A system for predicting relationship dynamics based on browsing behavior and method thereof

Abstract

The invention discloses a system (100) for predicting the relationship dynamics based on browsing behavior and comprises a profiling unit (101) for profiling the browsing behavior of a first user in a user group. The system comprises a processing unit (102) for determining the relationship correlation of the browsing behavior of the first user and other users in the user group. The system (100) further comprises a mapping unit (103) to facilitate creation of a relationship correlation map using location-based parameters. The system (100) comprises an analysis unit (104) for determining the similarities in the browsing behavior of the first user and other users in the user group in a geographical location, facilitating creation of relationship-location correlation map depending on the similarities in the behavior of plurality of user groups.

Description

Internal Ref: OR25C066PCT07 TITLE OF THE INVENTION A system for predicting relationship dynamics based on browsing behavior and method thereof DESCRIPTION OF THE INVENTION Technical field of the invention

[0001] The present invention relates to a system for predicting the relationship dynamics between the users based on the browsing pattern and method thereof. The present invention particularly relates to determination of relationship among the users using location data and browsing behavior. Background of the invention

[0002] The browsing behavior of a user can be determined based on various parameters such as age, gender, location, browsing pattern etc. The user browsing behavior helps to determine various parameters to build a user profile. One such parameter is the relationship among the users. The unique web browsing habits of each user helps in creating accurate user profiles and the user profiles can be used to track and re-identify users.

[0003] The users provide the relationship details in the social media platforms where the users explicitly identify the particular family members or friends. It can be advantageous to understand the relationship dynamics among users, where the data is not provided by the users. The big data platforms are highly used in prediction of the user profiles, relationship dynamics and location correlation among the users based on their browsing behavior, but most of the big data platforms do not have a clear understanding of the relationship and location dynamics of the users based on their search activity and there are no focused methods available for understanding the relationship dynamics among the user’sInternal Ref: OR25C066PCT07 family members in different geographic locations and the factors influencing the same. Further, the existing methods lack in the accuracy of understanding the influence of the family / community members on each other based on the location associated differences all around the world.

[0004] In order to overcome the drawbacks of the existing systems, several technologies have been developed over the decades to predict the relationship dynamics between the users based on their browsing patterns.

[0005] The Patent Application No. US2018336488A1 entitled “Machine Learning Based Family Relationship Inference” discloses systems, methods, and techniques for classifying relationships between people (e.g., users of a platform or ecosystem) based on relationship data. In an example, the relationship data can be provided as input into a two-layer classification framework in which the first layer acts a filter for the second layer. The framework can identify relationships such as a self- relationship (e.g., two different accounts on the platform are operated by the same person), a non-self, family-member relationship (e.g., two users are different people but part of the same family), and a non-family-member relationship (e.g., the two users are different people and not part of the same family, such as coworkers or roommates).

[0006] The Patent Application No. US201313910890 entitled “Determining family connections of individuals in a database” discloses a method for determining relative connections between individuals, wherein the method includes: obtaining identification information of a first individual and identification information of a second individual; determining, based at least in part on a relative connections graph, a relative connections path connecting the first individual, the second individual, and at least one additional individual; and outputting information pertaining to the relative connections path.

[0007] The Patent Application No. US2015178373A1 entitled “Mapping relationships using electronic communications data” discloses a system where a pairwise relationship data set with multiple attributes (such as, who, what, when, where, how) and with the what attribute (also called the topic attribute) having aInternal Ref: OR25C066PCT07 word dimension and a people dimension. The data in the topic dimension of the what attribute relates to topics (including other people) relating to the specific, human, personal relationship between the first person and the second person of the pairwise pair. The what attribute data is derived by processing basis data, which includes correspondence data (that is, the substance of correspondence that the first and second persons participate in, including instant messaging and e-mail exchanges. Pairwise relationship data is displayed to a user in real time during a chat session.

