阅读说明：本技术 在线小配件推荐系统和方法 (Online gadget recommendation system and method ) 是由 E.托雷斯 J.萨哈斯 于 2018-10-05 设计创作，主要内容包括：小配件推荐系统和方法为包含内容或展示的事件推荐用户界面小配件。在一个实施例中,系统为事件的内容或展示推荐用于登陆页面的用户界面小配件。系统和方法可以从过去的事件中提取特征,并推荐用户界面小配件。(Widget recommendation systems and methods recommend user interface widgets for events that contain content or presentations. In one embodiment, the system recommends a user interface widget for a landing page for the content or presentation of an event. The system and method may extract features from past events and recommend user interface widgets.)

1. A method, comprising:

receiving a set of characteristics for an event;

generating a feature vector associated with the event using the set of characteristics;

comparing the feature vector of the event to a co-occurrence matrix to generate one or more recommended user interface gadgets for the event, the gadget to be included in one of a web workshop and an event page for the event, the co-occurrence matrix further including an array of values, wherein each value corresponds to an occurrence of both a first user interface gadget and a second user interface gadget on the event page for a previous high engagement event;

displaying the one or more recommended user interface widgets for the event to a presenter of the event.

2. The method of claim 1, wherein comparing the eigenvector of the event and the co-occurrence matrix further comprises performing a cross-product operation with the eigenvector of the event and the co-occurrence matrix.

3. The method of claim 1, further comprising automatically selecting the one or more recommended user interface widgets and inserting the selected one or more recommended user interface widgets onto the event page for the event.

4. The method of claim 1, further comprising retrieving data about a plurality of previous events, the data for each previous event comprising an engagement level of a viewer for the previous event and one or more user interface widgets included in an event page of the previous event, and generating the co-occurrence matrix using the data about the previous event.

5. The method of claim 1, wherein the set of characteristics comprises one or more of an industry related to the event, an application related to the event, a category related to the event, and a department related to the event.

6. The method of claim 1, wherein each user interface widget further comprises a user interface element on an event page that performs a particular function when a user clicks on the user interface element.

7. The method of claim 6, wherein the event page is a landing page having an event media player and the one or more recommended user interface widgets.

8. The method of claim 7, wherein the event is one of a web seminar, an interactive video, and an animation book.

9. The method of claim 7, further comprising presenting the event and the landing page to a user.

10. A system, comprising:

a computing device having a processor, a memory, and a display;

a back-end computer system connectable to each computing device, the back-end having a processor, a memory, and a plurality of rows of instructions configured to:

receiving a set of characteristics for an event;

generating a feature vector associated with the event using the set of characteristics;

comparing the feature vector of the event to a co-occurrence matrix to generate one or more recommended user interface gadgets for the event, the gadget to be included in one of a Web workshop and a landing page of the event, the co-occurrence matrix further including an array of values, wherein each value corresponds to an occurrence of both a first user interface gadget and a second user interface gadget on an event page for a previous high engagement event;

transmitting the one or more recommended user interface widgets for the event to the computing device; and

the computing device display is configured to display the one or more recommended user interface widgets for the event.

11. The system of claim 10, wherein the backend is further configured to perform a cross product operation with the feature vector of the event and the co-occurrence matrix to generate one or more recommended user interface gadgets for the event to be included in a landing page of the event.

12. The system of claim 10, wherein the backend is further configured to automatically select the one or more recommended user interface widgets and insert the selected one or more recommended user interface widgets onto the event page for the event.

13. The system of claim 10, wherein the backend is further configured to retrieve data regarding a plurality of previous events, the data for each previous event including an engagement level of a viewer for the previous event and one or more user interface widgets included in an event page of the previous event, and generate the co-occurrence matrix using the data regarding the previous event.

14. The system of claim 10, wherein the set of characteristics comprises one or more of an industry related to the event, an application related to the event, a category related to the event, and a department related to the event.

15. The system of claim 10, wherein each user interface widget further comprises a user interface element on the event page that performs a particular function when a user clicks on the user interface element.

16. The system of claim 15, wherein the event page is a landing page having an event media player and the one or more recommended user interface widgets.

17. The system of claim 16, wherein the event is one of a web seminar, an interactive video, and an animation book.

18. The system of claim 16, further comprising a second computing device having a processor, a memory, and a display, the display displaying the landing page for an audience member.

