizes the artificial intelligence recognition of consumer behavior tracks, the rapid judgment and information filtration, the instant positioning of advertisement propagation target groups, the pre-judgment and analysis of data and the accurate touch of target audience groups through a programmed path through the user behavior data. On the basis of programming, algorithms and data are utilized to dynamically display advertisements for different users and carry out creative optimization, so that intelligent system identification and targeted delivery are realized.
The selection of marketing propagation objects (including user interests, personal attributes, purchasing power, potential purchasing intentions and the like) is completed according to the user portrait, on the basis of deeply understanding the personalized requirements of the user, through automatic crowd tracking, artificial intelligence can accurately identify the media preference and the scene preference of a target user, a high-cost-performance delivery channel which can match the dual requirements of the user demand and the user portrait and is suitable for the creative content form is screened out, and efficient flow configuration is achieved in the modes of automatic planning, accurate orientation and the like.
Driven by user benefits, the user activity is high, the user has certain purpose in the process that the user participates in advertisement interaction, the user obtains real rewards through the interaction process with the advertisement, and the advertiser induces the user to deeply contact with advertisement information through issuing coupons, cash red packages or small gifts, so that the user activity is greatly improved.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within 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 (10)
1. An audience accurate advertisement pushing method based on artificial intelligence is characterized by comprising the following steps:
acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
acquiring a user scoring vector according to the user behavior information, and judging whether the sparsity of the user scoring vector is greater than a preset threshold value or not;
if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
2. The audience accurate advertisement pushing method based on artificial intelligence as claimed in claim 1, wherein: the user behavior information comprises one or more of historical browsing information, historical purchased commodity information, historical searched commodity information, historical collected data information and historical searched video resources.
3. The audience accurate advertisement pushing method based on artificial intelligence as claimed in claim 1, wherein: and scoring the favor of the advertisement by the user to obtain a scoring matrix, and analyzing the scoring matrix to obtain the users with high similarity to obtain a recommendation list.
4. The audience accurate advertisement pushing method based on artificial intelligence as claimed in claim 3, wherein: the scoring unit is used for grading the user into 5 gradients, and the user marks 1 score when clicking the advertisement; the user clicks the advertisement and stays on the advertisement page for more than 10-20s and records the time for 2 minutes; the user stays on the advertisement page for more than 1 minute and is marked as 3 minutes; the user downloads and registers for 4 points; the user generated consumption behavior as 5 points.
5. The audience accurate advertisement pushing method based on artificial intelligence as claimed in claim 3, wherein: the building of the advertisement recommendation model specifically comprises the steps of performing local convolution calculation on input data through convolution kernels in the convolution layer, sharing convolution kernel parameters, generating a plurality of feature maps,
the nonlinear data output by the activation function is input into the pooling layer,
extracting key features and information of users and advertisements, filtering, performing feature dimension reduction,
and outputting the characteristic map to the height purification characteristics of the full connecting layer, and outputting a result.
6. The audience accurate advertisement pushing method based on artificial intelligence as claimed in claim 1, wherein: the similarity calculation is to vectorize the data characteristics, judge the relevance of the data items by utilizing the vector inner product, obtain higher inner integral for the more similar data items,
when the similarity between two features reaches a predetermined value, the two features are associated.
7. An audience accurate advertisement push system based on artificial intelligence, the system comprising: the system comprises a memory and a processor, wherein the memory comprises an audience accurate advertisement pushing method program based on artificial intelligence, and the audience accurate advertisement pushing method program based on artificial intelligence realizes the following steps when being executed by the processor:
acquiring user portrait data through big data analysis, performing behavior modeling on the user portrait data, and constructing a user data platform;
collecting user behavior information, collecting user traffic advertisement materials, performing semantic analysis, establishing a feature word bank, and generating a user behavior log;
establishing an advertisement recommendation model through a user behavior log, inputting user behavior information into the recommendation model, generating a plurality of feature maps, outputting nonlinear data through an activation function, and extracting similarity features of a user and an advertisement;
acquiring a user scoring vector according to the user behavior information;
judging whether the sparsity of the user scoring vector is larger than a preset threshold value or not;
if the similarity is smaller than the preset threshold value, calculating the similarity between the advertisement materials and the user interest set to obtain user preference information, weighting the user preference information, obtaining the advertisement materials which are interested by the user, sequencing and generating a push list.
