Interactive Image System and Method

Abstract

The interactive portrate system includes a camera and a controller configured to capture an image of the environment. The controller analyzes the image to identify visitors in the environment, instructs an output device to provide an initial output for attempting to interact with the visitors, and is configured to analyze the image to identify the actions of the visitors during, after, or both during and after the initial output. Further, the controller is configured to evaluate the actions of the visitors using one or more artificial intelligence algorithms and determine whether the visitors have responded to the initial output. The controller is further configured to, in response to determining that the visitors have responded to the initial output, instruct the output device to provide an additional output and continue to attempt to interact with the visitors.

Description

Technical Field

[0001] (Cross - Reference to Related Applications) This application claims the priority and benefit of U.S. Provisional Application No. 63 / 354,886, filed on June 23, 2022, entitled "INTERACTIVE IMAGERY SYSTEMS AND METHODS", which is hereby incorporated by reference in its entirety for all purposes.

Background Art

[0002] This section is intended to introduce the reader to various aspects of technologies that may be relevant to various aspects of the present disclosure. The discussions here are considered to be helpful in providing the reader with background information that facilitates a better understanding of various aspects of the present disclosure. Thus, it should be understood that these descriptions are not an admission of prior art and should be read in light of this perspective.

[0003] Theme parks, amusement parks, theaters, cinemas, stadiums, concert halls, and others provide various immersive experiences to visitors. These entertainment facilities can include show attractions (e.g., movies, plays, rides, games) that offer immersive experiences to visitors. For example, conventional show attractions can utilize various combinations of physical show elements (e.g., props), display elements (e.g., animations), and lighting to create visual effects for visitors. As the popularity of entertainment facilities grows, visitors come to have expectations for improved and varied immersive experiences.

Summary of the Invention

[0004] Some embodiments within the scope of the invention as initially claimed are summarized below. These embodiments are not intended to limit the scope of the present disclosure; rather, these embodiments are only intended to provide a concise overview of the specific embodiments disclosed. In fact, the present disclosure can encompass various forms that may be similar to or different from the embodiments described below.

[0005] In one embodiment, an interactive port rate system includes a camera and a controller configured to capture an image of an environment. The controller analyzes the image to identify visitors in the environment, instructs an output device to provide an initial output attempting to interact with the visitors, and analyzes the image to identify the actions of the visitors during, after, or both during and after the initial output. The controller is also configured to evaluate the actions of the visitors using one or more artificial intelligence algorithms and determine whether the visitors have responded to the initial output. The controller is further configured to, in response to determining that the visitors have responded to the initial output, provide additional output and instruct the output device to continue attempting to interact with the visitors.

[0006] In one embodiment, the entertainment facility includes a path for passing through the interactive area, a display and a speaker disposed adjacent to the interactive area, a camera configured to capture an image of the interactive area, a microphone configured to capture sound within the interactive area, and a controller. The controller is configured to analyze the image to identify that a visitor is moving toward the interactive area along the path, and to instruct the display, the speaker, or both to provide an initial output for attempting to interact with the visitor when the visitor approaches the interactive area. The controller is also configured to analyze the image, the sound, or both to identify the behavior of the visitor during, after, or both during and after the initial output. The controller is further configured to evaluate the behavior of the visitor using one or more artificial intelligence algorithms and to determine whether the visitor has responded to the initial output. In response to determining that the visitor has responded to the initial output, the controller is further configured to instruct the display and the speaker to provide an additional output to engage in a conversational interaction with the visitor.

[0007] In one embodiment, a method of operating an interactive portrait system in an entertainment facility includes analyzing, using one or more processors, an image captured by a camera to identify the behavior of a visitor. The method also includes evaluating, using one or more processors and one or more artificial intelligence algorithms, the behavior of the visitor to determine whether the visitor has shown signs of interest in the interactive area of the entertainment facility. The method further includes, in response to determining that the visitor has shown signs of interest in the interactive area of the entertainment facility, instructing, using one or more processors, an output device to provide an initial output for attempting to interact with the visitor.

[0008] These and other features, aspects, and advantages of the present disclosure will be further understood upon reading the following detailed description with reference to the accompanying drawings in which like reference numerals represent like elements throughout the drawings.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Mode for Carrying Out the Invention

[0010] One or more specific embodiments of the present disclosure will be described below. For the sake of brevity in the description of these embodiments, not all features of the actual embodiments will be described herein. It should be understood that, like any technical or design project, in the development of such any actual implementation configuration, numerous implementation-specific decisions need to be made to achieve the specific goals of the developer, which may vary for each implementation configuration, such as compliance with system- and business-related constraints. Further, although such development efforts may be complex and time-consuming, it should be understood by those skilled in the art having the advantages of the present disclosure that they are routine in the daily business of design, fabrication, and manufacturing.

[0011] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that one or more of the elements are present. The terms "comprising," "including," and "having" are inclusive and mean that additional elements other than the recited elements can exist. One or more specific embodiments will be described below. For the sake of brevity of description of these embodiments, not all features of actual implementations will be described herein. As in any technical or design project, in the development of any such actual implementation, it should be noted that numerous implementation-specific decisions need to be made to achieve the specific goals of the developer, which may vary from implementation to implementation, such as compliance with system- and business-related constraints. Further, although such development efforts can be complex and time-consuming, it should be noted that for those skilled in the art having the advantages of the present disclosure, they are routine in the daily business of design, fabrication, and manufacture.

[0012] The present disclosure generally relates to an interactive portrait system and method for entertainment facilities (e.g., theme parks, amusement parks, theaters, cinemas, stadiums, concert halls). More particularly, the present disclosure relates to an interactive portrait system that provides dynamic and personalized interactions with park visitors. The interactive portrait system can utilize various technologies to collect information about park visitors, such as computer vision to identify the characteristics, actions, and / or locations of park visitors. The interactive portrait system can communicate with devices associated with park visitors to obtain identifiers and / or related data that can indicate the characteristics, actions, locations, and / or past performance of park visitors. The interactive portrait system can communicate with one or more sensors to obtain sensor data that indicates the characteristics, actions, and / or locations of park visitors. In one embodiment, the interactive portrait system utilizes artificial intelligence (AI) (e.g., machine learning) to evaluate the interests of park visitors or control the output to effectively interact with park visitors. For example, the interactive portrait system can utilize an AI algorithm to evaluate an image and determine that a park visitor is gazing at a display (e.g., a display screen) in a manner that indicates sufficient interest (e.g., is likely to engage if presented with an output). Next, the interactive portrait system can utilize an AI algorithm to display an animation and / or emit a sound based on the characteristics, identifiers and / or related data, actions, locations, and / or prior performance of the park visitor. Further, the interactive portrait system can utilize an AI algorithm to conduct a conversational interaction with a park visitor (e.g., emulating a natural conversation between two humans).

[0013] As a more specific example, the interactive portrait system can capture image data of the environment (e.g., one or more images; a capture device) using one or more cameras. The interactive portrait system can analyze the image data using computer vision to identify visitors. This can include identifying one or more characteristics of the visitors, such as analyzing the image data using computer vision to identify a first visitor wearing a red shirt of a first team symbol (e.g., a dragon team). Additionally or alternatively, this can include using computer vision to analyze the image data to identify the actions of the visitors, such as the movement of the visitors, and / or the position of the visitors, such as the position of the visitors along a path within the environment. It should be understood that the interactive portrait system can additionally or alternatively obtain other types of data, including identifiers obtained via communication with devices carried by the visitors and / or sensor data obtained via one or more sensors.

