A system and method for deriving relationships between one or more user profiles

Priority Claim:

[0001] This application claims priority from the provisional application numbered 202141059338 filed with Indian Patent Office, Chennai on 20 ^th December 2021 entitled “A system and method for deriving relationships between one or more user profiles " , the entirety of which is expressly incorporated herein by reference.

Preamble to the Description

[0002] The following specification describes the invention and the manner in which it is to be performed:

DESCRIPTION OF THE INVENTION

Technical field of the invention

[0003] The present invention relates to a system and method for deriving relationships between one or more user profiles using deep learning techniques.

Background of the invention

[0004] In this fast-growing digital world, the digital data is growing exponentially in different shapes, formats and sizes, and therefore it is very important to manage this large volume of data according to the needs of the organization. Big Data is the collection of huge amounts of digital raw data that is difficult to manage and analyze using traditional tools. The datasets may come from a wide range of sources, such as computer systems, mobile devices, card transactions, and transportation systems. Further, due to the popularity of social online media companies such as YouTube, Twitter and Facebook, a huge amount of data is generated by billions of users. However, this bulk of information cannot be managed by conventional tools. Therefore, different organizations have developed various products/technologies by using Big Data Analytics for experimentation, simulations, data analysis, monitoring and many more business needs, which makes it an important topic of data science.

[0005] However, the existing big data analytics do not comprehend the correlation between two different online user’s profiles. Further, correlating relationships between two different online user profiles will help service providers to target potential buyer/influencer within a community. Thus, there exists a need for a system and method for deriving relationships between one or more user profiles.

Summary of the invention

[0006] The present invention overcomes the drawbacks of the prior art by disclosing a system for deriving relationships between one or more user profiles, wherein the system comprises a data acquisition unit for collecting user data of one or more users from one or more web applications and services. Further, the system comprises a processor unit and a memory unit, wherein the memory unit is coupled to the processor unit for storing the processor unit executable instructions, which, on execution by the processor unit, causes the processor unit to collect user data of one or more users from one or more web applications and services by the data acquisition unit and corelate relationship between one or more attributes of user’s profiles to identify potential influencers both negative and positive within a community using the collected user data associated with the one or more users.

[0007] The present invention discloses a method for deriving relationships between one or more user profiles, wherein the method comprises the steps of: collecting user data of one or more users from one or more web applications and services by a data acquisition unit. Further, relationships between one or more attributes of the user profiles are semantically correlated. Furthermore, the collected user data is clustered in a correlation bucket for identifying potential influencers both negative and positive within a community using the details present in the correlation bucket.

[0008] The present invention analyses the behavior of online users. The present invention aims to uncover correlations between two or more user attributes. Furthermore, the present invention aids in determining the impact of a relationship on the purchasing behavior of users in a community. Furthermore, the present invention aims to comprehend a community holistically and discover community influencers through relationship correlation.

Brief Description of drawings

[0009] Figure 1 illustrates a system for deriving relationships between one or more user profiles, in accordance with one embodiment of the present invention.

[0010] Figure 2 illustrates a flowchart of a method for deriving relationships between one or more user profiles, in accordance with one embodiment of the present invention.

[0011] Figure 3 illustrates a flowchart of the method for establishing correlation between one or more user profiles, in accordance with one embodiment of the present invention.

[0012] Figure 4 illustrates a diagram for predefined format of representing correlation parameters, in accordance with one embodiment of the present invention.

Detailed description of the invention

[0013] In order to more clearly and concisely describe and point out the subject matter of the claimed invention, the following definitions are provided for specific terms, which are used in the following written description.

[0014] The invention relates to a system and method for deriving relationships between one or more user profiles. The system is configured to collect user data of one or more users from one or more web applications and services. The system applies deep learning techniques, semantical and sentimental analysis, and artificial intelligence algorithms on the collected user data to correlate relationship between one or more attributes of user profiles to identify potential buyer within a community.

[0015] Figure 1 illustrates a system for deriving relationships between one or more user profiles, in accordance with one embodiment of the present invention.

[0016] As exemplarily illustrated in Figure 1, the system (100) is configured to collect user data of one or more users from one or more web applications and services. In an embodiment, the user data is collected from one or more online social media platforms. In an embodiment, the user data may include profile data of one or more users. In another embodiment, the user data may include various attributes associated with the user such as buying behavior pattern of one or more users from online shopping portals. Further, the system (100) is configured to semantically correlate the relationship between one or more attributes of the user profiles. More particularly, the system is configured to apply deep learning techniques, semantical and sentimental analysis, and artificial intelligence algorithms on the collected user data to correlate relationship between one or more user profiles.

