WO2013041345A1

WO2013041345A1 - Context-based processing of interaction events

Info

Publication number: WO2013041345A1
Application number: PCT/EP2012/066980
Authority: WO
Inventors: Akhil MATHUR; Samik Datta; Anirban Majumder; Sreedal MENON
Original assignee: Alcatel Lucent SAS
Current assignee: Alcatel Lucent SAS
Priority date: 2011-09-20
Filing date: 2012-08-31
Publication date: 2013-03-28
Anticipated expiration: 2014-03-20

Abstract

According to an implementation, a method for context-based processing of interaction events in a communication network is described. In said implementation, the method includes extracting one or more context features for each of a plurality of interaction events. The context features can be extracted from interaction information associated with the plurality of interaction event. Further, from among the plurality of interaction events, linked interaction events are identified, based on a query parameter. The query parameter can be based on one or more of the context feature. Based on comparisons between the linked interaction events, relevant interaction events are determined from among the linked interaction events. Further, the relevant interaction events are rendered to depict the relevant interaction events as graphics. The rendering of the relevant interaction events can be based on the context features and the comparisons between the linked interaction events.

Description

CONTEXT-BASED PROCESSING OF INTERACTION EVENTS

FIELD OF INVENTION

[0001] The present subject matter relates to interaction events in a communication network and, particularly but not exclusively, to context-based processing of interaction events in the communication networks.

BACKGROUND

[0002] Digital technology has found its way into different aspects of human life, professional as well as personal. Capturing life related events and interactions through digital media, such as pictures, audio, and video, is becoming increasingly popular. Usually, the captured events are stored digitally and are later accessed to view and reminisce about the events, and even retrieve past information from such events.

[0003] Conventionally, interactions taking place through a mobile phone are captured to create a library of events based on the interactions. The interactions can include, for example, text messages, emails, phone calls, memos, reminders, and calendar updates. The captured interactions are then displayed to the user on the mobile phone in a raw form. For example, the interactions are captured and the details of the interaction, such as sender and time, are displayed to the user in the same format as captured. Usually, a large number of interactions take place through the mobile phone over a small period of time, say a week, and displaying a list of all the interactions for that period may overwhelm the user.

SUMMARY

[0004] This summary is provided to introduce concepts related to context-based processing of interaction events in a communication network. This summary is not intended to identify essential features of the claimed subject matter nor is it directed to use in determining or limiting the scope of the claimed subject matter.

[0005] According to an implementation, a method for context-based processing of interaction events in a communication network is described. In said implementation, the method includes extracting one or more context features for each of a plurality of interaction events. The context features can be extracted from interaction information associated with the plurality of interaction event. Further, from among the plurality of interaction events, linked interaction events are identified, based on a query parameter. The query parameter can be based on one or more of the context feature. Based on comparisons between the linked interaction events, relevant interaction events are determined from among the linked interaction events. Further, the relevant interaction events are rendered to depict the relevant interaction events as graphics. The rendering of the relevant interaction events can be based on the context features and the comparisons between the linked interaction events.

[0006] According to another implementation, an interaction processing system for context- based processing of interaction events in a communication network is described. In said implementation, the interaction processing system includes a processor and a memory coupled to the processor. The memory includes an interaction identification module configured to identify linked interaction events from a plurality of interaction events based on a query parameter. The query parameter can be based on at least one context feature associated with each of the plurality of interaction events. The interaction identification module is further configured to select relevant interaction events from among the linked interaction events based on a relational score. The relational score is computed for each comparison between the linked interaction events. The interaction processing system further comprises a rendering module configured to obtain graphics for each of the relevant interaction events and render the relevant interaction events based on the obtained graphics.

[0007] According to yet another embodiment, a computer-readable medium having embodied thereon a computer program for executing a method for context-based processing of interaction events is described herein. According to said implementation, the method of the computer-readable medium includes obtaining interaction information associated with a plurality of interaction events and extracting one or more context features for each of the plurality of interaction events, from the interaction information. From the plurality of interaction events, linked interaction events are identified based on a query parameter. The query parameter can be based on one or more of the context features. Further, relevant interaction events are determined from among the linked interaction events, based on comparisons between the linked interaction events. The comparison can include ascertaining a similarity between the linked interaction events being compared. In addition, the relevant interaction events are rendered based on graphics associated with each of the relevant interaction events. BRIEF DESCRIPTION OF THE FIGURES

[0008] The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:

[0009] Figure 1 illustrates a network implementation of an interaction processing system for context-based processing of interaction events in a communication network, according to an embodiment of the present subject matter.

[0010] Figure 2 illustrates a visualization rendered by the interaction processing system, according to an embodiment of the present subject matter.

[0011] Figure 3 illustrates a method for context-based processing of interaction events in a communication network, according to an embodiment of the present subject matter.

[0012] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DESCRIPTION OF EMBODIMENTS

[0013] The present subject matter relates to context-based processing of interaction events in a communication network.

[0014] Conventionally, interaction events, such as mails, text messages, phone calls, taking place through a mobile phone are captured and displayed to a user in raw form, i.e., the metadata of the interaction For example, the sender, the recipients, and a time stamp associated with the interaction, are displayed to the user. In addition, conventional tools can be used to track and maintain a log of the interactions and events taking place through a computing device, such as a personal computer or a laptop. Such events can include web pages visited and files accessed by the user on the computing device, along with the time stamp. In both the above cases, the content of the interaction, such as the text in the mail or the message, or the content of the file accessed are not captured. In certain other cases, where the contents of the interactions may be captured, the contents of two different events relating to the same topic or similar topics are not linked.

