Claims:We Claim:
1. A system for presenting personalized news recommendations for users by considering user’s location and news interest comprising of;
a. A server system;
b. Memory;
c. Processor; and
d. the communication network.
wherein the system determines from the general population data and items are selected by generic user associated with at least a subset of the item categories and one or more programs stored in the memory and configured for execution by the one or more processors, the one or more programs including: instructions for obtaining data associated with one or more item categories.
2. A server system as claimed in claim 1 including a front end, a user profile database, a general population interest recommendation module, a community database.
3. The system as claimed in claim1, wherein the particular user selecting items associated with at least a subset of the item categories are determined based on selecting one or more items associated with a respective item category by the generic user and the particular user.
4. A method for presenting personalized news recommendations for users by considering user’s location and news interest comprising the steps of;
a. receiving request to the server system from user of client device;
b. obtaining data from server regarding general population interests through internet;
c. selecting item categories by generic user ;
d. determines collection of news items that user is interested in; and
e. transmits data of user’s interesting news articles.
5. The method as claimed in claim 4, wherein the said data of user’s interesting articles are based on particular user recommendations to the user of the client device.
6. The system as claimed in claim 1, wherein the said front end is for receiving click data from the client devices and items from other server systems
7. The system as claimed in claim 1, wherein the said user profile database is for creating and maintaining at least some user profiles for users of the server system and stores the profiles in the user profile database.
8. The system as claimed in claim 1, wherein the said general population interest recommendation module is for determining a set of items from the item repository based on the relative likelihood.
9. The system as claimed in claim 1, wherein the said community database can be any wired or wireless local area network (LAN) and/or wide area network (WAN), such as the Internet.
, Description:Technical field of the Invention:
The present invention relates to provide personalized news recommendations. The present invention more particularly relates to a system and method for suggesting personalized news recommendations by considering user’s location and news interest.
Background of the Invention:
News items are commonly distributed and consumed through online news services. Online news services seek to recommend news items that users are likely to be interested and therefore likely to view. Typically, popular news items are recommended to users. However, popularity alone may not accurately reflect a user’s interest and thus may not accurately predict what items a user will select to view.
News items can also be recommended based on a user’s selection history. However recommending news items solely on a user’s selection history fails to account for news trends. For example, during the Olympics, a user may have many selections for sports related items but the user may not have a strong preference for sports. On the other hand, the user may want to view sports related items for exceptional sporting events such as the Olympics.
So there is a need for a system and method for predicting user’s news interest by considering a user’s selection history of news items relative to the selections made by a community of users. The present invention is a system and method for presenting personalized news recommendations for users.
Objects of the Invention:
An object of the present invention is to provide a system and method for suggesting personalized news recommendations by considering user’s location and news interest.
Another object of the present invention is to predict user’s news interest by considering a user’s selection history of news items relative to the selections made by a community of users.
Another object of the present invention is to provide news recommendations for news items in the categories in which the user has a strong interest in and news recommendations for news items that are very popular with the general population
Other objects and benefits of the present invention will be more apparent from the following description, which is not intended to bind the scope of the present invention.
Summary of the invention:
Accordingly, the present invention is a system and method for presenting personalized news recommendations for users by considering user’s location and news interest is disclosed. The present invention predicts user’s news interest by considering a user’s selection history of news items relative to the selections made by a community of users. This enables a user to receive news recommendations for news items in the categories in which the user has a strong interest in and news recommendations for news items that are very popular with the general population.
Brief Description of the Drawings:
Fig 1 describes the flowchart showing systems and method for news display based on interest and location of the user.
Detailed description of the invention:
The present invention is a system and method for presenting personalized news recommendations for users by considering user’s location and news interest. In present invention, personalized news recommendations are provided based on prediction of user's interests. The prediction of the user's interest is based on the user's selection history and the selection history of a community of users or general population. This enables user to receive news recommendations for news items in the categories in which the user has a strong interest in and news recommendations for news items that are very popular with the general population. For example, a user may have little or no interest in sports related news items except for exceptional events such as the Olympics. In the example, the user would receive news recommendations for exceptional sporting events such as the Olympics that score high enough with the general population.
In one embodiment, the system comprising of: a server system having a front end, a user profile database, a general population interest recommendation module, a community database and the communication network. The communication network can be any wired or wireless local area network (LAN) and/or wide area network (WAN), such as the Internet.
The server system includes a general population interest recommendation module, a community database, a user profile module and a user profile database. The server system receives requests from a user of a client device, determines a collection of items that the user is likely to be interested in, and sends the collection of news to the user of the client device. The data refers to any type of information that can be determined from user selections (i.e., clicks). The data includes selection duration (amount of time between user selection of a URL link and user exiting the document), the time at which the click occurred, the type of browser used to view the content clicked on, the location of the user performing the click (e.g., through the IP address of the user), the URL or name of the item clicked on and the type of click (search click or browse click). A search click is a click on a search result. A browse click is a click on any item that is not included in a search result. All type of search click, browse click is included in data.