[0017] In an embodiment the system (100) is configured to cluster the collected user data comprising profile data of the one or more user and one or more attributes associated with profile of the one or more user in a correlation bucket, where a correlation between two or more attributes of the user profile is established. Furthermore, the system (100) uses the details present in the correlation bucket to identify potential influencers both negative and positive within a community.

[0018] In an embodiment, the system (100) uses non-intrusive data capture applications and devices to collect user data of one or more users from one or more web applications and services.

[0019] In an embodiment, the system (100) of the present invention is implemented in an electronic device comprising memory unit (103) and processor unit (102). The memory unit (103) may store instructions that, when executed by the processor unit (102), cause the processor unit (102) to collect user data of one or more users from one or more web applications and services by the data acquisition unit (101) and corelate relationship between one or more attributes associated with profiles of the one or more user to identify potential influencers both negative and positive within a community using the collected user data of one or more users.

[0020] The memory unit (103) may be a non-volatile memory or a volatile memory. Examples of non-volatile memory may include, but are not limited to a flash memory, a Read-Only Memory (ROM), a Programmable ROM (PROM), Erasable PROM (EPROM), and Electrically EPROM (EEPROM) memory. Examples of volatile memory may include but are not limited to Dynamic Random-Access Memory (DRAM), and Static Random- Access memory (SRAM). The memory unit (103) may also store various data that may be captured, processed, and/or required by the system.

[0021] The processor unit (102) may include suitable logic, circuitry, interfaces, and/or code that may be configured to identify potential influencers both negative and positive within a community. The processor unit (102) may be implemented based on a number of processor technologies, which may be known to one ordinarily skilled in the art. Examples of implementations of the processor unit (102) may be a Graphics Processing Unit (GPU), a Reduced Instruction Set Computing (RISC) processor, an Application-Specific Integrated Circuit (ASIC) processor, a Complex Instruction Set Computing (CISC) processor, a microcontroller, Artificial Intelligence (Al) accelerator chips, a co-processor, a central processing unit (CPU), and/or a combination thereof.

[0022] Figure 2 illustrates a flowchart of a method for deriving relationships between one or more user profiles, in accordance with one embodiment of the present invention. The method for deriving relationships between one or more user profiles comprises the steps of collecting user data of one or more users from one or more web applications and services at step 201. In an embodiment, the user data comprises profile of the one or more user and one or more attributes associated with the profile of the user. The method at step 202 semantically correlates relationship between two or more attributes associated with one or more user profiles. More particularly the method is configured to apply deep learning techniques, semantical and sentimental analysis, and artificial intelligence algorithms on the collected user data to correlate relationship between one or more attributes associated with one or more user profiles. At step 203, the method clusters the collected user data in a correlation bucket where a correlation between one or more profile data of the users is established.

[0023] The method at step 204, uses the details present in the correlation bucket to identify potential influencers both negative and positive within a community.

[0024] Figure 3 illustrates a flowchart of the method for establishing correlation between one or more user profiles, in accordance with one embodiment of the present invention. The method for establishing correlation between one or more user profiles comprises the steps of collecting user data of one or more users from one or more web applications and services such as Facebook, Amazon, Flipkart, and the like at step 301. In an embodiment, the user data is collected by the data acquisition unit (101) of the system (100). The user data is collected using gamification learning theory.

[0025] In an embodiment, gamification for learning is about applying gaming strategies to improve learning and make it more engaging for individuals. Gamification for learning is beneficial because games instill lifelong skills such as problem-solving, critical thinking, social awareness, cooperation, and collaboration. Games also motivate individuals, increase interest in certain subjects, reduce the rate of attrition among learners, improve grades, and enhance the cognitive abilities of the learners.

[0026] In an embodiment, the user data comprises profile data of the one or more user, browsing data associated with the one or user, attributable data such as the buying pattern of the one or more user.

[0027] At step 302, deep learning techniques, semantical and sentimental analysis, and artificial intelligence algorithms are applied on the collected user data of the users to correlate relationship between one or more attributes of the one or more user profiles to identify potential buyer within the community. In an embodiment, the user data comprises profile data and attributable data of the user such as buying behavior pattern of the one or more users in the community. At step 303, the system (100) may be configured to establish correlation between the one or more attributes of the user profile, or the system (100) may create a group preference profile in the correlation bucket by merging consistent patterns associated with the preferred profiles for the one or more users in the community, or the system (100) may store all the relevant data for later analysis based on the preference of the user. At step 304, the correlated parameters are depicted in the predefined format as shown in Figure 4.

[0028] The present invention provides the analysis of behavior of online users. The present system (100) aims at revealing correlations between two or more attributes of the users. Further, the present invention helps in knowing the influence of the relationship in buying behavior of users in a community. Furthermore, the present invention aims at understanding a community in a holistic manner and identifying the influencers within a community through relationship correlation.