[go: up one dir, main page]

CN112241894A - Content delivery method and device and terminal - Google Patents

Content delivery method and device and terminal Download PDF

Info

Publication number
CN112241894A
CN112241894A CN201910643869.0A CN201910643869A CN112241894A CN 112241894 A CN112241894 A CN 112241894A CN 201910643869 A CN201910643869 A CN 201910643869A CN 112241894 A CN112241894 A CN 112241894A
Authority
CN
China
Prior art keywords
category
content
user
belonging
prediction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910643869.0A
Other languages
Chinese (zh)
Other versions
CN112241894B (en
Inventor
王鑫
陈美娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu com Times Technology Beijing Co Ltd
Original Assignee
Baidu com Times Technology Beijing Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Baidu com Times Technology Beijing Co Ltd filed Critical Baidu com Times Technology Beijing Co Ltd
Priority to CN201910643869.0A priority Critical patent/CN112241894B/en
Publication of CN112241894A publication Critical patent/CN112241894A/en
Application granted granted Critical
Publication of CN112241894B publication Critical patent/CN112241894B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06Q30/0282—Rating or review of business operators or products

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention provides a content delivery method, a content delivery device and a terminal, wherein the method comprises the following steps: clustering according to portrait information of a user to obtain a first category to which the user belongs; clustering according to the evaluation information of the first content set by the user to obtain a second category to which the user belongs; determining a target delivery page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page; selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set; and delivering the target delivery content to the target delivery page. The ability to deliver content on the function, path of the most frequently used pages or applications by the user also allows delivery of their favorite content types for different user types. The method and the device not only improve the accuracy of content delivery, but also improve the pertinence of content delivery to different types of users.

