PUSHING SPECIFIC CONTENT TO A PREDETERMINED WEBPAGE

• US 20140067818A1
• Filed: 08/28/2013
• Published: 03/06/2014
• Est. Priority Date: 08/31/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bao, Sheng Hua, Guo, Hong Lei, Guo, Zhili, Su, Zhong, Zhu, Hui Jia
• Granted Patent: US 9,230,035 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

A method and an apparatus for pushing specific content for a predetermined webpage, and a website server. The method for pushing specific content for text content on a predetermined webpage comprises: subjecting text content on a predetermined webpage to emotional analysis; determining a matching degree between a result of the emotional analysis and an emotion expressed by specific content to be pushed; and responding to that the matching degree determined above satisfies a predetermined condition, combining a part of the text content with the specific content to be pushed, thereby forming content to be pushed specific for users. By using the technology of the present invention, user can be avoided from feeling disgust for content to be pushed and accuracy of push can be enhanced.

Claims

1. A method for pushing specific content for text content on a predetermined webpage, comprising:

subjecting the text content on a predetermined webpage to emotional analysis;

determining a matching degree between a result of the emotional analysis and an emotion expressed by the specific content to be pushed; and

responding to the determined matching degree that satisfies a predetermined condition, combining at least a part of the text content with the specific content to be pushed, thereby forming pushing content specific for users.

2. The method of claim 1, wherein the emotional analysis for the text content comprises at least one of:

extracting an emotional symbol from the predetermined webpage, wherein the emotional symbol belongs to a predefined symbol set; and

extracting an emotional word from the text content on the predetermined webpage.

3. The method of claim 2, wherein the emotional analysis for text content comprises:

classifying the extracted emotional symbol and/or emotional word into emotion types in a predetermined set of emotion types as a target emotion type, wherein the emotion types in the predetermined set of emotion types are predefined;

wherein, correspondence relation between the emotional symbol and/or the emotional word and the emotion type is obtained by searching a database in which correspondence relations between the emotional symbols and/or the emotional words and emotion types are stored.

4. The method of claim 3, wherein determining the matching degree between the result of the emotional analysis and the emotion expressed by the specific content to be pushed comprises:

regarding the emotion type to which specific content to be pushed belongs as a reference emotion type;

mapping the target emotion type and the reference emotion type as emotion coordinates in an emotion coordinate system, so as to obtain a target emotion coordinate and a reference emotion coordinate; and

calculating a distance between the target emotion coordinate and the reference emotion coordinate as a measure of the matching degree.

5. The method of claim 4, wherein the matching degree that satisfies a predetermined condition refers to one of:

the matching degree satisfies the predetermined condition if the distance between the target emotion coordinate and the reference emotion coordinate is less than a predetermined threshold; and

the matching degree of this target emotion coordinate with the reference emotion coordinate satisfies the predetermined condition if a target emotion coordinate is the one that provides the shortest distance from the reference emotion coordinate.

6. The method of claim 1, wherein a part of the text content is combined with the specific content to be pushed by means of a predetermined template.

7. The method of claim 1 further comprises:

determining an appropriateness of the combination of the part of the text content and the specific content to be pushed, and displaying the combination on the webpage only when the combination is appropriate.

8. A method for pushing specific content for text content on a predetermined webpage, comprising:

subjecting both text content on a predetermined webpage and a reply text to the content to emotional analysis;

determining a matching degree between a result of the emotional analysis of the reply text and a result of the emotional analysis of text content and a matching degree between the result of emotional analysis of the reply text and an emotion expressed by the specific content to be pushed, thereby obtaining a first matching degree and a second matching degree; and

in response to that the first matching degree and the second matching degree determined satisfying a predetermined condition, combining a part of the reply text with the specific content to be pushed to form pushing content specific for users.

9. The method of claim 8, wherein the emotional analysis for the text content and the reply text comprises at least one of

extracting emotional symbols from the text content and the reply text, wherein the emotional symbols belong to a predefined symbol set;

and

extracting emotional words from the text content and the reply text.

10. The method of claim 9, wherein the emotional analysis for the text content and the reply text comprises:

classifying the emotional symbols and/or emotional words extracted from the text content into emotion types in a predetermined set of emotion types as a first emotion type, and classifying the emotional symbols and/or emotional words extracted from the reply text into emotion types in the predetermined set of emotion types as a second emotion type,

wherein correspondence relations between the emotional symbols and/or emotional words and the emotion types are obtained by searching a database in which correspondence relations between the emotional symbols and/or emotional words and the emotion types are stored.

11. The method of claim 10, wherein obtaining the first matching degree and the second matching degree comprises:

regarding the emotion type to which the specific content to be pushed belongs as a third emotion type;

if the reply text does not contain emotional transition,

mapping the first emotion type, the second emotion type and the third emotion type into an emotion coordinate system, so as to obtain a first emotion coordinate, a second emotion coordinate and a third emotion coordinate; and

calculating a distance between the first emotion coordinate and the second emotion coordinate as measure of a first matching degree and calculating a distance between the second emotion coordinate and the third emotion coordinate as measure of a second matching degree.

12. The method of claim 10, wherein obtaining the first matching degree and the second matching degree comprises:

regarding the emotion type to which the specific content to be pushed belongs as a third emotion type;

if the replied text contains emotional transition,

extracting emotional symbols and/or emotional words before the emotional transition and emotional symbols and/or emotional words after the emotional transition, classifying them into emotion types in the predetermined set of emotion types, thereby respectively obtaining a fourth emotion type and a fifth emotion type;

mapping the first emotion type, the third emotion type, the fourth emotion type and the fifth emotion type into an emotion coordinate system, so as to obtain a first emotion coordinate, a third emotion coordinate, a fourth emotion coordinate and a fifth emotion coordinate; and

calculating a distance between the first emotion coordinate and the fourth emotion coordinate as a measure of a first matching degree and calculating a distance between the third emotion coordinate and the fifth emotion coordinate as a measure of a second matching degree.

13. The method of claim 12, wherein the matching degree satisfying a predetermined condition refers to one of:

the first matching degree and the second matching degree satisfy the predetermined condition if a sum of the measure of the first matching degree and the measure of the second matching degree is less than a predetermined threshold; and

a sum of the measure of the first matching degree and the measure of the second matching degree is obtained for all the reply texts, wherein the matching degree of the reply text that provides the minimum sum satisfies the predetermined condition.

14. The method of claim 8, wherein a part of the reply text is combined with the specific content to be pushed by means of a predetermined template.

15. The method of claim 8 further comprises:

determining an appropriateness of the combination of the part of the replied text with the specific content to be pushed, and displaying this combination on the webpage on which the text content locates only when the combination is appropriate.

16. An apparatus for pushing specific content for text content on a predetermined webpage comprising:

an emotional analysis unit configured to subject both text content on a predetermined webpage and reply text to emotional analysis;

a matching degree determination unit configured to determine a matching degree between a result of emotional analysis of the reply text and an emotion expressed by specific content and a matching degree between a result of emotional analysis of the text content and an emotion expressed by specific content to be pushed, there by obtaining a first matching degree and a second matching degree; and

a pushing unit configured to combine a part of the reply text with the specific content to be pushed, in response to the first matching degree and the second matching degree that satisfy a predetermined condition, thereby forming content to be pushed specific for users.

17. A non-transitory computer readable article of manufacture tangibly embodying computer readable instructions which, when executed, cause a computer to carry out the steps of a method comprising:

subjecting the text content on a predetermined webpage to emotional analysis;

determining a matching degree between a result of the emotional analysis and an emotion expressed by the specific content to be pushed; and

responding to the determined matching degree that satisfies a predetermined condition, combining at least a part of the text content with the specific content to be pushed, thereby forming pushing content specific for users.