CN112950256B - Method and system for customizing advertisement form based on App pushing - Google Patents
Method and system for customizing advertisement form based on App pushing Download PDFInfo
- Publication number
- CN112950256B CN112950256B CN202110144462.0A CN202110144462A CN112950256B CN 112950256 B CN112950256 B CN 112950256B CN 202110144462 A CN202110144462 A CN 202110144462A CN 112950256 B CN112950256 B CN 112950256B
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- app
- commodities
- advertisement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000001914 filtration Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 30
- 238000013145 classification model Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000002537 cosmetic Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000692 anti-sense effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008685 targeting Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9574—Browsing optimisation, e.g. caching or content distillation of access to content, e.g. by caching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to the technical field of networks, in particular to a method and a system for customizing an advertisement form based on App pushing, which comprises the following steps: obtaining: acquiring user-related preference commodities, and recording: recording the stay time of the user for the related commodity and the content searched by the related commodity, and carrying out statistics: counting the browsing time, browsing times and purchasing times of related commodities acquired by a user, and comparing: compared with other commodity information, pushing: the advertisement is pushed to the user with respect to the preferred merchandise. According to the method and the device, the related preference commodity of the APP is obtained through the browsing time of the APP when the user selects the commodity every time, the advertisement is pushed to the user according to the recorded and compared related preference commodity, the limitation of traditional advertisement display is solved, the display cost of the traditional advertisement is greatly reduced, the convenience of advertisement display operation is greatly improved, the labor cost is saved, and the push management of the advertisement can be controlled online.
Description
Technical Field
The invention relates to a method and a system for customizing an advertisement form, in particular to a method and a system for pushing the customized advertisement form based on an App, and belongs to the technical field of networks.
Background
The mobile phone software is the software installed on the smart phone, and a corresponding mobile phone system is required to operate, and the main functions of the mobile phone software are the deficiency and individuation of the original system, so that the functions of the mobile phone are more perfect, and richer use experience is provided for users.
With popularization and deep application of the network, the Internet gathers extremely abundant information resources, and under the network environment of information explosion, people are not satisfied with the active information acquisition mode such as portal websites and search engines, more hopefully, the information resources which are relevant to own interests, rich in sources and clear in theme are known in a customizable and instant mode through content monitoring, one common mode is information push, and the information push of mobile phone App is rapid in development due to the advantages of high popularity, convenience in carrying and high information real-time performance of mobile phones compared with computers.
The existing APP advertisement pushing is generally indistinguishable, when a merchant pushes commodity information of all users, the merchant does not have targeting, and some useless messages can be pushed to the users to a great extent, so that discomfort of the clients can be caused, the users can feel dislike seriously, and the problems of advertisement operation, high replacement cost, low replacement time and the like exist.
Accordingly, there is a need for an improved method and system for customizing ad formats based on App push to address the above-described problems.
Disclosure of Invention
The invention aims to provide a method and a system for customizing advertisement forms based on App pushing, which are used for acquiring related preference commodities of APP browsed by a user through browsing time of the related commodities of APP when the user selects the commodities each time, pushing advertisements to the user according to the recorded and compared related preference commodities, solving the limitation of traditional advertisement display, greatly reducing the display cost of the traditional advertisement, simultaneously achieving advertisement display with higher timeliness, greatly improving the convenience of advertisement display operation, saving the labor cost and realizing on-line controllable advertisement pushing management.
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
a method for customizing an advertisement form based on App pushing comprises the following steps:
s1: obtaining: acquiring related preference commodities of the APP browsed by a user according to the browsing time of the APP related commodities when the user selects the commodities each time;
s2: recording: a background control system on the APP total server records the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
S3: and (3) statistics: the background control system counts the browsing time, browsing times and purchasing times of related commodities acquired by the user;
s4: comparison: comparing the time of browsing on other commodity information with the time of browsing on other commodity information by the user, and counting out related preference commodities of the user;
s5: pushing: pushing advertisements to the user according to the recorded and compared related preference commodities;
according to the technical scheme, when a user selects commodities each time, the related APP commodity browsing time is obtained, the related APP commodity browsing time is recorded, the user stay time for the related commodities and the related commodity searching content are recorded, the related commodity browsing time, browsing times and purchasing times are counted through the background control system, the related APP commodity browsing time is compared with the browsing time of the user on other commodity information, advertisements are pushed to the user according to the recorded and compared related APP commodity, and a company performs preferential activities in a certain city to release an advertisement message, however, the information accords with the user preference information, the user can watch, the limitation of traditional advertisement display is solved, the display cost of the traditional advertisement is greatly reduced, meanwhile, the advertisement display operation convenience is greatly improved, the labor cost is saved, and the on-line advertisement push management can be controlled.
Preferably, in step S5, the push advertisement includes an advertisement poster, a video advertisement and an H5 applet, the push advertisement is pushed to an APP client through an APP total server, the APP client reports a display log to the APP total server, and the APP total server calculates advertisement cost.
Preferably, the background control system comprises any one or more of an android system, an IOS system, a Mac system, a Windows system, a NetWare system, a Unix system and a Linux system.
Preferably, the APP establishes a connection with the internet and a retail management platform for accessing and acquiring related commodities, and the related commodities of the APP include living goods, sports goods, literature goods and electronic goods.
Preferably, step S5 further comprises the steps of:
s5.1: when a user browses commodities by using an APP;
when the APP total server pushes common commodity advertisement content to an APP client, after the APP client receives an advertisement closing instruction, stopping advertisement pushing and starting the APP;
when the APP total server pushes the content of the related preference commodity advertisement to the APP client, starting the APP after the advertisement is played;
meanwhile, the APP total server receives the commodity selected by the user through the APP client terminal in a self-defining way;
S5.2: the APP total server records commodity keywords input by each user, establishes a word-gathering word stock, and sorts the word-gathering word stock according to the input times and the purchase times;
s5.3: the APP total server generates a filtering condition of information pushing according to the word stock of the word class, wherein the filtering condition is a relation list, and the relation list comprises a user group, commodity heat and one or more word class gathering keywords corresponding to the user group;
s5.4: the APP total server screens out users containing specified keywords according to filtering conditions;
s5.5: and the APP total server pushes the information to the APP client of the screened user, wherein the information pushed to the APP client of the user comprises advertisement poster information, video screen information, H5 information and network article information.
Preferably, in step S3:
the App total server takes the message type, the message style and the time information input by a user as a part of the filtering condition;
the App total server takes the message type, the message style, the time information and as part of its keywords.