Description

Content delivery method and device and terminal
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a content delivery method, device and terminal.
Background
Mobile terminals have replaced personal computer terminals to provide users with new ways to access the internet. Internet services and information are also centered on mobile terminals such as mobile phones, so that the mobile terminals will become one of the main carriers for advertisements. The prospect of mobile internet advertising seems to be good, but no effective display mode seems to be found yet. Currently, advertisers adopt a plurality of advertisement forms, which have disadvantages.
Four common advertisement putting modes in the internet page of the mobile terminal are listed.
First, a banner advertisement banner is a mobile internet advertisement except for a text chain. The banner advertisement bars are embedded in all application programs, the display position and the display form are single, and the same releasing strategy is used for all users. The personalized requirements of the user are damaged, and the user experience is not facilitated.
And secondly, pushing advertisements, wherein the pushed advertisements are displayed in a notification bar of the mobile phone and are separated from each application program. The click may be opened if the user wishes. However, not only is the presentation time of push ads short, but too frequent notification bar ads are clearly annoying to the user. Some notification bar push advertisements do not provide too much value to the user, but occupy the traffic of the user, and cause a sense of incongruity to the user.
Third, screen opening/screen inserting/screen locking/screen removing advertisement: the display area of the advertisements accounts for more than 90% of the screen, the visual impact is stronger, and the eyeballs of the user can be easily grasped. But the display frequency is limited, and the advertisement effect is greatly reduced due to single display position and display time.
Fourth, the video advertisements and the rich media, and the mobile rich media advertisements are the same as the video advertisements, so that the multi-dimensional expression forms of sound, pictures, characters, animations and the like of the traditional rich media advertisements are absorbed. Compared with other mobile advertisement modes, the mobile rich media advertisement is more free and has larger creative space. However, the display content is fixed, and the best advertising content can not be displayed for different users, so that the advertising spot occupation ratio is often unsatisfactory.
In summary, the above advertisement delivery methods cannot deliver advertisements according to the user's preference, the delivered content is single, and the delivery location in the internet is not reasonable.
Disclosure of Invention
The embodiment of the invention provides a content delivery method, a content delivery device and a terminal, which are used for solving one or more technical problems in the prior art.
In a first aspect, an embodiment of the present invention provides a content delivery method, including:
clustering according to portrait information of a user to obtain a first category to which the user belongs;
clustering according to the evaluation information of the first content set by the user to obtain a second category to which the user belongs;
determining a target delivery page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page;
selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set;
and delivering the target delivery content to the target delivery page.
In one embodiment, determining a target delivery page corresponding to a user belonging to a first category according to access information of the user belonging to the first category to each page includes:
calculating the access weight value of the user belonging to the first category to each page according to the access information of the user belonging to the first category to each page;
and determining a target delivery page corresponding to the user belonging to the first category according to the sequencing result of the access weight value of the user belonging to the first category to each page.
In one embodiment, selecting target delivered content corresponding to a user belonging to a first category according to evaluation information of the user belonging to a second category on a second content set includes:
predicting the evaluation information of the users belonging to the first category on the second content set according to the evaluation information of the users belonging to the second category on the second content set, the evaluation information of the users belonging to the second category on the first content set and the evaluation information of the users belonging to the first category on the first content set;
and selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the first category on the second content set.
In one embodiment, predicting the rating information of the user belonging to the first category on the second content set based on the rating information of the user belonging to the second category on the second content set, the rating information of the user belonging to the second category on the first content set, and the rating information of the user belonging to the first category on the first content set includes:
acquiring the evaluation information of the user i belonging to the first category on the first content set, wherein the evaluation information comprises the following steps: the prediction score of a user i belonging to a first category for any content c1 in a first set of content is called first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure BDA0002131623070000037
Acquiring the evaluation information of the user j belonging to the second category on the first content set, wherein the evaluation information comprises the following steps: the prediction score of any content c1 in the first set of content, attributed to user j in the second category, is referred to as the second prediction score Rj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure BDA0002131623070000031
Acquiring the evaluation information of the user j belonging to the second category on the second content set, wherein the evaluation information comprises the following steps: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
Obtaining said usage attributed to the second categoryThe evaluation information of the user j on all the contents in the first content set and the second content set comprises the following steps: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure BDA0002131623070000032
According to the first prediction score Ri，c1The second prediction score Rj，c1The first prediction average score
Figure BDA0002131623070000033
And the second prediction average score
Figure BDA0002131623070000034
Calculating the similarity sim (i, j) of the content click prediction scores;
according to the similarity sim (i, j) of the content click prediction score and the first prediction average score
Figure BDA0002131623070000035
The third prediction score Rj，c2The third prediction average score
Figure BDA0002131623070000036
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
In a second aspect, an embodiment of the present invention provides a content delivery apparatus, including:
the first category clustering module is used for clustering according to portrait information of the user to obtain a first category to which the user belongs;
the second category clustering module is used for clustering the evaluation information of the first content set according to the user to obtain a second category to which the user belongs;
the target release page determining module is used for determining a target release page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page;
the target release content selection module is used for selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set;
and the delivery operation module is used for delivering the target delivery content to the target delivery page.
In one embodiment, the target placement page determining module includes:
the access weight value calculation unit is used for calculating the access weight value of the user belonging to the first category to each page according to the access information of the user belonging to the first category to each page;
and the target release page determining unit is used for determining a target release page corresponding to the user belonging to the first category according to the sequencing result of the access weight value of the user belonging to the first category to each page.
In one embodiment, the targeted delivery content selection module comprises:
an evaluation information prediction unit configured to predict evaluation information of the user belonging to the first category on the second content set based on evaluation information of the user belonging to the second category on the second content set, evaluation information of the user belonging to the second category on the first content set, and evaluation information of the user belonging to the first category on the first content set;
and the target release content selecting unit is used for selecting the target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the first category on the second content set.
In one embodiment, the evaluation information prediction unit includes:
a first prediction information obtaining subunit, configured to obtain evaluation information of the user i belonging to the first category on the first content set, where the first prediction information obtaining subunit includes: the prediction score of a user i belonging to a first category for any content c1 in a first set of content is called first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure BDA0002131623070000041
A second prediction information obtaining subunit, configured to obtain evaluation information of the first content set by the user j belonging to the second category, where the second prediction information obtaining subunit is configured to: the prediction score of any content c1 in the first set of content, attributed to user j in the second category, is referred to as the second prediction score Rj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure BDA0002131623070000042
A third prediction information obtaining subunit, configured to obtain evaluation information of the second content set by the user j belonging to the second category, where the third prediction information obtaining subunit includes: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
A fourth prediction information obtaining subunit, configured to obtain evaluation information of all contents in the first content set and the second content set by the user j belonging to the second category, where the evaluation information includes: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure BDA0002131623070000051
A similarity operator unit for calculating a first prediction score R from the first prediction scores Ri，c1The second prediction score Rj，c1The first prediction average score
Figure BDA0002131623070000052
And the second prediction average score
Figure BDA0002131623070000053
Calculating content click prediction score similarity sim (i, j)
An evaluation information calculating subunit, configured to calculate, according to the content click prediction score similarity sim (i, j), a first prediction average score
Figure BDA0002131623070000054
The third prediction score Rj，c2The third prediction average score
Figure BDA0002131623070000055
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
In a third aspect, an embodiment of the present invention provides a content delivery terminal, where functions of the content delivery terminal may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described functions.
In one possible design, the content delivery terminal includes a processor and a memory, the memory is used for storing a program supporting the content delivery terminal to execute the content delivery method, and the processor is configured to execute the program stored in the memory. The content delivery terminal may further include a communication interface for communicating with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium for storing computer software instructions for a content delivery terminal, which includes a program for executing the content delivery method.
One of the above technical solutions has the following advantages or beneficial effects: the content delivery method can deliver the content on the functions and paths of the most frequently used pages or application programs of the users, and also enables the favorite content types to be delivered for different user types. The method and the device not only improve the accuracy of content delivery, but also improve the pertinence of content delivery to different types of users.
The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and following detailed description.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1 shows a flow chart of a content delivery method according to an embodiment of the invention.
FIG. 2 shows a schematic diagram of an advertisement placement interface, according to an embodiment of the invention.
Fig. 3 shows a flow chart of another content delivery method according to an embodiment of the invention.
FIG. 4 is a diagram illustrating a user accessing different page chains according to an embodiment of the present invention.
Fig. 5 shows a flowchart for determining a targeted delivery page according to an embodiment of the invention.
Fig. 6 shows a flow chart of another content delivery method according to an embodiment of the invention.
Fig. 7 is a block diagram illustrating a content delivery apparatus according to an embodiment of the present invention.
Fig. 8 is a block diagram illustrating another content delivery apparatus according to an embodiment of the present invention.
Fig. 9 is a block diagram illustrating another content delivery apparatus according to an embodiment of the present invention.
Fig. 10 is a schematic structural diagram of a content delivery terminal according to an embodiment of the present invention.
Detailed Description
In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
Example one
In one embodiment, a content delivery method is provided, and content delivery can include delivery of advertisements, videos, pictures and the like in internet pages. As shown in fig. 1, the method includes:
step S10: and clustering according to the portrait information of the user to obtain a first category to which the user belongs.
In one example, the portrait information of the user may be data information for describing attributes of the user. Such as data on the user's age, region, school calendar, occupation, gender, etc. When clustering is performed according to portrait information of a user, clustering can be performed according to occupation of the user. For example, the portrait information of the user a includes: age 18, local Beijing, school calendar high school, professional student, etc. The portrait information of the user B includes: age 32, area beijing, scholars, professional teachers. The portrait information of the user C includes: age 22, regional shanghai, academic textbook, and vocational actors. According to the professional classification, the user A belongs to the class of students, the user B belongs to the class of teachers, and the user C belongs to the class of actors. Of course, it may also include: student category, teacher category, scientist category, actor category, doctor category, writer category, and the like. It should be noted that when the user a needs to be delivered with the corresponding content, the user a may be first categorized into a first category, i.e., a student category.
Step S20: and clustering according to the evaluation information of the first content set by the user to obtain a second category to which the user belongs.
In one example, the evaluation information of various contents can be obtained by recording the user's access to various types of contents in a page when the user accesses various types of contents in the page, such as advertisements, videos, and the like, through a respective access page buried point in the mobile terminal. The first set of content may include various different types of advertisements in the advertisement-type content, such as travel-type advertisements, house-type advertisements, food-type advertisements, book-type advertisements, and so forth. Building materials advertisements, etc. Of course, the set of first content may also include a set of videos, a set of pictures, and the like, all within the protection scope of the present embodiment.
The user rating information for the first content set may include user click-through rate prediction scores for individual content in the first content set, such as click-through rate prediction scores for travel advertisements, click-through rate prediction scores for house advertisements, and so on. And clustering the evaluation information of the various advertisements in the first content set according to the user, wherein the clustering basis can be the similarity of the evaluation information of the various advertisements by the user. For example, the click rate prediction scores of the student users for the food advertisements are respectively compared with the click rate prediction scores of the teacher users for the food advertisements, the click rate prediction scores of the scientist users for the food advertisements, and the click rate prediction scores of the actor users for the food advertisements. If the click rate prediction scores of the student users, the teacher users, the scientist users and the writer users for the food advertisements are closer, the student users, the teacher users, the scientist users and the writer users can be classified as a second category.
Of course, various users in the second category may also be ranked according to the similarity of the click rate prediction scores between each two users. For example, if three-out-of-three content delivery is to be performed on the student users at present, the scores are predicted according to click rates of the student users and other users on food advertisements, and similarity ranking is performed from high to low to obtain a similarity-ranked set { teacher class, writer class, and scientist class }.
Step S30: and determining a target delivery page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page.