In some embodiments the data may include those clicks where a user accessed a respective document for at least a pre-determined time interval. In this regard, the use of the pre-determined time interval may allow the system to distinguish between so-called good clicks (the user access a document that he or she may currently be interested in) and so-called bad clicks (the user inadvertently accesses a document that he or she may not currently be interested in). Thus, the pre-determined time interval may provide a way to filter out such bad clicks from the data.
The front end provides an interface between the server system and the client devices. The front end is configured to receive click data from the client devices and items from other server systems or other client devices. In some embodiments, the click data is stored in the user profile database. The front end is also configured to receive requests for items and to send items to the client devices. In some embodiments, the front end sends a feed of items to the client devices. Optionally, the front end is configured to send links to items to the client devices.
The user profile database stores a plurality of profiles, each profile storing for a respective user (or group of users), click data, custom preferences and a user/group id. In some embodiments, a profile corresponds to a group of users organized by some criteria, such as users who consume items in a particular language, (e.g., English, Japanese, Chinese, French, German, etc.), users from a particular geographical location (e.g., city, state, country or region), users having IP addresses within a certain range, users using a certain device (e.g., net book, mobile phone, desktop, tablet, laptop), or any suitable combination of such criteria.
Optionally, a respective user or group profile includes a set of predictions. The set of predictions includes a list of categories and for each category the likelihood that the user will view items associated with the category. For example, a user may be likely to select health related items 60% of the time.
A category refers to a division or class of items (e.g., news, sports, travel, and finance). In some embodiments, the categories are also related to specific groups of users for example by geographic location or language. For example, there may be a news category for Germans speakers and a news category for French speakers. Each item can be associated with one or more categories. For example, one web page may have a category of sports and entertainment. In some embodiments, a category refers to a type of item (e.g., article, video or sound recording).
The user profile module creates and maintains at least some user profiles for users of the server system and stores the profiles in the user profile database. As described in more detail below, the item recommendation module in part uses the click data for a respective user stored in the user profile database to determine a set of items to recommend to a user.
The community database stores click data and click distributions for a community of users. A click distribution is the percentage of total clicks for each category. For example, 10% of the clicks from a community of users may have been for news items in the category of health and 90% of the clicks may have been for news items in the category of sports.
The group of users are organized by some criteria, such as users who consume items in a particular language, (e.g., English, Japanese, Chinese, French, German, etc.), users from a particular geographical location (e.g., city, state, country or region), users have IP addresses within a certain range, users using a certain device (e.g., net book, mobile phone, desktop, tablet, laptop), or any suitable combination of such criteria. The item recommendation module is configured to use the click data stored in the profile database , the click distributions and the click data from the community statistics database to determine the relatively likelihood of a particular user selecting items associated with particular categories as compared to a generic user. In some embodiments, the relatively likelihoods or predictions are stored in the particular user's profile. The item recommendation module determines a set of items from the item repository based on the relative likelihood and sends the items to the particular user by way of the front end.
The item repository stores the news items including but not limited to news articles, blog postings, videos, images and sound recordings. Optionally, the news item repository also stores links to news articles, links to blog postings, links to videos, links to image and links to sound recordings. In some embodiments, the news item repository stores both metadata (e.g., title, description, URL, date/time, and possibly other metadata) and the content of each news item. In some embodiments, the news item repository stores the location of one or more content feeds.
A user interfaces with the server system and views news items at a client device. The client device may be any suitable computer devices that are capable of connecting to the communication network, such as computers, desktop computers, laptop computers, tablet devices, cell phones, gaming devices, or any other device that is capable of receiving documents, content feeds and links from the server system. The client device typically includes one or more processors, hard disk drive and a display. The client device may also have input devices such as a keyboard and a mouse.
In another embodiment, the method for presenting personalized news recommendations for users comprising the steps of; server system receives request from user of client device; obtaining data from server regarding general population interests through internet; generic user selecting item categories; determines collection of news items that user is interested in; and transmits data of user’s interesting news articles based on particular user recommendations to the user of the client device.
A respective client may contain at least one client application for receiving items from the server system. The client application can be a software application that permits a user to interact with the client and/or network resources to perform one or more tasks. For example, the client application can be a browser (e.g., Google Chrome) or other type of application that permits a user to search for, browse, and/or use resources (e.g., web pages and web services) identified by a URL (universal resource locator). Similarly, the term “URL” means a network address or location of a news item. The client application may be a feed reader. The user may create a list of feed subscriptions using the feed reader. The list of feed subscriptions is stored with the user's profile in the user profile database .A user profile stores click data for one or more categories during a predefined period of time. The period of time can be any period of time such as hours, days, weeks, months or years. The click data includes clicks, location of the user at the time each click was made, the type of the user's browser or application used for each click, the selection duration (amount of time between user selection of a URL link and user exiting the document) for each click, type of clicks (search click or browse click) for each click and timestamp of each click.