Through the technical proposal, the App total server receives user information input by a user on the APP and/or browsing habit information of the user, compares the information with user group characteristic information which is set for each advertisement content in a background control system and allows pushing, wherein the advertisement content which is matched with the user group characteristic information and allows pushing is advertisement content meeting advertisement pushing standards on the user dimension, when the advertisement content is screened, according to the user browsing goods by using the APP, the APP total server receives goods which are custom selected by the user through the APP client, establishes a word class word stock, sorts the word class word stock according to the input times and the purchase times, generates a filtering condition of information pushing according to the word class word stock, the filtering condition is a relation list, the relation list comprises a user group, commodity heat and one or more similar keywords corresponding to the user group, then the APP total server screens out the users containing the specified keywords according to the filtering condition, and when the APP total server pushes information to the APP client of the screened users, advertisement contents conforming to the current advertisement pushing type and the like are calculated to obtain advertisement contents meeting related preference commodities simultaneously, of course, different advertisement contents can be forced advertisement pushing or common advertisement pushing according to merchant settings, when more than one advertisement content exists in the advertisement contents after being calculated, the advertisement contents are pushed according to the priority relation set by the merchant, or alternatively the advertisement contents are pushed, that is, the advertisement contents can be pushed next time, the next time another advertisement content is pushed again until one round goes through the next round of circulation.
Through the technical scheme, the push information is common push or forced push, the common push means that a user can select to close an advertisement, the forced push means that the user can start the APP after watching the advertisement, that is, when the APP total server pushes the advertisement content of a common type to a terminal, a button for closing the advertisement is reserved on an APP client page, after the user clicks the button, the APP client sends an advertisement closing instruction to the APP total server, after receiving the advertisement closing instruction of the APP client, the APP total server stops advertisement push and starts the APP, merchants can set different push information for different advertisement contents, the push information comprises advertisement poster information, video screen information, H5 information and network article information, the advertisement can be forcefully played for important advertisements, the advertisement with relatively low important degree can be set to be closed by the user, the anti-sense degree of the advertisement push of the user is reduced, meanwhile, the related preference of the user for browsing the APP commodity is acquired according to the time of the user for selecting the APP commodity each time, the user can ensure the user experience of the commodity browsing, the advertisement is greatly improved, the advertisement display cost is greatly reduced, the convenience of the advertisement display is realized, and the convenience of the user has the advertisement display is greatly reduced, and the operation cost is greatly reduced.
Preferably, a method for customizing advertisement forms based on App push, in step S2:
s2.1: the App total server is used for acquiring the content retrieved by the user for the related commodity;
s2.2: formatting the retrieved content of the acquired related commodity to obtain initial data, acquiring preset classification characteristics, and preprocessing the classification characteristics to obtain training data;
s2.3: training the initial data based on the training data to obtain characteristic data of content retrieved by related commodities in the initial data;
s2.4: constructing a target data classification model, and inputting the characteristic data of the content retrieved by the related commodity in the initial data into the target data classification model to obtain a probability output matrix corresponding to the characteristic data of the content retrieved by the related commodity;
s2.5: acquiring a preset weight matrix, and correcting the probability output matrix through the preset weight matrix to obtain a weighted probability output matrix;
the weight matrix is generated according to the classification result of the target data classification model on each training sample in a preset training sample set;
s2.5: determining a classification result of the content retrieved by the related commodity based on the weighted probability output matrix;
S2.6: acquiring feature data corresponding to the content retrieved by related commodities in each category, and determining feature weights of the feature data;
s2.7: taking the characteristic data corresponding to the content searched by the related commodity in each category as first training data in each category, and calculating the Euclidean distance between the first training data in each category and the common data corresponding to the content searched by the related commodity in the category;
s2.8: determining the weight of common data corresponding to the content retrieved by the related commodity in each category based on the Euclidean distance and the characteristic weight of the characteristic data;
s2.9: obtaining comprehensive weights of the content retrieved by the related commodities in each category according to the weights of the common data corresponding to the content retrieved by the related commodities in each category and the characteristic weights of the characteristic data;
s2.10: and ordering the classification results based on the comprehensive weight of the content searched by the related commodity in each category, and completing the record of the content searched by the user on the related commodity.
Preferably, a method for customizing advertisement forms based on App push, in step S4:
acquiring the time length of browsing related commodities by the user and the time length of browsing other commodity information by the user;
According to the browsing time of the user on the related commodity and other commodity information, calculating the importance degree value of the related commodity relative to other commodity information, and calculating the accuracy of the counted related preference commodity of the user according to the importance degree value, wherein the specific steps comprise:
calculating the importance degree value of the related commodity relative to other commodities according to the following formula:
wherein, gamma represents the importance value of the related commodity relative to other commodities, and the value range is (0, 1); μ represents a coefficient of tendency of the user to the related commodity, and the value range is (0.5,0.7); sigma represents a weight value of the related commodity; the E represents the tendency coefficient of the user to other commodity information, and the value range is (0.3, 0.5); omega represents the weight value of the other commodity information; τ represents a time specific gravity factor; t is t 1 A value representing a length of time the user has spent browsing related items; t is t 2 A value representing a length of time for the user to browse other merchandise information;
the accuracy of the counted user-related preference commodity is calculated according to the following formula:
wherein ,
the accuracy of the counted user-related preference commodity is represented, and the value range is (0, 1); gamma represents the importance value of the related commodity relative to other commodities, and the value range is (0, 1); θ represents the demand coefficient of the user for the related preference commodity, and the value range is (0.6,0.8); epsilon represents the correlation Preference for the number of goods; />
Representing the total number of commodities browsed by the user; beta represents an error coefficient, and the value range is 0.25,0.56; kappa indicates the number of times the user browses the relevant preferred items; q represents the number of times the user purchased the relevant preference commodity;
comparing the accuracy obtained by calculation with preset accuracy;
if the accuracy is greater than or equal to the preset accuracy, judging that the statistical result is qualified, and pushing the related advertisement of the user related preference commodity to the user terminal;
otherwise, judging that the statistical result is unqualified, and re-acquiring the time length of browsing the related goods by the user and the time length of browsing other goods information by the user, and calculating the accuracy of counting the related preference goods of the user again until the calculated accuracy is greater than or equal to the preset accuracy, so that the related advertisement of the related preference goods of the user is pushed to the user terminal.
The system based on the APP pushing customized advertisement form comprises an APP total server, a background control system, a retail management platform and an APP client which are respectively connected with the APP total server, wherein the APP total server comprises an acquisition module, a recording module, a statistics module, a comparison module and a pushing module,
The acquisition module is used for acquiring related preference commodities of the APP browsed by the user according to the browsing time of the APP related commodities when the user selects the commodities each time;
the recording module is used for recording the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
the statistics module is used for counting the browsing time, the browsing times and the purchasing times of the related commodities acquired by the user;
the comparison module is used for comparing the browsing time of the user on other commodity information and counting the related preference commodities of the user;
and the pushing module is used for pushing advertisements to the user according to the recorded and compared related preference commodities.
