Patent Application
20210357983
The application relates in general to advertising online, and in particular to the advertisement push methods and systems of deciding which advertisement to push based on the user's search history, reactions corresponding to each pushed advertisement, and application usage records.
Existing multimedia players also serve as a platform for various software services. For operators, hardware devices used to play multimedia are no longer a main source of revenue, and attracting users to continue to purchase online services is necessary. However, despite various types of notification channels between users and operators, when faced with large amounts of marketing notifications, users can easily turn off notifications and ignore information important to the operators. Selecting advertisements to which the user will respond is problematic.
Implementations of the present technology will now be described, by way of example only, with reference to the attached figures, wherein:
Further areas to which the present disclosure can be applied will become apparent from the detailed description provided herein. It should be understood that the detailed description and specific examples, while indicating exemplary embodiments, are intended for purposes of illustration only and are not intended to limit the scope of the claims.
According to an embodiment, after receiving the advertisement, the processing module 120 directly presents the advertisement to the user through the display module 130 if there is only one advertisement, and records the user's reactions. Otherwise, the processing module 120 will select an advertisement that the user may be interested in according to the words contained in the advertisement and the user's word database to improve the efficacy of the presentation if there are more than one advertisement. The preference scores of different words corresponding to each user are calculated based on each user's search history, reactions corresponding to advertisements, and application usage records. Further, the user reactions include the watching duration of the user looking at the content of the advertisement, the user's clicking records and bookmarking records corresponding to the advertisement, and the application usage records including the usage time of each application, the number of clicks (the number that the user clicked the application corresponding to the pushed advertisements) corresponding to the clicking records and the bookmarked times (the number that the user bookmarked the pushed advertisement) corresponding to the bookmarking records.
When the user searches through the motion sensing module (such as by pressing buttons or voice inputting), the processing module 120 will give a certain word used in the search a search weight (such as 50), and accumulate the scores of the corresponding words stored in the word database. For example, if the user searches for “costume drama”, if the original preference score for the “costume drama” in the word database is 20, after the user search, the preference score for the “costume drama” will be 70. Conversely, if “costume drama” is not stored in the word database, the processing module 120 adds the phrase “costume drama” and records its preference score as 50.
In addition, after the display module 130 displays the advertisement, the processing module 120 further determines the user's reactions, and calculates the preference scores for the words contained in the advertisement according to the reactions. The words in the advertisement can be obtained through any general word division method, and the user's reactions include the watching duration of the user looking at the content of the advertisement, whether the user clicked on the application corresponding to the advertisement (clicking record) and whether the user bookmarked the advertisement (bookmarking record), etc.. If the user clicked on the application corresponding to the advertisement, the processing module 120 multiplies the scores of all the words included in the advertisement by a click weight (such as 1.2). If the user bookmarks the advertisement information, the processing module 120 further multiplies the scores of all the words included in the advertisement by a bookmark weight (such as 1.5). The preference score corresponding to each word contained in each advertisement is the product of the watching duration, the click weight, and the bookmark weight. It should be noted that the values of the click weight and the bookmark weight can be defined by the user, but are usually less than the search weight. In other words, after the user searches using a certain word, the increase in its preference score is usually much greater than the increase in clicking and/or bookmarking in relation to certain advertisements. Finally, after obtaining the user's preference scores corresponding to different words, when the processing module 120 receives further advertisements, the further advertisement can be selected according to the words contained in each of the advertisements with higher preference scores to improve the efficacy of the presentation. In addition, if there is only one further or new advertisement, the processing module 120 directly pushes the new advertisement, records the reactions of the user, and updates the preference scores of all words contained in the new advertisement according to the reactions.
According to another embodiment, the processing module 120 further determines a viewing situation in which to play the new advertisement based on the product of a ratio of the watching duration and residing time of the advertisement, and a ratio of the number of clicks and the number of all advertisements. The residing time of the advertisement represents the time from the display module 130 displaying the advertisement until the user closes the display of the advertisement. The viewing situation for playing the advertisement may include playing the advertisement before executing the application, playing the advertisement after leaving the application, and playing the advertisement during idle mode (such as after leaving the application for a predetermined time). It should be noted that the viewing situations for playing advertisements as described above are only some examples and are not limited thereto.
When the watching duration and the residing time are closer in duration, and the more that the user clicks on the applications related to the advertisement, this is taken to signify a better user-reaction and the higher the calculated value. Conversely, when the ratio of the watching duration and the residing time is smaller, or the number of clicks is less, the calculated value will be lower, as it is taken to indicate that the user did not specifically watch the content of the advertisements, that is, the efficacy of such advertising is not high. Finally, when the processing module 120 is to put forward a further or new advertisement, it will preferentially select the viewing situation having the highest product value.
According to another embodiment, the processing module 120 further determines the time point of the presentation of the advertisement according to the delay between clicks (click-delay) in each application. For example, the processing module 120 records the time point of each operation (such as pressing any key on the remote control) implemented on the motion sensing module 110 by the user in the application, and calculates the click-delays between each time point. Next, the processing module 120 groups the click-delays into multiple clusters, and selects the maximum delay of the largest cluster as the time point for presenting the new advertisement. For example, the processing module 120 divides the clusters of the click-delays into 1-3 seconds, 5-10 seconds, and 30-180 seconds categories, and counts the number of click-delays falling within the three clusters in each application. If the number of click-delays falling within 1-3 seconds is the largest, the processing module 120 pushes the new advertisement 3 seconds after the user presses any key on the remote control. If the number of click-delays falling within 5-10 seconds is the largest, the processing module 120 pushes the new advertisement 10 seconds after the user presses any key on the remote control. If the number of click-delays falling within 30-180 seconds is the largest, the processing module 120 pushes the new advertisement 180 seconds after the user presses any key on the remote control. In this way, the advertisements can be most effectively pushed to the user, and there is no inconvenience or annoyance caused to the user.
In addition, before pushing the advertisement, the processing module 120 may further decide the viewing situation to be pushed according to the residence time, the watching duration, the click record and bookmark record of the displayed advertisements, and decide the time point according to the user's click-delays in each application. The methods of determining the viewing situation and the time point of the presentation of the advertisement are as described above, and it will not be described again to simplify the description.
It should be noted that although the method as described above has been described through a series of steps or blocks of a flowchart, the process is not limited to any order of the steps, and some steps may be different from the order of the remaining steps or the remaining steps can be done at the same time. In addition, those skilled in the art should understand that the steps shown in the flowchart are not exclusive, other steps may be included, or one or more steps may be deleted without departing from the scope.
In summary, according to the advertising information pushing method and system described in the embodiments of the present invention, by recording the user's search history, application usage records, and the user's reactions corresponding to each advertisement, the user's preference habits can be utilized, so as to select the advertisements that the user may be interested in, so as to improve the effectiveness of the advertisement. In addition, by recording the user's operating habits in different viewing situations and the user's click-delays in each application, it will be possible to deduce the user's browsing habits, attention time to information, and the time when the continuous operation is not disturbed. This will enable users to focus more on information that is interest or importance, and reduce the bandwidth required by not sending unneeded background information.
It will be apparent to those skilled in the art that various modifications and variations can be made to the structure disclosed without departing from the scope or spirit of the claims. In view of the foregoing, it is intended that the present disclosure covers modifications and variations, provided they fall within the scope of the following claims and their equivalents.