8. The system of claim 7, wherein the system comprises: the picture recommendation system further comprises a self-editing unit, and a user edits the picture data through the self-editing unit and transmits the picture data to the advertisement recommendation unit to match with the advertisement material with high user similarity.
9. The system of claim 8, wherein the system comprises: the system also comprises a reward unit, a user edits portrait data by self, the portrait data comprises basic characteristics, purchasing ability, interests, behaviors and social networks of the user, the user participates in advertisement pushing to induce the user to be in deep contact with advertisement information, the user inputs the portrait data into a user data platform and rewards the user, and the reward form comprises the issue of coupons, cash red packages or small gifts.
10. A computer-readable storage medium characterized by: the computer readable storage medium includes an artificial intelligence-based audience precise advertisement pushing method program, and when the artificial intelligence-based audience precise advertisement pushing method program is executed by a processor, the steps of the artificial intelligence-based audience precise advertisement pushing method according to any one of claims 1 to 6 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010758398.0A CN111882361A (en) | 2020-07-31 | 2020-07-31 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010758398.0A CN111882361A (en) | 2020-07-31 | 2020-07-31 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111882361A true CN111882361A (en) | 2020-11-03 |
Family
ID=73204856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010758398.0A Pending CN111882361A (en) | 2020-07-31 | 2020-07-31 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111882361A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418935A (en) * | 2020-11-24 | 2021-02-26 | 陈敏 | Data processing method and big data platform based on big data and advertisement push |
| CN112418924A (en) * | 2020-11-17 | 2021-02-26 | 单高峰 | Advertisement pushing method based on big data and cloud computing and artificial intelligence platform |
| CN112435065A (en) * | 2020-11-27 | 2021-03-02 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement delivery method and system |
| CN113393275A (en) * | 2021-06-21 | 2021-09-14 | 安徽西柚酷媒信息科技有限公司 | Intelligent medium management system based on VOC (volatile organic compound) vehicle owner big data platform |
| CN113469755A (en) * | 2021-09-03 | 2021-10-01 | 广东联讯科技发展股份有限公司 | Intelligent accurate marketing management system based on advertisement pushing |
| CN114638646A (en) * | 2022-03-25 | 2022-06-17 | 广州华多网络科技有限公司 | Advertisement putting recommendation method and device, equipment, medium and product thereof |
| CN114912948A (en) * | 2022-04-24 | 2022-08-16 | 深圳船奇科技有限公司 | Cloud service-based cross-border e-commerce big data intelligent processing method, device and equipment |
| CN115115401A (en) * | 2022-06-27 | 2022-09-27 | 上海汇付支付有限公司 | Network advertisement aggregation platform system and operation method thereof |
| JP2023093284A (en) * | 2021-12-22 | 2023-07-04 | アウー インテリジェンス， インコーポレイテッド | Electronic marketing system and execution method thereof |
| CN116503115A (en) * | 2023-06-27 | 2023-07-28 | 深圳市火星人互动娱乐有限公司 | Advertisement resource recommendation method and system based on Internet game platform |
| CN116662671A (en) * | 2023-07-24 | 2023-08-29 | 中国标准化研究院 | Digital library data pushing method based on user preference |
| CN116757749A (en) * | 2023-08-18 | 2023-09-15 | 苏州遥遥在望科技有限公司 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
| CN116894709A (en) * | 2023-07-14 | 2023-10-17 | 广州洋葱时尚集团有限公司 | Advertisement commodity recommendation method and system |
| CN117196725A (en) * | 2023-11-06 | 2023-12-08 | 厦门乾升网络科技有限公司 | Advertisement intelligent pushing system suitable for short video platform |
| CN117333800A (en) * | 2023-10-12 | 2024-01-02 | 广州有好戏网络科技有限公司 | Cross-platform content operation optimization method and system based on artificial intelligence |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412644A (en) * | 2016-09-19 | 2017-02-15 | 北京喂呦科技有限公司 | Accurate advertising method and system based on smart TV player |
| CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术（深圳）有限公司 | Advertisement intelligent recommends method, server and storage medium |