Preferably, the pushing module comprises a receiving module, a keyword word stock generation module, a filtering condition generation module and a screening module,
the receiving module is used for receiving the user to select commodities in a self-defined mode through the APP client;
the class gathering keyword lexicon generating module is used for recording commodity keywords input by each user, establishing a class gathering lexicon and sequencing the class gathering lexicon according to the input times and the purchase times;
the filtering condition generation module is used for generating a filtering condition of information pushing according to the word stock of the class aggregation, wherein the filtering condition is a relation list, and the relation list comprises a user group, commodity heat and one or more class aggregation keywords corresponding to the user group;
The screening module is used for screening out users containing specified keywords according to the filtering conditions.
Through the technical scheme, the receiving module is used for receiving keywords which are required to be contained in the push information which is input by the user through the App client terminal in a self-defining way;
the generation module of the word stock of the clustering key words is used for recording the key words input by each user and establishing the word stock of the clustering key words, and the generation module is further used for: and sorting the word libraries of the clustering keywords according to the input times of the keywords, displaying N clustering keywords before the sorting in an input interface of an App client, and selecting by a user.
The invention has at least the following beneficial effects:
1. the method has the advantages that the time for browsing the APP related commodities is obtained when the user selects the commodities each time, the user browses the APP related preference commodities, advertisements are pushed to the user according to the recorded and compared related preference commodities, the limitation of traditional advertisement display is solved, the display cost of the traditional advertisements is greatly reduced, meanwhile, advertisement display with higher timeliness is achieved, the convenience of advertisement display operation is greatly improved, the labor cost is saved, and the push management of the advertisements can be controlled online.
2. According to the method, when a user browses commodities by using an APP, the APP total server receives the commodities selected by the user through the APP client terminal in a self-defining way, establishes a word-gathering word library, sorts the word-gathering word library according to the input times and the purchase times, generates a filtering condition of information pushing according to the word-gathering word library, wherein the filtering condition is a relation list, the relation list comprises a user group, commodity heat and one or more word-gathering keywords corresponding to the user group, then the APP total server screens out the users containing the specified keywords according to the filtering condition, and pushes the information to the APP client terminal of the screened user by the APP total server, advertisement contents meeting the current advertisement pushing types and the like are calculated to obtain advertisement contents meeting the related preference commodities at the same time, so that the objection of the user is avoided, and the purpose of popularization is achieved.
3. The obtained content of the related commodity retrieval is classified by the user, the weight value of each category is determined, and the commodity category retrieved by the user is sequenced and recorded according to the weight value, so that the efficiency of determining the deviation of the user to the commodity is improved, meanwhile, the favorite commodity of the user is conveniently and accurately recommended to the user according to the sequencing result, and the accuracy of advertisement pushing is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic flow chart of a pushing method according to the present invention;
FIG. 3 is a schematic diagram of the structure of the present invention;
fig. 4 is a schematic diagram of a push information structure according to the present invention.
Detailed Description
The embodiments of the present application will be described in detail below with reference to the accompanying drawings and examples, so that the implementation process of how the technical means are applied to solve the technical problems and achieve the technical effects of the present application can be fully understood and implemented accordingly.
As shown in fig. 1 to fig. 4, the method for customizing an advertisement form based on App push provided in this embodiment includes the following steps:
S1: obtaining: acquiring related preference commodities of the APP browsed by a user according to the browsing time of the APP related commodities when the user selects the commodities each time;
s2: recording: the background control system on the APP total server records the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
s3: and (3) statistics: the background control system counts the browsing time, browsing times and purchasing times of related commodities acquired by a user;
s4: comparison: comparing the time of browsing on other commodity information with the time of browsing on other commodity information by the user, and counting out related preference commodities of the user;
s5: pushing: and pushing advertisements to the users according to the recorded and compared related preference commodities.
The conventional APP advertisement pushing is generally indistinguishable, when a merchant pushes commodity information of all users, the merchant does not have targeting, a plurality of useless messages are pushed to the users to a great extent, discomfort of the clients is caused, and the users are seriously dislike, the related preference commodities of the APP are obtained through browsing time of the APP related commodities when the users select the commodities each time, stay time of the users aiming at the related commodities and content of related commodity retrieval are recorded, statistics is carried out on time, browsing times and purchasing times of the related commodities obtained by the users through a background control system, the related commodities of the users are counted and compared with the browsing time of the users on other commodity information, advertisements are pushed to the users according to the recorded and compared related preference commodities, and if a company does preferential activities in a certain city, one piece of advertisement information is required to be released, however, the information accords with the preference information of the users, the users can watch the limitation of traditional advertisement display is solved, the cost of the traditional advertisement is greatly reduced, meanwhile, the time efficiency is higher, the advertisement display is greatly improved, the operation cost of the advertisement can be controlled, and the advertisement can be pushed, and the advertisement is convenient is controlled.
In step S5, the push advertisement includes advertisement poster, video advertisement and H5 applet, push advertisement to APP client through APP total server, APP client reports display log to APP total server, APP total server calculates advertisement cost, first make picture advertisement poster or video advertisement, applet or APP total server upload advertisement poster or video push to APP client display, APP end reports display log to APP total server, APP total server carries out advertisement cost calculation, unify by the display of online management advertisement, online make advertisement poster or video, push to APP end through the backstage program, advertisement show, promote the efficiency of popularization greatly.
The background control system comprises any one or a combination of a plurality of android system, IOS system, mac system, windows system, netWare system, unix system and Linux system, and the application range of the background control system is improved.
In this embodiment, as shown in fig. 3, APP establishes a connection with the internet and a retail management platform, and is used for accessing and acquiring related commodities, including living goods, sports goods, literature goods and electronic goods, so as to enlarge a commodity coverage area and promote retail profits.
In this embodiment, as shown in fig. 2, step S5 further includes the following steps:
s5.1: when a user browses commodities by using an APP;
when the APP total server pushes common commodity advertisement content to an APP client, after the APP client receives an advertisement closing instruction, stopping advertisement pushing and starting the APP;
when the APP total server pushes the content of the related preference commodity advertisement to the APP client, the APP is started after the advertisement is played
Meanwhile, the APP total server receives the commodity selected by the user through the APP client terminal in a self-defining way;
s5.2: the APP total server records commodity keywords input by each user, establishes a word-gathering word stock, and sorts the word-gathering word stock according to the input times and the purchase times;
s5.3: the APP total server generates a filtering condition of information pushing according to the word-gathering word stock, wherein the filtering condition is a relation list, and the relation list comprises a user group, commodity heat and one or more word-gathering keywords corresponding to the user group;
s5.4: the APP total server screens out users containing specified keywords according to the filtering conditions;
s5.5: and the APP total server pushes the information to the APP client of the screened user, wherein the information pushed to the APP client of the user comprises advertisement poster information, video screen information, H5 information and network article information.
