Systems and methods for persistent and personalized data set solutions for improving customer interaction with interaction areas

Abstract

A system for facilitating user interaction with an interactive area includes a memory encoding a processor-executable routine. The system is further configured to access the memory and execute the processor-executable routine. The processor can identify the user's data in the interactive area based on identification data acquired in the interactive area. The processor can further utilize a user-personalized trained machine learning model, the user-personalized trained machine learning model configured to recognize the user's idiosyncrasies. The processor can further utilize the user-personalized trained machine learning model to detect an idiosyncratic task performed by the user interacting with the interactive area to activate a special effect associated with the interactive area based on the interaction data acquired in the interactive area. The processor can further be instructed to initiate the special effect in response to detecting the idiosyncratic task.

Description

[Background technology]

[0001] This section is intended to introduce the reader to various aspects of art that may be related to various aspects of the present disclosure, which are described below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. As such, it should be understood that these statements are to be read in this light, and not as admissions of prior art.

[0002] Amusement parks and other entertainment venues, among many other attractions, often include interactive areas where guests perform activities or tasks (e.g., providing voice commands, performing gestures, etc.) that trigger various special effects in response to the activity or task. Guests often experience difficulty properly performing these activities or tasks to trigger the special effects. As a result, guests may become frustrated with the interactive areas. One reason this problem occurs is that machine learning models (trained on data aggregates composed of diverse people) do not take into account the idiosyncrasies of individuals. For example, machine learning models are typically trained by providing a large number of examples, each of which differs in some way in ways unrelated to the characteristics the model is trained on. For example, to train a model to detect push-up poses, photos of different people performing the pose are provided. By varying the people in the photos, the model is trained to recognize different body types, skin tones, and heights, yet still fails to recognize the push-up pose. Thus, when starting to run the model, without a sufficiently large set of training photos, the model may have difficulty recognizing that the pose has occurred. Furthermore, once a machine learning model is trained, it has no room for adjustment or improvement and cannot account for customer differences or intuition. Instead, it is hoped that the majority of customers will fit the model or fall within the range of the trained machine learning model. Even if the trained machine learning model is updated, it is generally updated for all customers, not for specific individuals. Therefore, it is desirable to improve machine learning dataset solutions to better take into account the idiosyncrasies of individual customers and improve the customer experience when performing activities or tasks. Summary of the Invention [Means for solving the problem]

[0003] Certain embodiments commensurate in scope with the originally claimed subject matter are summarized below. These embodiments are merely intended to provide a brief summary of possible forms of the subject matter and are not intended to limit the scope of the claimed subject matter. Indeed, the subject matter may encompass a variety of forms that may be similar to or different from the following embodiments.

[0004] In one embodiment, a system for facilitating user interaction with an interactive area includes a memory encoding a processor-executable routine. The system also includes a processor configured to access the memory and execute the processor-executable routine, which, when executed by the processor, causes the processor to perform an act. The act includes identifying a user of the interactive area based on identification data acquired at a user interface. The act also includes utilizing a trained machine learning model to detect, based on interactive data acquired at the interactive area, a specific task performed by a user interacting with the interactive area to activate a special effect associated with the interactive area, the trained machine learning model being configured to recognize the user's specificity. The act further includes initiating the special effect in response to detecting the specific task.

[0005] In one embodiment, a computer-implemented method for facilitating user interaction with an interactive area includes identifying a user of the interactive area based on identification data acquired at the interactive area. The act further includes obtaining a trained machine learning model personalized for the user, the trained machine learning model configured to recognize an idiosyncrasy of the user. The act further includes utilizing the trained machine learning model to detect, based on the interaction data acquired at the interactive area, an idiosyncratic task performed by a user interacting with the interactive area to activate a special effect associated with the interactive area. The act further includes initiating the special effect in response to detecting the idiosyncratic task.

