Description:TECHNICAL FIELD
The present disclosure relates to methods for providing personalized metaverse experiences in metaverses. The present disclosure also relates to systems for providing personalized metaverse experiences in metaverses.
BACKGROUND
With technological advancements, metaverse has become increasingly popular in various fields such as entertainment, real estate, training, simulators, navigation, and the like. In general, the metaverse can be understood as a universe being created on the internet by utilizing, for example, extended-reality (XR) technologies, blockchain technologies, and the like. Thus, users can interact in three-dimensional (3D) virtual environments of the metaverse realistically and immersively, in real time or near-real time. Several real-world activities (such as social interaction, travelling, playing sports, shopping, and the like) can be carried out virtually in the metaverse. The metaverse can also be personalized with respect to a particular user, wherein the metaverse enables creation of an XR environment for the user based on information provided by the user, for example, using a user device. Such information can, for example, be personal information of the user, interests of the user, and the like.
However, the existing technologies for providing personalized metaverse experience in the metaverse are associated with certain limitations and complications. The existing technologies for creating a personalized metaverse require the user to select and customize each object individually in the metaverse, according to his/her preferences or interests. This is extremely laborious and time consuming for the user, and the user may eventually lose his/her interest in joining and interacting in the personalized metaverse. Furthermore, each time the user wants to join and interact with the personalized metaverse, same or similar inputs from the user are repetitively required by some existing technologies for creating the personalized metaverse. In such a case, this repetitive provisioning of input is considerably tedious and time consuming for the user. Moreover, sometimes even after providing requisite inputs, the personalized metaverse is inappropriately and inaccurately created. Some existing technologies provide personalized metaverse experience by recommending different personalisation options to the user. This is again effort-intensive and time-consuming for the user, as he/she has to respond by either accepting or rejecting the different personalisation options. Resultantly, this lowers user's experience and interest in joining and interacting in the metaverse.
Therefore, in the light of foregoing discussion, there exists a need to overcome the aforementioned drawbacks associated with the existing technologies for providing personalized metaverse experiences in the metaverse.
SUMMARY
The present disclosure seeks to provide a method for providing a personalized metaverse experience in a metaverse. The present disclosure also seeks to provide a system for providing a personalized metaverse experience in a metaverse. An aim of the present disclosure is to provide a solution that overcomes at least partially the problems encountered in prior art.
In a first aspect, an embodiment of the present disclosure provides a method for providing a personalized metaverse experience in a metaverse, the method comprising:
- receiving historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse;
- employing a machine learning model to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users;
- presenting personalized content in the metaverse, for each of the plurality of clusters;
- receiving present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse;
- employing the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data;
- determining whether any probability amongst the probabilities exceeds a predetermined threshold; and
- when it is determined that any probability amongst the probabilities exceeds the predetermined threshold, assigning the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
Optionally, the method further comprises:
- when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, collecting additional personal data and additional interaction data associated with the new user;
- employing the machine learning model for predicting updated probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the additional personal data and the additional interaction data;
- determining whether any probability amongst the updated probabilities exceeds the predetermined threshold; and
- when it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold, assigning the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
Optionally, when it is determined that any probability amongst the updated probabilities does not exceed the predetermined threshold, the method further comprises repeating the steps of employing the machine learning model for predicting the updated probabilities and determining whether the given probability amongst the updated probabilities exceeds the predetermined threshold until it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold.
Optionally, in the method, the step of employing the machine learning model to identify the plurality of clusters comprises utilizing a clustering algorithm for dividing the plurality of users into the plurality of clusters according to the historical personal data and the historical interaction data.
Optionally, in the method, the step of presenting personalized content in the metaverse, comprises digitally manipulating at least one space associated with each cluster, by at least one of: placing objects selected by at least some users of said cluster, adjusting a type and/or a characteristic of objects as selected by at least some users of said cluster, applying a theme that is selected by at least some users of said cluster, applying an environmental effect that is selected by at least some users of said cluster, applying a mood that is selected by at least some users of said cluster, adding locations visited by at least some users of said cluster.
Optionally, a given personal data comprises at least one of: a real-world location, an age, a gender, device information, a relationship status, an occupation, a contact list, of a given user.
Optionally, a given interaction data comprises at least one of: an appearance of an avatar, a location visited in the metaverse, time spent at a location visited in the metaverse, a theme that is selected, an environmental effect that is selected, a mood that is selected, a type and/or a characteristic of an object that is selected, a placement of objects, similarity of selections with other users, of/by a given user.
Optionally, the predetermined threshold lies in a range of 0.7 to 0.8.
Optionally, the specifications of the given cluster comprise at least one of: a centroid of the given cluster, a location of the given cluster in the metaverse, size of the given cluster, objects placed in a space associated with the given cluster.
In a second aspect, an embodiment of the present disclosure provides a system for providing a personalized metaverse experience in a metaverse, the system comprising at least one processor configured to:
- receive historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse;
- employ a machine learning model to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users;
- present personalized content in the metaverse, for each of the plurality of clusters;
- receive present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse;
- employ the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data;
- determine whether any probability amongst the probabilities exceeds a predetermined threshold; and
- when it is determined that any probability amongst the probabilities exceeds the predetermined threshold, assign the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
Optionally, the at least one processor is further configured to:
- when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, collect additional personal data and additional interaction data associated with the new user;
- employ the machine learning model for predicting updated probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the additional personal data and the additional interaction data;
- determine whether any probability amongst the updated probabilities exceeds the predetermined threshold; and
- when it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold, assign the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
Optionally, when it is determined that any probability amongst the updated probabilities does not exceed the predetermined threshold, the at least one processor is further configured to repeatedly employ the machine learning model for predicting the updated probabilities and determine whether the given probability amongst the updated probabilities exceeds the predetermined threshold until it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold.
Optionally, when employing the machine learning model to identify the plurality of clusters, the at least one processor is configured to utilize a clustering algorithm for dividing the plurality of users into the plurality of clusters according to the historical personal data and the historical interaction data.
Optionally, when presenting personalized content in the metaverse, the at least one processor is configured to digitally manipulate at least one space associated with each cluster, by at least one of: placing objects selected by at least some users of said cluster, adjusting a type and/or a characteristic of objects as selected by at least some users of said cluster, applying a theme that is selected by at least some users of said cluster, applying an environmental effect that is selected by at least some users of said cluster, applying a mood that is selected by at least some users of said cluster, adding locations visited by at least some users of said cluster.
Optionally, in the system, a given personal data comprises at least one of: a real-world location, an age, a gender, device information, a relationship status, an occupation, a contact list, of a given user.
Optionally, in the system, a given interaction data comprises at least one of: an appearance of an avatar, a location visited in the metaverse, time spent at a location visited in the metaverse, a theme that is selected, an environmental effect that is selected, a mood that is selected, a type and/or a characteristic of an object that is selected, a placement of objects, similarity of selections with other users, of/by a given user.
Optionally, in the system, the predetermined threshold lies in a range of 0.7 to 0.8.
Optionally, in the system, the specifications of the given cluster comprise at least one of: a centroid of the given cluster, a location of the given cluster in the metaverse, a size the given cluster, objects placed in a space associated with the given cluster.
Optionally, the system further comprises a data repository communicably coupled to the at least one processor, wherein the at least one processor is configured to store, at the data repository, at least one of: the historical personal data and the historical interaction data, the present personal data and the present interaction data, information indicative of the plurality of clusters and of the one or more users in each of the plurality of clusters, information indicative of the given cluster to which the new user is assigned, specifications of the plurality of clusters.
Embodiments of the present disclosure substantially eliminate or at least partially address the aforementioned problems in the prior art, and enable assignment of the new user into a cluster for which the personalised content is already available in the metaverse, thereby minimizing time and efforts for customising each object individually according to the new user.
Additional aspects, advantages, features and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments construed in conjunction with the appended claims that follow.
It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.
BRIEF DESCRIPTION OF THE DRAWINGS
The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those skilled in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.
Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein:
FIGs. 1A and 1B illustrate steps of a method for providing a personalized metaverse experience in a metaverse, in accordance with an embodiment of the present disclosure;
FIG. 2 illustrates a block diagram of an architecture of a system for providing a personalized metaverse experience in a metaverse, in accordance with an embodiment of the present disclosure;
FIG. 3 illustrates exemplary clusters that are identified by a machine learning model, in accordance with an embodiment of the present disclosure; and
FIG. 4A illustrates an exemplary layout of a metaverse representing a shopping and entertainment complex, while FIG. 4B illustrates an exemplary schematic illustration of personalized content present in a region of the shopping and entertainment complex, in accordance with an embodiment of the present disclosure.
In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.
DETAILED DESCRIPTION
The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practising the present disclosure are also possible.
The present disclosure provides a method and a system for providing a personalized metaverse experience in a metaverse. Herein, a new user is assigned to a cluster for which personalized content is already present in the metaverse. The system enables in automatically recommending content preferences for a personalized metaverse experience of the new user, based on historical interactions, behavior, preferences of users in other metaverses. Such a manner of providing the personalized metaverse experience is relatively simple and time-efficient as the new user need not select and customize each object individually in the metaverse, according to his/her preferences or interests. Thus, interest of users in joining the metaverse is not compromised, and user's experience in the metaverse is highly realistic and immersive. Moreover, the personalised content present in the cluster is highly relevant and is conveniently available to the new user, thus the new user need not check and respond to (i.e., either accept or reject) any personalisation options. This potentially improves the user's experience and increases the user's interest in joining and interacting in the metaverse. The method and the system are simple, robust, support in providing real-time personalized metaverse experience, and can be implemented with ease.
Referring to FIGs. 1A and 1B, illustrated are steps of a method for providing a personalized metaverse experience in a metaverse, in accordance with an embodiment of the present disclosure. At step 102, there are received historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse. At step 104, a machine learning model is employed to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users. At step 106, personalized content is presented in the metaverse, for each of the plurality of clusters. At step 108, there are received present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse. At step 110, the machine learning model is employed for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data. At step 112, it is determined whether any probability amongst the probabilities exceeds a predetermined threshold. When it is determined that any probability amongst the probabilities exceeds the predetermined threshold, at step 114, the new user is assigned to a given cluster corresponding to said probability and specifications of the given cluster are updated. Otherwise, when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, optionally, at step 116, additional information is collected (for example, from the user) and processed for assigning the new user to the given cluster.
The aforementioned steps are only illustrative and other alternatives can also be provided where one or more steps are added, one or more steps are removed, or one or more steps are provided in a different sequence without departing from the scope of the claims herein. Each of these steps is described later in more detail.
Referring to FIG. 2, illustrated is a block diagram of an architecture of a system 200 for providing a personalized metaverse experience in a metaverse, in accordance with an embodiment of the present disclosure. The system 200 comprises at least one processor (depicted as a processor 202). Optionally, the system 200 further comprises a data repository 204 communicably coupled to the at least one processor 202. The at least one processor 202 is configured to:
- receive historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse;
- employ a machine learning model to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users;
- present personalized content in the metaverse, for each of the plurality of clusters;
- receive present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse;
- employ the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data;
- determine whether any probability amongst the probabilities exceeds a predetermined threshold; and
- when it is determined that any probability amongst the probabilities exceeds the predetermined threshold, assign the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
It may be understood by a person skilled in the art that the FIG. 2 includes a simplified architecture of the system 200 for sake of clarity, which should not unduly limit the scope of the claims herein. It is to be understood that the specific implementation of the system 200 is provided as an example, and is not to be construed as limiting it to specific numbers or types of processors and/or data repositories. The person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure.
Throughout the present disclosure, the term "metaverse" refers to a digital universe (namely, virtual world) that is created by utilizing, for example, one or more of extended-reality (XR) technologies, blockchain technologies, Web3 technologies, and the like. The term "extended-reality" encompasses virtual reality (VR), augmented reality (AR), mixed reality (MR), and the like. In the metaverse, there could be several different three-dimensional (3D) XR environments. A given XR environment of the metaverse is presented to a given user, for example, by way of an XR device. The XR device could, for example, be a head-mounted display (HMD) device, a pair of XR glasses, an XR console, and the like. The given user uses the XR device to access and to interact in the metaverse. When the given user is present in the metaverse, different real-world activities (such as social interaction, travelling, playing sports, shopping, and the like) can be done virtually by the given user. The metaverse is well-known in the art.
Throughout the present disclosure, the term "personalized metaverse experience" refers to a virtual experience in the metaverse that is customized (i.e., designed) according to an individual user's requirements, preferences, and/or interests. Such a personalized metaverse experience can be created, for example, such as for gaming, social networking, education, entertainment, and the like. Generally, the metaverse enables creation of an XR environment for the given user, based on information provided by the given user, for example, using a user device. Such information can, for example, be personal information of the given user, interests of the given user, an avatar appearance of the given user, and the like. The user device could, for example, be a laptop, a desktop, a tablet, a phablet, a personal digital assistant, a cellphone, and the like.
Throughout the present disclosure, the term "personal data" associated with the given user refers to any information that is related to (and is indicative of a personality of) the given user. Throughout the present disclosure, the term "historical personal data" associated with the given user refers to personal data of the given user when he/she previously joined and interacted with the metaverse. In this regard, the historical personal data is already available to the at least one processor 202 based on past visits of the given user in the metaverse. It will be appreciated that the term "given personal data" encompasses at least historical personal data associated with the given user.
Optionally, a given personal data comprises at least one of: a real-world location, an age, a gender, device information, a relationship status, an occupation, a contact list, of a given user. The real-world location could be a geographical location of the given user, such as an address of the given user. Real-world locations of the plurality of users could, for example, be useful for determining which users amongst the plurality of users belong to a same geographical location, and then subsequently said users could be included to a same cluster. Similarly, ages and/or genders of the plurality of users could be useful for determining which users amongst the plurality of users belong to a same age group and/or a same gender category. This may facilitate in including said users to a same cluster. The device information could, for example, be a type of a device used by the given user, a specification of the device, and the like. In an example, devices associated with some users amongst the plurality of users may have a same operating system. Thus, said users could be included in a same cluster. Such a cluster may present device-specific digital representations (for example, specific operating system-related digital features) in a space associated with said cluster.
Furthermore, the relationship status could, for example, be 'married', 'single', 'engaged', 'separated', 'divorced', and the like. The relationship statuses of the plurality of users could be useful for creating dating experiences, matchmaking experiences, community self-help group experiences (for example, for divorced users), and the like, in the metaverse. The occupation of the given user could, for example, be an artist, a business analyst, a defence personnel, a designer, an entrepreneur, a social worker, and the like. Occupations of the plurality of users could be useful for creating occupational experiences, well-being experiences for certain occupations (for example, experiences to deal with post-traumatic stress disorder (PTSD) for defence personnel, healthcare professionals, and similar), and the like, in the metaverse. The contact list of the given user may include at least one of: names, contact numbers, email addresses, relation, of persons acquainted with or related to the given user. The contact list of the given user could be useful for providing shared experiences to family, friends, colleagues, and the like, of the given user.
Throughout the present disclosure, the term "interaction data" associated with the given user refers to information pertaining to how the given user interacts with and behaves in the metaverse. Throughout the present disclosure, the term "historical interaction data" associated with the given user refers to interaction data of the given user when he/she previously joined and interacted with the metaverse. In this regard, the historical interaction data is already available to the at least one processor 202 based on past visits of the given user in the metaverse. It will be appreciated that the term "given interaction data" encompasses at least historical interaction data associated with the given user. It will also be appreciated that the historical personal data and the historical interaction data can be received by the at least one processor 202 from the data repository 204 which receives the historical personal data and the historical interaction data from a user device associated with the given user (or optionally, directly from the user device associated with the given user).
Optionally, a given interaction data comprises at least one of: an appearance of an avatar, a location visited in the metaverse, time spent at a location visited in the metaverse, a theme that is selected, an environmental effect that is selected, a mood that is selected, a type and/or a characteristic of an object that is selected, a placement of objects, similarity of selections with other users, of/by a given user. Herein, the term "avatar" refers to a digital representation of the user in the metaverse. The avatar of the given user moves around in the metaverse for interaction. In general, the appearance of the avatar of the given user may be similar to or different than an appearance of the given user in his/her real life. However, the given user can customize the appearance of his/her avatar according to his/her requirements or choice, for example, by modifying clothing, facial features/expressions, body sizes, and the like, of the avatar. Users whose avatars have similar appearances (for example, similar hair colour, similar dress types, and the like) may have a higher probability of being included into a same cluster, as compared to users whose avatars are considerably different.
Moreover, knowing locations in the metaverse which have been frequently visited by considerable number of users (in the past interactions with the metaverse) could be useful for including said users into a same cluster. In other words, users having similar location preferences may have a higher probability of being included in the same cluster. Similarly, users who visited at a same location and spent considerable amount of time spent at the same location in the metaverse could be included into a same cluster. For example, some users may spend more time at a beach side location in the metaverse, as compared to a mountainous location in the metaverse, and such users may be included in the same cluster. The theme selected by the given user may, for example, be a dark theme, a light theme, or similar. Users having similar theme preferences may have a higher chance of being included in a same cluster.
The environmental effect may, for example, relate to a weather condition, a change of a season, a lighting situation, and similar. Such environmental effects may be presented using different lighting conditions in the metaverse, different sound effects in the metaverse, haptic effects (such as vibrations), different objects in the metaverse, and the like. In an example, users may experience a sunny day on a beach side location in the metaverse, a rainy weather on a hilly area in the metaverse, thunderstorms on a trek in the metaverse, or similar. The mood selected by the given user may, for example, be happy, sad, romantic, party, adventurous, and the like. Users having similar mood preferences may have a higher chance of being included in a same cluster. In an example, some users amongst the plurality of users may have a same mood, such as a party mood. Thus, said users could be included in a same cluster.
Furthermore, the object could be a car, a motorcycle, a truck, a pen, a bottle, a fighter jet, a bowling ball, a skiing stick, and the like. Characteristics of the objects could be their shapes, sizes, orientations, and the like. Users having similar preferences for certain objects or their placements in the metaverse have a higher chance of being included into a same cluster. There could also be similarity of selections of the given user with the other users i.e., a selection made by the given user (for example, selection of an object, a theme, a mood, and similar) may be similar to what the other users have selected. In such a case, the given user and the other users may be included in the same cluster.
Referring to FIG. 3, illustrated are exemplary clusters (depicted as clusters 302a, 302b, 302c, 302d, and 302e) identified by a machine learning model, in accordance with an embodiment of the present disclosure. The machine learning model identifies, for example, five clusters 302a-e, based on historical personal data and historical interaction data of 13 users. Out of the 13 users, five users are included into the cluster 302a, three users are included into the cluster 302b, two users are included into each of the clusters 302c and 302d, and one remaining user is included into the cluster 302e.
FIG. 3 is merely an example, which should not unduly limit the scope of the claims herein. The person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure. For sake of simplicity, only five clusters 302a-e are shown in FIG. 3, and only 13 users are shown to be divided into the five clusters 302a-e. In an example, the machine learning model may identity 25 different clusters, and may divide 200 users into said 25 different clusters. It will be appreciated that pursuant to embodiments of the present disclosure, various numbers of users can be divided into various numbers of clusters identified by the machine learning model.
Throughout the present disclosure, the term "cluster" refers to a set of one or more entities (for example, users) having similar preferences or interests. Notably, a given cluster 302a-e includes one or more users. Optionally, the historical personal data and the historical interaction data are analyzed by the machine learning model for identifying patterns in said data. In this regard, the machine learning model ascertains, for at least two users, how much similarity (namely, an overlap) is present in their respective historical personal data and respective historical interaction data, in order to include the at least two users in a given cluster 302a-e. When the respective historical personal data and historical interaction data are (considerably) similar, the at least two users are included in the given cluster 302a-e. In some implementations, there could be an exact match between the respective historical personal data and historical interaction data of the at least two users. In other words, for the at least two users, values of all attributes in the respective historical personal data and historical interaction data match exactly. In other implementations, only some attributes amongst attributes in the respective historical personal data and historical interaction data match for the at least two users. In an example, for the at least two users, values of 10 out of 20 attributes in the respective historical personal data match, and values of 8 out of 12 attributes in the respective historical interaction data match. It will be appreciated that when the machine learning model identifies that historical personal data and historical interaction data of a particular user is entirely unique (i.e., is not matching with historical personal data and historical interaction data of any other user amongst the plurality of users), the particular user is exclusively included in a separate cluster (for example, the cluster 302e).
Optionally, in the method, the step of employing the machine learning model to identify the plurality of clusters comprises utilizing a clustering algorithm for dividing the plurality of users into the plurality of clusters according to the historical personal data and the historical interaction data. In this regard, the plurality of users are divided into different clusters 302a-e such that each cluster includes the one or more users. Such a division is performed upon analyzing historical personal data and historical interaction data of the plurality of users, and then the users are included into the plurality of clusters 302a-e upon identifying patterns and similarities, as described earlier in detail. Optionally, the clustering algorithm is at least one of: a k-means clustering algorithm, a hierarchical clustering algorithm, a density-based clustering algorithm, an expectation-maximization clustering algorithm, a mean-shift clustering algorithm. The aforesaid clustering algorithms and their utilization by the machine learning model for identifying clusters are well-known in the art. It will be appreciated that a number of clusters to be identified by the machine learning model can either be user-defined or be system-defined.
Referring to FIG. 4A, illustrated is an exemplary layout of a metaverse representing a shopping and entertainment complex, while FIG. 4B illustrates an exemplary schematic illustration of personalized content present in a region of the shopping and entertainment complex, in accordance with an embodiment of the present disclosure. With reference to FIG. 4A, six different spaces 402a, 402b, 402c, 402d, 402e, and 402f associated different clusters are shown in the metaverse representing the shopping and entertainment complex. The six different spaces 402a-f are shown to have different shapes and sizes in the metaverse. In the shopping and entertainment complex, the space 402a represents a cosmetic shop, the space 402b represents a sports shop, the space 402c represents an XR gaming lounge, the space 402d represents an apparel shop, the space 402e represents a jewelry shop, and the space 402f represents a common area that can be accessed by any user of any cluster amongst the different clusters. Thus, the space 402f is a space associated with a cluster in which all users (of other clusters) are included. The space 402f may represent lifts, stairs, flooring, escalators, and the like.
With reference to FIG. 4B, as shown, the region of the shopping and entertainment complex comprises the cosmetic shop and the sports shop present in the spaces 402a and 402b, respectively. The cosmetic shop is shown to comprise objects such as, for example, a lamp, a mirror, a plurality of lights arranged around the mirror, a wall-mount storage box, and a table. The table has a make-up palette and other similar cosmetic items. The sports shop is shown to comprise objects such as, for example, a basketball ring, a football, a punching bag, a table. The table has a cricket ball, a basketball, a bat, and three wickets.
FIGs. 4A and 4B are merely examples, which should not unduly limit the scope of the claims herein. The person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure. As an example, in the space 402f, a gadget shop may be represented in a corner between the spaces 402a and 402b.
Throughout the present disclosure, the term "content" refers to computer-generated content (namely, digital content). Such computer-generated content could, for example, be visual content, audio content, audio-visual content, haptic content, and the like. The visual content can be in form of text, images, graphics, videos, and the like. The audio content can be in form of a sound effect, a soundtrack, a podcast, or similar. The haptic content can be in form of a vibration, a motion, or similar. It is to be understood that different personalized content are presented for different clusters. Optionally, the personalized content for each cluster is presented in at least one space in the metaverse associated with said cluster. Since different clusters would have different (3D) spaces 402a-f associated with them in the metaverse, in these different spaces 402a-f, the personalized content for the corresponding cluster is presented. One or more spaces 402a-f in the metaverse can be associated with a given cluster. Moreover, a single space 402a-f in the metaverse can be associated with multiple clusters.
In an example, a cluster of users who are interested in mountaineering (as indicated by their personal data and interaction data) may be arranged in a space representing a mountainous region in the metaverse. In another example, a cluster of users who are living in a same real-world region (for example, a same town or a same country) may be arranged in a space representing the same real-world region in the metaverse. In yet another example, a cluster of users who enjoy rock music and a cluster of users who are music critics may be arranged in a space representing a rock concert in the metaverse. In such an example, despite the different clusters being formed based on different personal attributes and different user interactions, the different clusters can be arranged in the space representing the rock concert since the rock concert may be of interest to users of both these clusters.
Optionally, the step of presenting personalized content in the metaverse, comprises digitally manipulating at least one space associated with each cluster, by at least one of: placing objects selected by at least some users of said cluster, adjusting a type and/or a characteristic of objects as selected by at least some users of said cluster, applying a theme that is selected by at least some users of said cluster, applying an environmental effect that is selected by at least some users of said cluster, applying a mood that is selected by at least some users of said cluster, adding locations visited by at least some users of said cluster. In this regard, the at least one space associated with each cluster is customized when at least one of the aforesaid operations are performed by the at least one processor 202. Optionally, when placing the objects selected by at least some users of said cluster, the at least one processor 202 is configured to digitally superimpose the selected objects in the at least one space. In this regard, the at least one processor 202 may employ at least one image processing algorithm. Image processing algorithms are well-known in the art. It will be appreciated that placement of the objects (or their parts) is performed accurately and realistically. In other words, said placement is performed (by the at least one processor) in a manner that (digitally-placed) objects appear to be well-aligned (namely, well-arranged or well-blended) with respect to geometries of existing objects or space in a cluster. As an example, an object to be placed on a slanted surface can be tilted accordingly during its placement on the slanted surface. As another example, an object (such as a virtual traffic light) can be placed on a vertical surface (such as a pole) in a manner that said object appears to be on the vertical surface, rather than appearing floating in front of the vertical surface. It will also be appreciated that when placing the objects in the at least one space, the at least one processor takes into account depth information, transparency information, surface geometry, lighting conditions, shadows, and the like.
Optionally, the type and/or the characteristic (such as a shape, a size, a colour, an operational state, a texture, a surface finish, and the like) of the objects can be modified (by the at least one processor 202) using image processing techniques, according to user's preferences, in the at least one space associated with each cluster. Optionally, the at least one processor digitally manipulates the at least one space by applying a particular theme in the at least one space. In an example, when a dark theme may be selected by at least some users of a cluster, the at least one processor 202 applies the dark theme to enable night mode in the at least one space of the cluster. Optionally, when applying the environmental effect, the at least one processor 202 may be configured to modify (namely, increase or decrease) lighting conditions, produce a sound effect, generate a haptic effect (such a vibration), or similar, in the at least one space associated with each cluster. Optionally, the at least one processor digitally manipulates the at least one space by applying a particular mood in the at least one space. In an example, when applying the mood, such as a party mood, in a cluster, the at least one processor 202 may, for example, generate digital representations of party-related accessories/objects, a disco theme, bright and colourful lighting, and the like, in the at least one space associated with said cluster. In another example, when applying the mood, such as a sad mood, in a cluster, the at least one processor 202 may, for example, apply soft and dark lighting, add an object representing a box of tissues, add an object representing self-help books, in the at least one space in said cluster. In such an example, the at least one space may be quiet and seclusive. Optionally, the at least one processor 202 generates digital representations of locations/places that are visited by at least some users of said cluster. In an example, a space associated with a cluster may represent a town that was visited by at least some users of said cluster. In such a case, the at least one processor may generate digital representations of places in the town that were visited by at least some users of said cluster. Such places could, for example, be a deli, shopping complexes, places of worship, places of transportation, places of entertainment, places of sightseeing, and the like. Optionally, the at least one processor is configured to digitally manipulate the at least one space associated with each cluster, by adding wishlisted locations (i.e., locations that are desired to be visited) of at least some users of said cluster. In an example, some users of said cluster may like to visit some common places in USA, such as Grand Canyon and Los Angeles. In such a case, digital representations of said common places can be added in the at least one space.
Notably, once the personalized content is presented in each cluster, the present personal data and the present interaction data associated with the new user is obtained by the at least one processor 202. Throughout the present disclosure, the term "present personal data" associated with the new user refers to personal data of the new user upon joining and interacting with the metaverse, and prior to being assigned to any cluster. Throughout the present disclosure, the term "present interaction data" associated with the new user refers to interaction data of the new user upon joining and interacting with the metaverse, and prior to being assigned to any cluster. The present interaction data interaction data is served as information pertaining to how the new user wants to interact with and behave in the metaverse. It will be appreciated that the present personal data and the present interaction data can be received by the at least one processor 202 from a user device associated with the new user (or optionally, from the data repository 204 which receives the present personal data and the present interaction data from the user device). It is to be understood that both the aforesaid data are not already available to the at least one processor 202, but are rather obtained in real time or near-real time, as the new user joins and interacts with the metaverse. It will be appreciated that both the aforesaid data are required to make a decision for assigning the new user to the given cluster. The aforesaid data is required for determining which cluster from amongst the plurality of clusters, is most relevant (i.e., most suitable) for the new user. A cluster is determined to be most relevant for the new user when historical personal data and historical interaction data of pre-existing users of that cluster matches the present personal data and the present interaction data of the new user.
Greater the extent of similarity (namely, the extent of matching) of attributes in the present personal data and the present interaction data of the new user with attributes in historical personal data and historical interaction data of users in a given cluster, greater is the probability of the new user belonging to the given cluster, or vice versa. Such an extent of similarity can be expressed as a percentage, or a fraction indicating a number of similar attributes between a first dataset (including the present personal data and the present interaction data) and a second dataset (including the historical personal data and the historical interaction data), divided by a total number of attributes in historical personal data and historical interaction data of users in the given cluster, or other similar ways. It will be appreciated that the machine learning model employs at least mathematical function for predicting the probability from the aforesaid extent of similarity. It will also be appreciated that when employing the machine learning model for predicting the probabilities, the machine learning model may utilize at least a classification algorithm (such as a logistic regression algorithm and a support vector machine (SVM) algorithm) and a regression algorithm (such as a linear regression and a random forest algorithm).
Once the probabilities are predicted, the at least one processor 202 is configured to compare each of the probabilities with the predetermined threshold. In this regard, a cluster corresponding to a given (predicted) probability that is greater than the predetermined threshold would be the one to which the new user is assigned. Optionally, when two or more probabilities from amongst the probabilities exceed the predetermined threshold, the at least one processor is configured to assign the given user to a cluster corresponding to a highest probability from amongst the two or more probabilities. Advantageously, in this way, assignment of the new user to the given cluster is performed in a time-efficient manner, thereby enabling the new user to be provided with a personalized experience of the metaverse quickly upon joining the metaverse. Moreover, an accuracy of such assignment is high, thereby enabling the personalized experience to be highly relevant and of interest to the new user. The new user need not select and customize each object individually for himself/herself in the metaverse, and he/she would simply be assigned to a cluster for which the personalized content would be already present in the metaverse.
Optionally, the predetermined threshold lies in a range of 0.7 to 0.8. More optionally, the predetermined threshold lies in a range of 0.725 to 0.775. Optionally, the predetermined threshold is 0.75. As an example, the predetermined threshold may lie from 0.7, 0.71, 0.73 or 0.75 up to 0.72, 0.74, 0.76, 0.78, 0.79 or 0.8. It will be appreciated that the predetermined threshold defines a minimum required probability for assigning the new user to the given cluster. Thus, the probability for assigning the user to the given cluster must be minimum 70 percent to 80 percent for assigning the new user to the given cluster. Therefore, any (predicted) probability greater than 80 percent would also be acceptable for assigning the new user to the given cluster.
In an example, extents of similarities of attributes in historical personal data and historical interaction data of users in 3 clusters C1, C2, and C3 with attributes in the present personal data and the present interaction data of the new user may be 70 percent, 30 percent, and 35 percent, respectively. In such a case, probabilities of the new user belonging to each of the 3 clusters C1-C3 could be 0.72, 0.12, 0.16, respectively. Thus, when the predetermined threshold is 0.7, the new user would be assigned to the cluster C1.
Optionally, the specifications of the given cluster comprise at least one of: a centroid of the given cluster, a location of the given cluster in the metaverse, a size the given cluster, objects placed in a space associated with the given cluster. In this regard, once the new user is assigned (namely, added) to the given cluster, the aforesaid specifications of the cluster in the metaverse would change. For example, the size of the cluster may increase when the new user and personalized content associated with the new user is added into a space of the given cluster. This may also result in a change of the centroid and the location of the given cluster. Thus, the given cluster is required to be updated. In an example, when the given cluster initially has 10 users, the size of the given cluster is 10 users. When the new user would be assigned (i.e., added) to the given cluster, the size of the given cluster would become 11 users.
Typically, a centroid of a cluster represents an average of said cluster. Such a centroid could be useful for understanding the cluster at a general level. Optionally the centroid of the given cluster comprises averages and/or most commonly-occurring values of attributes amongst attributes in the personal data and the interaction data of users belonging to the given cluster. Optionally, the centroid of the given cluster is determined using the k-means clustering algorithm. Such determination is well-known in the art.
It will be appreciated that the location of the given cluster in the metaverse can be determined as coordinates of extremities of the location of the given cluster, or as coordinates of a central point of the given cluster, or similar. Moreover, when the new user would be assigned to the given cluster, the location of the given cluster may be changed in the metaverse. This is because upon addition of the new user into the given cluster, an allocated space associated with the given cluster in the metaverse may be (physically) increased. Therefore, the location of the given cluster is required to be updated accordingly. Furthermore, it is to be understood that prior to assigning the new user to the given cluster, the space associated with the given cluster would already comprise one or more objects. Once the new user is assigned to the given cluster, it is likely that at least one object would also be added/placed in the space associated with the given cluster (where the one or more objects are already present), for example, based on the present interaction data associated with the new user. Therefore, the given cluster is required to be updated accordingly.
Optionally, the method further comprises:
- when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, collecting additional personal data and additional interaction data associated with the new user;
- employing the machine learning model for predicting updated probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the additional personal data and the additional interaction data;
- determining whether any probability amongst the updated probabilities exceeds the predetermined threshold; and
- when it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold, assigning the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
In this regard, there could be a scenario in which any probability amongst the probabilities does not exceed the predetermined threshold. This means that the new user could not be assigned to any cluster. This may occur when the present personal data and the present interaction data associated with the new user may be insufficient so as to assign the new user to any cluster, or may not quite match the personal data and the interaction data of users of any other cluster. In such a case, the additional personal data and the additional interaction data are required by the machine learning model to predict updated (namely, modified) probabilities. It will be appreciated that the additional personal data and the additional interaction data would comprise new information associated with the user, said information being different from the present personal data and the present interaction data that was initially received by the at least one processor 202. It is to be understood that the steps of employing the machine learning model for predicting the updated probabilities, and determining whether any (updated) probability exceeds the predetermined threshold, are performed in similar manner as described earlier. Once any (updated) probability exceeds the predetermined threshold, the new user could be assigned to the given cluster corresponding to said probability.
Optionally, when it is determined that any probability amongst the updated probabilities does not exceed the predetermined threshold, the method further comprises repeating the steps of employing the machine learning model for predicting the updated probabilities and determining whether the given probability amongst the updated probabilities exceeds the predetermined threshold until it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold. In this regard, even after receiving the additional personal data and the additional interaction data, there could be a scenario in which the new user still could not be assigned to any cluster. Therefore, the aforesaid steps are repeated until the new user is assigned to a particular cluster.
It will be appreciated that the new user that has been assigned to the given cluster in the metaverse would experience some behavioral/preferential changes over a period of time, and thus personal data and/or interaction data associated with the new user may no longer be similar to (namely, matching with) personal data and/or interaction data associated with other users in the given cluster. Optionally, in this regard, the at least one processor is configured to employ the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on latest personal data and latest interaction data. Optionally, when it is determined that any probability amongst the aforesaid probabilities exceeds the predetermined threshold, the at least one processor is configured to assign the new user to another given cluster corresponding to said probability and updating specifications of the another given cluster, the another given cluster being different from the given cluster. Alternatively, optionally, when it is determined that any probability amongst the aforesaid probabilities does not exceed the predetermined threshold, the at least one processor is configured to create a new cluster which includes the new user. Hereinabove, the latest personal data is personal data of the new user upon occurrence of the behavioral/preferential changes and similarly, the latest interaction data is interaction data of the new user upon occurrence of the behavioral/preferential changes.
Optionally, the at least one processor is further configured to:
- when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, collect additional personal data and additional interaction data associated with the new user;
- employ the machine learning model for predicting updated probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the additional personal data and the additional interaction data;
- determine whether any probability amongst the updated probabilities exceeds the predetermined threshold; and
- when it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold, assign the new user to a given cluster corresponding to said probability and update specifications of the given cluster.
Optionally, when it is determined that any probability amongst the updated probabilities does not exceed the predetermined threshold, the at least one processor is further configured to repeatedly employ the machine learning model for predicting the updated probabilities and determine whether the given probability amongst the updated probabilities exceeds the predetermined threshold until it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold.
Optionally, when employing the machine learning model to identify the plurality of clusters, the at least one processor is configured to utilize a clustering algorithm for dividing the plurality of users into the plurality of clusters according to the historical personal data and the historical interaction data.
Optionally, when presenting personalized content in the metaverse, the at least one processor is configured to digitally manipulate at least one space associated with each cluster, by at least one of: placing objects selected by at least some users of said cluster, adjusting a type and/or a characteristic of objects as selected by at least some users of said cluster, applying a theme that is selected by at least some users of said cluster, applying an environmental effect that is selected by at least some users of said cluster, applying a mood that is selected by at least some users of said cluster, adding locations visited by at least some users of said cluster.
Optionally, in the system, a given personal data comprises at least one of: a real-world location, an age, a gender, device information, a relationship status, an occupation, a contact list, of a given user.
Optionally, in the system, a given interaction data comprises at least one of: an appearance of an avatar, a location visited in the metaverse, time spent at a location visited in the metaverse, a theme that is selected, an environmental effect that is selected, a mood that is selected, a type and/or a characteristic of an object that is selected, a placement of objects, similarity of selections with other users, of/by a given user.
Optionally, in the system, the predetermined threshold lies in a range of 0.7 to 0.8.
Optionally, in the system, the specifications of the given cluster comprise at least one of: a centroid of the given cluster, a location of the given cluster in the metaverse, a size the given cluster, objects placed in a space associated with the given cluster.
Optionally, the system 200 further comprises the data repository 204 communicably coupled to the at least one processor 202, wherein the at least one processor 202 is configured to store, at the data repository 204, at least one of: the historical personal data and the historical interaction data, the present personal data and the present interaction data, information indicative of the plurality of clusters and of the one or more users in each of the plurality of clusters, information indicative of the given cluster to which the new user is assigned, specifications of the plurality of clusters.
It will be appreciated that the data repository 204 could, for example, be implemented as a memory of the at least one processor 202, a memory of a computing device, a removable memory, a cloud-based database, or similar. Examples of the computing device include, but are not limited to, a laptop, a desktop, a tablet, a workstation, and a console.
Modifications to embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present disclosure as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "have", "is" used to describe and claim the present disclosure are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural.
, Claims:CLAIMS
What is claimed is:
1. A method for providing a personalized metaverse experience in a metaverse, the method comprising:
- receiving historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse;
- employing a machine learning model to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users;
- presenting personalized content in the metaverse, for each of the plurality of clusters;
- receiving present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse;
- employing the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data;
- determining whether any probability amongst the probabilities exceeds a predetermined threshold; and
- when it is determined that any probability amongst the probabilities exceeds the predetermined threshold, assigning the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
2. A method as claimed in claim 1, further comprising:
- when it is determined that any probability amongst the probabilities does not exceed the predetermined threshold, collecting additional personal data and additional interaction data associated with the new user;
- employing the machine learning model for predicting updated probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the additional personal data and the additional interaction data;
- determining whether any probability amongst the updated probabilities exceeds the predetermined threshold; and
- when it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold, assigning the new user to a given cluster corresponding to said probability and updating specifications of the given cluster.
3. A method as claimed in claim 2, wherein when it is determined that any probability amongst the updated probabilities does not exceed the predetermined threshold, the method further comprises repeating the steps of employing the machine learning model for predicting the updated probabilities and determining whether the given probability amongst the updated probabilities exceeds the predetermined threshold until it is determined that any probability amongst the updated probabilities exceeds the predetermined threshold.
4. A method as claimed in any of claims 1-3, wherein the step of employing the machine learning model to identify the plurality of clusters comprises utilizing a clustering algorithm for dividing the plurality of users into the plurality of clusters according to the historical personal data and the historical interaction data.
5. A method as claimed in any of claims 1-4, wherein the step of presenting personalized content in the metaverse, comprises digitally manipulating at least one space associated with each cluster, by at least one of: placing objects selected by at least some users of said cluster, adjusting a type and/or a characteristic of objects as selected by at least some users of said cluster, applying a theme that is selected by at least some users of said cluster, applying an environmental effect that is selected by at least some users of said cluster, applying a mood that is selected by at least some users of said cluster, adding locations visited by at least some users of said cluster.
6. A method as claimed in any of claims 1-5, wherein a given personal data comprises at least one of: a real-world location, an age, a gender, device information, a relationship status, an occupation, a contact list, of a given user.
7. A method as claimed in any of claims 1-6, wherein a given interaction data comprises at least one of: an appearance of an avatar, a location visited in the metaverse, time spent at a location visited in the metaverse, a theme that is selected, an environmental effect that is selected, a mood that is selected, a type and/or a characteristic of an object that is selected, a placement of objects, similarity of selections with other users, of/by a given user.
8. A method as claimed in any of claims 1-7, wherein the predetermined threshold lies in a range of 0.7 to 0.8.
9. A method as claimed in any of claims 1-8, wherein the specifications of the cluster comprise at least one of: a centroid of the cluster, a location of the cluster in the metaverse, a size the cluster, objects placed in a space associated with the cluster.
10. A system for providing a personalized metaverse experiences in a metaverse, the system comprising at least one processor configured to:
- receive historical personal data and historical interaction data associated with a plurality of users that have historically joined and interacted with the metaverse;
- employ a machine learning model to identify a plurality of clusters, based on the historical personal data and the historical interaction data, each of the plurality of clusters including one or more users from amongst the plurality of users;
- present personalized content in the metaverse, for each of the plurality of clusters;
- receive present personal data and present interaction data associated with a new user, when the new user joins and interacts with the metaverse;
- employ the machine learning model for predicting probabilities of the new user belonging to each cluster from amongst the plurality of clusters, based on the present personal data and the present interaction data;
- determine whether any probability amongst the probabilities exceeds a predetermined threshold; and
- when it is determined that any probability amongst the probabilities exceeds the predetermined threshold, assign the new user to a given cluster corresponding to said probability and update specifications of the given cluster.