In this embodiment, as shown in fig. 4, the push information includes advertisement poster information, video screen information, H5 information, and web article information, and the push information is pushed to the APP client through the APP total server.
In step S3:
the App total server takes the message type, the message style and the time information input by the user as a part of the filtering condition;
the App total server will message type, message style, time information and as part of its keywords.
The App total server receives user information and/or browsing habit information of the user input by the user on the APP, compares the user information with user group feature information which is set for each advertisement content and allows pushing in a background control system, wherein the advertisement content which is matched with the user group feature information which allows pushing is the advertisement content which meets the advertisement pushing standard in the user dimension, when the advertisement content is screened, according to the fact that when the user browses commodities by using the APP, the APP total server receives the commodity selected by the user through the APP client terminal in a self-defining way, and establishes a word stock of the class, sorts the word stock of the class according to the input times and the purchase times, generates a filtering condition of information pushing according to the word stock of the class, wherein the filtering condition is a relation list which comprises a user group, commodity heat and one or more class gathering keywords corresponding to the user group, then the APP total server screens out users containing specified keywords according to the filtering conditions, in the process that the APP total server pushes information to the APP client of the screened user, advertisement contents conforming to the current advertisement pushing type and the like are calculated to obtain advertisement contents meeting related preference commodities at the same time, of course, different advertisement contents can be forced pushing advertisements according to merchant settings, or common push advertisement, when more than one advertisement content exists in the advertisement content after calculation, pushing the advertisement content according to the priority relation set by the merchant, or alternatively push the advertisement content in turn, that is, this time the advertisement content can be pushed, another advertisement content is pushed next, and another advertisement content is pushed next again until one round goes through the next round.
The push information is common push or forced push, the common push means that a user can select to close an advertisement, the forced push means that the user can start the APP after watching the advertisement, that is, when the APP total server pushes the common type advertisement content to the terminal, a button for closing the advertisement is reserved on an APP client page, after the user clicks the button, the APP client sends an advertisement closing instruction to the APP total server, after receiving the advertisement closing instruction of the APP client, the APP total server stops advertisement push and starts the APP, different push information can be set for different advertisement contents, the push information comprises advertisement poster information, video screen information, H5 information and network article information, the important advertisement can be forcefully played, the advertisement with relatively low importance degree can be set to be closed by the user, the anti-sense degree of the user on advertisement push is reduced, meanwhile, the related preference commodity of the APP is obtained for the user according to the time of browsing the APP related commodity when the user selects the commodity each time, the user can greatly improve the user experience, the traditional advertisement display cost is greatly reduced, the advertisement display cost is greatly improved, the convenience is realized, and the advertisement management line is displayed, and the convenience is greatly improved.
The invention provides a method for customizing an advertisement form based on App pushing, which comprises the following steps of:
s2.1: the App total server is used for acquiring the content retrieved by the user for the related commodity;
s2.2: formatting the retrieved content of the acquired related commodity to obtain initial data, acquiring preset classification characteristics, and preprocessing the classification characteristics to obtain training data;
s2.3: training the initial data based on the training data to obtain characteristic data of content retrieved by related commodities in the initial data;
s2.4: constructing a target data classification model, and inputting the characteristic data of the content retrieved by the related commodity in the initial data into the target data classification model to obtain a probability output matrix corresponding to the characteristic data of the content retrieved by the related commodity;
s2.5: acquiring a preset weight matrix, and correcting the probability output matrix through the preset weight matrix to obtain a weighted probability output matrix;
the weight matrix is generated according to the classification result of the target data classification model on each training sample in a preset training sample set;
s2.5: determining a classification result of the content retrieved by the related commodity based on the weighted probability output matrix;
S2.6: acquiring feature data corresponding to the content retrieved by related commodities in each category, and determining feature weights of the feature data;
s2.7: taking the characteristic data corresponding to the content searched by the related commodity in each category as first training data in each category, and calculating the Euclidean distance between the first training data in each category and the common data corresponding to the content searched by the related commodity in the category;
s2.8: determining the weight of common data corresponding to the content retrieved by the related commodity in each category based on the Euclidean distance and the characteristic weight of the characteristic data;
s2.9: obtaining comprehensive weights of the content retrieved by the related commodities in each category according to the weights of the common data corresponding to the content retrieved by the related commodities in each category and the characteristic weights of the characteristic data;
s2.10: and ordering the classification results based on the comprehensive weight of the content searched by the related commodity in each category, and completing the record of the content searched by the user on the related commodity.
In this embodiment, the formatting process is to process the content retrieved by the relevant commodity to obtain the data corresponding to the commodity, so as to process the data corresponding to the commodity.
In this embodiment, the classification feature refers to a classification rule set in advance, and may be, for example, a use object for each commodity, a material property of the commodity, or the like.
In this embodiment, the feature data refers to a certain key data segment, which can represent the whole data, in the data corresponding to the commodity, and is used to represent the attribute of the data corresponding to the commodity.
In this embodiment, the feature weight refers to the proportion of feature data in the data corresponding to the commodity to all the data.
In this embodiment, the integrated weight is obtained by integrating the weight value of the feature data in the data corresponding to the commodity with the weight of the other data except the feature data.
In this embodiment, the normal data refers to data other than the characteristic data among the data corresponding to the commodity.
In this embodiment, the probability value of each category is assigned to the content retrieved by each matrix element in the probability output matrix corresponding to the relevant commodity, for example, the probability of the retrieved content of cosmetics being classified into the cosmetic category is 0.2, and the probability of the retrieved content of daily necessities being classified into the daily necessities is 0.4.
In this embodiment, the weight matrix is generated according to the classification result of each training sample in the training sample set by the target data classification model, that is, the weight matrix makes the classification evaluation index reach the highest value, the classification evaluation quality guarantee may be the accuracy of classification, and each matrix element in the weight matrix is used for correcting each matrix element in the probability output matrix, for example, the probability correction weight for the cosmetics is 0.5, and the probability correction weight for the household goods is 0.3.
In this embodiment, the weighted probability output matrix is obtained by multiplying the elements in the same position in the probability output matrix and the weight matrix, and is the final basis for distinguishing the category of the related commodity retrieval content.
The beneficial effects of the technical scheme are as follows: the obtained content of the related commodity retrieval is classified by the user, the weight value of each category is determined, and the commodity category retrieved by the user is sequenced and recorded according to the weight value, so that the efficiency of determining the deviation of the user to the commodity is improved, meanwhile, the favorite commodity of the user is conveniently and accurately recommended to the user according to the sequencing result, and the accuracy of advertisement pushing is improved.