19. An apparatus, comprising:

a back-end computer system having a processor, a memory, and a plurality of rows of instructions configured to:

receiving a set of characteristics for an event;

generating a feature vector associated with the event using the set of characteristics;

comparing the feature vector of the event to a co-occurrence matrix to generate one or more recommended user interface widgets for the event, the widgets to be included in a landing page for the event, the co-occurrence matrix further including an array of values, wherein each value corresponds to an occurrence of both a first user interface widget and a second user interface widget on an event page for a previous high engagement event; and

generating a user interface that displays the one or more recommended user interface widgets for the event.

20. The apparatus of claim 19, wherein the backend is further configured to perform a cross product operation with the feature vector of the event and the co-occurrence matrix to generate one or more recommended user interface gadgets for the event to be included in a landing page of the event.

21. The apparatus of claim 19, wherein the backend is further configured to automatically select the one or more recommended user interface widgets and insert the selected one or more recommended user interface widgets onto the event page for the event.

22. The apparatus of claim 19, wherein the backend is further configured to retrieve data regarding a plurality of previous events, the data for each previous event comprising an engagement level of a viewer for the previous event and one or more user interface widgets included in an event page of the previous event, and generate the co-occurrence matrix using the data regarding the previous event.

23. The apparatus of claim 19, wherein the set of characteristics comprises one or more of an industry related to the event, an application related to the event, a category related to the event, and a department related to the event.

24. The apparatus of claim 19, wherein each user interface widget further comprises a user interface element on an event page that performs a particular function when a user clicks on the user interface element.

25. The apparatus of claim 24, wherein the event page is a landing page having an event media player and the one or more recommended user interface widgets.

26. The apparatus of claim 25, wherein the event is one of a web seminar, an interactive video, and an animation book.

Technical Field

The present disclosure relates generally to systems and methods for recommending user interface elements for web pages, and more particularly to systems and methods for recommending widgets for web seminars (webinars) or for displayed landing pages.

Background

When a person creates a new online presentation or new content, it may be desirable to create a landing page for the content or web workshop. Therefore, the presenter needs to set a landing page for the content. However, the presenter does not know which combination of user interface widgets in the landing page or web conference presents the best participation in any particular type of content. The appearance of the landing page is the basis for a good presentation. Some viewers do not participate well in the content if the content is irrelevant, static, or uninteresting. Proper selection of an interactive widget is critical to a highly appealing online content experience. From a marketer's perspective, highly appealing viewers are crucial for the correct dissemination of information or to collect behavioral profiles about people who may become patrons (prospects).

Many solutions have been proposed to increase user engagement with web content. However, the problem is always treated from the perspective of the viewer. For example, Aimojo uses tags to recommend customized content for a user and finds a meaningful distance to recommend favorite topics that are close to the user. The user may add this plug-in to the web page and it may recommend more customized content for the user. Another example is that Kindred Post uses machine learning to analyze how visitors to a web site browse the web site and recommend content based on their interests. These methods have proven to increase the amount of time spent on a web page.

A problem with other approaches is that they are not suitable for recommending user interface widgets. In particular, since the presenter has only one opportunity to attract the attention of the audience, it may be desirable to promote a high engagement opportunity. It would therefore be desirable to be able to recommend one or more user interface widgets in a landing page, which is a technical problem that has not yet been overcome, and which is also a problem specific to web pages and the internet.

Drawings

FIG. 1 illustrates a widget recommendation process;

FIG. 2 illustrates a client-side perspective of a recommendation system approach;

FIG. 3 illustrates an online presentation system that may be incorporated into a widget recommendation system;

FIG. 4 shows more details of the front and back ends of the widget recommendation system;

FIG. 5 shows an example of a covariance matrix for a widget recommendation system;

FIG. 6 shows more details of the widget recommendation process; and

FIG. 7 shows an example of a landing page with a presentation and content and one or more recommended widgets.

Detailed Description

The present disclosure is particularly applicable to user interface widget recommendation systems and methods integrated into a network presentation system for recommending user interface widgets for landing pages for events, and will be described in this context. However, it should be appreciated that the system and method has greater utility because it can be used to recommend user interface widgets for other systems, the widget recommendation system can be a stand-alone system or have a software as a service (SaaS) architecture that provides widget recommendations to third-party systems, and the widget recommendation system can be used to recommend widgets for other pages, other applications, and the like. In addition, the widget recommender may be used for a variety of different types of content, including web presentations, web seminars, interactive videos, or animations in the examples below. Network seminars, presentations, interactive video, animations, and the like may be referred to as events.

The one or more user interface widgets that may be recommended by the system (where each user interface widget is also referred to simply as a widget) may include, for example, a player media widget, a player slide widget, a player Q & a widget, a player online help widget, a resource list widget, a speaker resume (bio) widget, a survey widget, a player URL target widget, a Twitter widget, a Contact us widget, a share this (sharthsis) widget, a group chat widget, an email widget, a player rich text (rich text) widget, a LinkedIn widget, and a Facebook widget, among others. The player media gadget plays audio and/or video for a network seminar or event. For archived events, this widget allows participants (attendees) to pause, fast forward, or rewind the presentation or event. The player slide gadget displays the slides presented to the viewer during the event. The slide gadget will also display votes, surveys, and video clips (clips) pushed to the slide section. Player Q & A gadgets allow participants to submit questions at any time during a live or on-demand event. The resource list gadget allows the presenter of the event to add documents, presentations, URLs, podcasts and other content to the event. The speaker resume gadget allows a person to introduce a presenter to an event using important information such as their name, photograph, title, company and brief biographies. The survey gadget allows a person to survey the audience during the event. The gadgets allow people to ask multiple choices, true/false and open questions, and participants reply directly within the event. Player URL target gadgets allow a person to direct event/web workshop attendees to the relevant URL, and the person may also provide a link that when clicked will open in a new tab, or the person may cause the website to load within the gadget window. The Twitter gadget allows participants of an event to view one or more Twitter feeds from within the event, such as the ON24 Web workshop. Sharing this gadget allows attendees of the event to share the title, description, and URL of the event/web workshop with their friends and colleagues on 17 popular social media websites. The group chat gadget allows audience members to chat directly with each other using the group chat gadget. The gadget may be configured to allow anonymous participation or display of the user's name in a text chat display. Sending an email gadget to a friend provides a simple way for viewers/attendees to share information about the event/web seminar with their friends and colleagues. The player rich text gadget allows text to be added to the webinar console. The LinkedIn gadget allows the viewer to connect to the company of the presenter of the event through LinkedIn. For example, audience members may track corporate or presenter Linkedin pages, see who is tracking corporate or presenter Linkedin pages in their network, and share corporate or presenter Linkedin pages with public, their contacts, groups, or private individuals. The Facebook gadget allows participants to connect with the company of the presenter of the event by liking (liking) and sharing the company's Facebook page with their contacts on the Facebook.

Each user interface widget exposed on a web page (such as a landing page) is a visual icon exposed on the web page. When a user clicks/selects a widget while interacting with one or more widgets, the widget causes an action specific to the particular widget. For example, a page may have Q & A gadgets that create a Q & A interface in which a user may type questions. In one embodiment of the system, each widget may be a plurality of lines of computer code that may be executed by a processor (such as the processor of the participant's computer) to implement the functionality for that widget. A page having an event and one or more user interface widgets may be referred to as an event page.

In the exemplary embodiment described below, the appearance of the landing page is the basis for a good presentation, and some audience members will be disappointed if the page shows a flat character. Thus, the system recommends the best combination of user interface widgets to increase the chance of good viewer engagement. The system will recommend a collection of widgets to accomplish this. The system will make recommendations based on the reported engagement in previously published content, evaluating which gadgets are more effective for each type of content. For example, the system may make recommendations based on user interface widgets used in other similar landing pages that have gained high engagement in the past. In the present disclosure, high engagement means having an engagement score of greater than 5 when the engagement score ranges from 0 to 10, where 0 means no engagement at all and 10 is the maximum engagement. The engagement score is a single number that is used to measure the participants' engagement, interactivity, and the use of the webcast/event feature. The algorithm for engagement scores measures scores based on its impact on viewer interest, factors that may include: the length of time the network is watched; the number of questions posed; the number of votes answered; the number of supplemental resources viewed; the number of widgets opened on the console; and completing the network broadcast survey. The higher the score, the more attracted the viewer is during the cyber workshop/event.

FIG. 1 illustrates a widget recommendation process 10. The method may be performed by various systems, including both hardware and software, such as the system shown in fig. 3. The method may also be performed by a dedicated system, such as a network-based field presentation system, or by a stand-alone/software-as-a-service system. The method 10 may include an ordered combination of processes including data and feature extraction 12, recommendations 14, and user interface widget selections 16. More specifically, the method may comprise:

0 data and feature extraction (12): the method extracts the user interface gadgets used in all published content, the category of each gadget, and the audience engagement. The method may construct a feature vector where each widget is represented in a column and we set the value to this number if the widget is used at least once. If the widget is not used, the value will be set to zero. The categories are encoded into integer values by a dictionary (dictionary). The median number of engagement is evaluated for all users consuming the content.

1 sum of meaningful data: the method may sum up feature vectors (number 1) from content belonging to the category of interest, and the category/content category may have different predetermined values like marketing, training/learning, communication, professional postings/recruitment. This process only considers gadgets used for at least 30% of the content in the category.

2 co-occurrence (co-occurrence) matrix based collaborative filtering recommender (14): the method may compute the co-occurrence matrix based on features extracted in the data and feature extraction stages, using only content reporting very high engagement.

3 customizing recommendations for categories or types: the method calculates the cross product between the co-occurrence matrix and the vector from the sum of the above meaningful data phases, which is the score vector.

The 4-method may rank the vectors and select one or more user interface widgets with higher scores for the landing page for a particular piece of content.

Fig. 2 shows a client-side perspective of a recommender system scheme 20. In the method, a client creates a piece of content (22) belonging to one or more specific categories and having one or more characteristics as described below. In the method, an Application Programming Interface (API) of the recommender system may receive the information and provide a set of recommended widgets (24) that will increase the engagement of that type of content once the client adds a widget to the landing page (26).

In the embodiment shown in FIG. 2, the client may add any of the one or more recommended user interface gadgets to their landing page (an example of which is shown in FIG. 7 as a landing page and user interface gadget). In an alternative implementation, the system may conduct automated A/B testing, add one or both of the recommended gadgets at a time, and track engagement. The configuration will then evolve over time based on the most successful results, based on the measure of audience engagement. The system may then also automatically select and add one or more recommended gadgets to the event page for the event.

These methods address a technical problem of being able to determine and recommend user interface widgets on an event page for increased participant engagement with a presentation. Thus, existing systems that select widgets by humans do not enable the solutions of the disclosed systems and methods or improve the accuracy of recommended user interface widgets for participant engagement. In addition, the system and method provide a technical solution to the problem using technical features (including feature extraction, co-occurrence matrix, and recommended gadgets) to implement a recommended user interface gadget or gadgets that provably promote participant engagement for a piece of content/presented landing page. The disclosed system and method are also not just general purpose computers, but specially configured and programmed systems (computers with instructions specially configuring the computer) implementing technical solutions. The disclosed system and method also has a co-occurrence matrix for gadgets, as a set of rules for performing facial animation, that are executed by a computer system providing this technical solution, and the recommended gadgets. Furthermore, user interface gadgets, event pages, co-occurrence matrices, and engagement using user interface gadgets require a computer and the internet, and are issues that do not exist before computers and the internet.

FIG. 3 illustrates an online presentation system 30 that may incorporate a widget recommendation system 36B that may perform a widget recommendation method. The system 30 may have a front end of a system 32, such as one or more computing devices 32A, 32B, …, 32N in the example in fig. 3, that may be connected to a back end 36 of the network presentation system by a communication path 34. The front end of the system may be used by various users of the system, including presenters/clients of the system, which may input data about events/presentations, and may receive one or more recommended user interface widgets from the system, and participants who will use the recommended user interface widget to view a landing page for a particular event/presentation. Each computing device of the front end of the system may allow entities, such as users, companies, etc., to connect to and interact with the back end 36, such as register for presentation, submit presentations or control presentations, see gadget recommendations, select recommended gadgets for a landing page for a presentation/event, and/or view a landing page for a particular event with a selected gadget. Each computing device 32A, 32B, or 32N may be a processor-based device having one or more processors, memory, persistent storage, a display, an input/output device such as a keyboard or printer, and connectivity circuitry to allow a user to connect to a backend using the computing device and then interact with the backend 36. For example, each computing device may be a personal computer, a smart phone or mobile device, a terminal device, a laptop computer, a tablet computer, and so on. In embodiments where HTTPS/HTTP and HTML are used for the protocol, each computing device may have a browser application or other application that receives data from the backend and generates a display of that data (such as a web page), and also allows the user to enter data into the form/web page and send the data to the backend system 36.

The communication path 34 may be a wired path, a wireless path, or a combination of wired and wireless paths. Each of the paths may be a wired network like ethernet, a wireless computer network, a wired computer network, a wireless digital data network, a cellular digital data network, a WiFi network, etc. The communication path 34 may use various communication and data transfer protocols. For example, in one embodiment, the communication path may use TCP/IP and HTTP or HTTPS data transport protocols as well as HTML data protocols.

The backend 36 may be implemented using one or more computing resources, such as cloud computing or Amazon Web Services (AWS) resources or server computers. The computing resources used to implement the back end 36 are specifically configured such that although the individual computing resources are general purpose computer elements, the combination of computing resources and software/hardware described below results in specialized hardware/software that performs the processes of the system described below.

The backend 36 may include a presentation generator and streamer (streamer) element 36A and a user interface widget recommendation engine 36B. The presentation generator and streamer element 36A may be used to assist the presenter in generating each presentation, storing the presentations, allowing the user to control and deliver the presentations to each participant, and collecting data about each participant for each presentation. Widget recommendation engine 36B is used to extract features about widgets and engagement from past events, may generate one or more recommended widgets based on the extracted features, and may present the one or more recommended widgets. In some embodiments, widget recommendation engine 36B may also perform testing of widgets and automatically select one or more widgets for each particular type of event. In the example in FIG. 3, widget recommendation engine 36B is incorporated into an online network presentation system 36, as shown. However, widget recommendation engine 36B may also be a stand-alone system or a software-as-a-service system that provides its widget recommendations to a plurality of third party presentation systems, which may provide the requisite data to determine recommended widgets.

Each of the presentation generator and streamer element 36A and the widget recommendation engine 36B may be implemented in hardware or software or a combination of hardware and software. When each of the presentation generator and streamer element 36A and the widget recommendation engine 36B are implemented in hardware, each of the elements may be a dedicated hardware device, such as a field programmable gate array, microcontroller, or the like, which may be configured to execute the processes of the presentation generator and streamer element 36A or the widget recommendation engine 36B such that each of these elements is implemented using a piece of dedicated hardware. When each of the presentation generator and streamer element 36A and the widget recommendation engine 36B are implemented in software, each of the elements may be lines of computer code/instructions executable by a processor of the computing resources of the backend 36, such that the processor is configured to execute processes of the presentation generator and streamer element 36A or the widget recommendation engine 36B, such that each of these elements is implemented using computing resources having multiple lines of computers, and the lines of code and implemented processes provide technical solutions. When each of the presentation generator and streamer element 36A and the widget recommendation engine 36B are implemented in hardware and software, each element may be a combination of the aforementioned elements, which are also special purpose computer systems that implement the processes and provide technical solutions. In a software implementation, widget recommendation engine 36B may use Python code for classifiers and a database engine for feature extraction and Java for services. In addition, the system may utilize Java based Rest API calls to communicate with the back-end and front-end as shown in fig. 4.

FIG. 4 shows more details of the front end 32 and the back end 36 of the widget recommendation system 30. The front end 32 may further include a client element 48 and a recommendation element 49, where each of these elements may be implemented using a computing device that allows users (i.e., to become participants/registrants for the registrant element and presenters for presenting the client element) to connect to and interact with the back end 36 as described above. For example, each of the elements 48, 49 may be a user interface displayed on a computing device that allows a user to interact with the backend 36. For example, the client element 48 may allow the presenter of the event to enter information about the new event, such as industry, application, category, and department for the event in the example in FIG. 4, and to transfer and save data about the event to the backend 36. For example, the application information may be partner training, investor relations, accounting, medical, consumer participation, sales, product release, employee training, Lead Generation, brand awareness, municipality, and/or sales training.

In one implementation, the POST request may be used to transfer new event data to the back end 36. The recommendation element 49 may also be a user interface that may be displayed to the presenter of a particular presentation/event and may show one or more recommended user interface widgets to add to the landing page for a new event. The user interface may be generated for each presentation/event based on the output of recommendation engine 36B. In one implementation, the data used to generate the user interface may be passed from the back end to the recommendation element 49 using a POST request.

The back end 36 may further include a feature extraction element 40 and a recommendation element 44. These two elements cooperate to perform the widget recommendation process and generate one or more recommended widgets for each presentation/event. In embodiments where the backend automatically selects recommended widgets for a particular show, the recommender element 44 may also perform program selection of one or more widgets for a landing page for a particular event. Each of the feature extraction element 40 and the recommender element 44 may be implemented in software or hardware as described above, and may together be a dedicated piece of hardware or software that provides a technical solution for the recommended gadgets that promotes engagement with the event. In addition, one or more user interface widgets and landing pages are unique to the internet and computer, and the computer must be used. Furthermore, aspects of the technical solution cannot be performed by a person with a pen and paper.

The feature extraction element 40 may comprise a database 41 and a feature extractor 42. Feature extraction component 40 may receive characteristic data about each event via a POST request and all of this data may be stored in database 41. Feature extractor 42 may be an algorithm/process that performs feature extraction based in part on data about each event, and feature extractor 42 may loop through each event to extract features. In one embodiment, the features extracted during the process may be communicated to the recommender 44 using a GET request. During feature extraction, for each event, features of the industry for the event, the application for the event, the category of the event, and the department for the event may be extracted, and each feature may be given a score for a particular event.

The recommender 44 of the back end 36 may further have a database 41, a co-occurrence matrix and recommendation process 45, and a save process 46 to save recommendations to the database 41, such as by using a POST request. The one or more recommendations for each event may then be communicated to recommendation element 49 of front end 32.

FIG. 5 shows an example of a covariance matrix 50 of the widget recommendation system, and FIG. 6 shows more details of the widget recommendation process 45. As shown in FIG. 6, the occurrence data of the user interface widget from all events stored in the database 41 is retrieved 60. The occurrence data may be the occurrence of each widget for each event with high engagement. Thus, for each previous event, the system calculates the above-described median engagement score for the participant, and this is an estimate of the engagement of the event. For example, as shown in fig. 6, a player media user interface widget appears in each previous event (100%) with high engagement, a resource list appears in 10% of the events with high engagement, and a speaker resume widget appears in 5% of the events with high engagement. The recommender 44 may fully cycle through the occurrence data and generate the co-occurrence matrix 50.

An example of a co-occurrence matrix is shown in fig. 5. In most embodiments, the co-occurrence matrix may have 24 columns and 24 rows for all gadgets that may be recommended. In the example of fig. 5, a smaller co-occurrence matrix is shown for illustrative purposes. The co-occurrence matrix 50 may show co-occurrence of two different user interface widgets for a high engagement event (which is why the value in the matrix for two identical widgets, such as contact us and survey 52, is 0.0). For example, for a high engagement event, the co-occurrence of the resource list gadget and the survey gadget is 0.9, which means that when the resource gadget is exposed in the high engagement event, the survey gadget is also used in the high engagement event.

Returning to fig. 6, the co-occurrence matrix may be stored in the database 41 and then used by the recommender 44. In addition to the occurrence data for past events, the occurrence data 64 for the gadget for event X may also be retrieved. In the example in FIG. 6, the occurrence data for event X (64) may be a "1" for the player media gadget and a "0" for the resource list gadget and the speaker resume gadget. For each widget, the value in the occurrence data for event X may indicate the number of times the widget is used in the landing page, as the widget may be used more than once in the landing page. The occurrence data from the event may be used to generate a feature vector that is passed to the recommender 44 via, for example, a GET request.

In one example, a new event (i.e., a new event for which recommendation of one or more gadgets was requested) may have the following characteristics: "biotechnology", "sales training", "training/learning". In this example, the feature vector for these characteristics may be: resource list: 60, speaker resume: 42, investigation: 21, Player URL target: 1 for other gadgets, 0. In this example, events having the same industry, category, and application are grouped in a matrix, with rows representing gadgets used in each event, with each column representing a gadget. We sum along the columns (same type of gadget). Gadgets that occur in less than 30% of events in the group are eliminated (column value set to 0).

As shown in fig. 6, the feature vector values are converted into a string of values, which are fed to the recommender 44. As shown, the recommender 44 may receive input of the co-occurrence matrix and feature vectors for events for which widgets are being recommended. Recommender 44 may perform a cross product process 66 between the co-occurrence matrix and the feature vector for the new event. The cross product is between the feature vector x (1 × n) and the co-occurrence matrix a (n × n), where n is the number of widgets, and the calculation result is in the vector (1 × n). The multiplication of the ith element (occurrence of ith widget) in the feature vector x _ i by the weight vector a _ i (column in co-occurrence matrix for ith widget) is a linear combination that will reveal which widgets occur simultaneously with the ith widget, the largest score revealing which widgets occur more frequently.

As shown in FIG. 6, the recommender 44 may generate a recommendation vector that may be used to recommend one or more gadgets for an event. In some embodiments, the recommendation vector may be used to automatically select one or more widgets that may be added to a landing page for a particular event.

The above example continues for events having the following characteristics: "Biotechnology", "sales training", "training/learning", recommendation process, get _ recommendation ("Biotechnology", "sales training", "training/learning") produces the following exemplary outputs:

small fittings	Score of
		Investigation	1.231428
Resource list	0.891438
		Speaker resume	0.651335
Player URL target	0.622844
		Contact us	0.494762
Twitter	0.439685

Using the scores above or the recommendation vector shown in fig. 6, the system may thus generate a recommendation element 49 (shown in fig. 4) to the presenter of a particular event with the recommended gadgets occurring in the high engagement event, and the presenter may choose to add any recommended gadgets, or the system may automatically select and add the recommended gadgets.

In embodiments where recommendations are used to automatically select widgets for landing pages, depending on account settings, the system may automatically pick the best widget configuration based on use cases (use cases), or present a prompt to the user to let them know that their current configuration does not contain the best combination of widgets for best audience participation, allowing them to decide to adopt (opt-in) and add those widgets to their audience console.

FIG. 7 shows an example of a landing page 70 with a presentation and content and one or more recommended widgets. As shown, the landing page 70 may have a presentation portion 72 and a slide portion 74 and one or more user interface widgets 76. The presentation portion 72 may be a media player that displays events to each member of the audience. Slide section 74 may be a user interface element capable of displaying slides (if any) accompanying the presentation. In the example in FIG. 7, the one or more user interface widgets may include a media player widget, a Q & A widget, a slideshow widget, a player online help widget, a chat widget, and a speaker resume widget.

The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosure and various embodiments with various modifications as are suited to the particular use contemplated.

The systems and methods disclosed herein may be implemented via one or more components, systems, servers, appliances, other subcomponents, or distributed between such elements. When implemented as a system, such a system may include and/or relate to components such as software modules, general purpose CPUs, RAMs, etc., found in general purpose computers. In implementations where the innovations reside on servers, such servers may include or involve components such as CPU, RAM, etc., such as those found in general purpose computers.

Additionally, in addition to what is set forth above, the systems and methods herein may be implemented via implementations utilizing disparate or disparate software, hardware, and/or firmware components. With respect to such other components (e.g., software, processing components, etc.) and/or computer-readable media associated with or embodying the present invention, the inventive aspects herein may be implemented, for example, in accordance with numerous general purpose or special purpose computing systems or configurations. Various exemplary computing systems, environments, and/or configurations that may be suitable for use with the innovations herein may include, but are not limited to: software or other components within or embodied on a personal computer, server, or server computing device, such as routing/connectivity components, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, set top boxes, consumer electronics, network PCs, other existing computer platforms, distributed computing environments that include one or more of the above systems or devices, and the like.

In some cases, aspects of the systems and methods may be implemented or performed, for example, via logic and/or logic instructions comprising program modules executed in association with such components or circuits. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular instructions herein. The invention may also be practiced in the context of distributed software, a computer, or a circuit arrangement where circuits are connected via a communications bus, circuit, or link. In a distributed setting, control/instructions may occur from both local and remote computer storage media, including memory storage devices.

The software, circuitry, and components herein may also include and/or utilize one or more types of computer-readable media. Computer-readable media can be any available media that can reside on, be associated with, or be accessed by such circuitry and/or computing components. By way of example, and not limitation, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computing component. Communication media may include computer readable instructions, data structures, program modules, and/or other components. Further, communication media may include wired media such as a wired network or direct-wired connection, although any such type of media herein does not include transitory media. Combinations of any of the above are also included within the scope of computer readable media.

In this specification, the terms component, module, device, and/or the like may refer to any type of logical or functional software element, circuit, block, and/or process that may be implemented in various ways. For example, the functions of the various circuits and/or blocks may be combined with one another into any other number of modules. Each module may even be implemented as a software program stored on a tangible memory (e.g., random access memory, read only memory, CD-ROM memory, hard drive, etc.) for reading by a central processing unit to implement the functionality of the innovations herein. Alternatively, the modules may include programming instructions transmitted to a general purpose computer or to processing/graphics hardware via a transmission carrier wave. Also, a module may be implemented as hardware logic circuitry that implements the functionality encompassed by the innovations herein. Finally, the modules may be implemented using dedicated instructions (SIMD instructions), field programmable logic arrays, or any mix thereof that provides the desired level of performance and cost.

As disclosed herein, features consistent with the present disclosure may be implemented via computer hardware, software, and/or firmware. For example, the systems and methods disclosed herein may be embodied in various forms including, for example, a data processor, such as a computer that also includes a database, digital electronic circuitry, firmware, software, or a combination thereof. Further, although some of the disclosed implementations describe specific hardware components, any combination of hardware, software, and/or firmware can be utilized to implement systems and methods consistent with the innovations herein. Furthermore, the above-identified features of the innovations herein, as well as other aspects and principles, may be implemented in various environments. Such environments and related applications may be specially constructed for performing various routines, processes and/or operations in accordance with the invention, or they may include a general-purpose computer or computing platform selectively activated or reconfigured by code to provide the necessary functionality. The processes disclosed herein are not inherently related to any particular computer, network, architecture, environment, or other apparatus, but may be implemented by any suitable combination of hardware, software, and/or firmware. For example, various general-purpose machines may be used with programs written in accordance with the teachings of the invention, or it may be more convenient to construct a specialized apparatus or system to perform the required methods and techniques.

Aspects of the methods and systems described herein, such as logic, may also be implemented as functionality programmed into any of a variety of circuits, including programmable logic devices ("PLDs"), such as field programmable gate arrays ("FPGAs"), programmable array logic ("PAL") devices, electrically programmable logic and memory devices, as well as standard cellular-based devices, and application specific integrated circuits. Some other possibilities for implementing aspects include: memory devices, microcontrollers with memory (such as EEPROM), embedded microprocessors, firmware, software, and the like. Further, aspects may be embodied in microprocessors having software-based circuit emulation, discrete logic (sequential and combinatorial), custom devices, fuzzy (neural) logic, quantum devices, and hybrids of any of the above device types. The underlying device technologies may be provided in a variety of component types (e.g., metal oxide semiconductor field effect transistor ("MOSFET") technologies like complementary metal oxide semiconductor ("CMOS"), bipolar technologies like transmitter coupled logic ("ECL"), polymer technologies (e.g., silicon-conjugated polymer and metal-conjugated polymer-metal structures), mixed analog and digital, etc.).

It should also be noted that in accordance with the behavior, register transfer, logic components, and/or other characteristics of the various logic and/or functions disclosed herein, the various logic and/or functions disclosed herein may be implemented using any number of combinations of hardware, firmware, and/or as data and/or instructions embodied in various machine-readable or computer-readable media. Computer-readable media that may embody such formatted data and/or instructions include, but are not limited to, non-volatile storage media in various forms (e.g., optical, magnetic or semiconductor storage media), but again excludes transitory media. Throughout the description, the words "comprise," "comprising," and the like are to be construed in an inclusive sense, as opposed to an exclusive or exhaustive sense, unless the context clearly requires otherwise; that is, in the meaning of "including but not limited to". Words using the singular or plural number also include the plural or singular number, respectively. Additionally, the words "herein," "below," "above," "below," and words of similar import refer to this application as a whole and not to any particular portions of this application. When the word "or" is used to reference a list of two or more items, the word encompasses all of the following interpretations of the word: any of the items in the list, all of the items in the list, and any combination of the items in the list.

While certain presently preferred implementations of the present invention have been described in detail herein, it will be apparent to those of ordinary skill in the art to which the present invention pertains that variations and modifications of the various implementations shown and described herein may be made without departing from the spirit and scope of the invention. Accordingly, it is intended that the invention be limited only to the extent required by applicable legal rules.

Although the foregoing has been with reference to a particular embodiment of the disclosure, it will be appreciated by those skilled in the art that changes in this embodiment may be made without departing from the principles and spirit of the disclosure, the scope of which is defined by the appended claims.