Pushing specific content to a predetermined webpage

• US 9,230,035 B2
• Filed: 08/28/2013
• Issued: 01/05/2016
• Est. Priority Date: 08/31/2012
• Status: Expired due to Fees

• 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
• Primary Examiner(s): Hicks, Michael
• Application Number:
  US14/012,085
• Publication Number:
  US 20140067818A1
• Time in Patent Office: 860 Days
• Field of Search: None
• US Class Current: 1/1
• 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 computer-implemented method for pushing specific content for text content on a predetermined webpage, comprising:

receiving, at a processing device of a computer, text content of a predetermined web page, said text content including a first text content input from a first user and reply text content input from other users in reply to the first user text content;

classifying, using the processor device, both the first text content of the first user and each of the reply text content of the other users received via the predetermined webpage according to an emotional type from among a predetermined set of emotional types; and

determining, by the processor device, for each said reply text content from said other users, a first matching degree between a classification result of the reply text content of a user and a classification result of the first text content, and determining a second matching degree between the classification result of the reply text content of the user and an emotion type expressed by the specific content to be pushed; and

determining, by the processor device, whether the first matching degree and the second matching degree satisfy a predetermined condition;

in response to that the first matching degree and the second matching degree determined satisfying a predetermined condition, combining, by the processor device, a part of the reply text content of the user with the specific content to be pushed to form pushing content specific for one or more said other users; and

generating, using said processor device, an output for communication over a communications network to provide said pushing content to the web page displayed on a device associated with said one or more other users.

2. The computer-implemented method of claim 1, wherein the classifying the first text content and the reply text content of the user comprises at least one of:

extracting, by the processor device, emotional symbols from the text content of the first user and the each said reply text content of the other users, wherein the emotional symbols belong to a predefined symbol set; and

extracting, by the processor device, emotional words from the text content of the first user and from each reply text content of the other users.

3. The computer-implemented method of claim 2, wherein the classifying comprises:

classifying, by the processor device, the emotional symbols and/or emotional words extracted from the first text content into corresponding emotion types from the predetermined set of emotion types as a first emotion type, and classifying the emotional symbols and/or emotional words extracted from each of the reply text content of the other users into corresponding second emotion types from the predetermined set of emotion types,

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.

4. The computer-implemented method of claim 3, further comprising:

obtaining, by the processor device, a third emotion type corresponding to the specific content to be pushed;

and for each said reply text content from other users;

determining, by the processor device, whether a reply text content of a user includes a word indicating an emotional transition; and

if the reply text content of the user does not contain emotional transition,

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

calculating, by the hardware processor device, a respective distance between the first emotion coordinate and the corresponding second emotion coordinate as a first matching degree measure, and calculating a distance between the corresponding second emotion coordinate and the third emotion coordinate as a second matching degree measure.

5. The computer-implemented method of claim 3, wherein obtaining the first matching degree and the second matching degree comprises:

obtaining, by the processor device, a third emotion type corresponding to the specific content to be pushed;

and for each said reply text content from other users;

determining, by the processor device, whether the reply text content of a user includes a word indicating an emotional transition; and

if the replied text content of the user contains emotional transition,

extracting, by the processor device, emotional symbols and/or emotional words before the emotional transition and emotional symbols and/or emotional words after the emotional transition word of the reply text content, and respectively classifying them into a corresponding fourth emotion and a corresponding fifth emotion types from the predetermined set of emotion types;

mapping, by the processor device, 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, by the processor device, a distance between the first emotion coordinate and the fourth emotion coordinate as a measure of the first matching degree and calculating a distance between the third emotion coordinate and the fifth emotion coordinate as a measure of the second matching degree.

6. The computer-implemented method of claim 5, wherein the determining whether the first matching degree and the second matching degree satisfy a predetermined condition comprises one of:

determining, by the processor device, 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

for each reply text content of the other users, determining by said processor device a corresponding sum of the measure of the first matching degree and the measure of the corresponding second matching degree, wherein the second matching degree of the reply text content that provides the minimum sum satisfies the predetermined condition.

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

8. The computer-implemented method of claim 1 further comprises:

determining, by the hardware processor device, 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.

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

a memory storage device;

a processing device of a computer in operative communication with said memory, the processing device configured to;

receive text content of a predetermined web page, said text content including a first text content input from a first user and reply text content input from other users in reply to the first user text content;

classify both the first text content of the first user and each of the reply text content of the other users received via the predetermined webpage according to an emotional type from among a predetermined set of emotional types;

determine, for each said reply text content from the other users, a first matching degree between a classification result of the reply text content of a user and a classification result of the first text content, and determining a second matching degree between the classification result of the reply text content of the user and an emotion type expressed by the specific content to be pushed; and

determine whether the first matching degree and the each respective second matching degree satisfy a predetermined condition;

in response to that the first matching degree and the second matching degree determined satisfying a predetermined condition, combine a part of the reply text content with the specific content to be pushed to form pushing content specific for one or more said other users; and

generate an output for communication over a communications network to provide said pushing content to the web page displayed on a device associated with said one or more other users.

10. The apparatus of claim 9, wherein to classify the first text content and the each reply text content, said processor is further configured to:

extract emotional symbols from the text content of the first user and each of the reply text content of the other users, wherein the emotional symbols belong to a predefined symbol set; and

extract emotional words from the text content of the first user and from each reply text content of the other users.

11. The apparatus of claim 10, wherein to classify the first text content and the each reply text content, said processor is further configured to:

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

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.

12. The apparatus of claim 11, wherein said processor device is further configured to:

obtain a third emotion type corresponding to the specific content to be pushed;

and for each said reply text content from said other users;

determine whether the reply text content of other users a user includes a word indicating an emotional transition; and

if the reply text content of the user does not contain emotional transition,

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

calculate a respective distance between the first emotion coordinate and the corresponding second emotion coordinate as a first matching degree measure, and calculate a distance between the corresponding second emotion coordinate and the third emotion coordinate as a measure of the second matching degree.

13. The apparatus of claim 11, wherein to determine the first matching degree and the second matching degree, said processor device is further configured to:

obtain a third emotion type corresponding to the specific content to be pushed;

and for each said reply text content from said other users;

determine whether the reply text content of a user includes a word indicating an emotional transition; and

if the replied text content of the user contains emotional transition,

extract emotional symbols and/or emotional words before the emotional transition and emotional symbols and/or emotional words after the emotional transition word of the reply text content, and respectively classify them into a corresponding fourth emotion and a corresponding fifth emotion types from the predetermined set of emotion types;

map 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

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

14. The apparatus of claim 13, wherein to determine whether the first matching degree and the second matching degree satisfy a predetermined condition, the processor device is further configured to one of:

determine 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

for each reply text content of the other users, determine a corresponding sum of the measure of the first matching degree and the measure of the corresponding second matching degree, wherein the second matching degree of the reply text content that provides the minimum sum satisfies the predetermined condition.

15. A computer program product comprising a non-transitory computer readable medium tangibly embodying computer readable instructions which, when executed, cause a computer to perform a method for pushing specific content for text content on a predetermined webpage, said method comprising:

receiving text content of a predetermined web page provided for display at one or more user devices connected to the computer over a network, said text content including a first text content associated with a first user and reply text content associated with other users in reply to the first user text content;

classifying both the first text content of the first user and each of the reply text contents of the other users received via the predetermined webpage according to an emotional type from among a predetermined set of emotional types;

determining, for each said reply text content from said other users, a first matching degree between a classification result of the reply text content of a user and a classification result of the first text content, and determining a second matching degree between the classification result of the reply text content of the user and an emotion type expressed by the specific content to be pushed; and

determining whether the first matching degree and the second matching degree satisfy a predetermined condition;

in response to that the first matching degree and the second matching degree determined satisfying a predetermined condition, combining, by the processor device, a part of the reply text content of the user with the specific content to be pushed to form pushing content specific for one or more said other users; and

generating an output for communication over a communications network to provide said pushing content to the web page displayed on a device associated with said one or more other users.

16. The computer program product of claim 15, wherein the classifying the first text content and the reply text content comprises at least one of:

extracting, by the processor device, emotional symbols from the text content of the first user and each the reply text content of the other users, wherein the emotional symbols belong to a predefined symbol set; and

extracting, by the processor device, emotional words from the text content of the first user and from each reply text content of the other users; and

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

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.

17. The computer program product of claim 16, further comprising:

obtaining a third emotion type corresponding to the specific content to be pushed;

and for each said reply text contents from other users;

determining whether a reply text content of a user includes a word indicating an emotional transition; and

if the reply text content of the user does not contain emotional transition,

mapping the first emotion type, the corresponding 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 respective distance between the first emotion coordinate and the corresponding second emotion coordinate as a first matching degree measure, and calculating a distance between the corresponding second emotion coordinate and the third emotion coordinate as a second matching degree measure.

18. The computer program product of claim 16, wherein obtaining the first matching degree and the second matching degree comprises:

obtaining a third emotion type corresponding to the specific content to be pushed;

and for each said reply text contents from other users;

determining whether the reply text content of a user includes a word indicating an emotional transition; and

if the replied text content of the user 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 word of the reply text content, and respectively classifying them into a corresponding fourth emotion and a corresponding fifth emotion types from the predetermined set of emotion types;

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