| CN109615408A (en) * | 2018-10-24 | 2019-04-12 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device, storage medium, electronic equipment based on big data |
| CN110210899A (en) * | 2019-05-23 | 2019-09-06 | 中国银行股份有限公司 | Advertisement sending method, device and equipment based on advertisement similitude |
| CN110232605A (en) * | 2019-06-21 | 2019-09-13 | 安吉艾格赛思生物科技有限公司 | A kind of crowd's method for delivering advertisement accurately and system based on internet big data |
| CN110874756A (en) * | 2018-09-03 | 2020-03-10 | 广州市微聚宝网络技术有限公司 | Reward type advertisement publishing system and method |
| CN110942351A (en) * | 2019-12-02 | 2020-03-31 | 广州诚毅科技咨询有限公司 | Product marketing method based on big data |
| CN111292168A (en) * | 2020-02-06 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Data processing method, device and equipment |
| CN111310056A (en) * | 2020-03-11 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN111344731A (en) * | 2017-11-14 | 2020-06-26 | 温奎斯特公司 | System and method for providing real-time targeted advertising |
-
2020
- 2020-07-31 CN CN202010758398.0A patent/CN111882361A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106412644A (en) * | 2016-09-19 | 2017-02-15 | 北京喂呦科技有限公司 | Accurate advertising method and system based on smart TV player |
| CN111344731A (en) * | 2017-11-14 | 2020-06-26 | 温奎斯特公司 | System and method for providing real-time targeted advertising |
| CN108776907A (en) * | 2018-05-31 | 2018-11-09 | 康键信息技术（深圳）有限公司 | Advertisement intelligent recommends method, server and storage medium |
| CN110874756A (en) * | 2018-09-03 | 2020-03-10 | 广州市微聚宝网络技术有限公司 | Reward type advertisement publishing system and method |
| CN109615408A (en) * | 2018-10-24 | 2019-04-12 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device, storage medium, electronic equipment based on big data |
| CN110210899A (en) * | 2019-05-23 | 2019-09-06 | 中国银行股份有限公司 | Advertisement sending method, device and equipment based on advertisement similitude |
| CN110232605A (en) * | 2019-06-21 | 2019-09-13 | 安吉艾格赛思生物科技有限公司 | A kind of crowd's method for delivering advertisement accurately and system based on internet big data |
| CN110942351A (en) * | 2019-12-02 | 2020-03-31 | 广州诚毅科技咨询有限公司 | Product marketing method based on big data |
| CN111292168A (en) * | 2020-02-06 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Data processing method, device and equipment |
| CN111310056A (en) * | 2020-03-11 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 高扬: "《人工智能与机器人先进技术丛书 智能摘要与深度学习》", vol. 2019, 30 April 2019, 北京理工大学出版社, pages: 41 - 44 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112418924A (en) * | 2020-11-17 | 2021-02-26 | 单高峰 | Advertisement pushing method based on big data and cloud computing and artificial intelligence platform |
| CN112418924B (en) * | 2020-11-17 | 2021-08-20 | 上海东方财富金融数据服务有限公司 | Advertisement pushing method based on big data and cloud computing and artificial intelligence platform |
| CN112418935A (en) * | 2020-11-24 | 2021-02-26 | 陈敏 | Data processing method and big data platform based on big data and advertisement push |
| CN112418935B (en) * | 2020-11-24 | 2021-08-20 | 上海东方财富金融数据服务有限公司 | Data processing method and big data platform based on big data and advertisement push |
| CN112435065A (en) * | 2020-11-27 | 2021-03-02 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement delivery method and system |
| CN112435065B (en) * | 2020-11-27 | 2024-03-01 | 杭州推啊网络科技有限公司 | Mobile internet non-standard position interactive advertisement putting method and system |
| CN113393275A (en) * | 2021-06-21 | 2021-09-14 | 安徽西柚酷媒信息科技有限公司 | Intelligent medium management system based on VOC (volatile organic compound) vehicle owner big data platform |
| CN113469755A (en) * | 2021-09-03 | 2021-10-01 | 广东联讯科技发展股份有限公司 | Intelligent accurate marketing management system based on advertisement pushing |
| CN113469755B (en) * | 2021-09-03 | 2022-02-08 | 广东联讯科技发展股份有限公司 | Intelligent accurate marketing management system based on advertisement pushing |
| JP2023093284A (en) * | 2021-12-22 | 2023-07-04 | アウー インテリジェンス， インコーポレイテッド | Electronic marketing system and execution method thereof |
| CN114638646A (en) * | 2022-03-25 | 2022-06-17 | 广州华多网络科技有限公司 | Advertisement putting recommendation method and device, equipment, medium and product thereof |
| CN114912948B (en) * | 2022-04-24 | 2023-03-24 | 深圳船奇科技有限公司 | Cloud service-based cross-border e-commerce big data intelligent processing method, device and equipment |