The invention provides a method for customizing an advertisement form based on App pushing, which comprises the following steps of:
acquiring the time length of browsing related commodities by the user and the time length of browsing other commodity information by the user;
according to the browsing time of the user on the related commodity and other commodity information, calculating the importance degree value of the related commodity relative to other commodity information, and calculating the accuracy of the counted related preference commodity of the user according to the importance degree value, wherein the specific steps comprise:
calculating the importance degree value of the related commodity relative to other commodities according to the following formula:
Wherein, gamma represents the importance value of the related commodity relative to other commodities, and the value range is (0, 1); μ represents a coefficient of tendency of the user to the related commodity, and the value range is (0.5,0.7); sigma represents a weight value of the related commodity; the E represents the tendency coefficient of the user to other commodity information, and the value range is (0.3, 0.5); omega represents the weight value of the other commodity information; τ represents a time specific gravity factor; t is t 1 Representing the use ofThe value of the time length used by the user to browse the related commodity; t is t 2 A value representing a length of time for the user to browse other merchandise information;
the accuracy of the counted user-related preference commodity is calculated according to the following formula:
wherein ,
the accuracy of the counted user-related preference commodity is represented, and the value range is (0, 1); gamma represents the importance value of the related commodity relative to other commodities, and the value range is (0, 1); θ represents the demand coefficient of the user for the related preference commodity, and the value range is (0.6,0.8); epsilon represents the number of related preference commodities; />
Representing the total number of commodities browsed by the user; beta represents an error coefficient, and the value range is 0.25,0.56; kappa indicates the number of times the user browses the relevant preferred items; q represents the number of times the user purchased the relevant preference commodity;
Comparing the accuracy obtained by calculation with preset accuracy;
if the accuracy is greater than or equal to the preset accuracy, judging that the statistical result is qualified, and pushing the related advertisement of the user related preference commodity to the user terminal;
otherwise, judging that the statistical result is unqualified, and re-acquiring the time length of browsing the related goods by the user and the time length of browsing other goods information by the user, and calculating the accuracy of counting the related preference goods of the user again until the calculated accuracy is greater than or equal to the preset accuracy, so that the related advertisement of the related preference goods of the user is pushed to the user terminal.
In this embodiment, the time scale factor is in the range of (0.5,0.8).
In this embodiment, the preset accuracy is trained in advance, and is used to measure a parameter for counting the accuracy of the commodity preferred by the user, and when the value of the parameter is exceeded, the statistical result is judged to be qualified.
The beneficial effects of the technical scheme are as follows: the method and the device have the advantages that the importance degree value of the related commodity relative to other commodity information is calculated, the accuracy of the counted user related preference commodity is calculated according to the importance degree value, the importance degree value of the related commodity, the weight value of other commodity information and the browsing time length value of the commodity by the user are related when the importance degree is calculated, the importance degree value of the related commodity relative to other commodities is calculated accurately and reliably, the number of times the user browses the related commodity, the number of times the user purchases the related commodity and the error coefficient are related when the accuracy is calculated, the accuracy of a calculation result is ensured, the accuracy of pushing advertisements to the user is ensured, and the user experience is improved.
The system based on the APP pushing customized advertisement form comprises an APP total server, a background control system, a retail management platform and an APP client which are respectively connected with the APP total server, wherein the APP total server comprises an acquisition module, a recording module, a statistics module, a comparison module and a pushing module,
the acquisition module is used for acquiring related preference commodities of the APP browsed by the user according to the browsing time of the APP related commodities when the user selects the commodities each time;
the recording module is used for recording the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
the statistics module is used for counting the browsing time, the browsing times and the purchasing times of the related commodities acquired by the user;
the comparison module is used for comparing the browsing time of the user on other commodity information and counting the related preference commodities of the user;
and the pushing module is used for pushing advertisements to the users according to the recorded and compared related preference commodities.
The background control system is used for inputting advertisement content and pushing the advertisement content to the terminal which initiates the advertisement pushing request.
In this embodiment, as shown in fig. 3, the pushing module includes a receiving module, a keyword word library generation module, a filtering condition generation module, and a filtering module.
The receiving module is used for receiving keywords which are required to be contained in the push information which is input by the user through the App client terminal in a self-defining way;
the generation module of the word stock of the clustering key words is used for recording the key words input by each user and establishing the word stock of the clustering key words, and the generation module is further used for: and sorting the word libraries of the clustering keywords according to the input times of the keywords, displaying N clustering keywords before the sorting in an input interface of an App client, and selecting by a user.
The limitation of traditional advertisement display is solved, the display cost of traditional advertisements is greatly reduced, meanwhile, the advertisement display with higher timeliness is achieved, the convenience of advertisement display operation is greatly improved, and the labor cost is saved.
As shown in fig. 1 to fig. 4, the method for customizing an advertisement form based on App push provided in this embodiment is as follows:
the method comprises the steps of acquiring the related preference commodity of the APP by a user when the user selects the commodity, recording the stay time of the user aiming at the related commodity and the searched content of the related commodity, counting the browsing time, the browsing times and the purchasing times of the related commodity by the user through a background control system, comparing the browsing time with the browsing time of other commodity information by the user, counting the related preference commodity of the user, pushing the advertisement to the user according to the recorded and compared related preference commodity, performing preferential activities in a certain city by a company, and needing to release advertisement information, wherein the information accords with the preference information of the user, the user can watch the advertisement, thereby solving the limitation of traditional advertisement display, greatly reducing the display cost of the traditional advertisement, simultaneously achieving the advertisement display with higher timeliness, greatly improving the convenience of advertisement display operation, saving the labor cost, realizing the push management of the advertisement on line, firstly making picture advertisement poster or video advertisement, uploading the advertisement poster or video to an APP general server, displaying the advertisement poster or the video to an APP client according to the recorded and comparing the obtained related preference commodity, and pushing the advertisement to the APP client to the APP general server to display the advertisement by a general program, and displaying the advertisement by the APP general server with high efficiency.
Certain terms are used throughout the description and claims to refer to particular components. Those of skill in the art will appreciate that a hardware manufacturer may refer to the same component by different names. The description and claims do not take the form of an element differentiated by name, but rather by functionality. As used throughout the specification and claims, the word "comprise" is an open-ended term, and thus should be interpreted to mean "include, but not limited to. By "substantially" is meant that within an acceptable error range, a person skilled in the art can solve the technical problem within a certain error range, substantially achieving the technical effect.
It should be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude that an additional identical element is present in a commodity or system comprising the element.