[0008] Hence, there is a need for a method to recursively analyze and predict the relationship dynamics based on the browsing behavior of the users within a family / community in different geographical locations and time periods Summary of the invention

[0009] The present invention discloses a system and a method for analyzing and predicting the relationship dynamics between the users within a user group (family or community) from their browsing behavior wherein, the system facilitates understanding of relationships among the first user and other users related to the first user in the user group, in correlation with their geographical location and factors influencing the behaviors of the users. The system comprises a profiling unit for analyzing and profiling the browsing behavior of the first user in the user group. The system further comprises a processing unit to process the data received from the profiling unit to determine the relationship correlation of the browsing behavior of the first user and other users related to the first user in the user group.

[0010] The system further comprises a mapping unit to facilitate creation of a relationship correlation map using location-based parameters. Further, an analysis unit uses the relationship correlation map created by the mapping unit with respect to time frames. The mapping unit creates a relationship location correlation map depending on the similarities in the behavior of plurality of user groups.

[0011] The present invention discloses a method for predicting the relationship dynamics between plurality of users at different geographical locations and inInternal Ref: OR25C066PCT07 different contexts, wherein the method comprises the steps of collecting the browsing data of the first user within a user group to determine the browsing behavior by the profiling unit, wherein the browsing behavior data is further processed by the processing unit. The processing unit processes the browsing behavior data to corelate the derived browsing behavior of the first user with the browsing behavior of other users in the user group and the correlation is carried out against all the users in the user group. Further, the processing unit processes the relationship correlation data of the browsing behavior of all the users within the user group.

[0012] A mapping unit uses the relationship correlation data of the first user and other users in the user group to create a relationship correlation map. The analysis unit uses the relationship correlation map to determine the similarities in the behavior of the first user with other users in the same geographical location with respect to the time frame, identities (IP address, device IDs, social media mentions, etc.), as well as the context. The analysis unit further determines if the behavior is similar in other user groups in the geographical location of the first user. The mapping unit further uses the data from the analysis unit to create a relationship- location correlation map, wherein the relationship data of various user group in a geographical location are mapped. The mapped data helps in understanding the relationship between plurality of users within the user group in correlation with their geographical location.

[0013] The present invention is advantageous as it facilitates mapping of various location-based parameters of various generations of users that influence the thoughts and behavior of each user in the user group. The system facilitates understanding of the differences in parenting styles and the familial relationship dynamics between all the users in the family of each location and the different social, economic and political factors influencing these. Further, the system facilitates understanding different generations of users in the user group and the influence of location-based factors in varying the development of the generations and their relationship dynamics.Internal Ref: OR25C066PCT07 Brief description of the drawings

[0014] The foregoing and other features of embodiments will become more apparent from the following detailed description of embodiments when read in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements.

[0015] Figure 1 illustrates a block diagram representation of the system for predicting the relationship dynamics based on the browsing pattern.

[0016] Figure 2 illustrates a flow diagram for the method for determination of the predicting the relationship dynamics based on the browsing pattern. Detailed description of the invention

[0017] Reference will now be made in detail to the description of the present subject matter, which is shown in the illustrations. Various changes and modifications obvious to one skilled in the art to which the invention pertains are deemed to be within the spirit, scope, and contemplation of the invention.

[0018] The terminology used in the description presented herein is not intended to be interpreted in any limited or restrictive way, simply because it is being utilized in conjunction with detailed description of certain specific embodiments of the invention. The term ‘user group’ may be a group of users located in a geographical location, wherein the users may / may not be biologically related to one another. The ‘user group’ may include family members, friends, colleagues, acquaintances and so on.

[0019] The present invention discloses a system and a method for predicting the relationship dynamics between the users within a user group from their browsing behavior. The system enables understanding the relationship between the first user and other users related to the first user in the user group, in correlation with their geographical location and factors influencing the behaviors of the users.Internal Ref: OR25C066PCT07

[0020] Figure 1 illustrates a block diagram representation of the system for predicting the relationship dynamics using the browsing behavior, wherein the system (100) comprises a profiling unit (101) for analyzing and profiling the browsing behavior of the first user in the user group. The profiling unit (101) collects and profiles the distinctive browsing data of the first user and others users in the user group in order to create a user profile and to facilitate determination of the relationship influence on all the users in the user group based on the location- based factors.