[0014] An interactive portrait system can process images and / or other types of data to evaluate the interest of visitors and determine whether to attempt to engage the visitors. For example, the interactive portrait system can process images and / or other types of data to identify that a first visitor is walking along a path towards an interactive area located proximate to a display (e.g., a display screen) and a speaker. In response, the interactive portrait system can generate an initial output that attempts to engage and initiate interaction with the first visitor. The initial output may be consistent across all visitors, selected via rotation from among available options, randomly selected from among available options, and / or selected to be personalized for the first visitor based on characteristics and / or other information about the first visitor from among available options. For example, the initial output can include displaying a shooting star (e.g., consistent across all visitors or otherwise not selected to be personalized for the first visitor based on characteristics and / or other information about the first visitor). As another example, the initial output can include displaying a small, blinking flame representing a dragon breathing fire in the distance, displaying a symbol of a first team, and / or emitting a sound directed at the first visitor (e.g., "Hey, the dragon team is my favorite"), providing an initial output that is personalized for the first visitor based on characteristics and / or other information about the first visitor.

[0015] The interactive portrate system can monitor the response of the first visitor (e.g., evaluate the interest of the first visitor during or after the first output). For example, if the image data indicates that the first visitor turns their head towards the interactive area (e.g., towards the display and / or speaker), the interactive portrate system can determine that the first visitor is sufficiently interested (e.g., engaged) and proceed to provide additional output to the first visitor. The additional output may also be consistent across all visitors, selected via rotation from among the available options, randomly selected from among the available options, and / or selected to be personalized for the first visitor based on characteristics and / or other information about the first visitor from among the available options. The additional output may be different from the initial output. In one embodiment, the additional output may be enhanced compared to the initial output, such as a display image that is larger (e.g., over more pixels; over a larger surface area of the display), brighter, more colorful, and / or has more movement compared to the initial output. In this way, the interactive portrate system can capture the attention of the visitor via the initial output and then attempt to provide a more entertaining and immersive additional output when the visitor shows sufficient interest in engaging with the interactive portrate system.

[0016] When a first visitor reaches the interactive area or enters the range of one or more communication devices (e.g., radio frequency identification readers), the one or more communication devices can detect and / or communicate with a device associated with the first user (e.g., a user device) (e.g., a wearable or portable object worn or carried by the first user). In this way, the one or more communication devices can receive a first identifier from the device. Next, the interactive portrate system can access data from a database using the first identifier. The data can include various types of information such as statistics related to the venue where the first visitor rode (e.g., the first visitor completed a ride attraction early that day) and / or other achievements of the first visitor. Then, the interactive portrate system can instruct an initial output and / or an additional output for the first visitor based on the first identifier and / or the data (e.g., "Did you enjoy the ride attraction?"). Additionally or alternatively, it should be understood that one or more communication devices may receive data from the device (e.g., from a storage device on the device). Further, when the first visitor provides an audible, spoken response, the interactive portrate system can detect the audible, spoken response via a microphone and then engage in conversation with the first visitor. As described herein, the interactive portrate system can utilize AI to determine relevant responses and utterances that emulate a natural conversation (e.g., as spoken between two humans).

[0017] However, during or after the initial output, if the first visitor does not perceive or show interest (e.g., does not turn their face towards the interactive area, etc., showing insufficient interest), the interactive portrait system can determine that the first visitor has no interest in interacting with the interactive portrait system. Next, the interactive portrait system can attempt to generate another initial output and start interacting with a second visitor. For example, the interactive portrait system can identify that the second visitor is approaching the interactive area and holding a cup for drinking. As a result, the interactive portrait system can display a character animation that appears to talk towards the second visitor and / or emits corresponding sounds (e.g., "Hey, is the drink good?"). If the image data indicates that the second visitor responds with sufficient interest (e.g., turns their face towards the display and / or speaker), the interactive portrait system can determine that the second visitor has sufficient interest (e.g., is engaged) and proceed to provide additional output to the second visitor. The interactive portrait system can perform steps to keep the second visitor engaged in the same way as set above for the first visitor.

[0018] In one embodiment, the interactive portrate system can generate an initial output (e.g., a displayed output and / or an audible output) in response to (e.g., only in response to) determining that a visitor has performed a particular action and / or shown sufficient interest, such as by approaching the interactive area (e.g., walking towards the display, passing by the display, being within a threshold distance of the display, gazing at the display). For example, when the first visitor approaches the interactive area, the interactive portrate system can command the display of a meteor or other suitable initial output. Next, when the second visitor approaches the interactive area, the interactive portrate system can command the display of a meteor or other suitable initial output. In this way, for each visitor (or group of visitors) who performs a particular action and / or shows sufficient interest (e.g., each visitor or group of visitors approaching the interactive area), the interactive portrate system can provide an appropriate initial output to attempt to engage that visitor (or group of visitors). Only some visitors (or groups of visitors) may attempt to view the display and / or show other signs of sufficient interest during and / or after the initial output. However, for each visitor (or group of visitors) who shows signs of sufficient interest during and / or after the first output, the interactive portrate system can then provide additional output to entertain that visitor (or group of visitors) and interact with that visitor (or group of visitors).

[0019] Advantageously, the interactive port rate system can use anonymous characteristics such as clothing items, personal belongings, or the like owned by the user to perform personalized interactions with park visitors. Further, the interactive port rate system can use anonymous identifiers such as achievements within the entertainment facility (e.g., ride completion, team participated) to perform personalized interactions with park visitors. Further, the interactive port rate system can use computer vision when a park visitor is out of range of one or more communication devices and / or sensors (e.g., outside the interactive area), and then, when the park visitor is within range of one or more communication devices and / or via sensors (e.g., within the interactive area), additional information can be collected via communication with the device carried by the park visitor. In this way, the interactive port rate system can execute a multi-stage engagement process to attract park visitors to the interactive area and then make the park visitors enjoy themselves in the interactive area. However, it should be understood that various techniques and processes for engaging park visitors are envisioned.

[0020] FIG. 1 is a schematic diagram of an embodiment of an interactive portrait system 10 when a visitor 12 (e.g., a first visitor) approaches the interactive area 14. The interactive portrait system 10 can include a controller 18 having a processor 20 and a memory device 22. The interactive portrait system 10 can also include a communication device 24, a camera 26, a sensor 28, a display 30, and / or a speaker 32 communicatively coupled to the controller 18. The interactive area 14 is generally an area proximate to and / or in front of the display 30. As shown, the visitor 12 can move along a path 34 (e.g., a sidewalk) and approach the interactive area 14. The visitor 12 can also carry (e.g., wear, hold, move with) a portable object 40. The portable object 40 can be any suitable type of object, such as a wearable band, jewelry, a toy, a wand, a mobile phone, etc. However, in one embodiment, to provide an additional layer of anonymity and / or to avoid receiving identification information by the interactive portrait system 10, the interactive portrait system 10 can not communicate with the visitor 12's mobile phone and / or not receive identification information from the visitor 12's mobile phone.

[0021] During operation, camera 26 can capture image data (e.g., one or more images; a capture device) within the field of view of camera 26. Camera 26 can capture image data from an environment surrounding and / or including interactive area 14. For example, the image data can include park visitor 12 as park visitor 12 moves along path 34 towards interactive area 14. Controller 18 can receive and process the image data using computer vision techniques to identify one or more characteristics (e.g., attributes) of park visitor 12. One or more characteristics of park visitor 12 can be anonymous characteristics, such as the color of clothing, the type of clothing, symbols or other prints on the clothing, accessories worn by the park visitor, personal belongings carried by the park visitor, etc. That is, the one or more characteristics may not include personally identifiable information (PII). The term PII can include information that directly indicates an individual (e.g., name, address, social security number, phone number) or data elements related to an individual (e.g., gender, race, date of birth, combination of geographical indications; face recognition). Accordingly, interactive portrait system 10 can use visual context cues, optionally in combination with an identifier from portable object 40 (e.g., using only visual context cues; or using only visual context cues and an identifier), and / or sensor data from sensor 28 to initiate and / or execute an interaction with park visitor 12.