While the foregoing description illustrates and describes the preferred embodiments of the present invention, it is to be understood that the invention is not limited to the forms disclosed herein, but is not to be construed as limited to other embodiments, and is capable of numerous other combinations, modifications and environments and is capable of changes or modifications within the scope of the inventive concept as described herein, either as a result of the foregoing teachings or as a result of the knowledge or technology in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (8)
1. The method for customizing the advertisement form based on the App pushing is characterized by comprising the following steps of:
s1: obtaining: acquiring related preference commodities of the APP browsed by a user according to the browsing time of the APP related commodities when the user selects the commodities each time;
s2: recording: a background control system on the APP total server records the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
s3: and (3) statistics: the background control system counts the browsing time, browsing times and purchasing times of related commodities acquired by the user;
s4: comparison: comparing the time of browsing on other commodity information with the time of browsing on other commodity information by the user, and counting out related preference commodities of the user;
S5: pushing: pushing advertisements to the user according to the recorded and compared related preference commodities;
wherein, step S2 includes:
s2.1: acquiring content retrieved by a user for related commodities based on an App total server;
s2.2: formatting the retrieved content of the acquired related commodity to obtain initial data, acquiring preset classification characteristics, and preprocessing the classification characteristics to obtain training data;
s2.3: training the initial data based on the training data to obtain characteristic data of content retrieved by related commodities in the initial data;
s2.4: constructing a target data classification model, and inputting the characteristic data of the content retrieved by the related commodity in the initial data into the target data classification model to obtain a probability output matrix corresponding to the characteristic data of the content retrieved by the related commodity;
s2.5: acquiring a preset weight matrix, and correcting the probability output matrix through the preset weight matrix to obtain a weighted probability output matrix;
the weight matrix is generated according to the classification result of the target data classification model on each training sample in a preset training sample set;
S2.5: determining a classification result of the content retrieved by the related commodity based on the weighted probability output matrix;
s2.6: acquiring feature data corresponding to the content retrieved by related commodities in each category, and determining feature weights of the feature data;
s2.7: taking the characteristic data corresponding to the content searched by the related commodity in each category as first training data in each category, and calculating the Euclidean distance between the first training data in each category and the common data corresponding to the content searched by the related commodity in the category;
s2.8: determining the weight of common data corresponding to the content retrieved by the related commodity in each category based on the Euclidean distance and the characteristic weight of the characteristic data;
s2.9: obtaining comprehensive weights of the content retrieved by the related commodities in each category according to the weights of the common data corresponding to the content retrieved by the related commodities in each category and the characteristic weights of the characteristic data;
s2.10: based on the comprehensive weight of the content retrieved by the related commodity in each category, sorting the sorting results and completing the record of the content retrieved by the user on the related commodity;
wherein, step S4 includes:
acquiring the time length of browsing related commodities by the user and the time length of browsing other commodity information by the user;
Calculating the importance degree value of the related commodity relative to other commodities according to the browsing time of the user on the related commodity and other commodity information, and calculating the accuracy of the counted related preference commodity of the user according to the importance degree value, wherein the specific steps comprise:
calculating the importance degree value of the related commodity relative to other commodities according to the following formula:
wherein ,
the importance degree value of the related commodity relative to other commodities is represented, and the value range is (0, 1); />
The coefficient of tendency of the user to the related commodity is represented, and the value range is 0.5,0.7; />
A weight value representing the related commodity; />
The coefficient of tendency of the user to other commodities is represented, and the value range is (0.3, 0.5); />
A weight value representing the other commodity information; />
Representing a time specific gravity factor; />
A value representing a length of time the user has spent browsing related items; />
A value representing a length of time the user spent browsing other merchandise;
the accuracy of the counted user-related preference commodity is calculated according to the following formula:
wherein ,
the accuracy of the counted user-related preference commodity is represented, and the value range is (0, 1); />
The importance degree value of the related commodity relative to other commodities is represented, and the value range is (0, 1); / >
A demand coefficient representing the user for the related preference commodity, and the value range is 0.6,0.8; />
Representing the number of the related preference commodities; />
Representing the total number of commodities browsed by the user; />
Representing error coefficients, and the value range is 0.25,0.56; />
Representing the number of times the user browses the related preference commodity; />
Representing the number of times the user purchased the related preference commodity;
comparing the accuracy obtained by calculation with preset accuracy;
if the accuracy is greater than or equal to the preset accuracy, judging that the statistical result is qualified, and pushing the related advertisement of the user related preference commodity to the user terminal;
otherwise, judging that the statistical result is unqualified, and re-acquiring the time length of browsing the related goods by the user and the time length of browsing other goods information by the user, and calculating the accuracy of counting the related preference goods of the user again until the calculated accuracy is greater than or equal to the preset accuracy, so that the related advertisement of the related preference goods of the user is pushed to the user terminal.
2. The method for customizing an advertisement format based on App push according to claim 1, wherein: in step S5, the push advertisement includes advertisement poster, video advertisement and H5 applet, the push advertisement is pushed to the APP client through the APP total server, the APP client reports the display log to the APP total server, and the APP total server calculates advertisement cost.
3. The method for customizing an advertisement format based on App push according to claim 1, wherein: the background control system comprises any one or more of an android system, an IOS system, a Mac system, a Windows system, a NetWare system, a Unix system and a Linux system.
4. The method for customizing an advertisement format based on App push according to claim 1, wherein: the APP establishes a connection with the Internet and a retail management platform and is used for accessing and acquiring related commodities, and the related commodities of the APP comprise living goods, sports goods, literature goods and electronic goods.
5. The method for customizing an advertisement format based on App push according to claim 1, wherein: step S5 further comprises the steps of:
s5.1: when a user browses commodities by using an APP;
when the APP total server pushes common commodity advertisement content to an APP client, after the APP client receives an advertisement closing instruction, stopping advertisement pushing and starting the APP;
when the APP total server pushes the content of the related preference commodity advertisement to the APP client, starting the APP after the advertisement is played;
meanwhile, the APP total server receives the commodity selected by the user through the APP client terminal in a self-defining way;
S5.2: the APP total server records commodity keywords input by each user, establishes a word-gathering word stock, and sorts the word-gathering word stock according to the input times and the purchase times;
s5.3: the APP total server generates a filtering condition of information pushing according to the word stock of the word class, wherein the filtering condition is a relation list, and the relation list comprises a user group, commodity heat and one or more word class gathering keywords corresponding to the user group;
s5.4: the APP total server screens out users containing specified keywords according to filtering conditions;
s5.5: and the APP total server pushes the information to the APP client of the screened user, wherein the information pushed to the APP client of the user comprises advertisement poster information, video screen information, H5 information and network article information.