[0015] Such interactions, when accumulated over a certain period of time, say a week or a month, may involve a large number of events that are captured and displayed. The user may be unable to use and access such large amounts of data at one time, and hence, the whole exercise of capturing the events may turn out to be futile. Additionally, when the log of the interactions is accessed by the user or a different entity, neither of them may be able to recognize and relate to the content of the interaction due to an absence of a context between the different interactions, and may not be able to link one event to another similar event belonging to the same topic.

[0016] The present subject matter relates to context-based processing of interaction events in a communication network. According to an implementation, the communication network includes an interaction processing system, which is capable of interacting with one or more user devices. The interaction processing system can be a central server communicating with the user devices over the communication network. The user devices can be understood as those devices through which the user achieves interaction events, such as text messages, emails, phone calls, and posts or photo uploads on social networking sites, and can include mobile terminals, laptops, personal computers, and tablets. The interaction events can further include information describing the files accessed, such as audio files played, movies watched, and books read, on the user devices, communication logs, such as logs of emails, social networking site updates, and chats, the websites visited using the user device, and user environment details, such as location, time and motion information.

[0017] Each interaction event achieved through the user devices is tracked and logged. In one example, with each interaction event occurring through the user devices, the user devices can transmit interaction information to the interaction processing system. The interaction information can include the interaction event itself, for example, the text message, email or an address of a website on which the interaction event is achieved. Hence, in one example, the interaction information can include the content of the interaction event and the metadata of the interaction event, such as the sender and recipient, and the time stamp associated with the interaction event. According to an implementation, for each interaction event achieved by the user devices, the interaction information is sent to the interaction processing system. According to another implementation, the interaction events can be monitored for a predetermined period of time, for example, a week, and the interaction information stored. Further, after the lapse of the predetermined period of time, the interaction information can be sent to the interaction processing system.

[0018] Further, the interaction information received from the user devices can be indexed and stored to generate various visualizations of the interaction events. For this, the interaction information is processed to extract context features from the interaction information. In said implementation, the context features can include features associated with users participating in the interaction event, location of occurrence of the event, and content of the interaction event.

[0019] Subsequent to extraction of context features, in an implementation, linked interaction events are determined, for example, to establish a context between different interaction events. Further, from amongst the linked interaction events, relevant interaction events are identified. The relevant interaction events can be understood as those interaction events which can be used for effectively depicting the interactions achieved by the users. In an example, the relevant interaction events can be identified based on one or more similar context features between the various interaction events or age of the interaction events, or both.

[0020] In an implementation, to determine the linked interaction events, a query parameter can be utilized. In an example, all the interaction events that include the query parameter in the extracted context features are identified as the linked interaction events.

[0021] The query parameter can include the rules on the basis of which it is determined whether the interaction events are linked or not. In an example, the query parameter can be based on one or more context features extracted from the interaction information to determine the linked interaction events on the basis of the users, the location, or the content, or a combination thereof. In another example, the query parameter can be based on an interaction event type to restrict the determination of linked interaction events from amongst the same kind of events.

[0022] Further, as mentioned before, the relevant interaction events are selected from amongst the linked interaction events. For selecting the relevant interaction events from the linked interaction events, each of linked interaction events are compared amongst themselves and for each comparison a relational score is computed. Based on the relational score, the linked interaction events are classified as relevant interaction events. In an implementation, the relational score is also based on a similarity between the two interaction events being matched based on the respective extracted context features. In another implementation, the relational score can be determined based on a recentness of the interaction events. For example, the linked interaction events which are older than, say, a month, are not classified as relevant interaction events.

[0023] As will be understood, the relevant interaction events obtained based on the relational score have high degree of similarity and can be related to each other based on various context features, for example, apart from those included in the query parameter. Further, the relevant interaction events and the relation between the relevant interaction events can be used to render a visualization of the relevant interaction events.

[0024] According to an implementation, the visualization can include the representation of a single interaction event. In an example, the representation is rendered in the form of a graphic. In said implementation, the graphics associated with the context features of an interaction event are obtained and used to render the representation of the interaction event. In an example, based on the context features, the graphics can include images of a primary user, one or more secondary users, the location of the interaction events, and the content associated with the interaction event.

[0025] In an implementation, the visualization can also include graphics depicting the various interaction events related to the representation based on various context features. Since, the various relevant interaction events can have common context features, the representation can be used to depict the relevant interaction events, related to each other through one or more context features. For example, the representation can include those interaction events which are related to each other on the basis of the location of the interaction events, i.e., the interaction events have occurred at the same location. Accordingly, the user can select one of the graphics in the representation to access all the interaction events related to that graphic. For example, the user can select the image of the primary user to obtain all the interaction events linked with the primary user, the linked interaction events being determined based in the same manner as described above. Further, in an implementation, the various representations can be provided on a time-line in the visualization to depict the various interaction events in a week-by-week, or day- by-day, or hour-by-hour manner.

[0026] Although the functionality related to the rendering the representation and the overall visualization is described with reference to the interaction processing system, it will be understood that one or more of the user devices can be configured to achieve the same functionality. In one example, the functionality of rendering can be provided on a cloud-based server which can provide the rendered representation as a web-service. In said example, various users can remotely access and view the rendered representation and the visualization of the interaction events.

[0027] The identification of the relation among the various interaction events based on the query parameter contextually associates one interaction event to other interaction events. Another user accessing the visualization, or a user of the user devices accessing the representations after a long period is able to easily recognize the context of the various interaction events in the representation. Additionally, the visualization of the interaction events can be can be easily shared with various other users over the communication network. In an example, the relevant interaction events achieved by the user can be summarized in the form of an engaging visualization, say, in the form of a comic strip, and shared with the users on a social networking portal. Hence, the experience of sharing and viewing the interaction events of oneself and of other users is enhanced and is made convenient.

[0028] The manner in which the systems and methods for context-based processing of interaction events in a communication network are implemented shall be explained in details with respect to the figures. While aspects of described systems and methods for context-based processing of interaction events in a communication network can be implemented in any number of different computing systems, environments, and/or configurations, the embodiments are described in the context of the following exemplary system(s).

[0029] It should be noted that the description and figures merely illustrate the principles of the present subject matter. It will thus be appreciated that those skilled in the art will be able to devise various arrangements that, although not explicitly described or shown herein, embody the principles of the present subject matter and are included within its spirit and scope. Furthermore, all examples recited herein are principally intended expressly to be only for pedagogical purposes to aid the reader in understanding the principles of the present subject matter and the concepts contributed by the inventor(s) to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions. Moreover, all statements herein reciting principles, aspects, and embodiments of the present subject matter, as well as specific examples thereof, are intended to encompass equivalents thereof.

[0030] It will also be appreciated by those skilled in the art that the words during, while, and when as used herein are not exact terms that mean an action takes place instantly upon an initiating action but that there may be some small but reasonable delay, such as a propagation delay, between the initial action and the reaction that is initiated by the initial action. Additionally, the word "connected" is used throughout for clarity of the description and can include either a direct connection or an indirect connection.

[0031] Figure 1 illustrates a network environment 100 implementing an interaction processing system 102, according to an embodiment of the present subject matter. The interaction processing system 102 is configured to process various interaction events achieved by a user, on the basis of context associated with each interaction event. The interaction processing system 102 is connected to and interacts with a plurality of user devices 104-1 , 104-2 ...104-N, collectively referred to as the user devices 104 and individually referred to as a user device 104. The interaction processing system 102 may be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, and a network server. The user devices 104, on the other hand, can include, without limitation, desktop computers, hand-held devices, laptops or other portable computers, tablet personal computers, network computers, mobile phones, multi-media enabled phones, and smart phones.

[0032] The interaction processing system 102 and the user devices 104 can communicate with each other over a communication network 106. The communication network 106 may be a wireless or a wired network, or a combination thereof. In an example, the communication network 106 can be implemented as a computer network, as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 106 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), to communicate with each other. Further, the network communication 106 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. [0033] In another example, the communication network 106 can be implemented as a telecommunication network. In said example, the communication network 106 can be a collection of individual networks, interconnected with each other and functioning as a single large network (e.g., the internet or an intranet). Examples of such individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network (NGN), IP -based network, Public Switched Telephone Network (PSTN), and Integrated Services Digital Network (ISDN). Depending on the technology, the communication network 106 includes various network entities, such as gateways, routers; however, such details have been omitted for the sake of brevity. Further in an example, the interaction processing system 102 can use General Packet Radio Service (GPRS) or Bluetooth for communicating with the user devices 104. In yet another example, the communication network can be implemented as a combination of a computer network as well as a telecommunication network. [0034] In an implementation, the interaction processing system 102 includes processors) 108 coupled to a memory 1 10. The interaction processing system 102 further includes interface(s) 1 12, for example, to facilitate communication with the user devices 104. The interface(s) 1 12 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, and a printer. Further, the interface(s) 1 12 enables the interaction processing system 102 to communicate with other devices, such as web servers and external repositories. The interface(s) 1 12 can also facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. For the purpose, the interface(s) 1 12 may include one or more ports. [0035] The processor(s) 108 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processors) 108 are configured to fetch and execute computer-readable instructions stored in the memory 1 10.

[0036] The memory 1 10 can include any computer-readable medium known in the art including, for example, volatile memory such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. Further, the memory 1 10 includes module(s) 1 14 and data 1 16.

[0037] The module(s) 1 14 include, for example, an extraction module 1 18, an interaction identification module 120, a rendering module 122, and other module(s) 124. The other module(s) 124 may include programs or coded instructions that supplement applications or functions performed by the interaction processing system 102. [0038] The data 1 16 can include interaction information data 126, linked interaction data 128, representation data 130, and other data 132. The other data 132, amongst other things, may serve as a repository for storing data that is processed, received, or generated as a result of the execution of one or more modules in the module(s) 1 14. Although the representation data 130 is shown internal to the interaction processing system 102, it may be understood that the representation data 130 can reside in an external repository (not shown in the figure), which is coupled to the interaction processing system 102. The interaction processing system 102 may communicate with the external repository through the interface(s) 1 12 to obtain information from the representation data 130.

[0039] In operation, the interaction processing system 102 is configured to track interaction events achieved through the user devices 104, and represent the interaction events in the form of a visualization. The interaction events can include, for example, text messages, emails, phone calls, blogs and photo uploads on a social networking website, files accessed, videos watched, websites visited, audio files played, movies watched, and documents or books read. In addition, the interaction events can also include physical interactions, such as locations visited. The user devices 104 can be understood to be operated by a single user carrying out the various interaction events.

[0040] In an implementation, the extraction module 118 can be configured to monitor and track the interaction events being achieved through the user devices 104 to obtain interaction information associated with the interaction events. The interaction information can include the interaction event, for example, the email sent or received, an address of the webpage browsed, or information relating to document accessed. In an example, the interaction information includes the content of the interaction event as well as the metadata, such as sender and recipient, of the interaction event.

[0041] In an example, the extraction module 118 periodically obtains the interaction information associated with the all interaction events achieved through the user devices 104, say, the interaction events achieved in a day or in a week. In another example, the extraction module 118 may track each interaction event occurring through the user devices 104 and obtains the interaction information from the user devices 104. In another implementation, the user device 104, such as the user device 104-1 , can include an interaction capture module 134. The interaction capture module 134, similar to the extraction module 118, can track the interaction events on the user device 104 and provide the interaction information associated with the interaction event to the extraction module 1 18 on the interaction processing system. Although the interaction capture module 134 is shown as implemented on the user device 104-1 in Figure 1 , it will be understood that the interaction capture module 134 can be independently implemented on each of the user devices 104.

[0042] Further, in addition to the above mentioned information, the extraction module 118 can also obtain other information such as that relating to an environment of each user device 104 in the interaction information. For example, as part of the interaction information, each user device 104 can transmit information relating to the location or geographical coordinates of the user device 104, say, to determine the location visited by the user, ambient light level, and acceleration values to determine whether the user device 104 is static or not, say, in case a gaming application is being accessed on the user device 104.

[0043] Upon receiving the interaction information relating to the interaction events, the extraction module 118 can further extract one or more context features from the interaction information. In case the interaction information is related to one interaction event, the extraction module 118 obtains the context features for that interaction event. The context features can be information for establishing a context of the interaction event and can include, for example, names of one or more users participating in the interaction event, a location of the occurrence of the interaction event, and a content of the interaction event. In said example, the users can include a primary user, say, a sender of text messages or emails, or a user writing a post on a social networking site, and can include one or more secondary users, say, those commenting on a post on a social networking website or recipients of the text messages or emails. Further, in said example, the location can be obtained based on the geographical coordinates of the user device 104 transmitted in the interaction information. Additionally, the content can include information, such as subject or a topic in an interaction event or a theme of a book or a movie accessed on the user device 104, and a type of interaction event, say, a text message or an email.

[0044] In an example, the content can also include a sentiment parameter associated with the interaction event, which is determined by, say, processing a digital photograph in the interaction event for emotion analysis, identifying a smiley in a message, or identifying a tone of a message based on the words used. Additionally, the sentiment parameters associated with the event can be determined based on the audio files accessed, video files played, and the books and web pages visited. In an implementation, the extraction module 118 can implement machine learning and data mining techniques to extract and obtain the context features associated with the interaction events from the interaction information.

[0045] In an example, during the extraction of the context features from the interaction information, the extraction module 118 can be configured to classify the features in one of users, location, and content categories described above, and store the extracted context features in the interaction information data 126.

[0046] Subsequent to the extraction of context features from the interaction information, relevant interaction events are determined from among the various interaction events tracked on the user devices 104. The relevant interaction events can be understood as those interaction events, which are considered for visualizing the interactions. To determine the relevant interaction events, in an implementation, the interaction identification module 120 can be configured to follow a two step approach. In said implementation, the interaction identification module 120 can first identify linked interaction events from among the various interaction events occurring on the user devices 104, and subsequently, select the relevant interaction events from the linked interaction events.

[0047] According to an implementation, to identify the linked interaction events, the interaction identification module 120 receives a query parameter. In an example, the query parameter can include a context feature, say, a user or a location or a keyword associated with the content, based on which the related or linked interaction events can be identified.

[0048] Further, in an example, the query parameter can also include an interaction event type, for example, text message, email, or web pages. In said example, the interaction identification module 120 can select the interaction events from among the type of interaction event included in the query parameter to be processed for identification. It will be understood that in case the query parameter is devoid of the interaction event type, all the interaction events are selected for identification. In an example, the interaction identification module 120 can include each interaction event type one by one in the query parameter, and then step-wise determine the linked interaction events, also based on the other parameters in the query parameter. In such a scheme of identifying the linked interaction events, the interaction identification module 120 ensures that the entire spectrum of types of interaction events is covered for identifying the linked interaction events.

[0049] In an implementation, the interaction identification module 120 can request the query parameter from the user and obtain the query parameter from the user. In another implementation, the interaction identification module 120 can be configured to automatically select the query parameter based on predefined rules, for example, the type of interaction events, the users, the content, or a combination thereof. The query parameter obtained from the user or the one automatically selected is stored in the linked interaction data 128.

[0050] In an implementation, to identify the linked interaction events, the interaction identification module 120 is configured to compare the context features extracted from the interaction information of each interaction event with the query parameter. In an example, the interaction events, whose context features include the query parameter and which also belong to the interaction type as specified in the query parameter, are selected as the linked interaction events. Subsequently, in an implementation, the relevant interaction events are determined from among the linked interaction events.

[0051] According to an implementation, the interaction identification module 120 is configured to compare the extracted context features associated with each of the linked interaction events among themselves and compute a relational score for each comparison. For example, the relational score is computed based on the extent to which the context features associated with one interaction event is similar to the context features associated with another interaction event. In said example, the relational score can be understood to be based on a similarity index computed for each comparison between the context features of the linked interaction events. Further, since the similarity between the linked interaction events is ascertained based on the context features of the interaction events, during the similarity mapping, the interaction identification module 120 can also identify the matching context features between the linked interaction events, and store the matching context features in the linked interaction data 128.

[0052] In another implementation, relational score can also be based on a recentness index of the linked interaction events. The recentness index can be indicative of an age or recentness of an interaction event. On the inclusion of the recentness index in the query parameter, the relational scores computed by the interaction identification module 120 is also based on the recentness index of the interaction events for which the context features are compared. For example, in case the recentness index of either of the interaction events being compared is low, which means that either of the interaction events is older than, say, a week, then even for a high similarity index, the relational score for the comparison is low. If the relational score for a comparison of context features, based on the similarity index, is s, then an updated relational score s ' computed based on the recentness index is represented, in one example, by the following equation: s '=Q.5 {s+e ^Age(d))

[0053] In the above relation, Age(d) represents a recentness factor associated with the interaction event and is indicative of the recentness of the interaction event. The recentness factor can be measured in terms of, for example, hours, days, or weeks. Based on the above relation, in case the two interaction events having a low overall relational score are not linked. Further, the above relation, on which the updated relational score s ' is based, can be stored in the linked interaction data 128.

[0054] Further, in case the extraction module 1 18 and the interaction capture module 134 obtain the interaction information for each interaction event and then proceed with the computation score, the interaction identification module 120, in such an implementation, can compare the context features of the captured interaction event with the context features of each of the previous interaction events. For each comparison, the interaction identification module 120 can compute the relational score in the manner as described above.

[0055] Further, in an implementation, based on the relational score, the interaction identification module 120 can determine the relevant interaction events. In an implementation, the interaction identification module 120 can associate the top k linked interaction events with highest relational score and determine the linked interaction events as the relevant interaction events. As will be understood, the relevant interaction events can be related to each other by more than one context features, as determined by the interaction identification module 120 and stored in the linked interaction data 128. For example, a text message can be linked with another text message based on the sender, and can be linked with an email based on the content or the subject. Hence, the related events group obtained includes a plurality of interaction events, which may be linked with each other on the basis of more than one context feature, and hence, involve a complex linking between among themselves. The linked interaction events and the linking of each interaction event with another interaction event in the related events group are also stored in the linked interaction data 128.

[0056] Although the identification of the relevant interaction events from the various interaction events taking place on the user devices 104 is described with reference to a two-step approach, it will be understood that the two-steps of the above approach can be combined to form a single step. In said implementation, the relevant interaction events can be identified from all the interaction events in one step.

[0057] In an implementation, once the identification of the relevant interaction events is achieved, the rendering module 122 is configured to generate a representation to depict the interaction events and the links between the interaction events. The representation, hence achieved serves as visualization of the interaction events and of the relationship between the various interaction events.

[0058] For rendering the representation, the rendering module 122 can obtain graphics related to the interaction events and use the graphics to render the representation. In an example, the rendering module 122 can obtain the graphics relating to the context features of the interaction events, say, images relating to the primary user, the one or more secondary users, location of the occurrence of the interaction event, and the content of the interaction event. In an implementation, the representation of the interaction events is achieved in the form of a cartoon strip, and the graphics relating to, for example, the context features, are obtained in the form of cartoon images. In an implementation, the rendering module 122 can obtain previously stored graphics from the representation data 130. In another implementation, the rendering module 122 can be configured to connect to the internet and fetch graphics relating to the interaction event, for example, based on the context features associated with the interaction event. In yet another implementation, the rendering module 122 can also request the user operating the user devices 104 to select or provide the graphics for generating the representation.

[0059] Further, in an implementation, upon a prompt from the user to view a certain interaction event, the rendering module 122 can generate the representation using the obtained graphics for that interaction event. In an example, in case the user prompts to view one of the graphics in the representation, say by clicking on the graphic, the rendering engine 122 can provide a list of all the linked interaction events, which include the selected graphic as a common feature.

[0060] In another implementation, the rendering module 122 can render the representation for each of the linked interaction event and generate a complete map of the linked interaction events, having interconnected graphics. The rendered representation can be stored in the representation data 130 and can be accessed by the user devices 104 over the network 106.

[0061] In an implementation, the rendering module 122 can further be configured to generate a thumbnail representation for each interaction event on a time-line and depict the interaction events relating to the user devices 104 on the time-line. Hence, in an example, the rendering module 122 can depict the interaction events in an hour-by-hour, a day-by-day, or a week-by- week manner. In said implementation, the user can view the time-line of the interaction events on a graphical user interface (not shown) connected to, for example, the user devices 104 or directly connected to the interaction processing system 102. Further, in case the user may request to view an enlarged graphic of one of the interaction events on the timeline, say, by clicking on the interaction event, the rendering module 122 can render the representation for that interaction event in the manner as described above.

[0062] Although the functionalities associated with the rendering module 122 are described with reference to the interaction processing system 102, it will be understood that the rendering module 122 can be provided as a client application on one or more of the user devices 104 or on a cloud based server. In the former case, the user devices 104 are provided with the capability of rendering the representation of the interaction events based on the interaction events, the context features, and the linking among the interaction events, for example, stored in the linked interaction data 128. In the latter case, the representation can be rendered and provided to the users on a web page associated with the cloud based server.

[0063] Figure 2 illustrates a visualization 200 of the interaction events provided by the interaction processing system 102, according to an embodiment of the present subject matter. The visualization 200 is an overall representation of the related interaction events and includes the interaction events shown on a time-line 202. In an implementation, when represented on the time-line 202, each interaction event is depicted as a miniaturized graphic 204. As shown in Figure 2, the interaction events are depicted by the miniaturized graphics 204-1 , 204-2,...204-N, respectively, collectively referred to as miniaturized graphics 204 and individually referred to as miniaturized graphic 204. In an example, the miniaturized graphics 204 can be in the form of thumbnail representations. Further, the time-line 202 can represent the interaction events in hour- wise manner, i.e., the interaction events occurring per hour, as shown in Figure 2. However, it will be understood that the time-line 202 can represent the interaction events in day-wise or in week- wise manner also.

[0064] When prompted by the user to view an enlarged representation of the miniaturized graphic 204, say by clicking on the miniaturized graphic 204, the rendering module 122 renders a representation 206 and provides the rendered representation 206 to the user. In an example, the representation 206 can be rendered by the rendering module 122 in real-time when prompted by the user. In another example, the rendering module 122 can store rendered representation 206 and can retrieve the representation 206 upon request by the user for viewing.

[0065] As described earlier, the rendering module 122 can render the representation 202 for the interaction event in the form of a graphical representation. In one example, the representation 202 can be in the form of a cartoon illustration formed by superimposing images related to the context features of the interaction event. In an implementation, based on the interaction event, the context features, and the relations with the context features of other interaction events, the rendering module 122 can obtain the graphics and render the representation 206. The rendering module 122 can obtain graphics relating to the context features of the interaction event and use the graphics to render the representation 206. For example, the rendering module 122 can use the image related to the location of the interaction event as background and may superimpose the images of the primary users, the secondary users, and the content over the background image.

[0066] Further, the rendering module 122 can be configured to generate a clear and uncluttered graphic by, for example, summarizing the content and using a graphic for the summarized content, and using a group image in case the secondary users exceed a predefined number, say, 3. In an example, the rendering module 122 can also render the representation 206 to depict all the relevant interaction events 208. The relevant interaction events 208, as explained earlier are related through one or more context features, and are also linked in the representation 206 by the context features. The relevant interaction events 208 can include various interaction events, such as mails, text messages, meetings, files accessed, and web pages visited.

[0067] Further, since an interaction event is linked to various other relevant interaction events 208 based on the context features, same or different, each graphic in the representation 206 can be linked to another graphic of another interaction event. In an example, when the user clicks on any graphic in the representation, the rendering module 122 provides a list of all the relevant interaction events 208 which are related through the context feature represented by the graphic, which is clicked on. In an implementation, the relevant interaction events 208 depicted in the visualization 202 can be selected for inclusion in the visualization 202 based on a relevance score. In an example, the relevance score can be based on the similarity index, i.e., based on the matching context features between the interaction events. [0068] The visualization 200 and the representations 206 rendered by the interaction processing system 102 can be understood with the help of the following example. Consider that the extraction module 118 or the interaction capture module 134 receive the interaction information for the following interaction events achieved through the user devices 104:

[0069] "Tom" receives an email from "Bob" about a project having content "Sparrow, Lifelog". "Tom" makes a phone call to "Bob" to discuss the content "Sparrow. Lifelog". In addition, "Tom" visits "Bob" at an office to attend a meeting regarding the content "Sparrow, Lifelog". The meeting, involving "Tom" and "Bob", is conducted in a conference room "Ellora".

[0070] The extraction module 118 can extract the various context features, for example, classified into users, location, and content, from the above interaction events. The context feature extracted from the interaction event "meeting" can include "Tom" and Bob classified as primary user and secondary user, respectively, "Ellora" as the location of the interaction event, and "Sparrow, Lifelog" as the content of the interaction event.

[0071] Further, the interaction identification module 120 can identify linked interaction events from among "email", "phone call" and "meeting", based on the content selected as the query parameter. In this case, the interaction events "email", "phone call", and "meeting" are linked based on the content. Further, the relational score is computed for the comparison of the interaction events, based on the similarity index and the recentness index for comparisons between the interaction events to identify the relevant interaction events. For the purpose of simplicity, in this example, the linked interaction events are selected as the relevant interaction events. Further, links between the relevant interaction events can be identified based on the other context features of the interaction events. In this case, apart from being linked on the basis of the content, the interaction events are linked based on the users "Tom" and "Bob". Hence, the links between the interaction events can be identified based on more than one context feature.

[0072] Subsequently, the rendering module 122 can render the representation 206 for the interaction event "meeting" based on the context features related to the interaction event. To render the representation 206, the rendering module 122 obtains the graphics related to the primary user "Tom", the secondary user "Bob", the location conference room "Ellora", and the content "Sparrow, Lifelog". As mentioned earlier, the graphic for the conference room is used as the background and the graphics for the primary user "Tom" and the secondary user "Bob" are superimposed on the graphic of the conference room. Further, the graphics for the location and the content, i.e., the name of the location "Ellora" and the content "Sparrow, Lifelog", are superimposed on the background graphic to include the content of the interaction event "meeting" in the representation 206.

[0073] In addition, the rendering module 122 can render the representation of the relevant interaction events 208 and provide the graphic of the linked interaction events. In this case, graphics for the linked interaction events "email" and "phone call" are obtained by the rendering module 122, and included in the overall visualization 200.

[0074] Further, when a user clicks on any graphic, for example, any one of the primary user, the secondary user, the content, or the location in the representation 206, the rendering module 122 provides all the interaction events linked to the graphic clicked upon.

[0075] Figure 3 illustrates a method 300 for context-based processing of interaction event in a communication network, according to an embodiment of the present subject matter. The order in which the method 300 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 300, or alternative methods. Additionally, individual blocks may be deleted from the method without departing from the spirit and scope of the subject matter described herein. Furthermore, the methods can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0076] A person skilled in the art will readily recognize that steps of the method can be performed by programmed computers. Herein, some embodiments are also intended to cover program storage devices, for example, digital data storage media, which are machine or computer readable and encode machine-executable or computer-executable programs of instructions, wherein said instructions perform some or all of the steps of the described method. The program storage devices may be, for example, digital memories, magnetic storage media such as a magnetic disks and magnetic tapes, hard drives, or optically readable digital data storage media. The embodiments are also intended to cover both, communication network and communication devices configured to perform said steps of the method 300.

[0077] Referring to Figure 3, at block 302, interaction information associated with a plurality of interaction events achieved through one or more user devices 104 is received. In an example, the extraction module 118 or the interaction capture module 134, or both, can track the plurality of interaction events on the user devices 104 obtain the interaction information associated with the interaction events. In an example, the interaction events can include a text message, an email, a phone call, a document accessed, an audio played, a video or movie watched, a location visited by the user, a photograph uploaded or a blog uploaded on a social networking site. Further, in an example, the interaction information associated with the interaction events can include the interaction event itself, say, the mail received or a text message sent, as well as a metadata associated with the interaction event, say, the sender and recipient of the mail of text message and time stamp associated with the interaction event. Additionally, the interaction information can include environmental information, such as geographical coordinates relating to a location of the user device 104, ambient light levels, and acceleration values.

[0078] In an implementation, the interaction information can be obtained in response to each interaction event achieved on the user device. In another implementation, the interaction events achieved on the user devices are tracked for a period of time, say a day or a week, and the interaction information is received periodically.

[0079] At block 304, one or more context features are extracted from the received interaction information for the plurality of interaction events. In an implementation, the context features extracted from the interaction information can be related to one or more of the users involved in the interaction event, location related to the interaction event, or content of the interaction event. In an example, the context features can include the sender and recipients of a text message relating to a project or a user uploading a photograph on the social networking site, the location of a meeting held in relation to a project, and the subject of the text messages or the agenda of the meeting, and type of the interaction event.

[0080] Further, the context features can also include sentiment parameters associated with the interaction event. Such context features can be determined based on, for example, processing the graphics for emotion analysis, a smiley identified in a text message, the books or web pages accessed, and the audio files or videos watched.

[0081] In an example, the extraction module 118 can implement variety of machine learning and data mining techniques to extract the context features from the interaction information. [0082] At block 306, linked interaction events are identified from the plurality of interaction events, based on a query parameter. In an example, the query parameter can be based on one or more of the context feature, such as the content, the user, or the location of the interaction events. In another example, the query parameter can include the type of the interaction event. In an implementation, the interaction identification module 120 sorts and identifies those interaction events as linked interaction events from among the plurality of interaction events whose context features include the query parameter. For example, in case the query parameter is based on the content of the interaction event and includes a keyword "Sparrow", then all the interaction events having the keyword "Sparrow" in the content-related context features are identified as linked interaction events. Further, in case the query parameter additionally includes "email" as the interaction event type, then the interaction events are further sorted out based on whether the interaction events are "email" type interaction events or not.

[0083] In another implementation, in which interaction information is received for every fresh interaction event, a context feature of the fresh interaction event, referred to as the captured interaction event, can be considered as the query parameter and the linked interaction events for the captured interaction event can be identified in the manner as described above.

[0084] Subsequent to the identification of the linked interaction events, at block 308, each of the linked interaction events are compared to obtain a relational score. In an implementation, to obtain the relational score, the interaction identification module 120 compares context features extracted from one of the linked interaction events to the context features of another linked interaction event. In an example, the relational score can be based on a similarity index between the context features of the two interaction events. The similarity index can be a measure of the extent to which the context features of the two interaction events are similar. In an example, higher the similarity index, higher is the relational score. Further, during the computation of the similarity index, the relationship between two linked interaction events can be identified based on the other context features apart from those included in the query parameter.

[0085] In another example, the relational score can be based on a recentness index associated with the two interaction events. The recentness index can be indicative of the age of the interaction event, say, whether the interaction event is a freshly occurred interaction event or an old event. A recent interaction event has a higher recentness index than an old interaction event. Accordingly, a high recentness index can translate into a high relational score, and a low recentness index can result in a low relational score.

[0086] According to an implementation, the relational score for the comparison between the linked interaction events is computed based on a cumulative score of the similarity index and the recentness index. In an example, the relational score is computed based on the following relation: s =0.5 (s+e ^Age(d))

[0087] In the above relation, s illustrates the relational score on the basis of similarity index, s ' indicates the relational score based on the recentness index, and Age(d) represents a recentness factor indicative of the recentness of the interaction event for which the relational score is computed.

[0088] In another case, in which each interaction event is tracked and the interaction information achieved, each of the linked interaction event is compared with the reference interaction event to compute a relational score for each linked interaction event.

[0089] In both the above implementations, the relational score for each comparison of the linked interaction events is computed and stored.

[0090] Further, at block 310, based on the relational scores, relevant interaction events are selected from the linked interaction events. In an implementation, the interaction identification module 120 selects the linked interaction events with the top k relational scores as the relevant interaction events. The relevant interaction events can be understood as the most related interaction events and are stored. As mentioned with reference to block 308, the additional links between the interaction events based on the other context features are also determined and stored. Hence, with the identification of the relevant interaction events, the various links between the interaction events are identified based on the various context features. As a result, complex interrelationships between the relevant interaction events are achieved based on different context features. For example, a text message may be related to a mail message based on the senders, whereas the text message may be related to a phone call based on the location of the two.

[0091] Subsequently, at block 312, a representation is rendered for the relevant interaction events. In an implementation, the representation is rendered in the form of a graphic, for example, a cartoon image. Further, in example, the rendering module 122 can generate the representation for the relevant interaction based on the query parameter and the context features not included in the query parameter. In said example, the rendering module 122 can obtain graphics associated with the query parameter and the contexts features, and render the representation using the graphics. In an example, the graphics obtained for rendering the representation for an interaction event can include images of a primary user operating the user devices 104 on which the interaction event is captured, one or more secondary users participating with the primary user in the interaction event, a location of occurrence of the interaction event, and the content of the interaction event. According to an example, if the number of secondary users is more than 3, a collage-type image of all the secondary users can be generated for use in the representation. As will be understood, the graphics in the representation, depicting a context feature, are linked to other graphics. As a result, when a user clicks on a graphic in the representation, the rendering module 122 can render the representations for all the related interaction events and provides a list of the other representations. It will be understood that, in said example, the rendered representations of the related interaction events include the graphic which was clicked on.

[0092] Further, the representation rendered by the rendering module 122 can also include a graphic depicting the various related interaction events. In addition, the rendering module 122 can further depict the various representations for the relevant interaction events on a time-line. In an example, the rendering module 122 can depict the various representations in an hour-wise, a day-wise, or a week-wise manner on the time-line.

[0093] Further, although implementations for context-based processing of interaction events in a communication network have been described in language specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as implementations for context-based processing of interaction events in a communication network.

Claims

A method for context-based processing of interaction events in a communication network, the method comprising:

extracting at least one context feature for each of a plurality of interaction events, from interaction information associated with the plurality of interaction event;

identifying linked interaction events from among the plurality of interaction events, based on a query parameter, wherein the query parameter is based on the at least one context feature;

determining relevant interaction events from among the linked interaction events based on a comparison between the linked interaction events; and

rendering the relevant interaction events, based on the at least one context feature and the comparison.

The method as claimed in claim 1 , wherein the comparison between the linked interaction events comprises determining a similarity between the linked interaction events.

The method as claimed in claim 1 , wherein the determining the relevant interaction events comprises:

computing a relational score for each comparison between the linked interaction events, wherein the relational score is based on at least one of a similarity index and a recentness index; and

selecting the relevant interaction events from the linked interaction events based on the relational score.

The method as claimed in claim 1 , wherein the at least one context feature is at least one of a user, a location, and a content associated with each of the plurality of interaction events.

The method as claimed in claim 1 , wherein the rendering the relevant interaction events comprises:

obtaining a plurality of graphics for each of the relevant interaction events; and rendering each of the relevant interaction events based on the plurality of graphics.

The method as claimed in claim 1 , wherein the query parameter is further based on an interaction event type.

An interaction processing system (102) for context-based processing of interaction events in a communication network (106), the interaction processing system (102) comprising: a processor (108); and

a memory (1 10) coupled to the processor (108), the memory (1 10) comprising:

an interaction identification module (120) configured to:

identify linked interaction events from a plurality of interaction events based on a query parameter, wherein the query parameter is based on at least one context feature associated with each of the plurality of interaction events; and

select relevant interaction events from among the linked interaction events based on a relational score, wherein the relational score is computed for each comparison between the linked interaction events; and

a rendering module (122) configured to:

obtain graphics for each of the relevant interaction events; and render the relevant interaction events based on the obtained graphics.

The interaction processing system (102) as claimed in claim 7, wherein the interaction identification module (120) is further configured to identify the linked interaction events from the plurality of interaction events, based on an interaction event type associated with each of the plurality of interaction events.

The interaction processing system (102) as claimed in claim 7, wherein the interaction identification module (120) is further configured to compute the relational score for each comparison based on a similarity between the linked interaction events and on a recentness of the linked interaction events being compared.

The interaction processing system (102) as claimed in claim 7, further comprising an extraction module (118) configured to: obtain interaction information associated with the plurality of interaction events; and extract the at least one context feature associated with each of the plurality of interaction events from the interaction information.

11. The interaction processing system (102) as claimed in claim 7, wherein the rendering module (122) is further configured to render each of the relevant interaction events, based on the at least one context feature associated with the relevant interaction events.

12. A computer-readable medium having embodied thereon a computer program for executing a method for context-based processing of interaction events, the method comprising:

obtaining interaction information associated with a plurality of interaction events; extracting at least one context feature for each of the plurality of interaction events from the interaction information;

identifying linked interaction events from the plurality of interaction events, based on a query parameter, wherein the query parameter is based on the at least one context feature; determining relevant interaction events from among the linked interaction events based on a comparison between the linked interaction events, wherein the comparison comprises ascertaining a similarity between the linked interaction events being compared; and

rendering the relevant interaction events based on graphics associated with each of the relevant interaction events.

13. The computer readable medium as claimed in claim 12, wherein the determining the relevant interaction events comprises computing a relational score for each comparison between the linked interaction events, wherein the relational score is based on a similarity between the linked interaction events and on a recentness of the linked interaction events being compared.

14. The computer readable medium as claimed in claim 12, wherein the rendering the relevant interaction events comprises superimposing the graphics associated with each of the relevant interaction events, and wherein the graphics for each of the relevant interaction events are obtained based on the at least one context feature associated with each of the relevant interaction events.

The computer readable medium as claimed in claim 12, wherein the extracting comprising obtaining a context feature associated with a captured interaction event, wherein the relevant interaction events are determined for the captured interaction event, based on the context feature, to render the captured interaction event.