[0022] The controller 18 can also process the image data to determine the actions of the visitor 12 and / or the position of the visitor 12 such as moving towards the interactive area 14 and / or being located within the interactive area 14. In one embodiment, markers 36 may be drawn on the ground to mark the boundaries of the interactive area 14, and the image data may indicate that the visitor 12 is standing within the boundaries of the interactive area 14. However, it should be understood that the controller 18 does not require the markers 36 and instead can determine that the visitor 12 is within the boundaries of the interactive area 14 by the relative positioning of the visitor 12 within the field of view of the camera 26. Thus, the controller 18 can process the image data to determine various actions of the visitor 12 (e.g., movements such as walking movements, gestures, mouth movements, etc.), line of sight direction, facial expressions, emotions, and / or other actions. In fact, the controller 18 utilizes an AI algorithm to process the image data and determine whether the visitor 12 shows sufficient signs of interest in the interactive area 14 (e.g., before the initial output; to trigger the initial output). For example, a specific movement or combination of movement / sound (e.g., an action; a gaze at the interactive area 14 for a threshold period such as 3 seconds or more) can indicate sufficient interest in the interactive area 14, indicating that the visitor 12 is likely to be involved (e.g., respond, interact) if the initial output is presented.

[0023] In one embodiment, the communication device 24 can communicate with each communication device 38 of the portable object 40. For example, the communication device 24 can be a radio frequency identification (RFID) reader configured to communicate with (e.g., read) the RFID tag of the portable object 40. As another example, the communication device 24 can be a transceiver configured to communicate with each transceiver of the portable object 40 via any suitable wireless protocol (e.g., Bluetooth (registered trademark)). In such a case, the position of the visitor 12 with respect to the interactive area 14 can be indicated by the strength of the signal received by the communication device 24 and / or triangulation techniques (e.g., based on the signals received by multiple communication devices 24). Additionally or alternatively, the communication device 24 can receive an identifier (e.g., a unique identifier) from the RFID tag and / or the storage device of the portable object. In such a case, the communication device 24 can provide the identifier to the controller 18, and the controller 18 can then use the identifier to access data from one or more databases 42. The data can include the performance related to the portable object 40. For example, the visitor 12 can carry the portable object 40 to each ride attraction in the entertainment facility, and at the completion of each ride attraction, the respective performance is associated with the identifier and stored in the database 42. In some cases, the data can include information about the visitor 12 and / or the preferences of the visitor 12, such as teams and / or favorite animations. It should be understood that the communication device 24 can additionally or alternatively receive data from the portable object 40 (e.g., from the storage device on the portable object). Further, in one embodiment, the sensor 28 (e.g., proximity sensor, pressure / weight sensor, temperature sensor, optical sensor) can detect the position of the visitor 12 with respect to the interactive area 14 and / or the behavior of the visitor 12. The sensor 28 can also include a microphone for detecting audible input (e.g., spoken words or expressions) from the visitor 12.

[0024] Accordingly, the controller 18 can analyze the image data, communication device, sensor data, and / or other data to determine the characteristics of the visitors, the behavior of the visitors, the position of the visitors 12 relative to the interactive area 14, and / or the prior performance of the visitors 12. In response to the visitors 12 showing sufficient interest, such as approaching (e.g., walking towards; being proximate to; and / or being within) the interactive area 14, the controller 18 can generate one or more initial outputs to provide an experience to the visitors 12. For example, the controller 18 can instruct the display 30 and / or the speaker 32 to provide an initial output that attempts to initiate an interaction with the visitors 12. In FIG. 1, the initial output is shown as a shooting star 46, which may draw further attention when presented on a display that looks like a painting. The initial output may be the same for all visitors, may be selected rotationally from among the available options, may be selected randomly from among the available options, and / or may be selected from among the available options and personalized for the visitors 12. For example, the initial output can include displaying a shooting star (e.g., being the same for all visitors or otherwise not selected to be personalized for the visitors 12). As another example, the initial output can include displaying a small, blinking flame based on one or more characteristics indicating that the visitors 12 likes a dragon that breathes fire (e.g., printed on the shirt of the visitors 12). Further or alternatively, the initial output can include emitting a sound directed at the visitors 12 (e.g., whispering "Hello" or "Hey, do you like dragons?").

[0025] The controller 18 can continue to analyze the captured data, communication, sensor data, and / or other data, and determine whether the visitor 12 shows sufficient interest during and / or after the initial output (e.g., whether the visitor 12 responds to the initial output). For example, the controller 18 can determine that the visitor 12 has responded to the initial output if the image data, communication, sensor data, and / or other data indicate that the visitor 12 has turned their head towards the display 30 and / or the speaker 32, walked towards the display 30 and / or the speaker 32, stopped walking, and stayed within the interactive area 14. The controller 18 can utilize an AI algorithm to determine whether the visitor 12 responds to the initial output. For example, a specific movement or combination of movement / sound (e.g., behavior; turning the head for more than a threshold time such as 3 seconds and saying "What is that?") may indicate sufficient interest and, if additional output is presented, may indicate that the visitor 12 is likely to continue their engagement.

[0026] When the controller 18 determines that the visitor 12 has responded to the initial output, it can determine that the visitor 12 has participated and proceed to provide an additional output to the visitor 12. The additional output may be the same for all visitors, may be selected from among the available options at random, may be selected from among the available options and personalized for the visitor 12, and / or may be selected from among the available options and be different from the initial output. In one embodiment, the additional output may be enhanced compared to the initial output, such as being larger (e.g., covering more pixels; covering a larger surface area of the display 30), brighter, more colorful, and / or having more movement, such as a display image having more movement. For example, the initial output may include a small flashing lightning strike, and the additional output may include multiple large lightning strikes (e.g., the same type of object but different in size). As another example, the initial output may include a small flashing flame, and the additional output may include a monster throwing fire (e.g., a different type of object / character). As another example, the initial output may include a whisper or a quieter (e.g., lower volume) sound, and the additional output may include a scream or a higher volume sound. In this way, the interactive portrait system can attract the attention of the visitor 12 through the initial output (e.g., a low-level operating state), and then, if the visitor 12 shows sufficient interest in interacting with the interactive portrait system 10 in response to the initial output, it can attempt to provide a more entertaining and immersive additional output (e.g., a high-level operating state). The interactive portrait system 10 can utilize an AI algorithm trained to identify or distinguish signs of interest, such as the visitor 12 gazing at the display 30 for a threshold time or pausing in front of the display 30 for the threshold time.The AI algorithm may be trained to receive some information (e.g., eye gaze, walking, movement, lack of movement, speech, and / or other actions) and identify signs of interest, and may be trained to evaluate the signs of interest, and then prompt the controller 18 to select the visitor 12, provide an initial output to the visitor 12, and / or provide an additional output to the visitor 12. The AI algorithm can be trained to identify an interest sufficient to trigger an initial output and / or an interest sufficient to trigger an additional output. The AI algorithm may be different, and / or the level of interest considered sufficient may be different (e.g., approaching the display 30 is considered an interest sufficient to trigger an initial output but not an interest sufficient to trigger an additional output, instead, gazing at the display 30 for a threshold time and providing an audible response detectable for the initial output is considered an interest sufficient to trigger an additional output).