[0006] In one embodiment, a non-transitory computer-readable medium includes processor-executable code that, when executed by a processor, causes the processor to perform acts. The acts include identifying a user of the interactive area based on identification data acquired at the interactive area. The acts also include utilizing a user-personalized trained machine learning model to detect, based on the interactivity data acquired at the interactive area, an idiosyncratic task performed by the user interacting with the interactive area to activate a special effect associated with the interactive area, the user-personalized trained machine learning model configured to recognize the user's idiosyncrasies. The acts further include instructing initiation of the special effect in response to detecting the idiosyncratic task. [Brief explanation of the drawings]

[0007] These and other features, aspects, and advantages of the present disclosure will be better understood from the following detailed description when read in conjunction with the accompanying drawings, in which like parts are designated by like numerals throughout.

[0008] [Figure 1] FIG. 1 is a schematic illustration of a user interacting with an interactive area (e.g., via body movements), according to an embodiment of the present disclosure.

[0009] [Figure 2] FIG. 2 is a schematic diagram of a user interacting with an interactive area (e.g., via manipulation of a device), according to an embodiment of the present disclosure.

[0010] [Figure 3] FIG. 3 is a schematic diagram of a user interacting with an interactive area (e.g., via voice commands) according to an embodiment of the present disclosure.

[0011] [Figure 4] FIG. 4 is a schematic diagram of a system for facilitating user interaction with an interactive area according to an embodiment of the present disclosure.

[0012] [Figure 5] FIG. 5 is a machine learning module for facilitating user interaction with an interactive area according to an embodiment of the present disclosure.

[0013] [Figure 6] FIG. 6 is a flow diagram of a method for facilitating user interaction with an interactive area according to an embodiment of the present disclosure.

[0014] [Figure 7] FIG. 7 is a flow diagram of a method for training a machine learning model to facilitate user interaction with an interactive area according to an embodiment of the present disclosure.

[0015] The present disclosure generally relates to systems and methods for persistent and personalized machine learning dataset solutions for improving customer interactions with interactive areas (e.g., by taking into account customer individual idiosyncrasies).

[0016] One or more specific embodiments of the present disclosure are described below. In an effort to provide a concise description of these embodiments, all features of an actual implementation may not be described in the specification. It will be understood that the development of any actual implementation will require many implementation-specific decisions to be made in order to achieve the developer's particular goals, including complying with system-related and business-related constraints. Moreover, it will be understood that such a development effort may be complex and time-consuming, but would nevertheless be a routine undertaking of design, manufacturing, and fabrication for those of ordinary skill having the benefit of this disclosure.

[0017] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean the presence of one or more of the element. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements other than the listed elements. Furthermore, references to "one embodiment" or "one embodiment" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also contain the recited features.

[0018] As will be appreciated, implementations of the present disclosure may be embodied as a system, method, device, or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which are generally referred to herein as a "circuit," "module," or "system." Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable medium(s) having computer-readable program code embodied therein.

[0019] Embodiments of the present disclosure are directed to systems and methods for a persistent, personalized machine learning dataset solution for improving guest interaction with an interactive area. In particular, the disclosed embodiments utilize a personalized machine learning model trained to recognize user idiosyncrasies when a user (e.g., a guest) performs a task or activity (e.g., voice command, body movement, or manipulated device movement) to activate or initiate a particular special effect in an interactive area. The personalized machine learning model takes into account the user's idiosyncrasies when the user performs a task (e.g., a specific task) in the way the user believes the task should be performed.

[0020] Each time a user performs a specific task in an interactive area, the performance of that task serves as a data point for training, retraining, or updating a personalized machine learning model. The personalized machine learning model can be updated after each data point is obtained or after a certain number of data points are obtained. In either case, the personalized machine learning model is constantly being trained or updated. The data points can consist of the same and / or different specific tasks performed in the same and / or different interactive areas. Initial training of the personalized machine learning model involves obtaining a general machine learning model when a customer is first identified in the interactive area. The general machine learning model is configured to fit most of the collected data. The general machine learning model is generated using predetermined data collected from tasks performed by many different users in different interactive areas. Once the general machine learning model is obtained, data points are obtained from the user (i.e., performance of a specific task that the user believes will initiate or activate a special effect associated with the interactive area). Once a certain number of data points are collected and used for training, a trained machine learning model personalized to the user is generated. In addition to being personalized to the user, the trained machine learning model is persistent and can be used for subsequent activities (e.g., performing different specific tasks performed in different interactive areas). The disclosed embodiments enable the activation of an experience, or what the user (e.g., guest) believes to be an activation, to actually activate the experience.

[0021] Figures 1-3 are schematic diagrams of a user 10 (e.g., a customer) interacting with an interactive area 12. The interactive area 12 can be an attraction at an amusement park or theme park. The user 10 can interact with the interactive area 12 by performing tasks or activities to initiate or activate a special effect 14. The special effect 14 can be any type of special effect, such as the display of an object's appearance (e.g., via a screen or projection), lighting effects, smoke, sound, the movement of animated figures or other objects, etc. As shown in Figures 1-3, the special effect 14 can be an animated movement on a screen or display 16.

[0022] The task or activity performed by user 10 to initiate or activate special effect 14 can take a variety of forms. For example, in FIG. 1 , user 10 moves one or more body parts to initiate or activate special effect 14. In FIG. 2 , user 10 moves a device or object 18 (e.g., in a specific pattern) to initiate or activate special effect 14. In FIG. 3 , user 10 issues a voice command to initiate or activate special effect 14. Each user 10 may have their own idiosyncrasies in performing a task or activity in a way that they believe will initiate or activate special effect 14. As described in more detail below, a personalized persistent machine learning model (e.g., model 44) can be created that is trained to recognize the idiosyncrasies of each user 10. The personalized machine learning model 44 can be utilized to detect tasks (e.g., idiosyncratic tasks) performed by users 10 interacting with interactive area 12 (e.g., along with their personal idiosyncrasies) to activate special effect 14 associated with interactive area 12. The use of personalized machine learning model 44 can help user 10 interact with interactive area 12 by taking into account the user's idiosyncrasies when attempting to initiate or activate special effect 14 so that the task or activity that user 10 believes to be a task or activity for initiating special effect 14 is actually the task or activity that initiates or activates special effect 14.

[0023] A personalized machine learning model 44 for a user 10 can be utilized for different specific tasks (e.g., in the same category as voice commands, body movements, or movements of a manipulated device 18) performed by the user 10 in different interactive areas 12. In particular embodiments, different personalized machine learning models 44 can be generated for different categories of specific tasks for different single users 10. For example, a first personalized machine learning model 44 can be utilized for voice command specific tasks, a second different personalized machine learning model 44 can be utilized for body movement specific tasks, and / or a third different personalized machine learning model 44 can be generated for the same user 10 for specific tasks related to device 18 movements.

[0024] The interactive area 12 may include devices (e.g., task detection device 30 of FIG. 4) for tracking or monitoring tasks or activities performed by the user 10. For example, a voice recognition system may be utilized to monitor voice commands uttered by the user 10. As another example, a motion tracking system may be utilized to monitor the body movements of the user 10. As yet another example, an infrared tracking system may be utilized to track the movement of a device 18 (e.g., an infrared-emitting device) operated by the user 10. Other types of devices may be utilized to track or monitor tasks or activities performed by the user 10.

[0025] The interactive areas 12 may also include different types of devices for identifying the users 10. In certain embodiments, a facial recognition device (e.g., utilizing one or more cameras) may be utilized to identify the users 10. In certain embodiments, a voice recognition device may be utilized to identify the users 10. In certain embodiments, a radio frequency identification (RFID) reader may be utilized to communicate with a device (e.g., having an RFID chip) worn or held by the users 10 (e.g., a band, necklace, badge, etc.). Other types of devices may be utilized to identify the users 10. Identifying the users 10 facilitates generating, retrieving, and utilizing personalized machine learning models 44 for the users 10 of different interactive areas 12.

[0026] 4 is a schematic diagram of a system 20 for facilitating user interaction with an interactive area 12. The system 20 includes a controller 22. The controller 22 may be a central or main controller 22. In certain embodiments, the controller 22 may be located remotely from any of the interactive areas 12. The controller 22 is in communication with a database 24 (e.g., physical storage and / or cloud-based storage) via a network or any suitable communication network, including a mobile communication network, a Wi-Fi network, a local area network (LAN), a wide area network (WAN), and / or the Internet.

[0027] The database 24 can store different machine learning models of the machine learning module or engine. The machine learning module can be associated with each customer (e.g., user of the interactive area 12) and can include a personalized machine learning model. The personalized machine learning model is configured to recognize the user's idiosyncrasies when the user interacts with the interactive area 12. The personalized machine learning model can be utilized to detect tasks (e.g., specific tasks) to be performed by the user interacting with the interactive area 12 (with their idiosyncrasies) to activate the special effects 14 associated with the interactive area 12. The utilization of the personalized machine learning model aids user interaction with the interactive area 12 by taking into account the user's idiosyncrasies so that when the user attempts to activate or activate a special effect, the task or activity that the user 10 believes will activate the special effect is the actual task or activity that will activate the special effect.

[0028] The database 24 also stores one or more generic machine learning models. The one or more generic machine learning models are configured to recognize tasks commonly performed by users to activate the respective special effects of the different interactive areas 12. The generic machine learning models are trained based on acquired data points (i.e., the same user's interactions with the interactive areas 12) to recognize the user's idiosyncrasies (when interacting with the interactive areas 12). The database 24 also stores customer identification information that can be linked to the machine learning models. In one embodiment, the database 24 also stores customer calibration data. The customer calibration data is obtained from a particular customer performing a series of tasks that are utilized in combination with the generic machine learning model to generate a personalized machine learning model to recognize the particular customer's idiosyncrasies.

[0029] The controller 22 communicates with each of the controllers 26 (e.g., via a wired or wireless connection) in the different interactive areas 12 via a network or any suitable communication network, including a mobile communication network, a Wi-Fi network, a local area network (LAN), a wide area network (WAN), Bluetooth, and / or the Internet. In certain embodiments, each controller 26 can communicate directly with the database 24. Each controller 26 can be coupled to an identification device 28 in each of the interactive areas 12 to identify users of the interactive areas 12. The identification devices 28 utilized in each of the interactive areas 12 can be the same or different. In certain embodiments, the identification device 28 can include a facial recognition device (e.g., utilizing one or more cameras) utilized to identify users. In certain embodiments, the identification device 28 can include a voice recognition device utilized to identify users. In certain embodiments, the identification device 28 can include an RFID reader utilized to communicate with a device (e.g., having an RFID chip) worn or held by the user 10 (e.g., a band, necklace, badge, etc.). Other types of identification devices 28 can be utilized to identify users. Identifying the user facilitates generating, retrieving and utilizing personalized machine learning models for users of different interactive areas 12 .

[0030] Each controller 26 can be coupled to a task detection device 30 in each interactive area 12 to track or monitor tasks or activities performed by a user. For example, the task detection device 30 can include a voice recognition system used to monitor voice commands issued by a user. As another example, the task detection device 30 can include a motion tracking system used to monitor the user's body movements. As yet another example, the task detection device 30 can include an infrared tracking system used to track the movement of a device (e.g., an infrared-emitting device) operated by a user. Other types of devices can be used to track or monitor tasks or activities performed by a user. The captured or detected tasks or activities performed by a user can be used as data points for training, retraining, and updating personalized machine learning models.

[0031] Each controller 26 may further be connected to a special effects device 32 in each interactive area 12. The special effects device 32 is configured to trigger special effects in response to control signals from the controller 26 (in response to specific tasks performed by a user to initiate or activate the special effects). The special effects may be any type of special effect, such as the display of the appearance of an object (e.g., via a screen or projection), lighting effects, smoke, sound or movement of animated figures or other objects, etc. It can be said that:

[0032] Each controller 22, 26 includes a memory 34 having stored therein instructions for facilitating user interaction with the interactive area 12 by controlling components of the interactive area 12 (e.g., the identification device 28, the task detection device 30, the special effects device 32, etc.). In certain embodiments, the controller 26 of each interactive area 12 can operate independently of the controller 22. In certain embodiments, the controller 26 of each interactive area 12 and the controller 22 can operate cooperatively. Furthermore, each controller 22, 26 includes a processor 36 configured to execute such instructions. For example, the processor 36 may include one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), one or more general-purpose processors, or any combination thereof. Furthermore, the memory 34 may include volatile memory, such as random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM), an optical drive, a hard disk drive, or a solid-state drive. The memory 34 may store information similar to that of the database 24 (e.g., user identification, machine learning models, etc.).

[0033] The controllers 22, 26 (via the processor 36) are configured to identify users of the interactive areas 12 (e.g., based on identification data obtained by the identification device 28). The controllers 22, 26 (via the processor 36) are configured to obtain general machine learning models (e.g., configured to recognize tasks commonly performed by users to activate special effects in each of the different interactive areas 12). The controllers 22, 26 (via the processor 36) are also configured to train these general machine learning models based on one or more specific tasks performed by users in one or more interactive areas 12 and to recognize the user's specificity to generate a personalized trained machine learning model for the user. If the user already has a personalized machine learning model, the controllers 22, 26 (via the processor 36) are configured to obtain or access the personalized trained machine learning model for the user. After identifying the user of the interactive area 12, the controllers 22, 26 (via the processor 36) are further configured to monitor tasks or activities (e.g., specific tasks) performed by the user and instruct the user to initiate and / or activate special effects in the interactive areas 12. The controllers 22, 26 are configured to utilize a machine learning module or engine (e.g., a machine learning model personalized and trained to recognize the user's idiosyncrasies) to detect specific tasks or activities performed by a user interacting with the interactive area 12 and to activate or initiate special effects associated with the interactive area (e.g., based on the interaction data obtained by the task detection device 30). The controllers 22, 26 (via the processor 36) are further configured to instruct (via the control signal) to initiate special effects in the interactive area in response to detecting the specific tasks performed by the user.The controller 22, 26 (via the processor) is further configured to update or retrain the machine learning model personalized for a particular user after each data point (interaction with an interactive area) is collected, or after a certain number of data points have been collected, which may be for the same task or different tasks in the same or different interactive areas.

[0034] In certain embodiments, the controller 22, 26 (via the processor 36) is configured to allow a particular user, after successfully completing a certain number of interactive areas (i.e., activating a special effect), to create their own task or activity in the next interactive area to activate or initiate a special effect in the next interactive area. For example, if a user has completed 10 interactive areas (taking into account their idiosyncrasies), the user may create their own task or activity to activate a special effect in the 11th interactive area.

[0035] FIG. 5 illustrates a machine learning module or engine 38 for facilitating user interaction with an interactive area. The machine learning module 38 can be part of the system 20 described in FIG. 4. The machine learning module 38 can utilize machine learning capabilities to facilitate user interaction with the interactive area. In particular, the machine learning module 38 is configured to recognize the idiosyncrasies of each user. The machine learning module 38 can be utilized to detect tasks (e.g., idiosyncratic tasks) performed by users interacting with the interactive area to activate special effects associated with the interactive area. Utilizing the machine learning module 38 helps users interact with the interactive area by taking the user's idiosyncrasies into account when the user attempts to activate or initiate a special effect, such that the task or activity the user believes is intended to activate the special effect is the actual task or activity intended to activate the special effect. For example, if a user is asked to perform a gesture that follows a straight, vertical path and consistently performs gestures that follow a path that turns right, this idiosyncrasy can be considered by the machine learning module 38 and utilized to interpret gestures that include a straight, vertical path. In other embodiments, similar adjustments can be made to other gestures, gesture components, body movements (e.g., hip movements when attempting to perform a particular arm gesture), audio modulation, etc. In this manner, the current embodiment can provide a more consistently successful, enjoyable, and personalized experience for individual users.

[0036] The machine learning module 38 may utilize one or more machine learning models 40. One or more of the multiple machine learning models 40 may be a general machine learning model 42. The one or more general machine learning models 42 may be configured to recognize tasks commonly performed by users to activate respective special effects in different interactive areas. Each general machine learning model may be configured to fit most collected data. Each general machine learning model may be generated using predetermined data collected from tasks performed by multiple different users in different interactive areas. In particular embodiments, a single general machine learning algorithm model 42 may be utilized that is configured to recognize different categories of interactions or tasks (e.g., voice commands, body movements, or manipulated device movements) that users perform when interacting with the interactive areas. In particular embodiments, different general machine learning models 42 may be utilized to recognize different categories of interaction tasks. For example, a first general machine learning model may be utilized for voice command tasks, a second different general machine learning model may be utilized for body movement tasks, and / or a third different general machine learning model may be utilized for tasks related to device movements. In certain embodiments, different general machine learning models 42 may be configured for different categories of general characteristics of people (e.g., based on height, age, or other characteristics relevant to performing tasks or activities).

[0037] One or more of the plurality of machine learning models 40 are personalized machine learning models 44. The one or more personalized machine learning models 44 are configured to recognize the idiosyncrasies of a particular user and to be utilized to detect specific tasks performed by a particular user to activate special effects associated with an interactive area. The personalized machine learning models 44 take into account the idiosyncrasies of a user when performing a task (e.g., a specific task) in the manner the user believes the task should be performed. In particular embodiments, a single personalized machine learning model 44 can be used to recognize different categories of specific tasks (e.g., voice commands, body movements, or manipulated device movements) performed by a user when interacting with an interactive area. In particular embodiments, a user can have a respective personalized machine learning model 44 used to recognize each different category of interaction or task (e.g., voice commands, body movements, or manipulated device movements) performed by a user when interacting with an interactive area.

[0038] The personalized machine learning model 44 is generated by training the general machine learning model 42 using data points acquired from the same user. Each time the user performs a specific task in an interactive area, the performance of that task serves as a data point for training, retraining, or updating the personalized machine learning model. The personalized machine learning model 44 can be updated after each data point is acquired or after a certain number of data points are acquired. In either case, the personalized machine learning model 44 is constantly being trained or updated. The data points can consist of the same and / or different specific tasks performed in the same and / or different interactive areas. In addition to being personalized to the user, the trained machine learning model 44 is persistent and can be used for subsequent activities (e.g., performance of different specific tasks performed in different interactive areas).

[0039] Figure 6 is a flow diagram of a method 46 for facilitating user interaction with an interactive area. Method 46 may be performed by system 20 (e.g., one or more of controllers 22, 26) of Figure 4. One or more of the steps of method 46 may be performed simultaneously and / or in a different order than that shown in Figure 6.

[0040] The method 46 includes identifying a user of the interactive area (e.g., based on identification data obtained by the identification device 28 of FIG. 4 ) (block 48). The method 46 also includes obtaining or accessing a trained machine learning model personalized to the user, the trained machine learning model configured to recognize a specificity of the user (e.g., based on the interactive data obtained by the task detection device 30 of FIG. 4 ) (block 50). The method 46 further includes monitoring a task performed by the user to activate a special effect associated with the interactive area (block 52). The method 46 further includes utilizing the trained machine learning model personalized to the user to detect a specific task performed by a user interacting with the interactive area to activate a special effect associated with the interactive area (e.g., based on the interactive data obtained by the task detection device 30 of FIG. 4 ) (block 54). The method 46 further includes initiating the special effect in response to detecting the specific task (block 56). An example of a specific task is a user consistently performing a gesture that follows a path that turns right when asked to perform a gesture that follows a straight, vertical path. In other embodiments, similar adjustments can be made to other gestures, gesture components, body movements (e.g., hip movements when attempting to perform a particular arm gesture), audio modulation, etc.

[0041] Method 46 further includes updating the user-personalized trained machine learning model using the recognized user specificity in performing the specific task (block 58). Each time the user performs the specific task in an interactive area, the performance of that task serves as a data point for retraining and / or updating the user-personalized trained machine learning model. The user-personalized trained machine learning model can be updated after each data point is obtained or after a certain number of data points are obtained. In either case, the user-personalized trained machine learning model is constantly being trained and / or updated. The data points can consist of the same or different specific tasks performed in the same and / or different interactive areas. The steps of method 46 (blocks 48-58) can be repeated in the same or different interactive areas, utilizing the same or different specific tasks.

[0042] 5 is a flow diagram of a method 60 for training a machine learning model to facilitate user interaction with an interactive area. Method 60 may be performed by system 20 (e.g., one or more of controllers 22, 26) of FIG. 4. One or more of the steps of method 60 may be performed simultaneously and / or in a different order than that shown in FIG.

[0043] Method 60 includes identifying users of the interactive areas (block 62). Method 60 also includes obtaining a general machine learning model configured to recognize tasks commonly performed by users to activate respective special effects in different interactive areas (e.g., based on the interactive data acquired by task detection device 30 of FIG. 4) (block 64). Method 60 also includes monitoring tasks performed by users in the interactive areas to activate special effects associated with the interactive areas (block 66). In particular embodiments, a user who utilizes a different type of task (e.g., voice vs. body movement) in an interactive area or a first interactive area than in a previous interactive area may be asked to perform a series of tasks (e.g., similar but not necessarily the same as tasks performed in a current interactive area) to obtain user-specific data (e.g., calibration data) to detect user idiosyncrasies. Method 60 further includes utilizing the general machine learning model to detect tasks performed by users interacting with the interactive areas to activate special effects associated with the interactive areas (e.g., based on the interactive data acquired by task detection device 30 of FIG. 4) (block 68). The method 60 further includes initiating a special effect in response to detecting the task (block 70).

[0044] Method 60 further includes training the general machine learning model based on one or more tasks performed by the user in one or more interactive areas to recognize the user's idiosyncrasies and generate a trained machine learning model personalized to the user (block 72). In particular embodiments, user-specific calibration data can also be utilized in training the general machine learning model to become a trained machine learning model personalized to the user. The general machine learning model can be trained after obtaining each data point or after obtaining a certain number of data points.

[0045] The technology presented and claimed herein is not abstract, intangible, or purely theoretical, since it refers to and is applied to tangible objects and specific examples of a practical nature, thereby providing a definite improvement in the art. Furthermore, where any claim appended at the end of this specification contains one or more elements designated as "means for [performing] ... [function]" or "step for [performing] ... [function]," it is intended that such elements be construed in accordance with 35 U.S.C. 112(f). Conversely, for any claim containing an element designated in any other manner, it is intended that such element not be construed in accordance with 35 U.S.C. 112(f).

[0046] While only certain features of the invention have been illustrated and described herein, many modifications and changes will occur to those skilled in the art and it is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

Claims

1. 1. A system for facilitating user interaction with an interactive area, the system comprising: a memory encoding a processor-executable routine; a processor configured to access the memory and execute the processor-executable routines, the routines, when executed by the processor, causing the processor to: identifying a user of the interactive area based on identification data obtained in the interactive area; utilizing a trained machine learning model personalized for the user to detect a specific task performed by the user interacting with the interactive area to activate a special effect associated with the interactive area based on interactive data acquired in the interactive area, wherein the trained machine learning model personalized for the user is configured to recognize the specific task of the user; initiating the special effect in response to detecting the specific task; a processor that executes a procedure including: Equipped with system.

2. 2. The system of claim 1, wherein the routine, when executed by the processor, causes the processor to update the trained machine learning model personalized for the user using the recognized idiosyncrasies of the user when performing the idiosyncratic tasks.

3. 3. The system of claim 2, wherein the trained machine learning model personalized for the user is updated after each performance of the specific task or a different specific task in a different interactive area.

4. 3. The system of claim 2, wherein the trained machine learning model personalized for the user is updated after performance of a certain number of specificity tasks performed in any interactive area.

5. The system of claim 1 , wherein the specific task comprises a voice command, a movement of the user, or a movement of a device operated by the user.

6. The routine, when executed by the processor, causes the processor to: identifying the user of the different interactive areas based on the identification data obtained in the different interactive areas; utilizing the trained machine learning model personalized for the user to detect different specific tasks to be performed by the user interacting with the different interactive areas to activate specific special effects associated with the different interactive areas based on additional interactive data acquired in the different interactive areas; initiating the initiation of the particular special effect in response to detecting the task of different specificity; The system of claim 1 , wherein the system causes a procedure including:

7. 2. The system of claim 1, wherein the routine, when executed by the processor, causes the processor to train a general machine learning model based on one or more specific tasks performed by the user in one or more interactive areas to recognize the specificities of the user and generate the trained machine learning model personalized for the user, the general machine learning model being configured to recognize tasks commonly performed by users to activate respective special effects in different interactive areas based on acquired interactive data.

8. 1. A computer-implemented method for facilitating user interaction with an interactive area, the computer-implemented method comprising: identifying a user of the interactive area based on identification data obtained from the interactive area; obtaining a trained machine learning model personalized for the user, the trained machine learning model personalized for the user configured to recognize idiosyncrasies of the user; utilizing the trained machine learning model to detect, based on interaction data acquired in the interactive area, a specific task performed by the user interacting with the interactive area to activate a special effect associated with the interactive area; initiating the special effect in response to detecting the specific task; 11. A computer-implemented method comprising:

9. 10. The computer-implemented method of claim 8, further comprising: utilizing the recognized idiosyncrasies of the user when performing the idiosyncratic tasks to update the trained machine learning model personalized for the user.

10. 10. The computer-implemented method of claim 9, wherein the trained machine learning model personalized for the user is updated after each performance of the specificity task or a different specificity task in a different interactive area.

11. 10. The computer-implemented method of claim 9, wherein the trained machine learning model personalized for the user is updated after performance of a certain number of specificity tasks performed in any interactive area.

12. The computer-implemented method of claim 8 , wherein the specific task comprises a voice command, a movement of the user, or a movement of a device operated by the user.

13. 10. The computer-implemented method of claim 8, wherein the trained machine learning model personalized for the user is configured to be utilized for performance of tasks of different types and specificities by the user in different interactive areas.

14. 10. The computer-implemented method of claim 8, further comprising: obtaining a general machine learning model, the general machine learning model configured to recognize tasks commonly performed by users to activate respective special effects in different interactive areas; and training the general machine learning model based on the acquired interactive data of one or more specific tasks performed by the user in one or more interactive areas to recognize the specificities of the user and generate the trained machine learning model personalized for the user.

15. A non-transitory computer-readable medium that, when executed by a processor, causes the processor to: identifying a user of the interactive area based on identification data obtained in the interactive area; utilizing a trained machine learning model personalized for the user to detect a specific task performed by the user interacting with the interactive area to activate a special effect associated with the interactive area based on interactive data acquired in the interactive area, wherein the trained machine learning model personalized for the user is configured to recognize the specific task of the user; initiating the special effect in response to detecting the specific task; A non-transitory computer-readable medium containing processor-executable code for causing a program to execute a procedure including:

16. 16. The non-transitory computer-readable medium of claim 15, wherein the code, when executed by the processor, causes the processor to utilize the recognized idiosyncrasies of the user when performing the idiosyncratic tasks to update the trained machine learning model personalized for the user.

17. 17. The non-transitory computer-readable medium of claim 16, wherein the trained machine learning model personalized for the user is updated after each performance of the specific task or a different specific task in a different interactive area, or the trained machine learning model personalized for the user is updated after performance of a certain number of specific tasks performed in any interactive area.

18. The non-transitory computer-readable medium of claim 17 , wherein the specific task comprises a voice command, a movement of the user, or a movement of a device operated by the user.

19. 16. The non-transitory computer-readable medium of claim 15, wherein the trained machine learning model personalized for the user is configured to be utilized for performance of tasks of different specificity by the user in different interactive areas.

20. 16. The non-transitory computer-readable medium of claim 15, wherein the code, when executed by the processor, causes the processor to train a general machine learning model based on one or more specific tasks performed by the user in one or more interactive areas to recognize the specificities of the user and generate the trained machine learning model personalized for the user, the general machine learning model configured to recognize tasks commonly performed by users to activate respective special effects in different interactive areas.

Images