| CN114912948A (en) * | 2022-04-24 | 2022-08-16 | 深圳船奇科技有限公司 | Cloud service-based cross-border e-commerce big data intelligent processing method, device and equipment |
| CN115115401A (en) * | 2022-06-27 | 2022-09-27 | 上海汇付支付有限公司 | Network advertisement aggregation platform system and operation method thereof |
| CN116503115A (en) * | 2023-06-27 | 2023-07-28 | 深圳市火星人互动娱乐有限公司 | Advertisement resource recommendation method and system based on Internet game platform |
| CN116503115B (en) * | 2023-06-27 | 2024-05-03 | 深圳市火星人互动娱乐有限公司 | Advertisement resource recommendation method and system based on Internet game platform |
| CN116894709A (en) * | 2023-07-14 | 2023-10-17 | 广州洋葱时尚集团有限公司 | Advertisement commodity recommendation method and system |
| CN116662671B (en) * | 2023-07-24 | 2023-10-27 | 中国标准化研究院 | Digital library data pushing method based on user preference |
| CN116662671A (en) * | 2023-07-24 | 2023-08-29 | 中国标准化研究院 | Digital library data pushing method based on user preference |
| CN116757749B (en) * | 2023-08-18 | 2023-11-10 | 苏州遥遥在望科技有限公司 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
| CN116757749A (en) * | 2023-08-18 | 2023-09-15 | 苏州遥遥在望科技有限公司 | Advertisement pushing effect evaluation method, system and storage medium based on big data |
| CN117333800A (en) * | 2023-10-12 | 2024-01-02 | 广州有好戏网络科技有限公司 | Cross-platform content operation optimization method and system based on artificial intelligence |
| CN117333800B (en) * | 2023-10-12 | 2024-04-05 | 广州有好戏网络科技有限公司 | Cross-platform content operation optimization method and system based on artificial intelligence |
| CN117196725A (en) * | 2023-11-06 | 2023-12-08 | 厦门乾升网络科技有限公司 | Advertisement intelligent pushing system suitable for short video platform |
| CN117196725B (en) * | 2023-11-06 | 2024-01-23 | 厦门乾升网络科技有限公司 | Advertisement intelligent pushing system suitable for short video platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111882361A (en) | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium | |
| Pantano et al. | Making sense of consumers’ tweets: Sentiment outcomes for fast fashion retailers through Big Data analytics | |
| CN112131472B (en) | Information recommendation method, device, electronic equipment and storage medium | |
| CN103886074A (en) | Commodity recommendation system based on social media | |
| CN107871244A (en) | The detection method and device of a kind of advertising results | |
| CN111882362A (en) | Artificial intelligence advertisement delivery system based on 5G communication network | |
| TW201905736A (en) | Information push method and system | |
| CN112287238B (en) | User characteristic determination method and device, storage medium and electronic equipment | |
| Saputra et al. | The impact of using ai chat gpt on marketing effectiveness: A case study on instagram marketing | |
| CN117114772A (en) | Method, device, equipment and storage medium for mining put-in materials | |
| Halkiopoulos et al. | Cultural and tourism promotion through digital marketing approaches. A case study of social media campaigns in Greece | |
| Kowalczyk et al. | Nudging creativity in digital marketing with generative artificial intelligence: Opportunities and limitations | |
| Priyanka et al. | Leadership Transition In Different Eras Of Marketing From 1950 Onwards | |
| Jain et al. | Improving customer experience using sentiment analysis in e-commerce | |
| Kim et al. | Competitive intelligence in Korean Ramen market using text mining and sentiment analysis | |
| Allaymoun et al. | Business intelligence model to analyze social network advertising | |
| KR102449602B1 (en) | Apparatus and method for processing information related to product in multimedia contents | |
| Zhao et al. | Predicting the voluntary donation to online content creators | |
| Zheng et al. | Big data usage in marketing research | |
| CN113077295B (en) | Advertisement graded delivery method based on user terminal, user terminal and storage medium | |
| Srivastava et al. | Social media analytics: current trends and future prospects | |
| Zu | The validity of visual communication design of online advertisement based on interactivity | |
| Jang et al. | Visual attributes of thumbnails in predicting top youTube brand channels: a machine learning approach | |
| Lindén | Path Analysis of Online Users Using Clickstream Da-ta: Case Online Magazine Website | |
| Hng et al. | The forefront of mobile shopping: an emerging economy's perspective |
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 |