[0027] It is to be understood that various processes and manners involving the visitor 12 are envisioned. For example, the initial output can be provided to the visitor 12 when the visitor 12 moves near the interactive area 14 and / or is located within the interactive area 14. In some cases, the initial output can be provided periodically (e.g., according to a schedule) and / or reactively (e.g., in response to the visitor 12 being in a specific position relative to the interactive area 14 or in response to the visitor 12 acting in a specific manner). The initial output can be provided while the visitor 12 is gazing at the display 30 or while the visitor 12 is not gazing at the display 30. In one embodiment, the display 30 can initially be blank (e.g., not illuminated or illuminated to a uniform color). Then, as the visitor 12 moves towards the display 30 and / or gazes at the display 30, the controller 18 can command the display 30 to display an image of a flickering flame or other capture device. The controller 18 can time the display of the image such that the image is displayed within the visitor 12's field of view when the visitor 12 passes by the display 30 and / or when the visitor 12 gazes at the display 30. For example, if the image data indicates that the visitor 12 is walking along a path in front of the display 30, the controller can time the display of the image such that the image is displayed as the visitor 12 reaches the front end of the display 30 and / or while the visitor 12 is directly in front of the display 30. As another example, if the image data indicates that the visitor 12 is scanning the environment with their head and line of sight from left to right, the controller 18 can time the display of the image such that the image is displayed when the visitor 12 is facing towards the display 30.As another example, if the date of the image indicates that the visitor 12 is looking at the display 30, the controller 18 can command an immediate (e.g., without delay and as quickly as possible) display of the image so that the image is displayed when the visitor 12 looks at the display 30.

[0028] In one embodiment, the display 30 can display a static scene (e.g., the interior of a store to make the display 30 look like a window of the store or another building). Then, when the visitor 12 moves towards the display 30 and / or gazes at the display 30, the controller 18 can command the display 30 to display a capturing device for an animation moving in the static scene (e.g., the flickering of a fireplace flame in the static scene). The controller 18 can measure the timing of the display of the capturing device so that the capturing device is displayed in the field of view of the visitor 12 when the visitor 12 passes by the display 30 and / or when the visitor 12 gazes at the display 30.

[0029] In one embodiment, the display 30 can display a plurality of animated characters (e.g., a robot and a princess) that interact with each other in conversation. Then, when the visitor 12 moves towards the display 30 and / or gazes at the display 30, the controller 18 can command the display 30 to adjust the plurality of animated characters, for example, to stop their conversation with each other, turn towards the visitor 12, and appear to talk about one or more features of the visitor 12 (e.g., the princess appears to say "I like your giraffe shirt"). The controller 18 can time the change so that the capture device appears within the field of view when the visitor 12 passes by the display 30 and / or when the visitor 12 gazes at the display 30. It should be understood that the AI algorithm can be trained based on various data indicating the behavior of the visitor, including movement, line of sight, and others, to evaluate the interest of the visitor 12 and provide an output in response to detecting sufficient interest of the visitor 12.

[0030] In one embodiment, the initial output can be relatively enhanced with respect to the additional output to make it easier to capture the attention of the visitor 12. In one embodiment, the additional output and the initial output may not be relatively enhanced. Or, the additional output and the initial output may be any suitable animation and / or sound that forms part of the story and / or the interaction with the visitor 12. The display 30 may be surrounded by a frame (e.g., a bezel) and may appear like a framed window, a framed entrance, or the like. Further, the display 30 may be textured to appear like a painting (e.g., an oil painting).

[0031] FIG. 2 is a schematic diagram in an embodiment of the interactive portrait system 10 while the visitor 12 is located in the interactive area 14 (e.g., near or in front of the display 30). As shown, additional output is presented on the display 30, and the additional output includes an animation 48 (e.g., character animation). When the visitor 12 engages in interaction with the interactive portrait system 10 (e.g., as determined by an AI algorithm; as indicated by showing sufficient interest in response to the initial output; by gazing at the display 30, making gestures towards the display 30, changing from a moving pace in front of the display 30 to a stationary position, and / or providing an audible spoken word or expression in response to a prompt directed at the animation on the display 30 and / or emitted through the speaker 32, as evidenced), the controller 18 can execute additional interaction modes. In one embodiment, the controller 18 can process multiple data inputs and provide appropriate animations and / or sounds to continue the interaction. For example, the controller 18 can use AI to generate an animation output by the display 30 and a corresponding prompt output by the speaker 32 (e.g., to make it appear as if the animation is speaking the corresponding prompt) and emulate a natural conversation with the visitor 12 (e.g., a conversation as if between two humans).

[0032] Furthermore, the controller 18 can select animations and corresponding prompts to respond to and / or be personalized for the visitor 12 using data collected via the communication device 24, the camera 26, and / or the sensor 28. For example, the communication device 24 can access an identifier and use this identifier to read out the achievements associated with the portable object 40 carried by the visitor 12. The communication device 24, the camera 26, and / or the sensor can monitor the actions (e.g., movements, expressions) of the visitor 12 during the interaction with the interactive portrait system 10. Further, the sensor 28 can include a microphone that detects voice input from the visitor 12. In this way, multiple inputs may be received over time (e.g., continuously) as the visitor 12 interacts with the animations on the display 30, and the multiple inputs are processed by the controller 18 (e.g., using AI), enabling the controller 18 to provide appropriate responses such as providing a targeted prompt and / or providing the effect of a natural conversation with the visitor 12.

[0033] As pointed out by reference to this specification and FIG. 1, when the visitor 12 moves towards the interactive area 14 or is otherwise selected for the involvement of the controller 18, the controller 18 can provide an initial output. If the visitor 12 responds, the controller 18 can then provide additional outputs to effectuate a dynamic interaction with the visitor 12. However, if the visitor 12 does not respond (e.g., shows insufficient interest as can be determined via an AI algorithm), the controller 18 can retry (e.g., with another initial output to the visitor 12) or select an additional visitor 44. For example, the controller 18 can analyze image data to identify additional visitors 44 approaching the interactive area 14. The controller 18 can then provide the initial output described herein at a particular timing, etc., based on one or more respective features of the additional visitor 44 and / or other features. The controller 18 can continue to attempt to engage with different visitors in this way until one of the different visitors responds to that initial output and begins to interact with the interactive portrait system 10.

[0034] The interactive port rate system 10 disclosed in this specification provides the visitor 12 with an interactive experience that is perhaps unexpected (for example, appears on the fake window of a retail store as the visitor 12 moves along the movement path 34). The interactive experience can be initiated based on the image data captured by the camera 26 and / or other data collected via the communication device 24 and / or the sensor 28. The interactive experience can be initiated by the visitor 12 simply approaching the interactive area 14, changing the line of sight to investigate the interactive environment, and / or speaking a specific word or expression within the range of the sensor 28, by performing one or more of these actions. The interactive experience can be initiated without the visitor 12 performing a key input (for example, without flipping a switch or pressing a button). This can provide efficient processing and computer operation for providing a responsive and realistic interaction with the visitor 12. In fact, the visitor 12 can initiate the interactive experience in a completely passive manner (for example, from the perspective of the visitor 12) simply by approaching the interactive area 14 without directing the line of sight towards the display 30, without speaking, and without providing a key input. The visitor 12 can continue the interactive experience (with at least one additional output) by slowing down the pace when passing in front of the display 30, changing the line of sight to look at the display 30, speaking a specific word or phrase determined to be related to the initial input within the range of the sensor 28, and / or indicating sufficient interest in the initial output (for example, responding to the initial output) without providing a key input. Subsequently, the continuous engagement and interaction may depend on the actions of the visitor 12, such as the position of the visitor 12, the movement of the visitor 12, the gestures made by the visitor 12, the line of sight of the visitor 12, the words or expressions spoken by the visitor 12, etc. For example, the engagement and interaction can continue with the visitor 12 for a certain period (for example, a set period not exceeding 5 minutes) and / or until another visitor approaches the interactive area 14 as long as the visitor 12 continues to engage / respond.