[0021] The system (100) comprises a processing unit (102) to determine the relationship correlation of the browsing behavior of the first user and other users in the user group, by processing the profiled browsing behavior data. According to an embodiment of the invention, the processing unit (102) uses deep learning algorithms for data processing. The system (100) further comprises a mapping unit (103) to facilitate creation of a relationship correlation map and relationship- location correlation map using location-based parameters. The mapping unit (103) uses various location-based factors and parameters including ethnicity, education level, amenities, lifestyle, etc. and their impact on the relationship dynamics in the user group, according to an embodiment of the invention.

[0022] Further, the system (100) comprises an analysis unit (104), wherein the analysis unit (104) uses the relationship correlation map created by the mapping unit (103) for determining the similarities in the browsing behavior of the first user and other users related to the first user in the user group in a geographical location. Further, the mapping unit (103) generates a relationship-location correlation map depending on the similarities in the behavior of plurality of user groups.

[0023] In one embodiment of the invention, the system (100) uses deep learning techniques, reinforced machine learning and predictive analytics of the user profile and the browsing behavior to identify the relationship dynamics between the user within the user group. Further, the system (100) uses statistical analysis, semantic correlation and sentimental analysis for analyzing the browsing behavior of the user and mapping the data. The system (100) collects the browsing pattern data from atInternal Ref: OR25C066PCT07 least one non-intrusive data capturing applications and devices, according to one embodiment.

[0024] Figure 2 illustrates a flow diagram of the method for predicting the relationship dynamics using the browsing behavior, wherein the method (200) comprises the steps of collecting the browsing data of the first user within the user group by the profiling unit (101) in order to determine the browsing behavior of the first user, in the step (201). The profiling unit (101) creates the profile for the first user by using the browsing data. Further, in the step (202), the processing unit (102) processes the data for correlating the browsing behavior of the first user with other users in the user group. The processing unit (102) processes the browsing behavior data to corelate the derived browsing behavior of the first user with the browsing behavior of other users in the user group. If there is no correlation found, then the processing unit (102) performs correlation against all the users in the user group, in the step (203), and directs the profiling unit (101) to collect more browsing data of the users, in the step (204). Similarly, in case of partial correlation of the browsing behavior data, the processing unit (102) prompts the profiling unit (101) for further data collection, in the step (205).

[0025] Subsequently, upon determining the correlation of browsing behavior of the first user with all the users in the user group, the processing unit (102) further processes the relationship correlation data in order to determine the relationship of the first user and other users in the user group based on their browsing behavior, in the step (206). The mapping unit (103) uses the relationship correlation data of the first user and other users in the user group to create a relationship correlation map, in the step (207).

[0026] Further, the analysis unit (104) uses the relationship correlation map to determine the similarities in the behavior of the first user with other users in the same geographical location, in the step (208). The analysis unit (104) further determines if the user behavior is similar in other user groups in the geographical location of the first user, in the step (209). Subsequently, in case of no similarities in the behavior, the analysis unit (104) studies the relationship correlation mapsInternal Ref: OR25C066PCT07 with geographical locations of similar characteristics, in the step (210). Upon identifying partial correlation, the analysis unit (104) prompts the profiling unit for further data collection, in the step (212).

[0027] Further, upon deriving no correlation in behavior, the analysis unit (104) stores the data for future analysis, in the step (213). Subsequently, upon deriving partial similarities in the behavior, the analysis unit (104) further studies other relationship correlation maps to determine the similarities in the browsing behavior, in the step (214). Further, upon identifying the correlation by the analysis unit (104) in the steps (209) and (211), the mapping unit (103) creates a relationship-location correlation map, wherein the relationship data of various user groups in a geographical location are mapped, in the step (215). The mapped data helps in understanding the relationship between plurality of users within the user group in correlation with their geographical location. According to an embodiment of the invention, the method (200) facilitates prediction of relationship dynamics in the relationships including but not limited to family relationships, friendships, work relationships, and community or group relationships.

