CN112115368A - Method for content information distribution engine based on big data - Google Patents

Method for content information distribution engine based on big data Download PDF

Info

Publication number
CN112115368A
CN112115368A CN202011045386.XA CN202011045386A CN112115368A CN 112115368 A CN112115368 A CN 112115368A CN 202011045386 A CN202011045386 A CN 202011045386A CN 112115368 A CN112115368 A CN 112115368A
Authority
CN
China
Prior art keywords
source content
recommendation
keywords
information
content
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
CN202011045386.XA
Other languages
Chinese (zh)
Other versions
CN112115368B (en
Inventor
方斌
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.)
Anhui Duodian Meihao Intelligent Technology Co ltd
Original Assignee
Anhui Wande Information Technology 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 Anhui Wande Information Technology Co ltd filed Critical Anhui Wande Information Technology Co ltd
Priority to CN202011045386.XA priority Critical patent/CN112115368B/en
Publication of CN112115368A publication Critical patent/CN112115368A/en
Application granted granted Critical
Publication of CN112115368B publication Critical patent/CN112115368B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • G06Q30/0257—User requested
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method for a content information distribution engine based on big data, which relates to the technical field of Internet and comprises the following steps: acquiring user behavior information; generating recommendation information according to the user behavior information; generating a recommendation keyword of the source content according to the recommendation information; adding source content to at least two more dimensions; providing recommendation service of any dimension to a client, wherein the recommendation service comprises selecting source content in the dimension associated with recommendation keywords with the most same words in comments of a user to be recommended and recommending the source content to the user; the method divides the content into multiple dimensions, gives different recommendation keywords to the content with different dimensions, extracts resources with different dimensions when the content is recommended to the client after being defined according to the different dimensions, and exposes a fixed form of business api to the external APP terminal to support the product requirements of different content type APPs.

Description

Method for content information distribution engine based on big data
Technical Field
The invention relates to the technical field of Internet, in particular to a method of a content information distribution engine based on big data.
Background
Internet advertisement refers to commercial advertisement that directly or indirectly promotes goods or services in the form of words, pictures, audio, video or other forms through internet media such as websites, web pages, internet applications and the like.
Compared with the traditional four-large-size broadcast media (newspaper, magazine, television and radio) advertisement and the outdoor advertisement which is prepared by the blue-green broadcast, the internet advertisement has the unique advantages and is an important part for implementing the modern marketing media strategy. The Internet is a brand new advertising medium, has the highest speed and ideal effect, is a good way for medium and small enterprises to expand and develop greatly, and is particularly suitable for companies which widely develop international business.
The internet advertisement can track and research the preference of the user, which is the advantage of the internet compared with the traditional media marketing and is the basis of the accurate marketing. Compared with the traditional media, the internet surfing behavior, browsing habits and registered personal information of the netizens behind each ip can be obtained and mined through technical means, advertisers have the opportunity to deeply know user behaviors and preferences through long-term accumulation and deep analysis of the contents, and the best matched advertising information is selected according to the behavior characteristics, regions, interests and the like of each user. When a tourist fan and an automobile fan visit the page of the same website, the seen advertisements are different, because the system records the behavior habits and preferences of the tourists and the automobile fan, so that the advertisement setting is not uniform. Of course, achieving this accuracy requires multiple technical support;
in the prior art, an internet advertisement platform generally carries out associated recommendation according to keywords of contents searched or used by a user, so that the requirements of the user are difficult to grasp accurately, and a large amount of useless content is recommended.
Disclosure of Invention
The invention provides a method of a content information distribution engine based on big data, which solves the technical problem that the requirements of users are difficult to grasp accurately in the related technology.
According to an aspect of the present invention, there is provided a method of a big data based content information distribution engine, comprising the steps of:
step 100, acquiring user behavior information;
200, generating recommendation information according to the user behavior information;
step 300, generating a recommendation keyword of the source content according to the recommendation information;
step 400, adding source content to at least two or more dimensions;
step 500, providing recommendation service of any dimension to the client, wherein the recommendation service comprises selecting the source content in the dimension associated with the recommendation keyword with the most common words in the comments of the user to be recommended and recommending the source content to the user.
According to an aspect of the present invention, there is provided a management platform of a big data based content information distribution engine, including:
the content resource platform can be operated to acquire user behavior information, endow recommended keywords for the source content according to the user behavior information and add the source content to at least more than two dimensions;
and the content service platform can be operated to provide recommendation service of any dimension to the client, and the recommendation service comprises selecting the source content in the dimension associated with the recommendation keyword with the most appeared words in the comments of the user to be recommended and recommending the source content to the user.
Further, the step of obtaining the user behavior information and giving the source content a recommendation keyword according to the user behavior information includes the following steps:
step S1, acquiring user behavior information;
step S2, generating recommendation information according to the user behavior information, wherein the recommendation information at least comprises source content, user evaluation information related to the source content, uniformity information and level information;
step S3, a recommendation keyword for the source content is generated based on the recommendation information.
Further, the generating of the recommendation keyword of the source content according to the recommendation information includes the following steps:
step S311, selecting at least more than one word with the frequency exceeding a frequency threshold value or the frequency exceeding a frequency threshold value in the evaluation of the user under the source content item as a new keyword to be endowed to the source content;
step S312, at least selecting more than one new keywords which are the same as the old keywords originally possessed by the source content as the keywords to be acquired;
step S313, calculating the association degree of the keywords to be acquired and the source content, specifically, calculating according to the level of the comments of the user, where the keywords to be acquired appear for the first time, the similarity degree of the keywords to be acquired, and the number of times of the keywords to be acquired appearing in the evaluation under the source content item;
step S314, selecting keywords with the relevance degree exceeding a threshold value to be selected as the recommendation keywords of the source content.
Further, the calculation formula for calculating the association degree between the keyword to be extracted and the source content is as follows:
the relevancy Z = W1 a + W2B + W3C, where a denotes the level of the comment of the user where the keyword to be taken first appears, B denotes the degree of similarity of the keyword to be taken, C denotes the number of times the keyword to be taken appears in the evaluation under the source content item, W1 denotes a first weight, W2 denotes a second weight, and W3 denotes a third weight.
Further, the degree of similarity of the to-be-taken keyword is the number of evaluations of the user under the source content item to which the to-be-taken keyword points positively.
Further, the adding the source content to at least two or more dimensions includes the steps of:
and respectively adding the source content into each dimension, wherein the source content in any dimension only retains the recommendation keywords matched with the attribute of the dimension.
Further, the content resource platform includes at least:
a data acquisition unit operable to acquire user behavior information and send the user behavior information to the recommendation information generation unit;
a recommendation information generation unit operable to generate recommendation information including at least source content, user evaluation information related to the source content, degree of uniformity information, level information;
and the dimension dividing unit is operable to generate a recommendation keyword according to the recommendation information and add the source content to at least two or more dimensions.
Further, the dimension dividing unit includes:
a word extraction unit operable to select at least one or more words, as new keywords, to be given to the source content, the words appearing in the user's evaluation under the source content item more than a frequency threshold or more than a frequency threshold;
a to-be-acquired keyword generation unit operable to select one or more new keywords that are the same as old keywords originally possessed by the source content as to-be-acquired keywords;
the relevancy calculation unit is operable to calculate the relevancy of the keywords to be acquired and the source content;
the recommendation keyword generation unit is operable to select keywords with the association degree with the source content exceeding a threshold value to be selected as recommendation keywords of the source content;
a content distribution unit operable to add source content to the respective dimensions separately.
The invention has the beneficial effects that:
the method comprises the steps of dividing content into multiple dimensions, giving different recommendation keywords to the content with different dimensions, defining the content according to different dimensions, extracting resources with different dimensions when recommending the content to a client, and exposing a fixed-form service api to an external APP terminal to support the product requirements of different content type APPs;
according to the method, the accurate advertisement recommendation can be performed on the user based on the evaluation of the user and the evaluation of the source content, the advertisement content with higher association can be recommended, the defect that the association between the keyword and the advertisement content is ignored in the representation interest recommendation of the keyword can be eliminated, the association is extracted based on the comments of the user, the user is taken as a cluster to perform humanized integrated interest extraction through the cluster, the defect that deviation from the actual demand of the user is caused by purely depending on machine calculation is changed, the recommendation of an internet advertisement platform is more accurate, and useless recommendation content is reduced.
Drawings
FIG. 1 is a block diagram of a management platform of a big data based content information distribution engine according to an embodiment of the present invention;
FIG. 2 is a flowchart of acquiring user behavior information and assigning recommended keywords to source content according to the user behavior information according to an embodiment of the present invention;
FIG. 3 is a flowchart of generating a recommendation keyword based on recommendation information according to an embodiment of the present invention;
FIG. 4 is a block diagram of a dimension partitioning unit according to an embodiment of the present invention;
fig. 5 is a flowchart of a method of a big-data based content information distribution engine according to an embodiment of the present invention.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thereby implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, features described with respect to some examples may also be combined in other examples.
For internet APP, content-type products generally include: video, graphics, consultation, etc., there are many commonalities in content, such as: the contents are used as a uniform platform abstraction basis according to a plurality of common indexes such as praise, concern, comment, author, browse and collection, and the abstraction is as follows: a content resource platform 100, a content service platform 200;
in the present embodiment, a management platform of a big data based content information distribution engine is provided, and as shown in fig. 1, the management platform of a big data based content information distribution engine according to the present invention includes:
a content resource platform 100 operable to obtain user behavior information and assign recommended keywords to source content according to the user behavior information, and add the source content to at least two or more dimensions.
As shown in fig. 2, the obtaining of the user behavior information and assigning the recommended keyword to the source content according to the user behavior information includes the following steps:
step S1, acquiring user behavior information;
step S2, generating recommendation information according to the user behavior information, wherein the recommendation information at least comprises source content, user evaluation information related to the source content, uniformity information and level information;
the user behavior information may be an evaluation of the user on the source content and an evaluation (a complex evaluation) of the user on the evaluation, the evaluation (the complex evaluation) of the user on the evaluation is graded, the evaluation of the user on the source content is a first-level evaluation, the evaluation of the first-level evaluation is a second-level evaluation, the evaluation of the second-level evaluation is a third-level evaluation, and so on;
of course, the similarity information may be a type of information for the user's rating, which may be selected but not limited to:
the number of next level evaluations for the user's evaluation; at the moment, the information of the degree of uniformity represents the number of other users which are similar to the user in a fuzzy way;
a number of lower-level ratings for the user's rating; at the moment, the similarity information represents the number of other users of the same type as the user in a fuzzy way in a larger range;
confirming the number of the user evaluation in the next evaluation of the user evaluation; at the moment, the similarity degree information highly represents the number of other users of the same class as the user;
affirming the number of the user's evaluations in lower-level evaluations for the user's evaluation; at the moment, the similarity degree information highly represents the number of other users of the same type as the user in a larger range;
the evaluation of the user is not limited to the first-level evaluation, but can be a second-level evaluation, a third-level evaluation or an N-level evaluation;
the data source provided by the embodiment can obtain user behavior information, similarity information and level information related to source content;
in the above process, the evaluation is not limited to the comment, but may also be a positive or negative selection by the user, such as a yes or no option, a good or bad option, a yes or step option, or the like, loaded on a web page or other user interface; the selection information of the user can be used as the evaluation, and the evaluation is not limited to the evaluation by the editing language and also comprises other types of evaluation modes and contents which can express the user attitude;
in the above process, the source content is also recommended content, and some source content may not have user rating information, degree of uniformity information, and level information related thereto because it is not rated;
but each source content has a corresponding at least one keyword; the keyword is a word representing the key attribute of the source content, and can also be a word self-defined by a provider of the source content, and represents the interest of the user and the recommendation direction of the advertising platform to the user with the interest, namely a key for linking the content with the interest of the user;
step S3, generating a recommendation keyword of the source content according to the recommendation information;
as shown in fig. 3, generating a recommendation keyword according to recommendation information includes:
step S311 is to select at least one word, which appears in the user' S evaluation under the source content item and has a frequency exceeding the frequency threshold, as a new keyword to be added to the source content.
In the above process, the frequency characterizes the ratio of the number of occurrences of a word to the total number of evaluations of the user under the source content item.
Step S312, at least selecting more than one new keywords which are the same as the old keywords originally possessed by the source content as the keywords to be acquired;
for example, new keywords "milk powder", "diaper", "beer" and the like are selected from comments of a user of a feeding bottle advertisement, and old keywords originally possessed by the source content include "milk powder", "diaper", and more than one of "milk powder" and "diaper" are selected as keywords to be taken;
step S313, calculating the association degree of the keywords to be acquired and the source content, specifically, calculating according to the level of the comments of the user, where the keywords to be acquired appear for the first time, the similarity degree of the keywords to be acquired, and the number of times of the keywords to be acquired appearing in the evaluation under the source content item;
the similarity of the keywords to be taken is the number of evaluations of the users under the source content items with positive orientation of the keywords to be taken;
the calculation formula is as follows: the relevancy Z = W1 a + W2B + W3C, where a denotes the level of the comment of the user where the keyword to be taken appears for the first time, B denotes the degree of similarity of the keyword to be taken, C denotes the number of times the keyword to be taken appears in the evaluation under the source content item, W1 denotes a first weight, W2 denotes a second weight, and W3 denotes a third weight;
taking "milk powder" as an example, a is 2 (first appearing in the second level of reviews), B is 23 (positive evaluation is 23), C is 50;
step S314, selecting keywords with the relevance degree exceeding a threshold value and to be selected as recommendation keywords of the source content;
adding source content to at least two more dimensions includes the steps of:
respectively adding source content into each dimension, wherein the source content in any dimension only retains recommendation keywords matched with the attribute of the dimension;
the attributes of the dimension can be an item, a name, a publisher, etc.;
for example, a football video content, in the dimension of shopping, the recommendation keywords reserved by the content are football and football shoes;
in the dimension of the video, the reserved recommended keywords are Ronaldol and the Adam tournament;
the content service platform 200 is operable to provide recommendation services of any dimension to the client 300, and the recommendation services include selecting source content in the dimension associated with a recommendation keyword with the most common words in the comments of the user to be recommended and recommending the source content to the user.
In an application field of this embodiment, the recommended service is provided to an APP product, and at this time, the content service platform 200 exposes a fixed-form service api to the external APP end to support product requirements of different content-type APPs;
moreover, the content resource platform 100 may also provide an api for collecting content to collect content from the APP product, and it should be noted that the content resource platform 100 may also obtain user behavior information from a database or a big data cloud platform;
the content resource platform 100 includes at least:
a data acquisition unit 110 operable to acquire user behavior information and send the user behavior information to the recommendation information generation unit 120;
a recommendation information generating unit 120 operable to generate recommendation information including at least source content, user evaluation information related to the source content, degree of uniformity information, level information;
a dimension division unit 130 operable to generate recommendation keywords from the recommendation information and add the source content to at least two or more dimensions.
The operation of the dimension division unit 130 includes:
at least one word appearing in the evaluation of the user under the source content item and having a frequency exceeding a frequency threshold is selected and given to the source content as a new keyword.
At least selecting more than one new keyword which is the same as the old keyword originally possessed by the source content as a keyword to be taken;
for example, new keywords "milk powder", "diaper", "beer" and the like are selected from comments of a user of a feeding bottle advertisement, and old keywords originally possessed by the source content include "milk powder", "diaper", and more than one of "milk powder" and "diaper" are selected as keywords to be taken;
calculating the association degree of the keywords to be acquired and the source content, specifically, according to the level of the comments of the user where the keywords to be acquired appear for the first time, the similarity degree of the keywords to be acquired and the number of times of the keywords to be acquired appearing in the evaluation under the source content item;
the similarity of the keywords to be taken is the number of evaluations of the users under the source content items with positive orientation of the keywords to be taken;
the calculation formula is as follows: the relevancy Z = W1 a + W2B + W3C, where a denotes the level of the comment of the user where the keyword to be taken appears for the first time, B denotes the degree of similarity of the keyword to be taken, C denotes the number of times the keyword to be taken appears in the evaluation under the source content item, W1 denotes a first weight, W2 denotes a second weight, and W3 denotes a third weight;
taking "milk powder" as an example, a is 2 (first appearing in the second level of reviews), B is 23 (positive evaluation is 23), C is 50;
selecting keywords with the relevance degree exceeding a threshold value and to be selected as recommended keywords of the source content;
respectively adding source content into each dimension, wherein the source content in any dimension only retains recommendation keywords matched with the attribute of the dimension;
as shown in fig. 4, according to the above operations, the present embodiment provides a dimension dividing unit 130, including:
a word extraction unit 131 operable to select at least one word, which appears in the evaluation of the user under the source content item more than a frequency threshold or more than a frequency threshold, as a new keyword to be given to the source content;
a to-be-taken keyword generation unit 132 operable to select one or more new keywords that are the same as the old keywords that the source content originally has as the to-be-taken keywords;
an association degree calculation unit 133 operable to calculate an association degree of the keyword to be retrieved with the source content;
a recommended keyword generation unit 134 operable to select a keyword to be extracted whose association with the source content exceeds a threshold as a recommended keyword of the source content;
a content distribution unit 135 operable to add source content to the respective dimensions, respectively;
the user behavior information further comprises source content;
as shown in fig. 5, based on the management platform of the big data based content information distribution engine, the present embodiment provides a method for a big data based content information distribution engine, which includes the following steps:
step 100, acquiring user behavior information;
200, generating recommendation information according to the user behavior information;
step 300, generating a recommendation keyword of the source content according to the recommendation information;
step 400, adding source content to at least two or more dimensions;
step 500, providing any recommendation service with one or more dimensions to the client 300, wherein the recommendation service includes selecting the source content in the dimension associated with the recommendation keyword with the most common words in the comments of the user to be recommended and recommending the source content to the user.

Claims (9)

1. A method of a big data based content information distribution engine, comprising the steps of:
step 100, acquiring user behavior information;
200, generating recommendation information according to the user behavior information;
step 300, generating a recommendation keyword of the source content according to the recommendation information;
step 400, adding source content to at least two or more dimensions;
step 500, providing recommendation service of any dimension to the client, wherein the recommendation service comprises selecting the source content in the dimension associated with the recommendation keyword with the most common words in the comments of the user to be recommended and recommending the source content to the user.
2. A management platform for a big data based content information distribution engine, comprising:
the content resource platform can be operated to acquire user behavior information, endow recommended keywords for the source content according to the user behavior information and add the source content to at least more than two dimensions;
and the content service platform can be operated to provide recommendation service of any dimension to the client, and the recommendation service comprises selecting the source content in the dimension associated with the recommendation keyword with the most appeared words in the comments of the user to be recommended and recommending the source content to the user.
3. The management platform of the big data based content information distribution engine according to claim 2, wherein the step of obtaining the user behavior information and assigning the recommended keywords to the source content according to the user behavior information comprises the steps of:
step S1, acquiring user behavior information;
step S2, generating recommendation information according to the user behavior information, wherein the recommendation information at least comprises source content, user evaluation information related to the source content, uniformity information and level information;
step S3, a recommendation keyword for the source content is generated based on the recommendation information.
4. The management platform of the big data based content information distribution engine according to claim 3, wherein the generating of the recommendation keyword of the source content according to the recommendation information comprises:
step S311, selecting at least more than one word with the frequency exceeding a frequency threshold value or the frequency exceeding a frequency threshold value in the evaluation of the user under the source content item as a new keyword to be endowed to the source content;
step S312, at least selecting more than one new keywords which are the same as the old keywords originally possessed by the source content as the keywords to be acquired;
step S313, calculating the association degree of the keywords to be acquired and the source content, specifically, calculating according to the level of the comments of the user, where the keywords to be acquired appear for the first time, the similarity degree of the keywords to be acquired, and the number of times of the keywords to be acquired appearing in the evaluation under the source content item;
step S314, selecting keywords with the relevance degree exceeding a threshold value to be selected as the recommendation keywords of the source content.
5. The management platform of the big-data-based content information distribution engine according to claim 4, wherein the calculation formula for calculating the association degree between the keywords to be extracted and the source content is as follows:
the relevancy Z = W1 a + W2B + W3C, where a denotes the level of the comment of the user where the keyword to be taken first appears, B denotes the degree of similarity of the keyword to be taken, C denotes the number of times the keyword to be taken appears in the evaluation under the source content item, W1 denotes a first weight, W2 denotes a second weight, and W3 denotes a third weight.
6. The platform of claim 4, wherein the similarity of the keywords to be retrieved is a number of ratings of users under source content items to which the keywords to be retrieved point positive.
7. The management platform of a big data based content information distribution engine according to claim 2, wherein the adding source content to at least two or more dimensions comprises the following steps:
and respectively adding the source content into each dimension, wherein the source content in any dimension only retains the recommendation keywords matched with the attribute of the dimension.
8. The management platform of a big data based content information distribution engine according to claim 2, wherein the content resource platform comprises at least:
a data acquisition unit operable to acquire user behavior information and send the user behavior information to the recommendation information generation unit;
a recommendation information generation unit operable to generate recommendation information including at least source content, user evaluation information related to the source content, degree of uniformity information, level information;
and the dimension dividing unit is operable to generate a recommendation keyword according to the recommendation information and add the source content to at least two or more dimensions.
9. The management platform of the big-data-based content information distribution engine according to claim 8, wherein the dimension division unit includes:
a word extraction unit operable to select at least one or more words, as new keywords, to be given to the source content, the words appearing in the user's evaluation under the source content item more than a frequency threshold or more than a frequency threshold;
a to-be-acquired keyword generation unit operable to select one or more new keywords that are the same as old keywords originally possessed by the source content as to-be-acquired keywords;
the relevancy calculation unit is operable to calculate the relevancy of the keywords to be acquired and the source content;
the recommendation keyword generation unit is operable to select keywords with the association degree with the source content exceeding a threshold value to be selected as recommendation keywords of the source content;
a content distribution unit operable to add source content to the respective dimensions separately.
CN202011045386.XA 2020-09-29 2020-09-29 Method for content information distribution engine based on big data Active CN112115368B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011045386.XA CN112115368B (en) 2020-09-29 2020-09-29 Method for content information distribution engine based on big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011045386.XA CN112115368B (en) 2020-09-29 2020-09-29 Method for content information distribution engine based on big data

Publications (2)

Publication Number Publication Date
CN112115368A true CN112115368A (en) 2020-12-22
CN112115368B CN112115368B (en) 2022-07-05

Family

ID=73798305

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011045386.XA Active CN112115368B (en) 2020-09-29 2020-09-29 Method for content information distribution engine based on big data

Country Status (1)

Country Link
CN (1) CN112115368B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103606097A (en) * 2013-11-21 2014-02-26 复旦大学 Method and system based on credibility evaluation for product information recommendation
CN104809154A (en) * 2015-03-19 2015-07-29 百度在线网络技术（北京）有限公司 Method and device for recommending information
CN105023171A (en) * 2015-06-29 2015-11-04 成都亿邻通科技有限公司 Method for recommending group purchase to user
US20160004774A1 (en) * 2013-03-27 2016-01-07 Tencent Technology (Shenzhen) Company Limited Information recommendation method and apparatus and information recommendation system
CN108256119A (en) * 2018-02-14 2018-07-06 北京方正阿帕比技术有限公司 A kind of construction method of resource recommendation model and the resource recommendation method based on the model
CN108573411A (en) * 2018-04-17 2018-09-25 重庆理工大学 Depth sentiment analysis and multi-source based on user comment recommend the mixing of view fusion to recommend method
CN109885770A (en) * 2019-02-20 2019-06-14 杭州威佩网络科技有限公司 A kind of information recommendation method, device, electronic equipment and storage medium
CN110069712A (en) * 2019-04-23 2019-07-30 平安城市建设科技(深圳)有限公司 Source of houses recommended method and relevant device based on source of houses evaluation semantic analysis
US20190279273A1 (en) * 2018-03-09 2019-09-12 Boe Technology Group Co., Ltd. Shopping recommendation method, client, and server
CN111125344A (en) * 2019-12-23 2020-05-08 北大方正集团有限公司 Related word recommendation method and device
US10706098B1 (en) * 2016-03-29 2020-07-07 A9.Com, Inc. Methods to present search keywords for image-based queries

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160004774A1 (en) * 2013-03-27 2016-01-07 Tencent Technology (Shenzhen) Company Limited Information recommendation method and apparatus and information recommendation system
CN103606097A (en) * 2013-11-21 2014-02-26 复旦大学 Method and system based on credibility evaluation for product information recommendation
CN104809154A (en) * 2015-03-19 2015-07-29 百度在线网络技术（北京）有限公司 Method and device for recommending information
CN105023171A (en) * 2015-06-29 2015-11-04 成都亿邻通科技有限公司 Method for recommending group purchase to user
US10706098B1 (en) * 2016-03-29 2020-07-07 A9.Com, Inc. Methods to present search keywords for image-based queries
CN108256119A (en) * 2018-02-14 2018-07-06 北京方正阿帕比技术有限公司 A kind of construction method of resource recommendation model and the resource recommendation method based on the model
US20190279273A1 (en) * 2018-03-09 2019-09-12 Boe Technology Group Co., Ltd. Shopping recommendation method, client, and server
CN108573411A (en) * 2018-04-17 2018-09-25 重庆理工大学 Depth sentiment analysis and multi-source based on user comment recommend the mixing of view fusion to recommend method
CN109885770A (en) * 2019-02-20 2019-06-14 杭州威佩网络科技有限公司 A kind of information recommendation method, device, electronic equipment and storage medium
CN110069712A (en) * 2019-04-23 2019-07-30 平安城市建设科技(深圳)有限公司 Source of houses recommended method and relevant device based on source of houses evaluation semantic analysis
CN111125344A (en) * 2019-12-23 2020-05-08 北大方正集团有限公司 Related word recommendation method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
崔春生等: "基于用户在线评论的旅游景点推荐算法研究", 《系统科学与数学》 *

Also Published As

Publication number Publication date
CN112115368B (en) 2022-07-05

Similar Documents

Publication Publication Date Title
US11494457B1 (en) Selecting a template for a content item
CN106156127B (en) Method and device for selecting data content to push to terminal
US7788250B2 (en) Flexible request and response communications interfaces
US20170286539A1 (en) User profile stitching
US8484205B1 (en) System and method for generating sources of prioritized content
US20070143176A1 (en) Advertising keyword cross-selling
US20130232154A1 (en) Social network message categorization systems and methods
JP4750814B2 (en) Advertising method and system for exposing contextual advertising information
US20110313848A1 (en) Metadata-enabled dynamic updates of online advertisements
US20060064411A1 (en) Search engine using user intent
CN101198978A (en) Suggesting targeting information for ads, such as websites and/or categories of websites for example
TW200917070A (en) System and method to facilitate matching of content to advertising information in a network
CN104866554B (en) A kind of individuation search method and system based on socialization mark
EP1660964A2 (en) System and method for determining quality of written product reviews in an automated manner
US20080208975A1 (en) Methods, systems, and computer program products for accessing a discussion forum and for associating network content for use in performing a search of a network database
JP2011524054A (en) Online reference collection and scoring
Jansen et al. Real time search on the web: Queries, topics, and economic value
JP2010102385A (en) User classification apparatus, advertisement distribution apparatus, user classification method, advertisement distribution method and program
JP2015521301A (en) Generate ad campaign
KR100987058B1 (en) Method and system for providing advertising service using the keywords of internet contents and program recording medium
KR101816205B1 (en) Server and computer readable recording medium for providing internet content
US20110208581A1 (en) Online advertising
CN112115368B (en) Method for content information distribution engine based on big data
JP2008269537A (en) Method and system for supplying relevant advertisement
KR101831701B1 (en) Apparatus and method for decideing target advertisingusing interest information of user

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
TA01 Transfer of patent application right

Effective date of registration: 20220614

Address after: 230001 floor 21, block C, phase II J2, innovation industrial park, No. 2800, innovation Avenue, high tech Zone, Hefei, Anhui

Applicant after: Anhui duodian Meihao Intelligent Technology Co.,Ltd.

Address before: 230001 room 2110, 21 / F, block C, zone J2, hi tech Zone, Hefei City, Anhui Province

Applicant before: Anhui Wande Information Technology Co.,Ltd.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant