GB2589606A

GB2589606A - System for providing adaptive training support for search platform

Info

Publication number: GB2589606A
Application number: GB1917702.1A
Authority: GB
Inventors: Fessl Angela; Simic Ilija; Pammer-Schindler Viktoria; Sabol Vedran; Wertner Alfred
Original assignee: Ernst and Young GmbH
Current assignee: Ernst and Young GmbH
Priority date: 2019-12-04
Filing date: 2019-12-04
Publication date: 2021-06-09
Also published as: GB201917702D0

Abstract

Provides adaptive training support for search platform, the system including server arrangement and plurality of user devices coupled in communication with the server arrangement. The plurality of user devices are associated with a plurality of users. The server arrangement is configured to track activity data of the plurality of users and analyse the activity data of the plurality of users to deduce a search behaviour of each of the plurality of users. Search behaviour may include search filters, concept graphs or uRank used by the user. Generating at least one recommendation for each of the plurality of users and providing each of the plurality of users with an interactive user interface to represent the given search behaviour, and the at least one recommendation for the given user. The recommendation may be text that recommends usage or avoiding use of different features of the search platform.

Description

SYSTEM FOR PROVIDING ADAPTIVE TRAINING SUPPORT FOR SEARCH

PLATFORM

TECHNICAL FIELD

The present disclosure relates generally to search platforms; and more specifically, to systems that, when operated, provide adaptive training support for search platforms.

BACKGROUND

With advancement in technology, there is a rapid increase in new technologies in digitalization process. Moreover, learning (for example such as workplace learning, life-long learning, self-regulated learning) needs to be supported in our everyday lives. Such a learning process requires various search technologies to learn every day in order to keep up to date with new knowledge and information that are quickly evolving.

Therefore, it is important for users of such technologies to improve their skills in order to cope with challenges associated with the new technologies established within the ongoing digitalization.

Notably, search requirements are different for various users, thereby resulting in different use of search platforms associated with existing technologies. In an example, search requirements for a given user in leisure time will be different from search requirements for the given user for work. As a result, use of various features of the search platform will be different for different users. However, the aim of efficient search is finding relevant information as per the search requirements. Therefore, there is a need for using the features of the search platform efficiently.

Presently, there exist several search platforms that are employed for searching. For example, search features like facetted search, visual overview of knowledge bases like graph visualizations are emerging beyond keyword searches. As a result, the users are required to be updated with the new features associated with various search platforms while searching for the necessary information in order to find desired information. Thus, it is necessary for the users such as, knowledge workers, auditors or students to cope with the challenges of the existing technology, knowledge, and so forth that is evolving in short development cycles and intervals.

However, there exist certain limitations associated with existing search platforms. Generally, the users are not fully aware of updated features of the search platform. Therefore, they keep using a limited number of existing features of the search platform, thereby resulting in inefficient results while searching. In one case, the user may be unaware of the updated features of the search platform. In another case, the user may be unaware of how to use the updated features of the search platform. For example, a financial auditor routinely searches internal as well as public knowledge bases as part of the auditing process. In such an example, efficient search strategies are crucial for auditors, thereby finding relevant information in accordance with law and compliance.

However, in such an example, working with outdated information and outdated features of the search platform have serious negative effects on the auditing. Therefore, finding the relevant and updated information is very important for improving performance of the auditor. Moreover, the search strategies of the given user may be highly routinised. Although, such search strategies may suffice needs of the given user, said search strategies may be time consuming and therefore, are sub-optimal.

Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks associated with use of existing search platforms.

SUMMARY

The present disclosure seeks to provide a system that, when operated, provides adaptive training support for a search platform. The present disclosure seeks to provide a solution to the existing problem of suboptimal use of existing search platforms by users. An aim of the present disclosure is to provide a solution that overcomes at least partially the problems encountered in prior art, and provides an efficient, reliable, user-friendly system for providing adaptive training support for a search platform.

In one aspect, an embodiment of the present disclosure provides a system that, when operated, provides adaptive training support for a search platform, the system comprising a server arrangement and a plurality of user devices coupled in communication with the server arrangement, wherein the plurality of user devices are associated with a plurality of users, and wherein the server arrangement is configured to: - track activity data of the plurality of users, said activity data pertaining to a manner in which the plurality of users use the search platform; analyze the activity data of the plurality of users to deduce a search behavior of each of the plurality of users; - generate at least one recommendation for each of the plurality of users, wherein the at least one recommendation for a given user is generated based upon a given search behavior of the given user; and provide each of the plurality of users with an interactive user interface, wherein a given interactive user interface for the given user is 25 employed to represent the given search behavior of the given user, and the at least one recommendation for the given user.

Embodiments of the present disclosure substantially eliminate or at least partially address the aforementioned problems in the prior art, and provide adaptive and reflective training support for a search platform.

Additional aspects, advantages, features and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments construed in conjunction with the appended claims that follow.

It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those skilled in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.

Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein: FIG. 1 is a schematic illustration of a network environment wherein a system that provides adaptive training support for a search platform is implemented, in accordance with an embodiment of the present disclosure; FIG. 2 is an exemplary illustration of information that can be 25 represented via an interactive user interface, in accordance with an embodiment of the present disclosure; FIG. 3 is an exemplary illustration of tab that can be represented via an interactive user interface, in accordance with an embodiment of the present disclosure; FIG. 4 is an exemplary illustration of learning-how-to-search widget 5 tab that can be represented via an interactive user interface, in accordance with different embodiments of the present disclosure; FIGs. 5A and 5B are exemplary illustrations of curriculum reflection widget tab that can be represented via an interactive user interface, in accordance with an embodiment of the present disclosure; and FIG. 6 is an exemplary illustration of overall progress tab that can be represented via an interactive user interface, in accordance with an embodiment of the present disclosure.

In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.

DETAILED DESCRIPTION OF EMBODIMENTS

The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.

In one aspect, an embodiment of the present disclosure provides a system that, when operated, provides adaptive training support for a search platform, the system comprising a server arrangement and a plurality of user devices coupled in communication with the server arrangement, wherein the plurality of user devices are associated with a plurality of users, and wherein the server arrangement is configured to: - track activity data of the plurality of users, said activity data pertaining to a manner in which the plurality of users use the search 5 platform; - analyze the activity data of the plurality of users to deduce a search behavior of each of the plurality of users; - generate at least one recommendation for each of the plurality of users, wherein the at least one recommendation for a given user is generated based upon a given search behavior of the given user; and - provide each of the plurality of users with an interactive user interface, wherein a given interactive user interface for the given user is employed to represent the given search behavior of the given user, and the at least one recommendation for the given user.

The present disclosure provides the aforementioned system for providing adaptive training support for search platforms. The aforementioned system is intelligent, easy to implement, and allows for accurately providing adaptive and reflective training support for the search platforms. Notably, the aforementioned system provides training and learning simultaneously with the adaptive training support. Consequently, the described system allows for analyzing the activity data of the plurality of users to deduce search behavior of each of the plurality of users. Furthermore, the system allows for improving search behavior of the plurality of users by providing reflective interventions based upon the search behavior of the plurality of users. In such a case, the system analyzes the search behavior of each of the plurality of users and generates the at least one recommendation based upon the search behavior of the user, thereby improving the search behavior of the user. Notably, the system provides training and learning adapted to the user's search behavior and the user's competence level. As a result, the system allows for use of the search platform in a simple, quick, and user-friendly manner. Beneficially, the system is accurate and reliable.

Throughout the present disclosure, the term "search platform" refers to a given search platform that is employed to search a knowledge base in 5 a systematic manner for information specified in a given search query. Notably, such a search platform provides search results associated with the given search query. The search results are available in multiple formats (for example, such as an article, a research paper, an image, a video and the like). In an example, the given search query may be 10 associated with change in laws and regulations relevant to audit. In such an example, the search results may be web pages associated with auditing, reports by government officials and/or expert professionals and the like.

The knowledge base comprises at least one of: an internal knowledge base, a public knowledge base and/or a combination thereof. The internal knowledge base refers to a given knowledge base, created by an organization or a department within the organization, having complete information associated with the organization. Therefore, such internal knowledge base provides an easy access to organizations information across departments within the organization. The public knowledge base refers to a given knowledge base that is available to everyone openly. Examples of the public knowledge base may include, but are not limited to, online and/or offline published journals, printed books, published papers.

Throughout the present disclosure, the term "adaptive training support" refers to a self-regulated training support for the search platform such that search efficiency of the plurality of users. Notably, the adaptive training support is also defined as personalized training support. In such a case, the system determines the search behavior of the plurality of users and provide guidance to the plurality of users to improve the search efficiency of the plurality of users. Beneficially, such an adaptive training support provides an efficient, effective and customized training and learning opportunities while searching, to improve the search efficiency of the plurality of users. Notably, while performing the search on the search platform the user's focus is mainly on finding desired information. In such a case, the adaptive training support provides guidance to train a given user on how to improve the search by making the given user aware of his/her search behavior and motivates him/her to work upon it for finding the desired information. Furthermore, the adaptive training support suggests information "to learn" in order to improve the given user's competence level with respect to curriculum. Therefore, the adaptive training support is a new way of providing training and learning in informal learning environments (for example, such as workplaces).

Notably, the adaptive training support for the search platform is provided by intellectual and affective activities. In such a case, each of the plurality of users engage to analyze their search behavior in order to improve their search behavior, thereby introducing new understanding and appreciations in their search behavior. The adaptive training support also emphasize on providing a higher level of effective knowledge transfer by integrating well-established learning strategies suitable for self-regulated learning context and providing recommendations that are needed to cope with requirements of the plurality of users. Therefore, the search behavior of the user is improved while performing a search, by learning on the fly with the adaptive training support. Moreover, the user becomes well educated in the area of information literacy and digital connpetences. Therefore, by learning on the fly with the adaptive training support, will affect both the user and companies and/or industries for which they work, thereby adding value to one's work.

It will be appreciated that the system that, when operated, provides adaptive and reflective training support for the search platform. Notably, the reflective training support is provided via reflective learning. In such a case, the reflective training can be defined as re-evaluation of the search behavior of the plurality of users, thereby motivating the plurality of users to improve the search behavior associated therewith. Notably, the reflective learning is referred to as a learning strategy in which the re-evaluation of past experiences of the search behavior of the plurality of users with respect to goals to learn from such experiences in order to guide future search behavior of the plurality of users. Beneficially, in the area of workplace training, adaptive and reflective training is significant for informal training, as it does not rely on explicitly available training material, curricula, or teachers.

Optionally, in the system, the server arrangement is configured to 15 provide adaptive training support for the search platform by employing at least one artificial intelligence algorithm.

Throughout the present disclosure, the term "server arrangement" refers to an arrangement of at least one server that, when operated, provides adaptive training support for the search platform. The term "server" generally refers to an application, program, process or device in a client-server relationship that responds to requests for information or services by another application, program, process or device (a client) on a communication network. The term "server" also encompasses software that makes the act of serving information or providing services possible.

Moreover, the term "client" generally refers to an application, program, process or device in a client-server relationship that requests information or services from another application, program, process or device (the server) on the communication network. Importantly, the terms "client" and "server" are relative since an application may be a client to one application but a server to another application. The term "client" also encompasses software that makes the connection between a requesting application, program, process or device and a server possible, such as an FTP client. It will be appreciated that the communication network can be an individual network, or a collection of individual networks that are interconnected with each other to function as a single large network. The communication network may be wired, wireless, or a combination thereof. Examples of the individual networks include, but are not limited to, Local Area Networks (LANs), Wide Area Networks (WANs), Metropolitan Area Networks (MANs), Wireless LANs (WLANs), Wireless WANs (WWANs), Wireless MANs (WMANs), the Internet, radio networks, telecommunication networks, and Worldwide Interoperability for Microwave Access (WiMAX) networks.

For illustration there will now be considered an exemplary network environment, wherein the system that, when operated, provides adaptive training support for the search platform, is implemented pursuant to embodiments of the present disclosure. One such network environment has been illustrated in conjunction with FIG. 1 as explained in more detail hereinafter. The exemplary network environment includes the plurality of user devices associated with the plurality of users, the server arrangement including the at least one server and the communication network. In such a case, the plurality of user devices can be understood to be the "clients" for the server arrangement. It is to be noted here that the plurality of user devices associated with a plurality of users are coupled in communication with the server arrangement. Notably, the plurality of user devices are coupled in communication with the server arrangement via the communication network. The term "user" used herein refers to a given user of a given user device using the search platform. Notably, the plurality of users refers to those whose search behavior is to be analyzed. In an example, the plurality of users may belong to a group of individuals within an organization. Examples of the plurality of user devices include, but are not limited to, mobile phones, smart telephones, Mobile Internet Devices (MIDs), tablet computers, Ultra-Mobile Personal Computers (UMPCs), phablet computers, Personal Digital Assistants (PDAs), web pads, Personal Computers (PCs), handheld PCs, laptop computers, and desktop computers.

The server arrangement is configured to track the activity data of the plurality of users. The term "activity data" used herein refers to a given data pertaining to a manner that the plurality of users uses the search platform. The aforementioned system provides training and learning opportunities based on the search behavior of the user, by presenting the content of the adaptive training support with real-time data based on the activity data of the plurality of users. Examples of the activity data include, but are not limited to, search filters used by the plurality of users, search strings used by the plurality of users, tags used by the plurality of users, concept graphs used by the plurality of users, date mentions by the plurality of users.

The server arrangement is configured to analyze the activity data of the plurality of users to deduce the search behavior of each of the plurality of users. In an example, the activity data may include various features (for example, such as search filters used, result visualizations used, and the like) of the search platform employed by the plurality of users during his/her search. In such an example, the server arrangement may be configured to analyze the activity data of the plurality of users to deduce the search behavior of each of the plurality of users.

Optionally, in the system, the server arrangement is configured to analyze the activity data of the plurality of users to deduce the search behavior of each of the plurality of users. Moreover, the server arrangement is configured to analyze the activity data of the plurality of users using reflective learning strategies in order to support learning on the fly. Such strategies may employ existing approaches (for example, such as data-driven visuals, micro-learning, activity log data analysis, and so forth) with supported reflective learning strategies. In an example, the data-driven visual may be used in learning how to search with reflective interventions. In another example, the micro learning may be used in curriculum reflection with reflective learning.

It will be appreciated that the server arrangement is configured to analyze the activity data of a given user to deduce the given search behavior of the given user.

Optionally, the given search behavior of the given user comprises at least one of: search filters used by the given user, concept graphs used by the given user, uRank used by the given user. Notably, the given search behavior of the given user is deduced by the server arrangement by analyzing various features of the search platform. In an example, the activity data of the given user may include the search filters used by the given user. In such an example, the server arrangement may be configured to analyze the activity data of the given user to deduce the search behavior of the given user.

Optionally, the server arrangement is configured to update the given search behavior of the given user based upon the use of the various search features of the search platform.

The server arrangement is configured to generate the at least one recommendation for each of the plurality of users, wherein the at least one recommendation for the given user is generated based upon the given search behavior of the given user. In such a case, the at least one recommendation is depicted in form a text message on the plurality of user devices. In an example, the at least one recommendation can be associated with usage of different features of the search platform. In another example, the at least one recommendation can be associated with avoiding usage of a given feature of the search platform. Beneficially, such recommendations motivate and provide guidance to the plurality of users to use features of the search platform.

Optionally, the at least one recommendation is associated with past 5 search behavior of the given user. Optionally, the at least one recommendation is generated based upon the analysis of the search behavior of the given user.

Optionally, in the system, the server arrangement is configured to generate the at least one recommendation for each of the plurality of 10 users by employing at least one artificial intelligence algorithm.

The server arrangement is configured to provide each of the plurality of users with the interactive user interface, wherein the given interactive user interface for the given user is employed to represent the given search behavior of the given user, and the at least one recommendation for the given user. Notably, the given search behavior of the given user is represented on the interactive user interface in form of a bar graph, table, and so forth. Throughout the present disclosure, the term "interactive user interface" relates to a space that allows for interaction between the given user and the system. Therefore, the term "interactive user interface" can also be referred to as a "human-machine interface". The interactive user interface is generally rendered upon a display screen of the given user device and allows for the system to receive input(s) from and/or provide output(s) to the given user.

For illustration purposes only, there will now be considered an exemplary two-part user interface, wherein the two-part user interface for the given user is employed to represent the given search behavior of the given user, and the at least one recommendation for the given user, in accordance with an embodiment of the present disclosure. One such exemplary two-part user interface has been illustrated in conjunction with FIG. 2 as explained in more details hereinafter. The exemplary two-part user interface is employed to represent the given search behavior of the given user, and the at least one recommendation for the given user.

In said two-part user interface, the given search behavior of the given user is depicted in a form of a bar chart which describes data values associated with search features used by the given user in the given search. Notably, in such a case, the horizontal axis of the bar chart depicts the search features for which the data values are to be obtained, and the vertical axis of the bar chart depicts data values associated with the search features. In an example, the bar chart may depict a given search behavior of the given user associated with five recent search features used by the given user. In such an example, the horizontal axis of the bar chart may depict the search features and the vertical axis of the bar chart depicts data values associated with said search features.

Furthermore, in such an example, search features may be search feature 1, search feature 2, search feature 3, search feature 4 and search feature 5 and the data value associated with the search feature 1 is 20, search feature 2 is 30, search feature 3 is 70, search feature 4 may be 50 and search feature 5 may be 40.

Moreover, in said two-part user interface, the at least one recommendation for the given user is provided in form of a message in a text box. In one example, the message may motivate to reflect past search behavior of the user. In another example, the message may motivate the given user to use another search functionality, thereby improving search efficiency of the given user.

Optionally, the server arrangement is further configured to enable, via the given interactive user interface, the given user to select at least one of: when the given user wishes to receive the at least one recommendation, a given user device on which the given user wishes to receive the at least one recommendation. Beneficially, in such a case, the given user is able to select when the given user wishes to receive the at least one recommendation, thereby not affecting workflow of the given user. When the said recommendations prompt during extensive tasks, then time efficiency of the given user is affected. Notably, in working 5 environments the working tasks are not always known beforehand, thus it is very challenging to adapt prompts to the working tasks of the user. For example, auditors have very tight timelines, therefore, it is important for any training support work in a manner that it would not affect work processes from operational view. In such an example, the at least one 10 recommendation can be in form of a short text message.

Optionally, the server arrangement is further configured to enable, via the given interactive user interface, the given user to select the given user device on which the given user wishes to receive the at least one recommendation. Notably, a prompt associated with the at least one recommendation is decoupled from the working activity. In such a case, the prompt can be presented on the given user device (for example, such as a mobile device) while the user is on his/her way home. Beneficially, in such a case, a time of the given user to reflect when a prompt pops up is utilized efficiently.

Optionally, the server arrangement is further configured to display, via the given interactive user interface, the search behavior of the given user. In such a case, the search behavior may be displayed in a form of a bar chart. Such a bar chart represents how often the given user uses which feature of the search platform based on the activity data of the given user. Therefore, by displaying such a search behavior, firstly the given user is made aware of his/her search behavior and secondly, he/she is motivated to think about the search behavior, thereby improving search expertise. In an example, the bar chart may depict search input interface used and search result presentation. In such an example, the presented features of the search input interface may include of three functionalities to initiate a search, namely "simple search", "advanced search", "faceted search", and five functionalities of presenting the search results, namely "Result List", "Concept Graph", "uRank", "Tag Cloud" and "Top Properties". Here, simple search refers to when the user enters a query in the simple search input bar and submits a form by clicking on a search button on the interactive user interface or by pressing enter on the user's device. The advanced search refers to when the user uses advanced search interface and after configuring the advanced search submits the form by clicking on the search button or by pressing enter. The faceted search refers to when the simple or advanced search had to be performed before and the user is on the page with the results. The user applies one or more of the filters from a side bar. The result list refers to list that appears when the user clicks on the Result tab on the results page.

Optionally, the server arrangement is configured to display, via the interactive user interface, a reflective question or sentence starter to stimulate reflection on the feature usage by the given user during a search, in order to provide at least one recommendation to use another rarely used feature. Such a reflective question or sentence starter stimulates reflection on the search behavior of the user. The focus of the reflection guidance provided by such a reflective question is at least one of: motivate the plurality of users to reflect on past feature usage (namely, reflection amplifier), motivate the plurality of users to use another feature (namely, reflection intervention). Notably, the reflective question is provided to the user based on his/her searching capabilities.

In such a case, a novice searcher may receive a first level reflection questions and reflection amplifiers that will make her/him aware of not used features of the search platform and ask questions to think about the first experiences while using them. As a result, these prompts make the user familiar with the functionalities of the search platform in a user-friendly manner. In another case, an intermediate user will get second level reflection questions and reflection amplifiers that will make the user aware of his/her feature usage behavior (reflection intervention) and motivate him/her to reflect on why different features are perceived as useful (reflection amplifier). In yet another case, an expert user will get third level prompts to stimulate reflection about the user's perceived benefit and learning on the search platform as well as to motivate users to think about whether a subjectively perceived behavior change, or an individual performance improvement has taken place. In an example, a reflective question may be "Do you think that using the "Concept Graph" can improve your search performance search skills? And if yes how?".

Optionally, the server arrangement is configured to enable, via the interactive user interface, the plurality of users to answer the reflective question. In such a case, a text field may appear on the interactive user interface, where the user can enter the answer corresponding to the reflective question. When the user submits the answer, the reflective

question and the answer field disappear.

It will be appreciated that the reflection guidance does not show the next reflective question immediately. It waits for a certain amount of time until the next reflective question is selected and shown to the user. The episode count is used to decide when to show the next reflective question.

The default is one episode of not showing any reflective question. This way it is avoided to annoy the user with too many reflective questions. The reflection guidance model tracks feature use and the answers given to the presented reflective questions. Based on this information it decides if it keeps displaying reflective question from the current category or if it moves on to the next one. After the start up stage three more stages in the reflection guidance model follow. In each stage the reflection guidance model uses one or more categories to select prompts. The categories between each stage differs and are adjusted according to an experience that the user should have at this stage. The reflective question categories in the different stages can be defined as a first stage, a second stage and a third stage. In the first stage, the reflective questions may ask about which features are less or not used, and also about the benefit and/or satisfaction of a specific feature. In the second stage, the reflective questions may ask about the feature mostly used in the platform, reflective question may ask about the reason why these features which are mostly used or less used, and reflection. In the third stage, the reflective question may ask about most beneficial/satisfactory features, and skill/performance increase, search behavior changes.

Moreover, it will be appreciated that the reflective question in the first stage is easy to answer and should keep user's motivation high. The switch from the first into the second stage happens when the reflective questions for each of the categories in the first stage has been answered and feature use exceeds a certain threshold. In the second stage, the reflective questions are aligned to the experience of the user collected so far. The effort of answering the reflective questions in the second stage is higher than in the first stage. The switch to the third stage depends as before on answering the reflective questions and feature use. In the third stage, the most challenging questions in terms of reflection are presented to the user. These questions are not only about feature use. For example, the reflective questions in the third stage address the question as to whether the user has observed a change in his search behavior influenced by the learning-how-to-search widget.

Optionally, the system further comprises a database arrangement coupled in communication with the server arrangement, wherein the server arrangement is configured to store, at the database arrangement, at least one of: the activity data of the plurality of users, the search behavior of each of the plurality of users, the at least one recommendation for each of the plurality of users.

Throughout the present disclosure, the term "database arrangement" 30 refers to an arrangement of at least one database that when employed, allows for the server arrangement to provide adaptive training support for the search platform. The term "database" generally refers to hardware, software, firmware, or a combination of these for storing information in an organized (namely, structured) manner, thereby, allowing for easy storage, access (namely, retrieval), updating and analysis of such information. The term "database" also encompasses database servers that provide the aforesaid database services to the server arrangement. It will be appreciated that the data repository is implemented by way of the database arrangement.

Optionally, the server arrangement is further configured to enable, via the given interactive user interface, at least one widget for supporting adaptive and reflective learning of the search platform. Such a widget is always available and visible to the given user while using the search platform. Beneficially, such a widget provides guidance for training to use the search platform efficiently and effectively. Additionally, such a widget provides learning guidance to raise the given user's competence level with respect to a competence framework, to teach information literacy and digital skills, for each competence in the curriculum to an expert level. For example, the competence framework may be a DigComp framework provided by the European Union.

In an example, the at least one widget may visualize the search behavior of the given user, thereby providing guidance for training the given user on how to use the search platform. Based on this, reflective guidance is provided in order to nudge the user to experiment with different search features and motivate them to reflect on their search efficiency. In such an example, the at least one widget may be referred to as "learninghow-to-search" widget. Notably, the learning-how-to-search widget is based on the search behavior of the user. In such a case, the learninghow-to-search widget fill collects, stores and analyze the search behavior of the user on the fly in order to reflect the search behavior of the user based on input interfaces and search result visualizations used by the search platform. Moreover, in such a case, if the tracking is switched of, not allowed or does not work, the widget is obsolete.

In another example, the at least one widget may visualize a learning 5 progress of the given user with respect to a digital information literacy curriculum. In such an example, the reflection guidance nudges the given user to reflect on own proficiency in terms of the curriculum. Moreover, in such an example, the at least one widget may be referred to as "curriculum reflection" widget. Notably, the curriculum reflection 10 widget tracks search abilities that the user already has and/or developed by the user over time.

Optionally, the sever arrangement is configured to display the at least one widget on the search platform via the interactive user interface. More optionally, when the at least one widget comprises a plurality of widgets, the server arrangement is configured to enable the user to switch between the plurality of widgets. In an example, a bar of three tabs may allow the user to switch between the widgets. Moreover, the tabs may be marked with icons referring to the corresponding widget. One such exemplary tab has been illustrated in FIG. 3 as explained in more detail hereinafter. The exemplary tab includes three icons. A first icon positioned in middle of three icons represents a small bar chart and is underlined depicting that it is the active, a second icon positioned towards left of the first icon represents a blackboard and a third icon positioned right of the first icon represents a pie chart. In such a case, upon clicking, the first icon corresponds to learning-how-to-search widget tab, the second icon corresponds to curriculum reflection widget tab and the third icon corresponds to an overall learning progress. Optionally, the server arrangement is configured to adjust a size of the icons of the at least one widget, based on a size of the display of the user device on which the user wishes to use the search platform.

Optionally, the curriculum reflection widget includes a learning prompt in order to suggest learning more about the next topic that would be the next in the current sub-module of their curriculum, and a button which opens the respective learning unit in a new tab. Such a learning prompt 5 constitutes a curriculum learning part of the curriculum reflection widget. Moreover, the curriculum reflection widget presents the reflective question that motivates the user to think about the currently learned topic. Such a reflective question constitutes a curriculum reflection part of the curriculum reflection widget. Additionally, the progress for the of 10 the current sub-module is displayed on the bottom of the widget.

It will be appreciated that learning prompts, in the curriculum learning part of the curriculum reflection widget, are displayed in the order according to the curriculum. Even if the user skips learning units or jumps across modules in the learning environment, the curriculum reflection widget will give the user the learning prompt associated with the next not completed learning unit, starting from the beginning of the curriculum. Every time a user completes a learning unit and gives an answer to the reflective question, the next learning prompt will be displayed. Since the learning units in the learning environment are very short, user interaction tracking cannot be applied there to infer the engagement level of the user with the page. Therefore, a learning unit counts as completed, if the user clicks on the "Next" button of the learning unit. Every time a user learns a unit, an appropriate record of the active learning unit will be created in the database with the users id, the learning unit id, the time the user completed this learning unit and that the question is completed but not yet answered. If the user has completed a learning unit, the reflective question is displayed. The reflective questions consist of a set of general questions, which should bring the user to reflect about the last learning unit. Every reflective question contains a placeholder, which is set dynamically based on the topic of the last unit learned. In an example, the prompt may be "Did you notice any motivating moments during this week for progressing with the <b>{{sub_competenceiR/b> competence?". In such an example, the {{sub_competence}} might be replaced with the name of the sub competence finding information, which would result in the 5 reflective question "Did you notice any motivating moments during this week for progressing with the finding information competence?". If the user answers this question, the answer will be stored in the database in a table as a record which contains the users id, question id, matching learning unit and time when it was answered. Additionally, the record of 10 the active learning unit will be updated that it was answered.

In the case that the user goes through multiple learning units in the learning environment, the reflective question will always be directed to the last learned unit.

Optionally, the server arrangement is configured to determine a progress of the given user. More optionally, the server arrangement is configured to enable, via the interactive user interface, to display the progress of the given user. In an example, a progress indicator may be employed to display the user's progress for the current submodule of the curriculum via the interactive user interface. The progress is calculated by taking the number of lessons for this submodule which the user has completed and dividing it by the total number of learning units in this submodule.

Optionally, the overall progress part of the widget shows the user's learning progress with regard to the curriculum using a sunburst visualization. One such sunburst visualization has been illustrated in Fig. 6, wherein it can be seen that the curriculum is divided into three modules. Furthermore, a fourth module is available for auditors of a particular company in case it is being used to improve in-house searching capabilities of the user. Each module is represented as section in the inner circle of the visualization and each module is additionally divided into three sub-modules in outer circle. Every time a user completes a new learning unit, the percentage in the respective section in the sunburst diagram is updated. Furthermore, the progress in each sub-module is encoded by color. In an example, if the user has not completed any learning units in a sub-module (0%) the respective section will be red; making progress in a sub-module will turn the section to yellow (50%) and finally, by completing a sub-module, the section will turn green (100%). This may be explained by the legend below the visualization. Moreover, the sections in the sunburst diagram are ordered to mirror the structure of the curriculum. Starting from the top, the sub-modules get completed clock-wise, slowly turning the visualization green. The sunburst visualization of the overall progress part was implemented using D3.js, and is dynamic and responsive. It is dynamic in the sense, that it adapts to a varying number of modules and submodules. Therefore, if changes in the curriculum happen, the visualization will handle the update itself, without the need to do any further development. It is responsive in the way that it uses SVG with a view box for the visualization. The SVG always fills the available width, while the view box guarantees that the sunbursts proportions stay intact.

DETAILED DESCRIPTION OF THE DRAWINGS

Referring to FIG. 1, illustrated is a schematic illustration of a network environment 100 wherein a system that provides adaptive training support for a search platform is implemented, in accordance with an embodiment of the present disclosure. Notably, the network environment 100 includes: a server arrangement 102, a communication network 104 and a plurality of user devices (depicted as user devices 106A, 106B and 106C) coupled in communication with the server arrangement 102. The plurality of user devices 106A, 106B and 106C are associated with a plurality of users of the system. As shown, in the network environment 100, the server arrangement 102 is coupled in communication with the user devices 106A, 106B and 106C via the communication network 104. It will be appreciated that for sake of simplicity and clarity, the server arrangement 102 is shown to include a single server. However, the server arrangement 102 can also include a plurality of servers.

It will be appreciated that FIG. 1 is merely an example, which should not 5 unduly limit the scope of the claims herein. It is to be understood that the specific designation for the network environment 100 is provided as an example and is not to be construed as limiting the network environment 100 to specific numbers, types, or arrangements of user devices, servers and communication networks. A person skilled in the art 10 will recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

Referring to FIG. 2, illustrated is an exemplary illustration of information that can be represented via an interactive user interface 200, in accordance with an embodiment of the present disclosure. Notably, a given user is provided with the interactive user interface 200. As shown, the interactive user interface 200 represents a search behavior of the given user, and at least one recommendation for the given user.

In the FIG. 2, the search behavior of the given user is depicted in a form of a bar chart 202 which describes data values associated with search features used by the given user in a given search. The bar chart 202 allows for the given user to analyze the search features of the given of user to deduce the search behavior of the given user. As shown, the horizontal axis of the bar chart 200 depicts the search features (for example, such as, Fl, F2, F3, F4 and F5) for which the data values are to be obtained, and the vertical axis of the bar chart 200 depicts data values (for example, such as, Y1-Y4) associated with search features.

The interactive user interface 200 represents the at least one recommendation for the given user in the form of a text box 204. As shown, the text box 204 displays the at least one recommendation for the given user in form of a message for example, such as "try the A'Y feature of the search platform, it will improve your search behaviour." It will be appreciated that FIG. 2 is merely an example, which should not unduly limit the scope of the claims herein. A person skilled in the art will 5 recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

Referring to FIG. 3, illustrated is an exemplary illustration of tab that can be represented via an interactive user interface, in accordance with an embodiment of the present disclosure. As shown, the tab 300 includes three icons. A first icon 302 positioned in middle of three icons represents a small bar chart and is underlined depicting that it is the active, a second icon 304 positioned towards left of the first icon 302 represents a blackboard and a third icon 306 positioned right of the first icon 302 represents a pie chart. Notably, the first icon 302 corresponds to learning-how-to-search widget tab, the second icon 304 corresponds to curriculum reflection widget tab and the third icon 306 corresponds to an overall learning progress.

It will be appreciated that FIG. 3 is merely an example, which should not unduly limit the scope of the claims herein. A person skilled in the art will 20 recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

Referring to FIG. 4, illustrated is an exemplary illustration of learninghow-to-search widget tab that can be represented via an interactive user interface 400, in accordance with different embodiments of the present disclosure. As shown, the learning how to search widget tab represents a bar chart 402 depicting information corresponding to search input interface used and search result presentation based on search behavior of a user. Notably, features of the search input interface include three functionalities to initiate a search, namely "simple search", "advanced search", "faceted search", and five functionalities of presenting the search results, namely "Result List", "Concept Graph", "uRank", "Tag Cloud" and "Top Properties". Moreover, a reflective question or sentence starter is displayed on the interactive user interface 400 to stimulate reflection on 5 the feature usage by the user during a search based on the search behavior of the user. As shown, the reflective question is "simple search is the most used feature on the search platform. What do you like best using this feature?". Furthermore, a text field 404 is present on the interactive user interface 400, where the user can enter the answer 10 corresponding to the reflective question. Therefore, submit the answer using a clickable icon 406 named as "submit answer".

It will be appreciated that FIG. 4 is merely an example, which should not unduly limit the scope of the claims herein. A person skilled in the art will recognize many variations, alternatives, and modifications of 15 embodiments of the present disclosure.

Referring to FIGs. 5A and 56, are exemplary illustrations of curriculum reflection widget tab that can be represented via an interactive user interface 500, in accordance with an embodiment of the present disclosure. It will be appreciated that FIGs. 5A and 5B are merely examples, which should not unduly limit the scope of the claims herein. A person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

In FIG. 5A, the curriculum reflection widget represents a curriculum learning part of the curriculum reflection widget. As shown the curriculum reflection widget includes a learning prompt 502, suggesting a user to learn more about the next topic that would be next in current sub-module of their curriculum, and a button 504 which opens the respective learning unit in a new tab. As shown, the learning prompt 502 displays a message "Already discovered? There are 2 more features that display your result by categories, tag or sources. Find out more about them here". Moreover, a progress of the user for the of the current sub-module is displayed on the bottom of the interactive user interface 500 via a progress indicator 506.

In FIG. 5B, the curriculum reflection widget represents a curriculum reflection part of the curriculum reflection widget. As shown the curriculum reflection widget presents prompt 508 consisting reflective question that motivates the user to think about the currently learned topic. As shown, the reflective question is "What are the top 3 reasons that you do not progress with the evaluating information?". Furthermore, a text field 510 is present on the interactive user interface 500, where the user can enter the answer corresponding to the reflective question. Therefore, submit the answer using a clickable icon 512 named as "submit ". Moreover, the progress of the user for the of the current sub-module is displayed on the bottom of the interactive user interface 500 via a progress indicator 506.

Referring to FIG. 6, illustrated is an exemplary illustration of overall progress tab that can be represented via an interactive user interface 600, in accordance with an embodiment of the present disclosure. As shown the overall progress of user's learning progress is represented using a sunburst visualization 602. Each module is represented as section in inner circle 602A of sunburst visualization 602 and each module is additionally divided into three sub-modules in outer circle 602B of the sunburst visualization 602. As shown, a first sub-module (depicted as lined portion) represents that the user has not completed any learning units in this first sub-module; a second sub module (depicted as squared portion) represents that the progress is being done in this second sub-module, and a third module (depicted as dotted portion)represents that the progress is complete in this third module.

It will be appreciated that FIG. 6 is merely an example, which should not 30 unduly limit the scope of the claims herein. A person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

Modifications to embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present 5 disclosure as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "have", "is" used to describe and claim the present disclosure are intended to be construed in a nonexclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is 10 also to be construed to relate to the plural.

Claims

CLAIMSWhat is claimed is: 1. A system that, when operated, provides adaptive training support for a search platform, the system comprising a server arrangement and a plurality of user devices coupled in communication with the server arrangement, wherein the plurality of user devices are associated with a plurality of users, and wherein the server arrangement is configured to: - track activity data of the plurality of users, said activity data pertaining to a manner in which the plurality of users use the search 10 platform; - analyze the activity data of the plurality of users to deduce a search behavior of each of the plurality of users; - generate at least one recommendation for each of the plurality of users, wherein the at least one recommendation for a given user is 15 generated based upon a given search behavior of the given user; and - provide each of the plurality of users with an interactive user interface, wherein a given interactive user interface for the given user is employed to represent the given search behavior of the given user, and the at least one recommendation for the given user.
2. A system of claim 1, further comprising a database arrangement coupled in communication with the server arrangement, wherein the server arrangement is configured to store, at the database arrangement, at least one of: the activity data of the plurality of users, the search behavior of each of the plurality of users, the at least one recommendation for each of the plurality of users.
3. A system of claim 1 or 2, wherein the given search behavior of the given user comprises at least one of: search filters used by the given user, concept graphs used by the given user, uRank used by the given user.
4. A system of any of claims 1 to 3, wherein the server arrangement is further configured to enable, via the given interactive user interface, the given user to select at least one of: when the given user wishes to receive the at least one recommendation, a given user device on which the given user wishes to receive the at least one recommendation.
5. A system of any claims 1 to 4, wherein the server arrangement is further configured to enable, via the given interactive user interface, at 10 least one widget for supporting adaptive and reflective learning of the search platform.