[0028] The present invention provides a system (100) and method (200) for understanding the relationships between plurality of users within the user group, in correlation with their locations and factors influencing the behaviors of the users. The system (100) facilitates understanding the various location-based factors and their impact on the relationship dynamics of plurality of users in the user group. Further, the system (100) enables collection of distinctive browsing data of all the users in the user group and facilitates determination of the influence of their relationship on other users, based on the geographical location factors.

[0029] Further, the system (100) facilitates mapping of various location-based parameters of various generations that influence the thoughts and behavior of each user in the user group. The system (100) enables understanding the differences in the parenting styles and the relationship dynamics between the users in the user group in various geographical locations, along with the social, economic and political factors influencing the relationship dynamics. Further, the system (100)Internal Ref: OR25C066PCT07 facilitates understanding different generations in the user groups and the influence of location-based factors in varying the development of the generations and their relationship dynamics.

[0030] For example, consider a first user in a geographical location “A” browsing through various webpages, wherein the browsing data of the user is collected to interpret the user behavior and create the user profile by the profiling unit (101). The system (100) processes the user’s browsing behavior data to corelate with other relationship behaviors. Upon identifying the correlation, the data is further processed by the processing unit (102) to determine the relationship correlation of the browsing behavior with all the users in the family, and to create a relationship correlation map by the mapping unit (103). The analysis unit (104) determines if the map has similar behavior in the same geographical location as the first user. Upon determining that the majority of the families in the geographical location behave in the similar manner, the analysis unit (104) directs the mapping unit (103) to create a relationship-location correlation map for the family of the first user in the geographical location “A” Reference numbers Components Reference Numbers System 100 Profiling unit 101 Processing unit 102 Mapping unit 103 Analysis unit 104

Claims

Internal Ref: OR25C066PCT07 Claims I Claim:

1. A system for predicting relationship dynamics from the browsing behavior, the system (100) comprising: a. a profiling unit (101) for profiling the browsing behavior of a first user in a user group; b. a processing unit (102) for determining the relationship correlation of the browsing behavior of the first user and other users related to the first user in the user group using the profiled browsing behavior data; c. a mapping unit (103) for facilitating creation of a relationship correlation map using at least one location-based parameter; d. an analysis unit (104) for predicting the relationship dynamics between the first user and other users in the family in a geographical location by determining the similarities in the browsing behavior.

2. The system (100) as claimed in claim 1 wherein, the profiling unit (101) facilitates creation of the user profile from the browsing data of the first user.

3. A method for determination of the relationship dynamics using the browsing behavior, the method (200) comprising the steps of: a. collecting the browsing data of the first user by the profiling unit (101) and facilitating creation of profile for the first user by using the collected browsing data; b. processing the user profile by the processing unit (102) for correlating the browsing behavior of the first user with the browsing behavior of other users in the user group; c. corelating the browsing behavior of the first user with the browsing behavior of all the users in the user group by the processing unit (102); d. processing the relationship correlation data by the processing unit (102) in order to determine the relationship of the first user and other users in the user group based on their browsing behavior;Internal Ref: OR25C066PCT07 e. creating a relationship correlation map by the mapping unit (103), wherein the mapping unit (103) uses the relationship correlation data of the first user and other users in the user group; f. determining the similarities in the behavior of the first user with other users in the geographical location of the first user by the analysis unit (104) by using the relationship correlation map; g. determining if the user behavior is similar to the users in at least one user group in the geographical location of the first user by the analysis unit (104); h. creating a relationship-location correlation map by the mapping unit (103) upon identifying the correlation by the analysis unit (104), wherein the relationship-location correlation map facilitates understanding the relationship between plurality of users within a user group in correlation with their geographical location.

4. The method (200) as claimed in claim 3, the mapping unit (103) generates a relationship-location correlation map depending on the similarities in the behavior of plurality of user groups.

5. The method (200) as claimed in claim 3, wherein the analysis unit (104) facilitates determination similarities in the browsing behavior of the first user and other users in the user group using the relationship correlation map created by the mapping unit (103).

6. The method (200) as claimed in claim 3, wherein the analysis unit (104) evaluates at least one relationship correlation map in at least one geographical location of similar characteristics in case of difference in the behavior.

Images