[0035] In one embodiment, visitor 12 moves within the environment around the interactive area 14, but may move outside the range of the communication device 24 and / or the sensor 28. Thus, the controller 18 may have the image data, but may not have additional data regarding the visitor 12 from the communication device 24 and / or the sensor 28. In such a case, the controller 18 can generate an initial output for inducing the visitor 12 to move within the range of the communication device 24 and / or the sensor 28 using information derived from the image data. Thereafter, when the visitor 12 enters the range, the controller 18 can perform a continuous dynamic interaction (e.g., a personalized conversation) with the visitor 12 using information derived from the communication device 24 and / or the sensor 28. In this way, the interactive portrait system 10 can use the image data to track the visitor 12 and attempt to engage with the visitor 12 until the visitor 12 and / or the portable object 40 enter the range of the communication device 24 and / or the sensor 28. It should be understood that the image data can also be used to perform a continuous dynamic interaction with the visitor in addition to the data from the communication device 24 and / or the sensor 28.

[0036] Furthermore, when the visitor 12 enters within the range, the controller 18 may instruct the display 30 and / or the speaker 32 to provide a task (e.g., "execute the box jump 5 times" or "copy the dance movement of the robot") for the visitor 12 to perform in order to collect the degree of achievement. This task can be stored in the database 42 in association with an identifier. The controller 18 can analyze the image data from the camera 26, and / or other data from the communication device 24, and / or other data from the sensor 28 to determine whether the visitor 12 has successfully completed the task. For example, the sensor 28 can include a light detector that tracks the movement of a light emitter on the portable object 40 to track gestures / movements (e.g., waving movement; pointing) performed on the portable object 40. As another example, the sensor 28 can include a pair of a light emitter / detector that emits light and detects the light after being reflected by the portable object 40, and can track gestures / movements performed on the portable object 40. The controller 18 can match the gesture / movement with a target gesture / movement that can be stored and accessed from the database 42 to determine whether the visitor 12 has normally completed the task.

[0037] In one embodiment, the controller 18 can apply an AI algorithm trained with a plurality of gesture / motion sample sets. Further, the AI algorithm can be trained with diverse sample sets and / or can have fuzziness to lower the barriers for certain visitors (e.g., children) who have difficulty accurately performing the target gesture / action. In certain embodiments, the controller 18 can determine whether to apply fuzziness and / or adjust fuzziness using one or more characteristics identified via image data and / or other data (e.g., data stored associated with an identifier; sensor data from one or more sensors 28). For example, if any of the data suggests that the visitor 12 is a child, the controller 18 can provide this as an input to the AI algorithm and / or add fuzziness such that this is accounted for in the evaluation of the gesture / motion.

[0038] The processor 20 can include a microprocessor and can execute software for controlling the display 30, the speaker 32, and / or other features of the interactive portrate system 10. The processor 20 can include a plurality of microprocessors, one or more “general-purpose” microprocessors, one or more special-purpose microprocessors, and / or one or more application-specific integrated circuits (ASICs), or combinations thereof. For example, the processor 20 can include one or more reduced instruction set computer (RISC) processors. The memory device 22 can include volatile memory such as random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM). The memory device 22 can store information such as control software, lookup tables, configuration data, communication device protocols, and the like.

[0039] For example, the memory device 22 can store processor-executable instructions including firmware or software for the processor 20 to execute, such as instructions for generating a derivative, instructions for controlling the display 30, instructions for controlling the speaker 32, and / or instructions for controlling other features of the interactive port rate system 10. In one embodiment, the memory device 22 is a tangible, non-transitory machine-readable medium that can store machine-readable instructions for the processor 20 to execute. The memory device 22 can include a ROM, flash memory, hard drive, any other suitable optical, magnetic, or solid-state storage medium, or a combination thereof. The communication device 24 can facilitate communication (e.g., wireless communication) with other components such as the portable object 40, the database 42, etc. The display 30 can be any suitable type of display, such as a projection screen (e.g., illuminated via light projected by a projector), a liquid crystal display (LCD), an organic light emitting diode display (OLED), and the like. Such a display can include a coating or filter that makes the image presented on the display look like a painting (e.g., an oil painting, a watercolor painting).

[0040] FIG. 3 is a schematic diagram of an embodiment of an interactive portrait system 10 while a plurality of visitors are located in the interactive area 14 to interact with the animation presented on the display 30. The plurality of visitors includes a first visitor 12, a second visitor 50, and a third visitor 52. The controller 18 identifies that a plurality of visitors are in the interactive area 14, selectively engages with the plurality of visitors, and has a dynamic conversation (e.g., an AI-led conversation) with the plurality of visitors sequentially (e.g., having a complete conversation with the first visitor 12, then having a complete conversation with the second visitor 50, and so on) and / or as a group (e.g., dynamically responding to the plurality of visitors based on the respective actions of the plurality of visitors). For example, the controller 18 selects the first visitor 12 (e.g., as the current primary participant) and can identify that the first visitor 12 is wearing a shirt with a monster symbol. Next, the controller 18 can attempt to start a conversation with the first visitor 12 by displaying an animation that appears to look at the first visitor 12 and emitting a corresponding sound including a prompt related to the monster. If the first visitor 12 responds as evidenced by their actions, the controller 18 can continue the response to conduct a conversation with the first visitor 12. Thereafter, at a certain later time (e.g., after a first set time such as 5 minutes, if the first visitor 12 loses interest by leaving, if the second visitor 50 shows interest by responding to the prompt, etc.), the controller 18 selects the second visitor 50 (e.g., as the current first participant) and can identify that the second visitor 50 is carrying a drink. Thereafter, the controller 18 can attempt to start a conversation with the second visitor 50 by displaying an animation that appears to look at the second visitor 50 and emitting a corresponding sound including a prompt related to the drink. If the second visitor 50 responds as apparent from their actions, the controller 18 can continue the response to conduct a conversation with the second visitor 50.The controller 18 may continue in this way as long as there are additional visitors waiting to have their turn to interact with the interactive port rate system 10.

[0041] As described herein, the controller 18 can treat multiple visitors as a group and can permit new visitors to join the group and / or other visitors to leave the group. Thus, the group can change over time. In such a case, the controller 18 can identify one or more respective characteristics, respective identifiers, and / or other respective data associated with the first visitor 12 and the second visitor 50. Next, the controller 18 can attempt to start a conversation as a group with both the first visitor 12 and the second visitor 50, such as by displaying an animation that appears to look at the first visitor 12 and emitting a corresponding sound that includes a prompt related to the monster. Next, the controller 18 can determine that the second visitor 50 has responded to one of the prompts, so the controller 18 can then display an animation that appears to look at the second visitor 50 and emit a corresponding sound that includes a prompt related to a drink. The controller 18 may effectively switch back and forth over time to accommodate different visitors within the group in order to receive multiple types of data and perform dynamic interactions with the multiple visitors.

[0042] When the number of visitors in the group exceeds a threshold value (e.g., 2, 3, 4, 5, 10, 15, or 20 or more visitors), the controller 18 can adjust the interaction based on the number of visitors in the group, such as reducing the words spoken per prompt, reducing the words spoken to each visitor, shortening the prompt spoken to each visitor, reducing the prompt spoken to each visitor, reducing the time involved with each visitor, etc. Similarly, when the number of visitors in the group is less than the threshold value, the controller 18 can adjust the interaction by speaking more words per prompt, speaking more words to each visitor, speaking a longer prompt to each visitor, speaking more prompts to each visitor, involving more time with each visitor, or doing such things. The number of words and / or the length can also change dynamically (e.g., on a sliding scale; following a curve) based on the number of visitors in the group. Thereby, the controller 18 may be able to influence and / or implement the crowd control means through dynamic interaction.