In an example, each page accessed by the user may be an interface in a mobile terminal, such as a mobile phone, and the interface may include a plurality of controls, and may also be each web page browsed, and the like. The access information of the pages by the users belonging to the first category may include information as follows: the unique device identifier, e.g., the Called User IDentification number, accessed by the User belonging to the first category. The ID (Identification, address) of each page in the page chain accessed by the user belonging to the first category includes an ID of the destination page, a type of the destination page, an ID of each jump page, and the like. When the user belonging to the first category operates each control (e.g., application) on the access page, the functions and the function paths thereof are frequently used. For example, the control ID of the control where the operation occurs in each page, the path sequence uniquely identifies the Pid (contribution, integration, differentiation), the operation occurrence time, the operation parameter, and so on. The user belonging to the first category accesses the page, and a weight value of the page accessed by the user belonging to the first category may be calculated. And determining a target delivery page according to the sequencing of the weight values. For example, the determination that the weight value is the largest is the targeted delivery page.
Step S40: and selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set.
In one example, the users belonging to the second category include: student class users, teacher class users, scientist class users, and writer class users. The evaluation information of the advertisements such as the real estate, the automobile and the body building of the teacher user, the scientist user and the writer user can be obtained, and the evaluation information of the advertisements such as the real estate, the automobile and the body building of the student user is not obtained. Therefore, the second set of content includes only teacher-like users, scientist-like users, and writer-like users advertising real estate, automobiles, fitness, and the like.
Since the set { teacher class, writer class, and scientist class } sorted by similarity is obtained in step S20, the evaluation information of the advertisements such as a house property, an automobile, and a fitness by the teacher class user, the scientist class user, and the writer class user can be used as a reference for the evaluation information of the advertisements such as a house property, an automobile, and a fitness by the student class user, and the target delivery content corresponding to the user belonging to the first category, i.e., the student class can be selected.
Step S50: and delivering the target delivery content to a target delivery page.
In one example, selected targeted content, such as various types of advertisements, videos, and pictures, etc., is delivered to a targeted delivery page. As shown in fig. 2, an advertisement of "super member free reception" is placed in a certain function page of an application, and an example of advertisement placement of "special interest gift bag free reception" is placed in a cell phone backup page. A plurality of selectable drop positions are arranged in each page. The target release position can be selected from a plurality of selectable release positions in the target release page, so that released content can be dynamically configured and freely displayed.
According to the content delivery method provided by the embodiment, the content is delivered on the function and path of the page or the application program which is most frequently used by the user, and the favorite content types of the user are delivered according to different user types. The method and the device not only improve the accuracy of content delivery, but also improve the pertinence of content delivery to different types of users.
In one embodiment, as shown in fig. 3, step S30 includes:
step S310: calculating the access weight value of the user belonging to the first category to each page according to the access information of the user belonging to the first category to each page;
step S320: and determining a target delivery page corresponding to the user belonging to the first category according to the sequencing result of the access weight value of the user belonging to the first category to each page.
In one example, the user's portrait information and access information to each page are input into a Back Propagation (BP) neural network, and the training result is output. And comparing the training result with the existing user access information, and obtaining the neural network model by modifying the network parameters and continuously carrying out iterative training. And inputting the portrait information of the users belonging to the first category and the access information of the users belonging to the first category to the neural network model to obtain the access weight value of the users belonging to the first category to each page.
And when the users belonging to the first category access the pages, acquiring the accessed page chains according to the access time and the access address. And corresponding the weight value with each page in the page chain, and giving an access weight value to each page. For example, as shown in fig. 4 and 5, page chain 1, which is attributed to a user access of the first category, includes page 1, page 2, page 3. The plurality of weighted values of page chain 1 visited by user a include: a weight value a1 of page 1, a weight value a2 of page 2, and a weight value An of page 3, a weight value An of page n. Page chain 2 accessed by B users includes page 1, page 2, and page 4. The plurality of weighted values of page chain 2 visited by B user include: a weight value B1 for page 1, a weight value B2 for page 2, and a weight value B4. for page 4.
In one embodiment, as shown in fig. 3, step S40 includes:
step S410: predicting the evaluation information of the users belonging to the first category on the second content set according to the evaluation information of the users belonging to the second category on the second content set, the evaluation information of the users belonging to the second category on the first content set and the evaluation information of the users belonging to the first category on the first content set;
step S420: and selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the first category on the second content set.
In one example, the rating information attributed to the second category of users for the second set of content may include: and scoring the advertisements such as real estate, automobiles, fitness and the like according to the prediction of teacher users, scientist users and writer users belonging to the second category. And calculating the click prediction scores of the students for the advertisements such as the real estate, the automobile, the fitness and the like according to the prediction scores to be 20, 40 and 60 respectively. And selecting the sequencing of the target release contents as body-building advertisements, automobile advertisements and house property advertisements in sequence according to the prediction score. Of course, the embodiments including but not limited to the above are within the scope of protection of the present embodiments.
In one embodiment, as shown in fig. 6, step S40 includes:
step S4101: acquiring evaluation information of a user i belonging to a first category on a first content set, wherein the evaluation information comprises the following steps: the prediction score of a user i belonging to a first category for any content c1 in a first set of content is called first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure BDA0002131623070000101
Step S4102: acquiring evaluation information of a user j belonging to a second category on the first content set, wherein the evaluation information comprises the following steps: the prediction score of any content c1 in the first set of content, attributed to user j in the second category, is referred to as the second prediction score Rj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure BDA0002131623070000102
Step S4103: acquiring evaluation information of a user j belonging to a second category on a second content set, wherein the evaluation information comprises the following steps: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
Step S4104: acquiring the evaluation information of the user j belonging to the second category on all the contents in the first content set and the second content set, wherein the evaluation information comprises the following steps: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure BDA0002131623070000103
Step S4105: according to the firstPrediction score Ri，c1A second prediction score Rj，c1First prediction average score
Figure BDA0002131623070000111
And second prediction average score
Figure BDA0002131623070000112
Calculating the similarity sim (i, j) of the content click prediction scores;
step S4106: according to the similarity sim (i, j) and the first prediction average score of the content click prediction score
Figure BDA0002131623070000113
Third prediction score Rj，c2Third prediction average score
Figure BDA0002131623070000114
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
In one example, clustering is performed based on portrait information of the user to obtain a first category to which the user belongs. For example, U is a data set of m j-dimension users to be clustered. U ═ Ui|ui＝(ui1，ui2，......uij) 1, 2.. m }, wherein uikIs the kth attribute value for user i. Such as: i: zhang III, Li Si, Wang Wu …; k: preference, occupation, age …. Clustering the users by calculating the Euclidean distance between the two users, wherein the Euclidean distance formula is as follows:
Figure BDA0002131623070000115
the smaller the euclidean distance, the more similar the two users. After the Euclidean distance is calculated, the output result is a two-dimensional matrix { u } of user classificationikAnd j, i: zhang III, Li Si, Wang Wu …; k: preference, occupation, age …. And outputting a two-dimensional matrix of the result, which shows that the users are clustered in the first category according to respective image information. In twoIn the dimension matrix, a first-class matrix U ═ U is extracted and classified according to a certain user attribute1，U2，U3.....UnAnd n is a user class, for example, classes are classified according to occupation, and the set of the first class includes a student class, an actor class, a scientist class, a teacher class, a dancer class and the like. Clustering the content according to the type of the content to obtain a content classification matrix I ═ I1，I2，I3.....IeL. For example, advertisements of the type of food, books, real estate, cars, fitness, etc. And multiplying the matrix of the first category by the content classification matrix to obtain an R ═ U | × | I |, which is a click ratio matrix of the user to each content. From R ═ U | × | I |, a first prediction score R can be derivedi，c1A second prediction score Rj，c1A third prediction score Rj，c2First prediction average score
Figure BDA0002131623070000116
Second prediction average score
Figure BDA0002131623070000117
Third prediction mean score
Figure BDA0002131623070000118
And calculating the similarity of various users belonging to the first category such as students, actors, scientists, teachers, dancers and the like through a similarity calculation formula, and predicting the scoring similarity by clicking contents between every two users. The similarity calculation formula has many options, such as cosine similarity, euclidean distance, spearman rank correlation coefficient, and the like.
In the present embodiment, the pearson correlation formula is used:
Figure BDA0002131623070000119
and according to the calculation result, the students with the similarity close to the similarity belong to a second category, and the exclusion is greatly different. In the second category, the set ordered in height may be M ═ teacher class, composer class, scientist class.
Finally, the prediction scores R of the users belonging to the first category for the second set of contents are calculatedi，c2，
Figure BDA0002131623070000121
Note that c1 is any content in the first content set, and in the second category, the student class and the teacher class, the writer class, and the scientist class have evaluation information on a common content set, which is the first content set. c2 is any content in the second content set, in the second category, the content set shared by the teacher class, the writer class and the scientist class has evaluation information, the student class does not have the evaluation information of the content set, and the content set is the second content set.
Example two
In another embodiment, as shown in fig. 7, there is provided a content delivery apparatus including:
the first category clustering module 10 is used for clustering according to portrait information of users to obtain a first category to which the users belong;
the second category clustering module 20 is configured to cluster according to the evaluation information of the user on the first content set, so as to obtain a second category to which the user belongs;
the target release page determining module 30 is configured to determine, according to the access information of the users belonging to the first category to each page, a target release page corresponding to the users belonging to the first category;
the target release content selection module 40 is configured to select target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set;
and the releasing operation module 50 is used for releasing the target releasing content to the target releasing page.
In one embodiment, as shown in fig. 8, the target placement page determining module 30 includes:
an access weight value calculating unit 301, configured to calculate an access weight value of each page by a user belonging to the first category according to access information of each page by the user belonging to the first category;
and a target delivery page determining unit 302, configured to determine, according to a ranking result of access weight values of the pages by the users belonging to the first category, a target delivery page corresponding to the user belonging to the first category.
In one embodiment, as shown in fig. 8, the targeted delivery content selection module 40 includes:
an evaluation information prediction unit 401 configured to predict evaluation information of a user belonging to the first category on the second content set based on evaluation information of a user belonging to the second category on the second content set, evaluation information of a user belonging to the second category on the first content set, and evaluation information of a user belonging to the first category on the first content set;
and a target released content selecting unit 402, configured to select, according to the evaluation information of the second content set by the user belonging to the first category, a target released content corresponding to the user belonging to the first category.
In one embodiment, as shown in fig. 9, the evaluation information prediction unit 401 includes:
the first prediction information obtaining sub-unit 4011 is configured to obtain evaluation information of the user i belonging to the first category on the first content set, and includes: the prediction score of a user i belonging to a first category for any content c1 in a first set of content is called first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure BDA0002131623070000131
The second prediction information obtaining sub-unit 4012 is configured to obtain evaluation information of the user j belonging to the second category on the first content set, and includes: any of the user j pairs in the first set of content belonging to the second categoryThe predicted score of content c1, referred to as the second predicted score Rj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure BDA0002131623070000132
The third prediction information obtaining sub-unit 4013 is configured to obtain evaluation information of the user j belonging to the second category on the second content set, and includes: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
A fourth prediction information obtaining sub-unit 4014, configured to obtain evaluation information of all contents in the first content set and the second content set from the user j belonging to the second category, where the evaluation information includes: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure BDA0002131623070000133
A similarity operator unit 4015 for calculating a first prediction score R based on the first prediction score Ri，c1The second prediction score Rj，c1The first prediction average score
Figure BDA0002131623070000134
And the second prediction average score
Figure BDA0002131623070000135
Calculating the similarity sim (i, j) of the content click prediction scores;
an evaluation information calculation subunit 4016, configured to calculate, according to the content click prediction score similarity sim (i, j), a first prediction average score
Figure BDA0002131623070000136
The third prediction score Rj，c2The third prediction average score
Figure BDA0002131623070000137
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
The functions of each module in each apparatus in the embodiments of the present invention may refer to the corresponding description in the above method, and are not described herein again.
EXAMPLE III
Fig. 10 is a block diagram illustrating a configuration of a content delivery terminal according to an embodiment of the present invention. As shown in fig. 10, the terminal includes: a memory 910 and a processor 920, the memory 910 having stored therein computer programs operable on the processor 920. The processor 920, when executing the computer program, implements the content delivery method in the above embodiments. The number of the memory 910 and the processor 920 may be one or more.
The terminal further includes:
and a communication interface 930 for communicating with an external device to perform data interactive transmission.
Memory 910 may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 910, the processor 920 and the communication interface 930 are implemented independently, the memory 910, the processor 920 and the communication interface 930 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
Optionally, in an implementation, if the memory 910, the processor 920 and the communication interface 930 are integrated on a chip, the memory 910, the processor 920 and the communication interface 930 may complete communication with each other through an internal interface.
An embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method in any one of the above embodiments.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment 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 various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (10)

1. A method for content delivery, comprising:
clustering according to portrait information of a user to obtain a first category to which the user belongs;
clustering according to the evaluation information of the first content set by the user to obtain a second category to which the user belongs;
determining a target delivery page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page;
selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set;
and delivering the target delivery content to the target delivery page.
2. The method according to claim 1, wherein determining the target delivery page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page comprises:
calculating the access weight value of the user belonging to the first category to each page according to the access information of the user belonging to the first category to each page;
and determining a target delivery page corresponding to the user belonging to the first category according to the sequencing result of the access weight value of the user belonging to the first category to each page.
3. The method according to claim 1, wherein selecting the targeted content to be delivered corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set comprises:
predicting the evaluation information of the users belonging to the first category on the second content set according to the evaluation information of the users belonging to the second category on the second content set, the evaluation information of the users belonging to the second category on the first content set and the evaluation information of the users belonging to the first category on the first content set;
and selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the first category on the second content set.
4. The method according to claim 3, wherein predicting the rating information of the user belonging to the first category for the second set of contents based on the rating information of the user belonging to the second category for the second set of contents, the rating information of the user belonging to the second category for the first set of contents, and the rating information of the user belonging to the first category for the first set of contents comprises:
acquiring the evaluation information of the user i belonging to the first category on the first content set, wherein the evaluation information comprises the following steps: user i belonging to the first category is interested in any content c in the first content setA prediction score of 1, referred to as a first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure FDA0002131623060000021
Acquiring the evaluation information of the user j belonging to the second category on the first content set, wherein the evaluation information comprises the following steps: the prediction score of any content c1 in the first set of content, attributed to user j in the second category, is referred to as the second prediction score Rj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure FDA0002131623060000022
Acquiring the evaluation information of the user j belonging to the second category on the second content set, wherein the evaluation information comprises the following steps: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
Acquiring the evaluation information of the user j belonging to the second category on all the contents in the first content set and the second content set, wherein the evaluation information comprises the following steps: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure FDA0002131623060000023
According to the first prediction score Ri，c1The second prediction score Rj，c1The first prediction average score
Figure FDA0002131623060000024
And the second prediction average score
Figure FDA0002131623060000025
Computing content clicksPredicting score similarity sim (i, j);
according to the similarity sim (i, j) of the content click prediction score and the first prediction average score
Figure FDA0002131623060000026
The third prediction score Rj，c2The third prediction average score
Figure FDA0002131623060000027
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
5. A content delivery apparatus, comprising:
the first category clustering module is used for clustering according to portrait information of the user to obtain a first category to which the user belongs;
the second category clustering module is used for clustering the evaluation information of the first content set according to the user to obtain a second category to which the user belongs;
the target release page determining module is used for determining a target release page corresponding to the user belonging to the first category according to the access information of the user belonging to the first category to each page;
the target release content selection module is used for selecting target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the second category on the second content set;
and the delivery operation module is used for delivering the target delivery content to the target delivery page.
6. The apparatus of claim 5, wherein the target placement page determining module comprises:
the access weight value calculation unit is used for calculating the access weight value of the user belonging to the first category to each page according to the access information of the user belonging to the first category to each page;
and the target release page determining unit is used for determining a target release page corresponding to the user belonging to the first category according to the sequencing result of the access weight value of the user belonging to the first category to each page.
7. The apparatus of claim 5, wherein the targeted delivery content selection module comprises:
an evaluation information prediction unit configured to predict evaluation information of the user belonging to the first category on the second content set based on evaluation information of the user belonging to the second category on the second content set, evaluation information of the user belonging to the second category on the first content set, and evaluation information of the user belonging to the first category on the first content set;
and the target release content selecting unit is used for selecting the target release content corresponding to the user belonging to the first category according to the evaluation information of the user belonging to the first category on the second content set.
8. The apparatus according to claim 7, wherein the evaluation information prediction unit includes:
a first prediction information obtaining subunit, configured to obtain evaluation information of the user i belonging to the first category on the first content set, where the first prediction information obtaining subunit includes: the prediction score of a user i belonging to a first category for any content c1 in a first set of content is called first prediction score Ri，c1And the average predicted score of the user i belonging to the first category on the total content of the first set of contents, called first predicted average score
Figure FDA0002131623060000031
A second prediction information obtaining subunit, configured to obtain evaluation information of the first content set by the user j belonging to the second category, where the second prediction information obtaining subunit is configured to: the predictive score of any content c1 in the first collection of content, attributed to user j in the second category, is referred to as the second predictive scoreR isj，c1And the average predicted score of the user j belonging to the second category on the total content in the first set of contents, called the second predicted average score
Figure FDA0002131623060000032
A third prediction information obtaining subunit, configured to obtain evaluation information of the second content set by the user j belonging to the second category, where the third prediction information obtaining subunit includes: the prediction score of any content c2 in the second set of content, attributed to user j in the second category, is referred to as the third prediction score Rj，c2；
A fourth prediction information obtaining subunit, configured to obtain evaluation information of all contents in the first content set and the second content set by the user j belonging to the second category, where the evaluation information includes: the average predicted score of the user j belonging to the second category for all the contents of the first and second content sets, called the third predicted average score
Figure FDA0002131623060000041
A similarity operator unit for calculating a first prediction score R from the first prediction scores Ri，c1The second prediction score Rj，c1The first prediction average score
Figure FDA0002131623060000042
And the second prediction average score
Figure FDA0002131623060000043
Calculating the similarity sim (i, j) of the content click prediction scores;
an evaluation information calculating subunit, configured to calculate, according to the content click prediction score similarity sim (i, j), a first prediction average score
Figure FDA0002131623060000044
The third prediction score Rj，c2The third prediction average score
Figure FDA0002131623060000045
Calculating a prediction score R for a second set of content for users belonging to a first categoryi，c2The evaluation information of the second content set by the users belonging to the first category comprises Ri，c2。
9. A content delivery terminal, comprising:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-4.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 4.
CN201910643869.0A 2019-07-16 2019-07-16 Content delivery method, device and terminal Active CN112241894B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910643869.0A CN112241894B (en) 2019-07-16 2019-07-16 Content delivery method, device and terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910643869.0A CN112241894B (en) 2019-07-16 2019-07-16 Content delivery method, device and terminal

Publications (2)

Publication Number Publication Date
CN112241894A true CN112241894A (en) 2021-01-19
CN112241894B CN112241894B (en) 2024-09-27

Family

ID=74167268

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910643869.0A Active CN112241894B (en) 2019-07-16 2019-07-16 Content delivery method, device and terminal

Country Status (1)

Country Link
CN (1) CN112241894B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090177526A1 (en) * 2008-01-07 2009-07-09 Cvon Innovations Ltd. System, method and computer program for selecting an information provider
US20130179504A1 (en) * 2012-01-11 2013-07-11 Paul Adams Generating Sponsored Story Units Including Related Posts and Input Elements
CN103412948A (en) * 2013-08-27 2013-11-27 北京交通大学 Cluster-based collaborative filtering commodity recommendation method and system
CN103679485A (en) * 2012-08-30 2014-03-26 天津亚智网络科技研发有限公司 Advertisement precise positioning method based on cookie
CN106570723A (en) * 2016-11-01 2017-04-19 深圳赢时通网络有限公司 Internet advertisement putting method and apparatus thereof
CN106991173A (en) * 2017-04-05 2017-07-28 合肥工业大学 Collaborative filtering recommending method based on user preference
CN108108998A (en) * 2017-12-14 2018-06-01 百度在线网络技术（北京）有限公司 Showing advertisement method and apparatus, server, storage medium
CN108241667A (en) * 2016-12-26 2018-07-03 百度在线网络技术（北京）有限公司 For the method and apparatus of pushed information
CN108415996A (en) * 2018-02-13 2018-08-17 北京奇虎科技有限公司 A kind of news information method for pushing, device and electronic equipment
CN108665323A (en) * 2018-05-20 2018-10-16 北京工业大学 A kind of integrated approach for finance product commending system
CN108960897A (en) * 2018-06-08 2018-12-07 成都信息工程大学 A kind of various dimensions user collaborative filtered recommendation method of combination correlation rule
CN109003143A (en) * 2018-08-03 2018-12-14 阿里巴巴集团控股有限公司 Recommend using deeply study the method and device of marketing
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
CN109636479A (en) * 2018-12-19 2019-04-16 武汉斗鱼鱼乐网络科技有限公司 A kind of advertisement recommended method, device, electronic equipment and storage medium
CN109784974A (en) * 2018-12-14 2019-05-21 平安科技（深圳）有限公司 Advertisement placement method, device, electronic equipment and storage medium based on big data
CN109815402A (en) * 2019-01-23 2019-05-28 北京工业大学 Collaborative filtering recommendation algorithm based on user characteristics

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090177526A1 (en) * 2008-01-07 2009-07-09 Cvon Innovations Ltd. System, method and computer program for selecting an information provider
US20130179504A1 (en) * 2012-01-11 2013-07-11 Paul Adams Generating Sponsored Story Units Including Related Posts and Input Elements
CN103679485A (en) * 2012-08-30 2014-03-26 天津亚智网络科技研发有限公司 Advertisement precise positioning method based on cookie
CN103412948A (en) * 2013-08-27 2013-11-27 北京交通大学 Cluster-based collaborative filtering commodity recommendation method and system
CN106570723A (en) * 2016-11-01 2017-04-19 深圳赢时通网络有限公司 Internet advertisement putting method and apparatus thereof
CN108241667A (en) * 2016-12-26 2018-07-03 百度在线网络技术（北京）有限公司 For the method and apparatus of pushed information
CN106991173A (en) * 2017-04-05 2017-07-28 合肥工业大学 Collaborative filtering recommending method based on user preference
CN108108998A (en) * 2017-12-14 2018-06-01 百度在线网络技术（北京）有限公司 Showing advertisement method and apparatus, server, storage medium
CN108415996A (en) * 2018-02-13 2018-08-17 北京奇虎科技有限公司 A kind of news information method for pushing, device and electronic equipment
CN108665323A (en) * 2018-05-20 2018-10-16 北京工业大学 A kind of integrated approach for finance product commending system
CN108960897A (en) * 2018-06-08 2018-12-07 成都信息工程大学 A kind of various dimensions user collaborative filtered recommendation method of combination correlation rule
CN109003143A (en) * 2018-08-03 2018-12-14 阿里巴巴集团控股有限公司 Recommend using deeply study the method and device of marketing
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
CN109784974A (en) * 2018-12-14 2019-05-21 平安科技（深圳）有限公司 Advertisement placement method, device, electronic equipment and storage medium based on big data
CN109636479A (en) * 2018-12-19 2019-04-16 武汉斗鱼鱼乐网络科技有限公司 A kind of advertisement recommended method, device, electronic equipment and storage medium
CN109815402A (en) * 2019-01-23 2019-05-28 北京工业大学 Collaborative filtering recommendation algorithm based on user characteristics

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
范虎;花伟伟;: "协同过滤推荐算法的研究与改进", 计算机技术 与发展, no. 09 *
高华;: "一种电子商务协同过滤推荐算法", 湖南城市学院学报(自然科学版), no. 01 *
黄国言;李有超;高建培;常旭亮;: "基于项目属性的用户聚类协同过滤推荐算法", 计算机工程与设计, no. 05 *

Also Published As

Publication number Publication date
CN112241894B (en) 2024-09-27

Similar Documents

Publication Publication Date Title
JP6940646B2 (en) Information recommendation method, information recommendation device, equipment and medium
US7840502B2 (en) Classification of images as advertisement images or non-advertisement images of web pages
CN108491529B (en) Information recommendation method and device
JP5961666B2 (en) System, method and computer executable program for customizing touchpoints
CN108491540B (en) Text information pushing method and device and intelligent terminal
CN105229631A (en) The collection of reading content, follow the tracks of and present
CN111061979B (en) User tag pushing method and device, electronic equipment and medium
CN110428277B (en) Touch method of recommended product, storage medium and program product
CN109255070A (en) Recommendation information processing method, device, computer equipment and storage medium
CN115757952A (en) Content information recommendation method, device, equipment and storage medium
CN105706081A (en) Structured informational link annotations
CN112182414A (en) The article recommends methods, devices and electronic equipment
US20120059719A1 (en) Advertisement distribution server and advertisement distribution method
CN108694211B (en) Application distribution method and device
CN110909154A (en) Abstract generation method and device
CN112084406B (en) Short message processing method, device, electronic device and storage medium
CN113869957A (en) Resource allocation method and resource allocation device
CN108288172A (en) Advertisement DSP orientations launch the method and terminal of advertisement
CN112241894B (en) Content delivery method, device and terminal
KR20240029797A (en) A device that provides customized video advertisements by predicting advertisement effectiveness
KR20240029798A (en) Program for providing customized video advertisement based on artificial intelligence
CN108615166A (en) A kind of showing advertisement method and apparatus
CN111339291B (en) Information display method and device and storage medium
CN114237460B (en) Label display method, device, terminal, storage medium and computer program product
CN110276030A (en) Methods of exhibiting, electronic equipment and the computer storage medium of Webpage

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