6. The method for customizing an advertisement format based on App push according to claim 1, wherein: in step S3:
the App total server takes the message type, the message style and the time information input by a user as a part of the filtering condition;
the App total server takes the message type, the message style, the time information and as part of its keywords.
7. A system for customizing an advertisement form based on App push, characterized in that: comprises an APP total server, a background control system, a retail management platform and an APP client which are respectively connected with the APP total server, wherein the APP total server comprises an acquisition module, a recording module, a statistics module, a comparison module and a pushing module,
the acquisition module is used for acquiring related preference commodities of the APP browsed by the user according to the browsing time of the APP related commodities when the user selects the commodities each time;
the recording module is used for recording the stay time of the user aiming at the related commodity and the content retrieved by the related commodity;
the statistics module is used for counting the browsing time, the browsing times and the purchasing times of the related commodities acquired by the user;
the comparison module is used for comparing the browsing time of the user on other commodity information and counting the related preference commodities of the user;
the pushing module is used for pushing advertisements to the user according to the recorded and compared related preference commodities;
wherein, the record module includes:
acquiring content retrieved by a user for related commodities based on an App total server;
formatting the retrieved content of the acquired related commodity to obtain initial data, acquiring preset classification characteristics, and preprocessing the classification characteristics to obtain training data;
Training the initial data based on the training data to obtain characteristic data of content retrieved by related commodities in the initial data;
constructing a target data classification model, and inputting the characteristic data of the content retrieved by the related commodity in the initial data into the target data classification model to obtain a probability output matrix corresponding to the characteristic data of the content retrieved by the related commodity;
acquiring a preset weight matrix, and correcting the probability output matrix through the preset weight matrix to obtain a weighted probability output matrix;
the weight matrix is generated according to the classification result of the target data classification model on each training sample in a preset training sample set;
determining a classification result of the content retrieved by the related commodity based on the weighted probability output matrix;
acquiring feature data corresponding to the content retrieved by related commodities in each category, and determining feature weights of the feature data;
taking the characteristic data corresponding to the content searched by the related commodity in each category as first training data in each category, and calculating the Euclidean distance between the first training data in each category and the common data corresponding to the content searched by the related commodity in the category;
Determining the weight of common data corresponding to the content retrieved by the related commodity in each category based on the Euclidean distance and the characteristic weight of the characteristic data;
obtaining comprehensive weights of the content retrieved by the related commodities in each category according to the weights of the common data corresponding to the content retrieved by the related commodities in each category and the characteristic weights of the characteristic data;
based on the comprehensive weight of the content retrieved by the related commodity in each category, sorting the sorting results and completing the record of the content retrieved by the user on the related commodity;
wherein the comparison module comprises:
acquiring the time length of browsing related commodities by the user and the time length of browsing other commodity information by the user;
calculating the importance degree value of the related commodity relative to other commodities according to the browsing time of the user on the related commodity and other commodity information, and calculating the accuracy of the counted related preference commodity of the user according to the importance degree value, wherein the specific steps comprise:
calculating the importance degree value of the related commodity relative to other commodities according to the following formula:
wherein ,
the importance degree value of the related commodity relative to other commodities is represented, and the value range is (0, 1); / >
The coefficient of tendency of the user to the related commodity is represented, and the value range is 0.5,0.7; />
A weight value representing the related commodity; />
The coefficient of tendency of the user to other commodities is represented, and the value range is (0.3, 0.5); />
A weight value representing the other commodity information; />
Representing a time specific gravity factor; />
A value representing a length of time the user has spent browsing related items; />
A value representing a length of time the user spent browsing other merchandise;
the accuracy of the counted user-related preference commodity is calculated according to the following formula:
wherein ,
the accuracy of the counted user-related preference commodity is represented, and the value range is (0, 1); />
The importance degree value of the related commodity relative to other commodities is represented, and the value range is (0, 1); />
Representing the user's demand coefficient for the relevant preferred commodity, and having a value in the range of (0.6,0.8）；/>
representing the number of the related preference commodities; />
Representing the total number of commodities browsed by the user; />
Representing error coefficients, and the value range is 0.25,0.56; />
Representing the number of times the user browses the related preference commodity; />
Representing the number of times the user purchased the related preference commodity;
Comparing the accuracy obtained by calculation with preset accuracy;
if the accuracy is greater than or equal to the preset accuracy, judging that the statistical result is qualified, and pushing the related advertisement of the user related preference commodity to the user terminal;
otherwise, judging that the statistical result is unqualified, and re-acquiring the time length of browsing the related goods by the user and the time length of browsing other goods information by the user, and calculating the accuracy of counting the related preference goods of the user again until the calculated accuracy is greater than or equal to the preset accuracy, so that the related advertisement of the related preference goods of the user is pushed to the user terminal.