[0043] The interactive port rate system 10 can be configured to perform other techniques in a congested situation. For example, in a congested situation, it may be difficult to accurately associate each of a plurality of visitors with the portable object 40. In one embodiment, the controller 18 collects all the identifiers of the portable objects 40 in the crowd, accesses the database 42 to collect all the achievements associated with the portable objects 40 in the crowd, and then, by selecting one of the called achievements, it may be possible to associate at least some of several visitors with the portable object 40. For example, the controller 18 determines that a visitor has recently completed a ride attraction, instructs the speaker 32 to issue a related prompt (e.g., "Which one completed the ride attraction?"), and instructs the display 30 to animate the character animation so that it appears as if it is speaking the prompt. Next, the image data captured by the camera 26 can identify the responding visitor (e.g., by raising a hand or moving the mouth to speak). The sensor data captured by the sensor 28 (e.g., an omnidirectional microphone) can also identify the responding visitor (e.g., by speaking). Therefore, the image data and / or the sensor data can identify the responding visitor, and the controller 18 can then use the image data and / or the sensor data to identify the position of the visitor, the visitor, and / or one or more characteristics of the visitor. Next, the controller 18 can control the display 30 and the speaker 32 to conduct a conversation with the visitor (e.g., the animated character faces the visitor and appears to be speaking a prompt such as "Ok. I like the monster on your shirt" issued by the speaker 32). At a later point in time, the controller 18 can select another achievement associated with another portable object 40 and attempt to initiate an interaction with another visitor. In any case, the interaction can be AI-driven to be dynamic and responsive to the visitor, thereby providing an enjoyable and natural interaction with the visitor.

[0044] FIG. 4 is a flowchart of an embodiment of a method 80 for operating an interactive portrait system 10. The method 80 includes various steps represented by blocks. It should be noted that the method 80 can be executed as an automated procedure by a system such as an interactive portrait system. Although the flowchart illustrates the steps in a certain order, it is to be understood that the steps may be executed in any suitable order and, where appropriate, certain steps may be executed simultaneously. Further, specific steps or portions of the method 80 can be executed by separate systems or devices.

[0045] In block 82, the method 80 can begin by identifying a visitor (e.g., a potential user of the interactive portrait system). For example, image data captured by a camera can include the visitor, and a controller can analyze the image data to identify one or more characteristics of the visitor. The field of view of the camera can be set to capture the interactive area in front of the display and / or the environment surrounding the interactive area. In this way, the image data can include the visitor, for example, when the visitor approaches the interactive area and / or when the visitor interacts with the media on the display.

[0046] In block 84, method 80 can continue to attempt to interact with visitors by instructing an initial output of an image (e.g., a capture device) via a display and / or sound via a speaker. As defined herein, the initial output can be intended to provide some visual and / or audible effect to attract the attention of the visitors. The initial output can be the same for all visitors, selected rotationally from among the available options, selected randomly from among the available options, and / or selected from among the available options and personalized for the visitors. For example, the initial output can include displaying a meteor (e.g., the same for all visitors or not selected to be personalized for the visitors). As another example, the initial output can include displaying a small, blinking flame due to one or more characteristics indicating that the visitor likes a dragon that breathes fire (e.g., printed on the visitor's shirt). Additionally or alternatively, the initial output can include emitting a sound directed at the visitor (e.g., whispering "Hello" or "Hey, do you like dragons?"). The initial output may be provided in response to the controller determining that the visitor is showing sufficient interest (e.g., approaching the interactive area and / or gazing at the display). The controller can utilize an AI algorithm to determine that the visitor is showing sufficient interest.

[0047] In block 86, method 80 can continue to analyze image data and / or other data (e.g., communication data generated by a communication device connected to an object carried by a visitor; sensor data generated by sensors related to an interactive area) to determine whether a visitor shows sufficient interest (e.g., responds; participates) in the initial output. For example, if the image data and / or other data indicate that the visitor turned their head towards the display and / or speaker, walked towards the display and / or speaker, said a specific word or expression indicating involvement or interest (e.g., "What was that?" or "Let's go see the fire"), and / or stopped walking and stayed within the interactive area, the controller can determine that the visitor has responded to the initial output. The controller can utilize an AI algorithm to determine that the visitor has responded to the initial output.

[0048] If a visitor is involved, method 80 can proceed to block 88. At block 88, method 80 can include instructing additional output of an image via a display and / or additional output of sound via a speaker to continue the interaction with the visitor. The additional output may be the same for all visitors, may be selected via rotation from among the available options, may be randomly selected from among the available options, and / or may be selected from among the available options and personalized for the visitor. The additional output may be different from the initial output. In one embodiment, the additional output can be enhanced compared to the initial output, such as a display image that is larger, brighter, more colorful, and / or has more movement compared to the initial output. In this way, the interactive portrait system can attract the customer's attention with the initial output and then, if the customer shows interest in interacting with the interactive portrait system, attempt to provide a more entertaining and immersive additional output. This can provide efficient processing and computer operation (e.g., by reserving computer resources and performing substantial processing in response to the visitor's interaction with the interactive portrait system).

[0049] When the visitor is within the range of the communication device and the visitor has their own portable object, method 80 can proceed to block 90. At block 90, method 80 can detect an identifier and / or obtain data through communication with a portable object carried by the visitor in other ways. For example, the controller can be coupled to an RFID reader configured to read an identifier from the RFID tag of the portable object. Next, the controller can use the identifier to access the records stored in the database associated with the identifier. Further, in one embodiment, the controller can continue to interact with the visitor based on the identifier and / or the data accessed through communication with the portable object carried by the visitor for additional output of an image via a display and / or sound via a speaker. It should be understood that the interactive portrait system can also include sensors, and the controller can provide an output based on sensor data from the sensors. As described herein, the interactive portrait system may switch between different visitors to provide interactions with different visitors (e.g., image data, one or more characteristics of the visitor, an identifier associated with the visitor, sensor data associated with the visitor; based on AI-driven interactions).

[0050] The interactive portrate system can include and / or operate any of various show effects, such as show effects other than a display and / or a speaker. For example, the show effects can include a light-emitting element that emits light for illuminating an area (e.g., a room), a haptic device that outputs a tactile effect (e.g., an air flow including vibration, a cold air flow, and / or a warm air flow), a torch that outputs a flame (e.g., hot air), etc. In an embodiment, the interactive portrate system can utilize AI to respond to and / or implement the show effects. For example, the interactive portrate system can determine that a visitor is wearing a winter coat and is likely to be cold, and then operate the haptic device to provide a warm air flow and / or operate the torch to output a flame to warm the visitor. Such show effects can also correspond to an image on a display and / or sound from a speaker so as to provide a consistent story and experience to the visitor (e.g., a flame on the display may be accompanied by warm air).

[0051] An interactive port rate system can enable the improvement of the interaction between park visitors and show attractions in entertainment facilities. It should be understood that the interactive port rate system may be modular and can be transported to different show attractions and / or different locations within the entertainment facility. In fact, the interactive port rate system can be connected to a movable robot (e.g., autonomously controlled to move within the entertainment facility or remotely controlled by an operator). In such a case, the movable robot can include a display, a speaker, a camera, a sensor, a communication device, and / or a controller (which is part of a remote computing system such as a cloud computing system or a central computing system or can communicate with a remote computing system to facilitate access to processing steps and / or databases). The movable robot can walk around the entertainment facility and interact with park visitors by executing the technologies disclosed herein (e.g., when a park visitor approaches the movable robot). However, the movable robot can also move relative to the customers (e.g., towards the customers) to draw the customers within the range of, for example, the communication device and / or the sensor.

[0052] In addition, the interaction can be carried out under the guidance of the AI, but it should be understood that an output can be provided via a display and / or a speaker such that an operator (e.g., a real person, a cast) guides the operator to talk to the visitors. Accordingly, the interactive portrait system can use the AI to determine the level of interest of the visitors and / or determine an appropriate output that the visitors are likely to be interested in. However, the interactive portrait system can provide instructions to the operator to talk an appropriate output to the visitors. In one embodiment, the interaction is initiated under the guidance of the AI (e.g., the first output and / or some outputs) via an output provided to the operator via a display and / or a speaker, and then the operator can continue the interaction without the guidance of the AI. Similarly, in one embodiment, the interaction may be carried out via an AI-driven interaction via a display and / or a speaker for the visitors, and the operator may monitor the output and / or may be able to intervene during the interaction (e.g., selection of the output, blocking of the output).

[0053] In one embodiment, supervised AI / machine learning can be implemented while specific known examples that correlate with future predictions are available. In supervised AI / machine learning, the mathematical model of the dataset includes both the input and the desired output. This data is called "training data" and is basically a set of training examples. Each training example has one or more inputs and a desired output, also known as a monitoring signal. In the mathematical model, each training example is represented as an array or vector, also called a feature vector, and the training data is represented as a matrix. The supervised learning algorithm can learn a function that can be used to predict the output associated with new inputs by repeatedly optimizing the objective function. The optimal function enables the algorithm to correctly determine the output of inputs not included in the training data. An algorithm that improves the accuracy of the output or prediction over time is said to have learned to perform that task. Supervised learning algorithms include classification and regression. Classification algorithms are used when the output is limited to a set of discrete values, and regression algorithms are used when the output can have any numerical value within a range. Furthermore, similarity learning is a field of supervised machine learning that is closely related to regression and classification, but its purpose is to learn from examples using a similarity function that determines the degree to which two objects are similar or related.

[0054] Additionally and / or alternatively, depending on the situation, it may be beneficial to utilize unsupervised learning (e.g., when a specific output type is unknown). Unsupervised learning algorithms receive a dataset containing only inputs and find structures within the data such as grouping or clustering of data points. Thus, this algorithm learns from unlabeled, unclassified, or test data. Unsupervised learning algorithms identify commonalities in the data and respond based on the presence or absence of such commonalities for each new piece of data, rather than responding to feedback. In any case, AI (e.g., machine learning) can be used to identify signs of interest from visitors and to determine appropriate outputs for interacting with visitors in order to provide dynamic and personalized interactions with them.

[0055] In this specification, only specific features of the present disclosure have been illustrated and described, but many modifications and variations will occur to those skilled in the art. Accordingly, it should be understood that the appended claims are intended to cover all such modifications and variations that fall within the true technical spirit of the present disclosure.

[0056] The methods presented and claimed in this specification refer to and are applied to practical and substantial purposes and specific examples that clearly improve the technical field of the present invention, and for this reason, are not abstract, intangible, or truly theoretical. Further, if any of the claims appended at the end of this specification contain one or more elements designated as "means for [performing]... [function]" or "steps for [performing]... [function]", such elements shall be construed in accordance with 35 U.S.C. § 112(f). However, for any claim containing elements designated in any other way, such elements shall not be construed in accordance with 35 U.S.C. § 112(f).

Explanation of Reference Numerals

[0057] 10 Interactive Portrait System 12 Visitor 14 Interactive Area 18 Controller 20 Processor 22 Memory Device 24 Communication Device 26 Camera 28 Sensor 30 Display 32 Speaker 34 Route

Claims

1. An interactive portrait system, A camera configured to capture images of the environment, Controller and The controller is equipped with, By analyzing the aforementioned images, the park visitors in the aforementioned environment are identified, The output device is instructed to provide an initial output for attempting to interact with the aforementioned park visitors, The image is analyzed to identify the visitor's actions during the initial output, after the initial output, or both. The process involves evaluating the visitor's behavior using one or more artificial intelligence algorithms and determining whether the visitor responded to the initial output, In response to determining that the visitor has responded to the initial output, the system provides an additional output and instructs the output device to continue attempting to interact with the visitor. In response to the determination that the aforementioned visitor did not respond to the initial output, Blocking the output device from providing the additional output, By analyzing the aforementioned images, additional visitors within the environment can be identified, To provide each initial output and instruct the output device to attempt to interact with the additional visitors, An interactive portrait system configured to perform the following actions.

2. The interactive portrait system according to claim 1, wherein the initial output comprises a first animation of a first type of object or character, and the additional output comprises a second animation of a second type of object or character different from the first type of object or character.

3. The interactive portrait system according to claim 1, wherein the initial output comprises a first animation, and the additional output comprises a second animation, the second animation being larger than the first animation.

4. The interactive portrait system according to claim 1, wherein the initial output comprises a first sound, the additional output comprises a second sound, and the volume of the first sound is lower than that of the second sound.

5. The interactive portrait system according to claim 1, wherein the controller is configured to analyze the image and identify one or more features of the visitor, and the initial output, the additional output, or both are based on one or more features of the visitor.

6. The interactive portrait system according to claim 1, wherein the actions include the visitor turning their head towards the output device, focusing their gaze on or near the output device, standing in front of the output device, walking toward the output device, or any combination thereof.

7. The interactive portrait system according to claim 1, further comprising a communication device communicatively coupled to the controller, wherein the communication device is configured to communicate with a portable object carried by the visitor and to read an identifier from the portable object.

8. The interactive portrait system according to claim 7, wherein the controller is configured to use the identifier to search a database of performance associated with the identifier, and the initial output, the additional output, or both are based on performance associated with the identifier.

9. The interactive portrait system according to claim 1, wherein the controller is configured to use one or more artificial intelligence algorithms to provide the initial output, the additional output, or both, to the visitor in a personalized manner based on the image.

10. It is an entertainment facility, Routes for moving between interactive areas, A display and speaker are positioned adjacent to the aforementioned interactive area, A camera configured to capture images of the aforementioned interactive area, A microphone configured to capture sound within the aforementioned interactive area, Controller and The controller is equipped with, The aforementioned images are analyzed to identify visitors moving along the aforementioned path toward the interactive area, When the visitor approaches the interactive area, the display, the speaker, or both are instructed to provide an initial output attempting to interact with the visitor. Analyzing the aforementioned images, sounds, or both to identify the visitor's actions during the initial output, after the initial output, or both; The process involves evaluating the visitor's behavior using one or more artificial intelligence algorithms and determining whether the visitor responded to the initial output, In response to determining that the visitor has responded to the initial output, the system provides additional output to the display and the speaker, and commands them to engage in conversational interaction with the visitor. An entertainment facility configured to provide entertainment.

11. The entertainment facility according to claim 10, wherein the initial output comprises a first animation, and the additional output comprises a second animation, the second animation being larger than the first animation.

12. The entertainment facility according to claim 10, wherein the initial output comprises a first sound, the additional output comprises a second sound, and the first sound is quieter than the second sound.

13. The amusement facility according to claim 10, wherein the controller is configured to analyze the image and identify one or more characteristics of the visitor, and the initial output, the additional output, or both are based on one or more characteristics of the visitor.

14. The aforementioned actions are, The visitor turns their head towards the display, the speaker, or both. The visitor focuses their gaze on the display, the speaker, or both. The visitor speaks a word or expression related to the initial output, Or a combination of these, An entertainment facility according to claim 10, including the following:

15. The controller is equipped with a communication device that is responsively coupled to it. The communication device is configured to communicate with a portable object carried by the park visitor and to obtain an identifier from the portable object. The controller is configured to use the identifier to search a database of records associated with the identifier. The initial output, the additional output, or both are based on the performance associated with the identifier. The entertainment facility according to claim 10.

16. The amusement facility according to claim 10, wherein the controller is configured to perform the conversational interaction using the one or more artificial intelligence algorithms.

17. A method for operating an interactive portrait system in an entertainment facility, A step of using one or more processors to analyze images captured by a camera and to identify the behavior of visitors as they move along a path through the interactive area of ​​the entertainment facility, A step of using the one or more processors described above to evaluate the behavior of the park visitors and to determine whether the visitors showed signs of interest in the interactive area of ​​the entertainment facility, A step of using the one or more processors to analyze the image and identify one or more features of one or more items worn or carried by the visitor, In response to determining that the visitor has shown signs of interest in the interactive area of ​​the amusement facility, the step of using one or more processors to instruct an output device to provide an initial output to attempt interaction with the visitor when the visitor approaches the interactive area of ​​the amusement facility, wherein the initial output is based on one or more features of one or more articles worn or carried by the visitor. A step of using one or more processors to evaluate the visitor's behavior during, after, or both of the initial output, and determining whether the visitor responded to the initial output. In response to determining that the visitor has responded to the initial output, the one or more processors are used to provide an additional output to the output device and instruct it to engage in conversational interaction with the visitor. Methods that include...

18. The aforementioned one or more articles include clothing worn by the visitor, accessories worn by the visitor, personal belongings carried by the visitor, or any combination thereof. The one or more of the above features include color, type, print, or any combination thereof. The method according to claim 17.

19. The method according to claim 17, further comprising the step of using one or more processors to evaluate the behavior of the park visitors using one or more artificial intelligence algorithms.

20. The method according to claim 17, further comprising the step of using one or more of the above-mentioned processors to analyze sound captured by a microphone and identify the behavior of the park visitors.

21. It is an interactive system, A camera configured to capture images of the environment over time, Controller and The controller is equipped with, By analyzing the first portion of the aforementioned image, the park visitors in the environment are identified, The output device is instructed to provide an initial output for attempting to interact with the aforementioned park visitors, The second portion of the aforementioned image is analyzed to determine whether the visitor responded to the initial output, In response to determining that the visitor has responded to the initial output, the output device is instructed to provide additional output specific to the visitor. In response to determining that the visitor did not respond to the initial output, the output device blocks providing additional outputs specific to the visitor. An interactive system configured to perform the following actions.

22. The controller is equipped with a communication device that is communicatively coupled to it, and the communication device is configured to communicate with a portable object carried by the park visitor and to read an identifier from the portable object. The controller uses the identifier to search a database of suitable animations associated with the identifier, and the additional output specific to the visitor is configured to include an animation corresponding to the suitable animation. The interactive system according to claim 21.

23. The controller is equipped with a communication device that is communicatively coupled to it, and the communication device is configured to communicate with a portable object carried by the park visitor and to read an identifier from the portable object. The controller is configured to use the identifier to search a database of performance data associated with the identifier, and the additional visitor-specific output is based on the performance data associated with the identifier. The interactive system according to claim 21.

24. The interactive system according to claim 21, wherein the controller is configured to analyze a first portion of the image to identify one or more characteristics of the visitor, and the additional visitor-specific output is based on the one or more characteristics of the visitor.

25. The interactive system according to claim 24, wherein the one or more features include the color of the clothing worn by the visitor, the type of clothing worn by the visitor, a symbol on the clothing worn by the visitor, a print on the clothing worn by the visitor, an accessory worn by the visitor, a personal belongings carried by the visitor, or any combination thereof.

26. The interactive system according to claim 21, wherein the controller is configured to analyze a second portion of the image and determine that the visitor has responded to the initial output based on the visitor turning their head towards the output device, focusing their gaze on or near the output device, standing in front of the output device, walking toward the output device, or any combination thereof.

27. The controller, in response to determining that the visitor did not respond to the initial output, Analyzing the third portion of the aforementioned image to identify additional visitors within the environment, Commanding the output device to provide the initial output or another initial output for attempting to interact with the additional visitors, The interactive system according to claim 21, configured to perform the following:

28. The interactive system according to claim 21, wherein the initial output includes an initial output specific to each visitor.

29. The interactive system according to claim 21, wherein the output device comprises a display and a speaker that provide visual and audible components in the initial output, the additional output specific to the visitor, or both.

30. The interactive system according to claim 21, wherein the controller is configured to analyze a first portion of the image to identify a visitor moving along a path in the environment toward the output device, and when the visitor approaches the output device, the controller is configured to instruct the output device to provide the initial output for attempting to interact with the visitor.

31. The interactive system according to claim 21, wherein the additional output specific to the visitor includes a conversational interaction with the visitor, and the controller is configured to perform the conversational interaction with the visitor using one or more artificial intelligence algorithms.

32. It is an interactive system, A controller is provided, and the controller is Commanding an output device to provide an initial output for attempting to interact with one or more visitors in the environment, The system analyzes images received from one or more cameras to determine whether at least one of the one or more visitors responded to the initial output. In response to determining that at least one of the one or more visitors has responded to the initial output, the output device is instructed to provide an enhanced additional output. In response to determining that one or more visitors did not respond to the initial output, the output device blocks providing the enhanced additional output. An interactive system configured to perform the following actions.

33. The interactive system according to claim 32, wherein the controller is configured to analyze sound received from one or more microphones and determine whether at least one of the one or more visitors has responded to the initial output.

34. The interactive system according to claim 32, wherein the initial output, the enhanced additional output, or both are based on one or more characteristics of the one or more visitors, and the controller is configured to identify the one or more characteristics of the one or more visitors based on the image, based on one or more identifiers received via radio frequency communication with one or more portable objects carried by the one or more visitors, or based on any combination thereof.

35. The controller is configured to perform multi-stage engagement with the one or more visitors, In response to one or more visitors entering the field of view of one or more cameras, initial information is collected from the images received from the one or more cameras using computer vision. Using the aforementioned initial information, determine whether at least one of the one or two or more visitors responded to the initial output, provide the initial output, or do both. The interactive system according to claim 32, configured to perform the following actions.

36. The controller is configured to perform the multi-stage interaction with the one or more visitors, In response to one or more visitors entering the communication range of the radio frequency reader, additional information is collected using radio frequency communication from one or more portable objects carried by the one or more visitors. Using the aforementioned additional information, determine whether at least one of the one or two or more visitors responded to the initial output, provide the initial output, provide the enhanced additional output, or perform any combination thereof. The interactive system according to claim 35, configured to perform the following:

37. The interactive system according to claim 32, wherein the enhanced additional output includes conversational interaction with at least one of the one or more visitors, and the controller is configured to perform the conversational interaction with at least one of the one or more visitors using one or more artificial intelligence algorithms.

38. The interactive system according to claim 32, wherein the initial output is not specific to a visitor, but is selected from a plurality of available initial outputs based on a rotation schedule.

39. A method for operating an interactive system, Using one or more processors, instruct an output device to provide an initial output for attempting to interact with one or more visitors in the environment, Using the one or more processors, the image captured by the camera is analyzed to determine whether at least one of the one or more visitors showed signs of interest in the initial output. In response to determining that at least one of the one or more visitors has shown signs of interest in the initial output, the one or more processors instruct the output device to provide additional visitor-specific outputs to continue attempting to interact with at least one of the one or more visitors. Methods that include...

40. The method according to claim 39, comprising using the one or more processors and one or more artificial intelligence algorithms to instruct the output device to perform a conversational interaction with at least one of the one or more visitors and provide additional output specific to the visitor.

Images