8. The App push customized advertising format based system of claim 7, wherein: the pushing module comprises a receiving module, a keyword word stock generation module, a filtering condition generation module and a screening module,
the receiving module is used for receiving the user to select commodities in a self-defined mode through the APP client;
the class gathering keyword lexicon generating module is used for recording commodity keywords input by each user, establishing a class gathering lexicon and sequencing the class gathering lexicon according to the input times and the purchase times;
The filtering condition generation module is used for generating a filtering condition of information pushing according to the word stock of the class aggregation, wherein the filtering condition is a relation list, and the relation list comprises a user group, commodity heat and one or more class aggregation keywords corresponding to the user group;
the screening module is used for screening out users containing specified keywords according to the filtering conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144462.0A CN112950256B (en) | 2021-02-02 | 2021-02-02 | Method and system for customizing advertisement form based on App pushing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110144462.0A CN112950256B (en) | 2021-02-02 | 2021-02-02 | Method and system for customizing advertisement form based on App pushing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112950256A CN112950256A (en) | 2021-06-11 |
| CN112950256B true CN112950256B (en) | 2023-05-23 |
Family
ID=76241772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110144462.0A Active CN112950256B (en) | 2021-02-02 | 2021-02-02 | Method and system for customizing advertisement form based on App pushing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950256B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793179A (en) * | 2021-09-13 | 2021-12-14 | 深圳市卓越鸿业信息技术有限公司 | Advertisement optimization analysis system based on big data and machine learning |
| CN114037475A (en) * | 2021-11-10 | 2022-02-11 | 珠海格力电器股份有限公司 | Advertisement pushing method and device, electronic equipment and storage medium |
| CN114331570B (en) * | 2022-03-09 | 2022-05-24 | 广东联讯科技发展股份有限公司 | Mobile terminal advertisement intelligent pushing system and method based on big data |
| 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 |
| CN115293823B (en) * | 2022-09-26 | 2023-01-03 | 深圳媒介之家文化传播有限公司 | User preference identification method based on advertisement click data analysis |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559265A (en) * | 2013-11-04 | 2014-02-05 | 北京中搜网络技术股份有限公司 | Individualized push method of cell phone client |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| CN105528374A (en) * | 2014-10-21 | 2016-04-27 | 苏宁云商集团股份有限公司 | A commodity recommendation method in electronic commerce and a system using the same |
| CN105761101A (en) * | 2016-02-04 | 2016-07-13 | 云南今日游情科技有限公司 | High-precision advertisement push system and method of mobile terminal based on mutual selection |
| CN106296257A (en) * | 2015-06-11 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of fixation of advertisement position put-on method based on user behavior analysis and system |
| CN106790405A (en) * | 2016-11-29 | 2017-05-31 | 中国通信建设集团设计院有限公司 | A kind of mobile phone A PP information-pushing methods customized based on user and system |
| CN106910108A (en) * | 2017-01-24 | 2017-06-30 | 武汉奇米网络科技有限公司 | A kind of items list methods of exhibiting and system |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN108109056A (en) * | 2018-01-10 | 2018-06-01 | 北京思特奇信息技术股份有限公司 | A kind of recommendation method and system of commodity |
| CN109636545A (en) * | 2018-12-26 | 2019-04-16 | 广州市耀锋电子网络科技有限公司 | A kind of electric business platform commercial product recommending algorithm |
| CN109978584A (en) * | 2017-12-28 | 2019-07-05 | 北京奇虎科技有限公司 | A kind of information flow advertisement sending method and device |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
| CN111582951A (en) * | 2020-05-28 | 2020-08-25 | 广州蓝深科技有限公司 | Advertisement putting system and method for cloud electronic commerce |
| CN112182214A (en) * | 2020-09-27 | 2021-01-05 | 中国建设银行股份有限公司 | Data classification method, device, equipment and medium |
-
2021
- 2021-02-02 CN CN202110144462.0A patent/CN112950256B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559265A (en) * | 2013-11-04 | 2014-02-05 | 北京中搜网络技术股份有限公司 | Individualized push method of cell phone client |
| CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
| CN105528374A (en) * | 2014-10-21 | 2016-04-27 | 苏宁云商集团股份有限公司 | A commodity recommendation method in electronic commerce and a system using the same |
| CN106296257A (en) * | 2015-06-11 | 2017-01-04 | 苏宁云商集团股份有限公司 | A kind of fixation of advertisement position put-on method based on user behavior analysis and system |
| CN105761101A (en) * | 2016-02-04 | 2016-07-13 | 云南今日游情科技有限公司 | High-precision advertisement push system and method of mobile terminal based on mutual selection |
| CN106790405A (en) * | 2016-11-29 | 2017-05-31 | 中国通信建设集团设计院有限公司 | A kind of mobile phone A PP information-pushing methods customized based on user and system |
| CN106910108A (en) * | 2017-01-24 | 2017-06-30 | 武汉奇米网络科技有限公司 | A kind of items list methods of exhibiting and system |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN109978584A (en) * | 2017-12-28 | 2019-07-05 | 北京奇虎科技有限公司 | A kind of information flow advertisement sending method and device |
| CN108109056A (en) * | 2018-01-10 | 2018-06-01 | 北京思特奇信息技术股份有限公司 | A kind of recommendation method and system of commodity |
| CN109636545A (en) * | 2018-12-26 | 2019-04-16 | 广州市耀锋电子网络科技有限公司 | A kind of electric business platform commercial product recommending algorithm |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
| CN111582951A (en) * | 2020-05-28 | 2020-08-25 | 广州蓝深科技有限公司 | Advertisement putting system and method for cloud electronic commerce |
| CN112182214A (en) * | 2020-09-27 | 2021-01-05 | 中国建设银行股份有限公司 | Data classification method, device, equipment and medium |
Non-Patent Citations (6)
| Title |
|---|
| XGBoost算法在电子商务商品推荐中的应用;张昊;纪宏超;张红宇;;物联网技术(第02期);102-104 * |
| 基于价格消费习惯的商品多样性推荐;王茜;喻继军;;系统工程(第03期);59-66 * |
| 基于情境化用户偏好的协同过滤推荐模型;吕苗;金淳;韩庆平;;系统工程理论与实践(第12期);3244-3254 * |
| 多会话网络购物商品信息搜寻行为研究;刘洪莲;张鹏翼;王军;;图书情报工作(第14期);117-125 * |
| 客户购买行为建模分析预测;朱珏樟;;现代计算机(第21期);27-32 * |
| 电子商务下消费者购买行为偏好的量化研究;王崇;赵金楼;;软科学(第08期);134-138 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112950256A (en) | 2021-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112950256B (en) | Method and system for customizing advertisement form based on App pushing | |
| US9800910B2 (en) | Recommending media items based on take rate signals | |
| US9146910B2 (en) | Method and system of displaying cross-website information | |
| US11843651B2 (en) | Personalized recommendation method and system, and terminal device | |
| US20120078725A1 (en) | Method and system for contextual advertisement recommendation across multiple devices of content delivery | |
| US9195753B1 (en) | Displaying interest information | |
| KR101003045B1 (en) | Apparatus and method for presenting personalized advertisements information based on artificial intelligence, and recording medium thereof | |
| JP5140289B2 (en) | Information processing system, server device, recommendation method, and program | |
| US20140279016A1 (en) | Behavioral tracking system and method in support of high-engagement communications | |
| CN104008184A (en) | Method and device for pushing information | |
| US20080215453A1 (en) | Server apparatus, information processing apparatus, and information processing method | |
| KR100970335B1 (en) | Method for updating interest keyword of user and system for executing the method | |
| JP5831204B2 (en) | Information providing system, information providing method, and program | |
| CN105812830A (en) | Recommendation method and system of hotel service content | |
| CN110430477A (en) | Recommended method, device, computer equipment and the storage medium of live content | |
| JP2002041670A (en) | Device and system for recommending information | |
| CN101763597A (en) | Rural informatization service platform based on information customization push technology and operating method thereof | |
| CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
| CN114168843A (en) | Search word recommendation method, device and storage medium | |
| US20140289054A1 (en) | Behavioral tracking system and method in support of high-engagement communications | |
| JP2006053616A (en) | Server device, web site recommendation method and program | |
| US9106974B2 (en) | System and method for storing advertising data | |
| JP2002304568A (en) | Correlation item detecting method and its device and recommendation item introducing method and its device and correlation item detecting program and recommendation item introducing program | |
| JP5293970B2 (en) | Product recommendation method and product recommendation system | |
| CN107181672A (en) | The friend recommendation method based on Annual distribution relative entropy in the social networks of position |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |