Interactive image system and method

Abstract

An interactive portrait system 10 includes a camera 26 configured to capture an image of an environment 14; and a controller 18. The controller 18 is configured to analyze the image to identify a customer 12 in the environment 14, instruct the output device 30 to provide an initial output 46 to attempt to interact with the customer 12, and analyze the image to identify a behavior of the customer 12 during, after, or both the initial output 46. The controller 18 is further configured to evaluate the behavior of the customer 12 using one or more artificial intelligence algorithms to determine whether the customer 12 is responsive to the initial output 46. The controller 18 is further configured to, in response to determining that the customer 12 is responsive to the initial output 46, instruct the output device 30 to provide an additional output 48 to continue to attempt to interact with the customer 12.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and the benefit of U.S. Provisional Application No. 63 / 354,886, filed on June 23, 2022, entitled “INTERACTIVE IMAGERY SYSTEMS AND METHODS,” which is incorporated herein by reference in its entirety for all purposes. Background Art

[0002] This section is intended to introduce the reader to various aspects of the technology that may be related to various aspects of the present disclosure, which are described and / or claimed below. It is believed that this discussion is helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. Therefore, it is understood that these statements are to be read in this light, and not as admissions of prior art.

[0003] Theme parks, amusement parks, theaters, cinemas, stadiums, concert halls, and the like provide patrons with a variety of immersive experiences. These entertainment venues may include performance attractions (e.g., movies, plays, rides, games) that provide patrons with immersive experiences. For example, traditional performance attractions may utilize various combinations of physical performance elements (e.g., props), display elements (e.g., animations), and lighting to create visual effects for patrons. As entertainment venues become more popular, patrons have an increased expectation for improvements and changes to immersive experiences. Summary of the invention

[0004] Certain embodiments commensurate in scope with the originally claimed subject matter are summarized below. These embodiments are not intended to limit the scope of the present disclosure, but rather these embodiments are intended only to provide a brief overview of certain disclosed embodiments. Indeed, the present disclosure may encompass a wide variety of forms that may be similar or different from the embodiments explained below.

[0005] In one embodiment, an interactive portrait system includes: a camera configured to capture an image of an environment; and a controller. The controller is configured to analyze the image to identify a customer in the environment, instruct an output device to provide an initial output in an attempt to interact with the customer, and analyze the image to identify the customer's behavior during, after, or both the initial output. The controller is further configured to evaluate the customer's behavior using one or more artificial intelligence algorithms to determine whether the customer responded to the initial output. The controller is further configured to, in response to determining that the customer responded to the initial output, instruct the output device to provide additional output to continue attempting to interact with the customer.

[0006] In one embodiment, an entertainment venue includes: a path through an interactive area, a display and a speaker located near the interactive area, a camera configured to capture an image of the interactive area, a microphone configured to capture sounds within the interactive area, and a controller. The controller is configured to analyze the image to identify a customer traveling along the path toward the interactive area, and instruct the display, the speaker, or both to provide an initial output to attempt to interact with the customer when the customer approaches the interactive area. The controller is also configured to analyze the image, the sound, or both to identify the customer's behavior during the initial output, after the initial output, or both. The controller is also configured to evaluate the customer's behavior using one or more artificial intelligence algorithms to determine whether the customer responded to the initial output. The controller is also configured to: in response to determining that the customer responded to the initial output, instruct the display and the speaker to provide additional output to conduct a conversational interaction with the customer.

[0007] In one embodiment, a method of operating an interactive portrait system in an entertainment venue includes: using one or more processors to analyze images captured by a camera to identify behavior of a patron. The method also includes using the one or more processors and one or more artificial intelligence algorithms to evaluate the patron's behavior to determine whether the patron shows signs of interest in an interactive area of ​​the entertainment venue. The method also includes: in response to determining that the patron shows signs of interest in the interactive area of ​​the entertainment venue and using the one or more processors, instructing an output device to provide an initial output to attempt to interact with the patron. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters refer to like parts throughout the drawings, and in which:

[0009] Figure 1 is a schematic diagram of an interactive portrait system as a customer approaches an interactive area including a display according to an aspect of the present disclosure;

[0010] Figure 2 According to one aspect of the present disclosure, when a customer is located in an interactive area to interact with an animation presented on a display Figure 1 Schematic diagram of the interactive portrait system;

[0011] Figure 3 According to one aspect of the present disclosure, when multiple customers are located in an interactive area to interact with the animation presented on the display Figure 1 A schematic diagram of an interactive portrait system; and

[0012] Figure 4 An operation according to one aspect of the present disclosure is Figure 1A flow chart of a method of an interactive portrait system. DETAILED DESCRIPTION

[0013] One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in this specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, many implementation-specific decisions must be made to achieve the developer's specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. In addition, it should be appreciated that such development work may be complex and time-consuming, but will be no more than a routine task of design, fabrication, and manufacturing for a person of ordinary skill having the benefit of this disclosure.

[0014] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that there are one or more of the elements. The terms "comprising," "including," and "having" are intended to be inclusive, and mean that there may be additional elements besides the listed elements. Additionally, it should be understood that references to "one embodiment" or "an embodiment" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

[0015] The present disclosure generally relates to interactive portrait systems and methods for entertainment venues (e.g., theme parks, amusement parks, theaters, cinemas, stadiums, concert halls). More specifically, the present disclosure relates to an interactive portrait system that provides dynamic personalized interactions with customers. The interactive portrait system can collect information about customers using various technologies (such as computer vision) to identify the characteristics, behaviors, and / or locations of customers. The interactive portrait system can communicate with a device associated with the customer to obtain an identifier and / or related data, which can indicate the characteristics, behaviors, locations, and / or previous achievements of the customer. The interactive portrait system can communicate with one or more sensors to obtain sensor data that can indicate the characteristics, behaviors, and / or locations of the customer. In one embodiment, the interactive portrait system uses artificial intelligence (AI) (e.g., machine learning) to evaluate the interests of customers and / or to control outputs to effectively interact with customers. For example, the interactive portrait system can use an AI algorithm to evaluate images to determine that the customer is staring at a display (e.g., a display screen) in a manner that shows sufficient interest (e.g., if an output is presented, the customer is likely to participate). The interactive portrait system may then utilize the AI ​​algorithm to display animations and / or sound based on the customer's characteristics, identifiers and / or related data, the customer's behavior, the customer's location, and / or the customer's prior achievements. Further, the interactive portrait system may utilize the AI ​​algorithm to perform a conversational interaction with the customer (e.g., simulating a natural conversation between two people).

[0016] As a more specific example, the interactive system may use one or more cameras to capture image data of the environment (e.g., one or more images; images). The interactive portrait system may use computer vision to analyze the image data to identify the customer. This may include using computer vision to analyze the image data to identify one or more characteristics of the customer, such as to identify a first customer wearing a red shirt with a first team logo (e.g., the Dragons). Additionally or alternatively, this may include using computer vision to analyze the image data to identify the customer's behavior (such as, the customer's movement) and / or the customer's location (such as, along a path in the environment). It should be appreciated that the interactive portrait system may additionally or alternatively obtain other types of data, including identifiers obtained via communication with a device carried by the customer and / or sensor data obtained via the one or more sensors.

[0017] The interactive portrait system may process images and / or other types of data to assess the interests of the customer and to determine whether to attempt to engage the customer. For example, the interactive portrait system may process images and / or other types of data to identify that the first customer is walking along a path toward an interactive area located near the display(s) (e.g., display(s)) and speaker(s). In response, the interactive portrait system may generate an initial output to attempt to engage the first customer and initiate interaction with the first customer. The initial output may be consistent across all customers, selected via rotation among available options, randomly selected among available options, and / or selected from available options to be personalized to the first customer based on characteristics and / or other information related to the first customer. For example, the initial output may include displaying a shooting star (e.g., consistent across all customers, or otherwise not selected to be personalized to the first customer based on characteristics and / or other information related to the first customer). As another example, the initial output may include displaying a small flickering flame representing a fire-breathing dragon in the distance, displaying a first team logo, and / or emitting a voice directed to the first customer (e.g., "Hey, the dragon team is my favorite") to provide the initial output to be personalized to the first customer based on characteristics and / or other information related to the first customer.

[0018] The interactive portrait system may monitor the response of the first customer (e.g., assess the first customer's interest during or after the initial output). For example, if the image data indicates that the first customer turns their head toward the interactive area (e.g., toward the display and / or speaker), the interactive portrait system may determine that the first customer is sufficiently interested (e.g., engaged) and then provide the first customer with additional output. The additional output may also be consistent across all customers, selected via rotation among available options, randomly selected among available options, and / or selected from available options to be personalized to the first customer based on characteristics and / or other information related to the first customer. The additional output may be different from the initial output. In an embodiment, the additional output may be enhanced compared to the initial output, such as, for example, a display image that is larger (e.g., across more pixels; across a larger surface area of ​​the display), brighter, more vivid, and / or has more movement than the initial output. In this way, the interactive portrait system may attempt to capture the customer's attention via the initial output, and then provide a more interesting and immersive additional output once the customer shows sufficient interest in interacting with the interactive portrait system.

[0019] Once the first customer arrives at the interactive area or is otherwise within range of one or more communication devices (e.g., a radio frequency identification reader), the one or more communication devices may detect and / or communicate with a device (e.g., a user device) associated with the first user (e.g., a wearable or portable object worn or carried by the first user). In this manner, the one or more communication devices may receive a first identifier from the device. The interactive portrait system may then access data from a database using the first identifier. The data may include various types of information, such as statistics related to the venue visited by the first customer (e.g., the first customer completed a ride attraction earlier in the day) and / or other achievements of the first customer. The interactive portrait system may then indicate an initial output and / or additional output to the first customer (e.g., "Did you enjoy the ride attraction?") based on the first identifier and / or the data. It should be appreciated that the one or more communication devices may additionally or alternatively receive data from the device (e.g., from a storage device on the device). Further, once the first customer provides an audible verbal response, the interactive portrait system may detect the audible verbal response via the microphone(s) and then engage in a conversation with the first customer. As noted herein, the interactive portrait system may utilize AI to determine relevant responses and statements that will simulate a natural conversation (eg, as if spoken between two people).

[0020] However, if the first customer does not confirm or show interest (e.g., sufficient interest, such as not turning their head toward the interactive area) during or after the initial output, the interactive portrait system may determine that the first customer is not interested in interacting with the interactive portrait system. The interactive portrait system may then generate another initial output to attempt to initiate interaction with the second customer. For example, the interactive portrait system may recognize that the second customer is approaching the interactive area and is carrying a beverage cup. As a result, the interactive portrait system may display a character animation that appears to be speaking to the second customer and / or making corresponding sounds (e.g., "Hey, is your drink good?"). If the image data indicates that the second customer responds with sufficient interest (e.g., turning their head toward the display and / or speaker), the interactive portrait system may determine that the second customer is sufficiently interested (e.g., engaged) and then provide additional output for the second customer. The interactive portrait system may perform steps to continue to engage the second customer in the same manner as explained above with respect to the first customer.

[0021] In one embodiment, the interactive portrait system may generate initial output(s) (e.g., displayed and / or audible outputs) in response to (e.g., only in response to) determining that a customer is performing certain actions and / or showing sufficient interest (such as by a customer approaching the interactive area (e.g., walking toward the display(s), walking past the display(s), being within a threshold distance of the display(s), staring at the display(s)). For example, when a first customer approaches the interactive area, the interactive portrait system may indicate the display of a shooting star or another suitable initial output. Then, when a second customer approaches the interactive area, the interactive portrait system may indicate the display of a shooting star or another suitable initial output, and so on (for a third customer, a fourth customer, and so on). In this manner, for each customer (or group of customers) who performs certain actions and / or shows sufficient interest (e.g., for each customer or group of customers who approaches the interactive area), the interactive portrait system may provide a suitable initial output to attempt to get the customer (or group of customers) to participate. Only some customers (or groups of customers) may turn around to look at the display(s) and / or otherwise show signs of sufficient interest during and / or after the initial output. However, for each customer (or group of customers) that shows sufficient signs of interest during and / or after the initial output, the interactive portrait system may then provide additional output to entertain and interact with the customer (or group of customers).

[0022] Advantageously, the interactive portrait system can use anonymous features such as clothing articles, personal belongings held by the user, or the like to perform personalized interactions with customers. Further, the interactive portrait system can use anonymous identifiers such as achievements within the entertainment venue (e.g., completed rides, joined teams) to perform personalized interactions with customers. Further, when the customer is out of range of the one or more communication devices and / or (one or more) sensors (e.g., outside the interactive area), the interactive portrait system can use computer vision and then collect additional information via communication with a device carried by the customer when the customer is in range of the one or more communication devices and / or via (one or more) sensors (e.g., in the interactive area). In this way, the interactive portrait system can perform a multi-level interactive process to attract customers to the interactive area and then entertain customers in the interactive area. However, it should be appreciated that a variety of techniques and processes for engaging customers are contemplated.

[0023] Figure 11 is a schematic diagram of an embodiment of an interactive portrait system 10 as a customer 12 (e.g., a first customer) approaches an interactive area 14. The interactive portrait system 10 may include a controller 18 having a processor 20 and a memory device 22. The interactive portrait system 10 may also include (one or more) communication devices 24, (one or more) cameras 26, (one or more) sensors 28, (one or more) displays 30, and / or (one or more) speakers 32 communicatively coupled to the controller 18. The interactive area 14 may generally be an area near and / or in front of the (one or more) displays 30. As shown, the customer 12 may travel along a path 34 (e.g., a sidewalk) to approach the interactive area 14. The customer 12 may also carry (e.g., wear, hold, travel with) a portable object 40. The portable object 40 may be any suitable type of object, such as a wearable band, jewelry, a toy, a scepter, a mobile phone, and the like. However, in one embodiment, to provide an additional layer of anonymity and / or to avoid receipt of identification information by interactive portrait system 10, interactive portrait system 10 may not communicate with patron 12's mobile phone and / or may not receive identification information from patron 12's mobile phone.

[0024] In operation, camera(s) 26 may capture image data (e.g., one or more images; images) within the field of view of camera(s) 26. Camera(s) 26 may capture image data from the environment surrounding and / or including interactive area 14. For example, image data may include customer 12 as customer 12 travels along path 34 toward interactive area 14. Controller 18 may receive and process image data using computer vision techniques to identify one or more characteristics (e.g., attributes) of customer 12. The one or more characteristics of customer 12 may be anonymous characteristics, such as clothing color, clothing type, a logo or another stamp on clothing, an ornament worn by the customer, a personal property carried by the customer, or the like. That is, the one or more characteristics may not include personally identifiable information (PII). The term PII may include information that directly identifies an individual (e.g., name, address, social security number, phone number) or data elements about an individual (e.g., a combination of gender, race, date of birth, geographic indicators; facial recognition). Thus, the interactive portrait system 10 may utilize visible contextual cues (possibly in combination with an identifier from the portable object 40 (e.g., utilizing only the visible contextual cues; or utilizing only the visible contextual cues and the identifier) ​​and / or sensor data from the sensor(s) 28) to initiate and / or conduct an interaction with the customer 12.

[0025] The controller 18 may also process the image data to determine the behavior of the customer 12 and / or the location of the customer 12, such as whether the customer 12 is moving toward and / or is positioned within the interactive area 14. In one embodiment, a marker 36 may be drawn onto the ground to mark the boundary of the interactive area 14, and the image data may indicate that the customer 12 is standing within the boundary of the interactive area 14. However, it should be appreciated that the controller 18 may not require the marker 36, but instead may determine that the customer 12 is within the boundary of the interactive area 14 via the relative positioning of the customer 12 within the field of view of the camera(s) 26. Thus, the controller 18 may process the image data to determine various behaviors of the customer 12 (e.g., movements, such as walking movements, gestures, mouth movements), gaze directions, facial expressions, emotions, and / or other behaviors of the customer 12. In fact, the controller 18 may utilize an AI algorithm to process the image data to determine whether the customer 12 shows sufficient signs of interest in the interactive area 14 (e.g., before the initial output; to trigger the initial output). For example, certain movements or movement / sound combinations (e.g., behavior; staring at interactive area 14 for more than a threshold period of time, such as 3 seconds) may indicate sufficient interest in interactive area 14 to indicate that patron 12 is likely to engage (e.g., respond, interact) if presented with an initial output.

[0026] In one embodiment, the communication device(s) 24 may communicate with the corresponding communication device 38 of the portable object 40. For example, the communication device(s) 24 may be a radio frequency identification (RFID) reader(s) configured to communicate with (e.g., read) an RFID tag of the portable object 40. As another example, the communication device(s) 24 may be a transceiver(s) configured to communicate with the corresponding transceiver(s) of the portable object 40 via any suitable wireless protocol (e.g., Bluetooth). In such cases, the strength of the signal received at the communication device(s) 24 and / or triangulation techniques (e.g., based on signals received by multiple communication devices 24) may indicate the location of the customer 12 relative to the interactive area 14. Additionally or alternatively, the communication device(s) 24 may receive an identifier (e.g., a unique identifier) ​​from a storage device and / or RFID tag of the portable object. In such cases, the communication device(s) 24 may provide the identifier to the controller 18, which may then use the identifier to access data from the one or more databases 42. The data may include achievements associated with the portable object 40. For example, the patron 12 may carry the portable object 40 to each ride attraction in the entertainment venue, and the corresponding achievements are stored in the database 42 in association with the identifier upon completion of each ride attraction. In some cases, the data may include information about the patron 12 and / or preferences of the patron 12, such as teams and / or preferred animations. It should be appreciated that the communication device(s) 24 may additionally or alternatively receive data from the portable object 40 (e.g., from a storage device on the portable object). Further, in one embodiment, the sensor(s) 28 (e.g., proximity sensor, pressure / weight sensor, temperature sensor, optical sensor) may detect the position of the patron 12 relative to the interactive area 14 and / or the behavior of the patron 12. The sensor(s) 28 may also include a microphone to detect audible input (e.g., spoken words or phrases) from the patron 12.

[0027] Thus, controller 18 may analyze image data, communications, sensor data, and / or other data to determine characteristics of the customer, the customer's behavior, the location of customer 12 relative to interactive area 14, and / or previous accomplishments of customer 12. In response to customer 12 indicating sufficient interest (such as by approaching interactive area 14 (e.g., walking toward; being near and / or within interactive area 14)), controller 18 may generate one or more initial outputs to provide an experience to customer 12. For example, controller 18 may instruct display(s) 30 and / or speaker(s) 32 to provide initial outputs in an attempt to initiate interaction with customer 12. Figure 1, the initial output is shown as a shooting star 46, which when presented in the display (which appears to be a painting) may attract additional attention. The initial output may be the same for all customers, selected via rotation among the available options, randomly selected among the available options, and / or selected from the available options to be personalized to the customer 12. For example, the initial output may include displaying a shooting star (e.g., the same for all customers or otherwise not selected to be personalized to the customer 12). As another example, the initial output may include displaying a small flickering flame due to one or more characteristics indicating that the customer 12 likes fire-breathing dragons (e.g., a stamp on the shirt of the customer 12). Additionally or alternatively, the initial output may include making a sound directed to the customer 12 (e.g., whispering "hello" or "hey, do you like dragons?").

[0028] Controller 18 may continue to analyze image data, communications, sensor data, and / or other data to determine whether customer 12 shows sufficient interest during and / or after the initial output (e.g., whether customer 12 responds to the initial output). For example, if image data, communications, sensor data, and / or other data indicate that customer 12 turns their head toward display(s) 30 and / or speaker(s) 32, customer 12 walks toward display(s) 30 and / or speaker(s) 32, customer 12 stops walking and remains within interactive area 14, controller 18 may determine that customer 12 responds to the initial output. Controller 18 may utilize an AI algorithm to determine whether customer 12 responds to the initial output. For example, certain movements or combinations of movements / sounds (e.g., behaviors; turning their head for more than a threshold time, such as three seconds, and saying “What’s that?”) may indicate sufficient interest and show that customer 12 is likely to continue the interaction if presented with additional output.

[0029] If the controller 18 determines that the customer 12 responds to the initial output, the controller 18 may determine that the customer 12 participates and then provides the customer 12 with additional outputs. The additional outputs may be the same across all customers, selected in turn among the available options, randomly selected among the available options, and / or selected from the available options to be personalized for the customer 12. The additional outputs 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., across more pixels; across a larger surface area of ​​(one or more) displays 30), brighter, more vivid, and / or has more movement than the initial output. For example, the initial output may include a small flickering lightning strike, and the additional output may include several larger lightning strikes (e.g., the same type of object, but different sizes). As another example, the initial output may include a small flickering flame, and the additional output may include a fire-throwing monster (e.g., a different type of object / character). As another example, the initial output may include a low or quieter (e.g., lower volume) sound, and the additional output may include a shouting or higher volume sound. In this manner, the interactive portrait system may attempt to capture the attention of the customer 12 via an initial output (e.g., a low-level activation state), and then provide more interesting and immersive additional outputs (e.g., a high-level activation state) once the customer 12 responds to the initial output to show sufficient interest in interacting with the interactive portrait system 10. The interactive portrait system 10 may utilize a trained AI algorithm to recognize or pick out signs of interest, such as the customer 12 staring at the display(s) 30 for more than a threshold time and / or staying in front of the display(s) 30 for a threshold time. The AI ​​algorithm may be trained to receive several pieces of information (e.g., gaze, gait, movement, lack of movement, speech, and / or other behavior) to recognize signs of interest, and evaluate the signs of interest, which may then prompt the controller 18 to select the customer 12, provide the initial output to the customer 12, and / or provide the additional output to the customer 12. The AI ​​algorithm may be trained to recognize sufficient interest to trigger the initial output and / or sufficient interest to trigger the additional output. The AI ​​algorithms may be different, and / or the level of interest considered to be of sufficient interest may vary (e.g., being in proximity to display(s) 30 is considered to be of sufficient interest to trigger an initial output, but not sufficient interest to trigger an additional output; alternatively, staring at display(s) 30 for more than a threshold period of time and providing a detectable audible response to the initial output is considered sufficient to trigger an additional output).

[0030] It should be appreciated that various processes and modes of interaction with the customer 12 are contemplated. For example, an initial output may be provided to the customer 12 when the customer 12 is traveling near and / or positioned within the interactive area 14. In some cases, the initial output may be provided periodically (e.g., according to a schedule) and / or responsively (e.g., in response to the customer 12 being in a particular position relative to the interactive area 14; in response to the customer 12 behaving in a particular manner). The initial output may be provided when the customer 12 is staring at the display(s) 30 or when the customer 12 is not staring at the display(s) 30. In one embodiment, the display(s) 30 may initially be blank (e.g., not illuminated or illuminated to a uniform color). Then, when the customer 12 is traveling toward and / or staring at the display(s) 30, the controller 18 may instruct the display(s) 30 to display an image of a flickering flame or another animation. Controller 18 may time the display of the image so that the image appears in the field of view of patron 12 as patron 12 travels past display(s) 30 and / or as patron 12 gazes at display(s) 30. For example, if image data indicates that patron 12 is walking along a sidewalk that passes in front of display(s) 30, controller 18 may time the display of the image so that the image appears when the patron reaches the leading edge of display(s) 30 and / or when patron 12 is directly in front of display(s) 30. As another example, if image data indicates that patron 12 is turning their head and their gaze from left to right to scan the environment, controller 18 may time the display of the image so that the image appears when patron 12 is facing display(s) 30. As another example, if image data indicates that patron 12 is looking at display(s) 30, controller 18 may instruct immediate (e.g., without delay, as quickly as possible) display of the image so that the image appears when patron 12 looks toward display(s) 30.

[0031] In one embodiment, the display(s) 30 may display a static scene (e.g., the interior of a store so that the display(s) 30 appear to be a window of the store or other building). Then, as the customer 12 moves toward and / or gazes at the display(s) 30, the controller 18 may instruct the display(s) 30 to display an image of a moving animation in the static scene (e.g., a flickering flame in a fireplace in the static scene). The controller 18 may time the display of the image so that the image appears in the field of view of the customer 12 as the customer 12 moves past the display(s) 30 and / or as the customer 12 gazes at the display(s) 30.

[0032] In one embodiment, the display(s) 30 may display a plurality of animated characters (e.g., a robot and a princess) engaging in a conversation with each other. Then, as the customer 12 moves toward and / or gazes at the display(s) 30, the controller 18 may instruct the display(s) 30 to adjust the plurality of animated characters, such as to stop the conversation with each other, turn toward the customer 12, appear to talk about one or more characteristics of the customer 12 (e.g., the princess appears to say "I like your giraffe shirt."). The controller 18 may time these changes so that the images appear in view as the customer 12 moves past the display(s) 30 and / or as the customer 12 gazes at the display(s) 30. It should be appreciated that the AI ​​algorithm may be trained on a variety of data indicative of customer behavior (including movement, gaze, etc.) to assess the interest of the customer 12 and provide an output in response to detecting sufficient interest of the customer 12.

[0033] In one embodiment, the initial output may be enhanced relative to the additional output to facilitate grabbing the attention of the customer 12. In one embodiment, the additional output and the initial output may not be enhanced relative to each other. Alternatively, the additional output and the initial output may be any suitable animation and / or sound that forms part of the storyline and / or interaction with the customer 12. The display(s) 30 may be surrounded by a frame (e.g., a bezel) to look like a framed window, a framed doorway, or the like. Further, the display(s) 30 may be textured to look like a painting (e.g., an oil painting).

[0034] Figure 21 is a schematic diagram of an embodiment of the interactive portrait system 10 when the customer 12 is located in the interactive area 14 (e.g., near or in front of the display(s) 30). As shown, additional outputs are presented on the display(s) 30, and the additional outputs include animations 48 (e.g., character animations). Once the customer 12 engages in interaction with the interactive portrait system 10 (e.g., as determined by the AI ​​algorithm; in response to sufficient interest in the initial output; as evidenced by gazing at the display(s) 30, gesturing at the display(s) 30, changing from a moving gait to a stationary posture in front of the display(s) 30, and / or providing audible spoken words or phrases in response to animations on the display(s) 30 and / or to prompts issued via the speaker(s) 32), the controller 18 may perform additional interaction aspects. In one embodiment, the controller 18 may process multiple data inputs and provide appropriate animations and / or sounds to continue the interaction. For example, the controller 18 may use AI to generate animations to be output via display(s) 30 and corresponding prompts to be output via speaker(s) 32 (e.g., so that the animations appear as if the corresponding prompts are being spoken), wherein the corresponding prompts simulate a natural conversation with the customer 12 (e.g., as if spoken between two people).

[0035] Further, controller 18 may use data collected via communication device(s) 24, camera(s) 26, and / or sensor(s) 28 to select animations and corresponding prompts to be responsive to and / or personalized for customer 12. For example, communication device(s) 24 may access an identifier that can be used to retrieve an achievement associated with portable object 40 carried by customer 12. Communication device(s) 24, camera(s) 26, and / or sensor(s) may monitor the behavior (e.g., movements, facial expressions) of customer 12 during interaction with interactive portrait system 10. Further, sensor(s) 28 may include microphone(s) that detect verbal input from customer 12. In this manner, multiple inputs may be received over time (e.g., continuously) as customer 12 interacts with the animation on display(s) 30, and the multiple inputs are processed by controller 18 (e.g., using AI) to enable controller 18 to respond appropriately, such as being able to provide a targeted prompt and / or being able to provide the effect of a natural conversation with customer 12.

[0036] As noted herein, and with reference to Figure 1, if customer 12 moves toward interactive area 14 or is otherwise selected by the controller for interaction, controller 18 may provide an initial output. If customer 12 responds, controller 18 may provide additional outputs to perform dynamic interactions with customer 12. However, if customer 12 does not respond (e.g., does not show sufficient interest, which may be determined via the AI ​​algorithm), controller 18 may try again (e.g., with another initial output for customer 12) or select an additional customer 44. For example, controller 18 may analyze image data to identify additional customers 44 near interactive area 14. Controller 18 may then provide initial outputs as described herein (such as at a certain timing) based on one or more corresponding characteristics and / or other features of additional customers 44. Controller 18 may continue to attempt to engage different customers in this manner until one of the different customers responds to its initial output and begins interacting with interactive portrait system 10.

[0037] The interactive portrait system 10 disclosed herein provides customers 12 with interactive experiences that may be unexpected (e.g., appearing on a false window of a retail store as the customer 12 travels along the path 34). The interactive experience may be initiated based on image data captured by the camera(s) 26 and / or other data collected via the communication device(s) 24 and / or the sensor(s) 28. The interactive experience may be initiated by the customer 12 simply doing one or more of the following: approaching the interactive area 14, changing their gaze to survey the environment, and / or speaking certain words or phrases within the range of the sensor(s) 28. The interactive experience may be initiated without requiring the customer 12 to provide any typed input (e.g., without flipping a switch or pushing a button). This may provide efficient processing and computer operations to provide responsive, realistic interactions with the customer 12. In fact, the interactive experience may be initiated in a completely passive manner (e.g., from the customer's 12's perspective) by the customer 12 simply approaching the interactive area 14 without directing their gaze to the display(s) 30, without speaking, and / or without providing any typed input. The interactive experience may continue (with at least one additional output) by the customer 12 simply indicating sufficient interest in (e.g., a response to) the initial output, such as by the customer 12 slowing their gait as they pass in front of the display(s) 30, changing their gaze to look at the display(s) 30, speaking certain words or phrases determined to be related to the initial input within the range of the sensor(s) 28, and / or without providing any typed input. Thereafter, continued interaction and interactions may depend on the behavior of the customer 12, such as the location of the customer 12, the movement of the customer 12, gestures made by the customer 12, the gaze of the customer 12, spoken words or phrases from the customer 12, and / or the like. For example, interaction and interactions may continue with the customer 12 as long as the customer 12 remains engaged / responsive for a certain period of time (e.g., a set period of time, such as no more than 5 minutes) and / or until other customers approach the interactive area 14.

[0038] In one embodiment, patron 12 may be traveling in the environment surrounding interactive area 14 but outside the range(s) of communication device(s) 24 and / or sensor(s) 28. Thus, controller 18 may have image data but no additional data from communication device(s) 24 and / or sensor(s) 28 relating to patron 12. In such a case, controller 18 may use information derived from the image data to generate an initial output to entice patron 12 to move into the range(s) of communication device(s) 24 and / or sensor(s) 28. Then, once patron 12 is within the range(s), controller 18 may use information derived from communication device(s) 24 and / or sensor(s) 28 to perform continued dynamic interaction (e.g., a personalized session) with patron 12. In this manner, interactive portrait system 10 may use image data to track patron 12 and attempt to engage patron 12 until patron 12 and / or portable object 40 are within the range(s) of communication device(s) 24 and / or sensor(s) 28. It should be appreciated that, in addition to data from the communication device(s) 24 and / or sensor(s) 28, image data may also be used to perform continued dynamic interaction with the customer.

[0039] Further, once the customer 12 is within the range(s), the controller 18 may instruct the display(s) 30 and / or the speaker(s) 32 to provide the customer 12 with a task(s) to complete (e.g., "perform five jumping jacks" or "copy the robot's dance moves") to collect an achievement, which may be stored in the database 42 in association with the identifier. The controller 18 may analyze image data from the camera(s) 26 and / or other data from the communication device(s) 24 and / or the sensor(s) 28 to determine whether the customer 12 successfully completed the task(s). For example, the sensor(s) 28 may include a light detector that tracks the movement of a light emitter on the portable object 40 to track gestures / movements (e.g., waving movements; pointing) made with the portable object 40. As another example, the sensor(s) 28 may include a light emitter / detector pair that emits light and detects the light after it is reflected by the portable object 40 to track gestures / movements made with the portable object 40. Controller 18 may match the gesture / movement with a target gesture / movement that may be stored and accessible from database 42 to determine whether customer 12 successfully completed the task(s).

[0040] In one embodiment, the controller 18 may apply an AI algorithm trained on multiple sample sets of gestures / movements. Further, the AI ​​algorithm may be trained on multiple sample sets and / or have fuzziness added to reduce barriers for certain customers (e.g., children) who may have difficulty accurately performing the target gesture / movement. In some embodiments, the controller 18 may use one or more characteristics identified via image data and / or other data (e.g., data stored in association with an identifier; sensor data from the one or more sensors 28) to determine whether to apply fuzziness and / or adjust the fuzziness. For example, if any of the data indicates that the customer 12 is a child, the controller 18 may provide this as input to the AI ​​algorithm and / or add fuzziness so that this is considered in evaluating the gesture / movement.

[0041] Processor 20 may include a microprocessor that can execute software to control display(s) 30, speaker(s) 32, and / or other features of interactive portrait system 10. Processor 20 may include multiple microprocessors, one or more "general purpose" microprocessors, one or more special purpose microprocessors, and / or one or more application specific integrated circuits (ASICs), or some combination thereof. For example, processor 20 may include one or more reduced instruction set computer (RISC) processors. Memory device 22 may include volatile memory (such as random access memory (RAM)) and / or non-volatile memory (such as read-only memory (ROM)). Memory device 22 may store information, such as control software, lookup tables, configuration data, communication protocols, or the like.

[0042] For example, the memory device 22 may store processor-executable instructions including firmware or software for execution by the processor 20, such as instructions for generating derivatives, controlling the display(s) 30, the speaker(s) 32, and / or other features of the interactive portrait system 10. In one embodiment, the memory device 22 is a tangible, non-transitory machine-readable medium that may store machine-readable instructions for execution by the processor 20. The memory device 22 may include ROM, flash memory, a hard drive, any other suitable optical, magnetic, or solid-state storage medium, or a combination thereof. The communication device(s) 24 may facilitate communication (e.g., wireless communication) with other components such as the portable object 40, the database 42, and the like. The display(s) 30 may 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 displays may include a coating or filter that makes the image presented on the display look like a painting (e.g., oil painting, watercolor painting).

[0043] Figure 3is a schematic diagram of an embodiment of the interactive portrait system 10 when multiple customers are located in the interactive area 14 to interact with the animation presented on the (one or more) display 30. The multiple customers include a first customer 12, a second customer 50, and a third customer 52. The controller 18 can recognize that the multiple customers are in the interactive area 14, and can selectively enable the multiple customers to participate in a dynamic conversation (e.g., an AI-driven conversation) with the multiple customers in sequence (e.g., having a complete conversation with the first customer 12, then a complete conversation with the second customer 50, etc.) and / or as a group (e.g., dynamically responding to the multiple customers based on their respective behaviors). For example, the controller 18 can select the first customer 12 (e.g., as the current main participant) and recognize that the first customer 12 is wearing a shirt with a monster logo. The controller 18 can then attempt to initiate a conversation with the first customer 12 by displaying the animation to appear to be looking at the first customer 12 and emitting corresponding sounds including monster-related prompts. If the first customer 12 responds (as evidenced by his behavior), the controller 18 may continue to respond to conduct the session with the first customer 12. Then, at some later time (e.g., after a set time such as five minutes; once the first customer 12 loses interest, such as walking away; once the second customer 50 shows interest, such as responding to a prompt), the controller 18 may select the second customer 50 (e.g., as the current primary participant) and recognize that the second customer 50 is carrying a beverage. The controller 18 may then attempt to initiate a session with the second customer 50 by displaying an animation that appears to be looking at the second customer 50 and emitting a corresponding sound that includes a prompt related to the beverage. If the second customer 50 responds (as evidenced by his behavior), the controller 18 may continue to respond to conduct the session with the second customer 50. The controller 18 may continue in this manner as long as there are additional customers waiting for their turn to interact with the interactive portrait system 10.

[0044] As noted herein, the controller 18 can process multiple customers as a group, thereby also allowing new customers to join the group and / or other customers to leave the group. Therefore, the group can change over time. In such cases, the controller 18 can identify one or more corresponding characteristics, corresponding identifiers and / or other corresponding data associated with the first customer 12 and the second customer 50. Then, the controller 18 can attempt to initiate a conversation with both the first customer 12 and the second customer 50 as a group, such as by displaying an animation that looks like looking at the first customer 12 and emitting a corresponding sound including a prompt associated with a monster. Then, the controller 18 can determine that the second customer 50 has responded to one of the prompts, so the controller 18 can then display an animation that looks like looking at the second customer 50 and emitting a corresponding sound including a prompt associated with a beverage. The controller 18 can receive several types of data to effectively switch back and forth to process different customers in the group over time to perform an attractive dynamic interaction with the multiple customers.

[0045] When the number of patrons in the group exceeds a threshold number (e.g., more than 2, 3, 4, 5, 10, 15, or 20 patrons), the controller 18 may adjust the interaction based on the number of patrons in the group (such as by saying fewer words per prompt, saying fewer words to each patron, saying shorter prompts to each patron, saying fewer prompts to each patron, spending less time interacting with each patron, or the like). Similarly, when the number of patrons in the group is less than the threshold number, the controller 18 may adjust the interaction by saying more words per prompt, saying more words to each patron, saying longer prompts to each patron, saying more prompts to each patron, spending more time interacting with each patron, or the like. The number of words and / or length of time may also vary dynamically (e.g., on a sliding scale; according to a curve) based on the number of patrons in the group. This may enable the controller 18 to influence and / or implement crowd control measures through dynamic interactions.

[0046] In crowded conditions, the interactive portrait system 10 may be configured to perform other techniques. For example, in a crowd, it may be difficult to accurately associate each of the plurality of customers with their portable objects 40. In one embodiment, the controller 18 may be able to associate at least some of the plurality of customers with their portable objects 40 by collecting all identifiers of the portable objects 40 in the crowd, accessing the database 42 to collect all achievements associated with the portable objects 40 in the crowd, and then selecting one of the achievements to call out. For example, the controller 18 may determine that a customer recently completed a ride attraction, and may instruct the speaker(s) 32 to issue a relevant prompt (e.g., "Which of you completed the ride attraction?") and instruct the display(s) 30 to animate the character animation to appear as if it is speaking the prompt. Then, the image data captured by the camera(s) 26 may reveal the customer who responded (e.g., by raising their hand or moving their mouth to speak). The sensor data captured by the sensor(s) 28 (e.g., a directional microphone) may also reveal the customer who responded (e.g., by speaking). Thus, the image data and / or sensor data may reveal a responsive customer, and the controller 18 may then use the image data and / or sensor data to identify the customer's location, the customer, and / or one or more characteristics of the customer. The controller 18 may then control the display(s) 30 and the speaker(s) 32 to conduct a conversation with the customer (e.g., the character animation turns toward the customer and appears to say a prompt issued by the speaker(s) 32, such as, "Okay. I like the monster on your shirt."). At some later time, the controller 18 may select another achievement associated with a different portable object 40 to attempt to initiate an interaction with another customer, and so on. In any case, the interaction may be driven by the AI ​​to be dynamic and responsive to the customer, which may provide a pleasant and natural interaction for the customer.

[0047] Figure 4 8 is a flow chart of one embodiment of a method 80 of operating the interactive portrait system 10. The method 80 includes various steps represented by boxes. It should be noted that the method 80 can be performed as an automated process by a system such as the interactive portrait system. Although the flow chart illustrates the steps in a certain sequence, it should be understood that the steps can be performed in any suitable order and that certain steps can be performed simultaneously where appropriate. Further, certain steps or portions of the method 80 can be performed by separate systems or devices.

[0048] In block 82, method 80 may begin by identifying a customer (e.g., a potential user of the interactive portrait system). For example, image data captured by the camera(s) may include the customer, and the controller may analyze the image data to identify one or more characteristics of the customer. The field of view(s) of the camera(s) may be set to capture an interactive area in front of the display(s) and / or the environment surrounding the interactive area. In this manner, for example, the image data may include the customer as the customer approaches the interactive area and / or as the customer interacts with media on the display(s).

[0049] In box 84, method 80 may continue to indicate an initial output of a sound via (one or more) speakers and / or an image (e.g., animation) via (one or more) displays in an attempt to interact with the customer. As explained herein, the initial output may be intended to provide a certain visual and / or audible effect to capture the customer's attention. The initial output may be the same for all customers, selected in turn among the available options, randomly selected among the available options, and / or selected from the available options to be personalized for the customer. For example, the initial output may include displaying a shooting star (e.g., the same for all customers or otherwise not selected to be personalized for the customer). As another example, the initial output may include displaying a small flickering flame due to one or more characteristics indicating that the customer likes a fire-breathing dragon (e.g., a stamp on the customer's shirt). Additionally or alternatively, the initial output may include emitting a sound directed to the customer (e.g., whispering "hello" or "hey, do you like dragons?"). The initial output may be provided in response to the controller determining that the customer shows sufficient interest (e.g., approaching the interactive area and / or staring at the (one or more) displays). The controller may use an AI algorithm to determine that the customer shows sufficient interest.

[0050] In box 86, method 80 may continue to analyze image data and / or other data (e.g., communication data generated by communication device(s) connected to a portable object carried by the customer; sensor data generated by sensor(s) related to the interactive area) to determine whether the customer showed sufficient interest in (e.g., responded to; interacted with) the initial output. For example, if the image data and / or other data indicates that the customer turned their head toward the display(s) and / or speaker(s), the customer walked toward the display(s) and / or speaker(s), the customer uttered certain words or phrases indicating engagement or interest (e.g., "What is that?" or "Let's go see the flames"), and / or the customer stopped walking and remained within the interactive area, the controller may determine that the customer responded to the initial output. The controller may utilize an AI algorithm to determine that the customer 12 responded to the initial output.

[0051] If the customer participates, the method 80 may continue to frame 88. In frame 88, the method 80 may include an additional output indicating the sound via (one or more) speakers and / or the image via (one or more) displays to continue the interaction with the customer. The additional output may be the same across all customers, selected in turn among the available options, randomly selected among the available options, and / or selected from the available options to be personalized for the customer. 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, brighter, more vivid, and / or has more movement compared to the initial output. In this way, the interactive portrait system may try to capture the attention of the customer via the initial output, and then provide a more interesting immersive additional output once the customer is interested in interacting with the interactive portrait system. This may provide efficient processing and computer operations (e.g., by retaining computer resources and a large amount of processing in response to the customer interacting with the interactive portrait system).

[0052] If the customer is within the range of (one or more) communication devices, and if the customer has his own portable object, method 80 may continue to box 90. In box 90, method 80 may detect an identifier and / or otherwise obtain data via communication with a portable object carried by the customer. For example, the controller may be coupled to an RFID reader configured to read the identifier from the RFID tag of the portable object. The controller can then use the identifier to access the achievements stored in the database associated with the identifier. Additionally, in one embodiment, the controller may indicate additional output of sound via (one or more) speakers and / or images via (one or more) displays based on the identifier and / or data accessed via communication with the portable object carried by the customer to continue to interact with the customer. It should be appreciated that the interactive portrait system may also include (one or more) sensors, and the controller may provide output based on sensor data from (one or more) sensors. As noted herein, the interactive portrait system may switch between different customers to provide interactions with different customers (e.g., based on image data, one or more characteristics of the customer, an identifier associated with the customer, sensor data related to the customer; AI-driven interaction).

[0053] The interactive portrait system may include and / or activate any of a variety of show effects, such as show effects in addition to the display(s) and / or speaker(s). For example, the show effects may include a light emitter that emits light to illuminate an area (e.g., a room), a haptic device that outputs a tactile effect (e.g., vibration, air flow including cold and / or hot air flow), a torch that outputs a flame (e.g., a hot flame), and the like. In one embodiment, the interactive portrait system may utilize AI to respond to and / or implement the show effects. For example, the interactive portrait system may determine that the customer is wearing a winter coat and that the customer may be cold, and then activate a haptic device that provides a warm air flow and / or a torch that outputs a flame to warm the customer. Such show effects may also correspond to images on the display(s) and / or sounds from the speaker(s) so as to provide a consistent story and experience to the customer (e.g., a flame on the display(s) may be accompanied by a warm air flow).

[0054] The interactive portrait system may be able to achieve improved customer interaction with the performance attractions at the entertainment venue. It should be appreciated that the interactive portrait system can be modular and can be transported to different performance attractions and / or different locations in the entertainment venue. In fact, the interactive portrait system can be coupled to a movable robot (e.g., autonomously controlled to travel around the entertainment venue or remotely controlled by an operator). In such cases, the movable robot may include (one or more) displays, (one or more) speakers, (one or more) cameras, (one or more) sensors, (one or more) communication devices and / or controllers (which may be part of or communicate with a remote computing system such as a cloud computing system or a central computing system to facilitate processing steps and / or access to a database). The movable robot can walk around the entertainment venue and perform the technology disclosed herein to interact with customers (e.g., when the customer is close to the movable robot). However, the movable robot can also move relative to the customer (e.g., toward the customer), such as to bring the customer within the range of, for example, (one or more) communication devices and / or (one or more) sensors.

[0055] It should also be appreciated that the interaction may be performed under the guidance of the AI; however, the output may be provided to an operator (e.g., a real person, an actor) via (one or more) displays and / or (one or more) speakers to guide the operator to speak to the customer. Thus, the interactive portrait system may use AI to determine the customer's interest level and / or determine appropriate outputs that may be of interest to the customer. However, the interactive portrait system may provide instructions to the operator to speak the appropriate output to the customer. In one embodiment, the interaction may begin with output provided to the operator via (one or more) displays and / or (one or more) speakers under the guidance of the AI ​​(e.g., initial output and / or a few outputs), and then the operator may continue the interaction without the guidance of the AI. Similarly, in one embodiment, the interaction may be performed via AI-driven interaction for the customer via (one or more) displays and / or (one or more) speakers, and the operator may monitor the output and / or be able to intervene (e.g., select output, block output) during the interaction.

[0056] In one embodiment, supervised AI / machine learning can be implemented, such as during the availability of specific known examples related to future predictions. In supervised AI / machine learning, a mathematical model of a collection of data contains both inputs and expected outputs. This data is called "training data" and is essentially a collection of training examples. Each training example has one or more inputs and expected outputs, also known as supervisory signals. In the mathematical model, each training example is represented by an array or vector (sometimes referred to as a feature vector), and the training data is represented by a matrix. Through iterative optimization of the objective function, a supervised learning algorithm learns a function that can be used to predict the output associated with a new input. The optimal function will allow the algorithm to correctly determine the output for inputs that are not part of the training data. An algorithm that improves the accuracy of its 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 restricted to a finite set of values, and regression algorithms are used when the output can have any numerical value within a range. Further, similarity learning is a field of supervised machine learning that is closely related to regression and classification, but the goal is to learn from examples using a similarity function that determines the extent to which two objects are similar or related.

[0057] Additionally and / or alternatively, in some cases, it may be beneficial to utilize unsupervised learning (e.g., when the specific output type is not known). An unsupervised learning algorithm takes a set of data containing only inputs and looks for structure in the data, such as groupings or clusters of data points. Thus, the algorithm learns from test data that has not yet been labeled, classified, or categorized. Rather than responding to feedback, an unsupervised learning algorithm identifies commonalities in the data and reacts based on the presence or absence of such commonalities in each new piece of data. In any case, AI (e.g., machine learning) can be used to identify signs of interest from a customer and determine appropriate outputs for engaging the customer to provide dynamic, personalized interactions for the customer.

[0058] Although only certain features of the disclosure have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. 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 disclosure.

[0059] The technology presented and claimed herein is cited and applied to specific examples and substantial objects that arguably improve the practical nature of the art, and thus is not abstract, intangible, or purely theoretical. Further, if any claim appended to the end of this specification contains one or more elements designated as "a means for [performing] ... [function]" or "a step for [performing] ... [function]," it is intended that such elements are to be interpreted in accordance with 35 U.S.C. 112(f). However, for any claim containing elements designated in any other manner, it is intended that such elements are not to be interpreted in accordance with 35 U.S.C. 112(f).

Claims

1. An interactive portrait system, comprising: a camera configured to capture an image of an environment; as well as A controller, wherein the controller is configured to: analyzing the image to identify customers in the environment; instructing an output device to provide an initial output in an attempt to interact with the customer; analyzing the imagery to identify behavior of the customer during the initial output, after the initial output, or both; evaluating said behavior of said customer using one or more artificial intelligence algorithms to determine whether said customer is responsive to said initial output; as well as In response to determining that the customer is responsive to the initial output, the output device is directed to provide additional output to continue attempting to interact with the customer.

2. The interactive portrait system of claim 1, wherein: The initial output includes a first animation of a first type of object or character, and the additional output includes 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 includes a first animation, the additional output includes a second animation, and the second animation is larger than the first animation.

4. The interactive portrait system of claim 1, wherein: The initial output includes a first sound, the additional output includes a second sound, and the first sound has a lower volume than the second sound.

5. The interactive portrait system of claim 1, wherein: The controller is configured to analyze the imagery to identify one or more characteristics of the customer, and the initial output, the additional output, or both are based on the one or more characteristics of the customer.

6. The interactive portrait system of claim 1, wherein: The behavior includes the customer turning their head toward 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 of claim 1, comprising a communication device communicatively coupled to the controller, wherein: The communication device is configured to communicate with a portable object carried by the customer to retrieve an identifier from the portable object.

8. The interactive portrait system of claim 7, wherein: The controller is configured to use the identifier to search a database for an achievement associated with the identifier.

9. The interactive portrait system of claim 8, wherein: The initial output, the additional output, or both are based on the achievement associated with the identifier.

10. The interactive portrait system of claim 1, wherein: The controller is configured to use the one or more artificial intelligence algorithms to provide the initial output, the additional output, or both in a manner personalized for the customer based on the imagery.

11. The interactive portrait system of claim 1, wherein: In response to determining that the customer fails to respond to the initial output, the controller is configured to: preventing the output device from providing the additional output; analyzing the imagery to identify additional patrons in the environment; as well as The output device is instructed to provide a corresponding initial output in an attempt to interact with the additional customer.

12. An entertainment venue, comprising: a path through the interactive area; a display and a speaker located 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; as well as A controller, wherein the controller is configured to: analyzing the imagery to identify customers traveling along the path toward the interactive area; instructing the display, the speaker, or both to provide an initial output in an attempt to interact with the customer when the customer approaches the interactive area; analyzing the images, the sounds, or both to identify behavior of the customer during the initial output, after the initial output, or both; evaluating said behavior of said customer using one or more artificial intelligence algorithms to determine whether said customer is responsive to said initial output; as well as In response to determining that the customer is responsive to the initial output, the display and the speaker are directed to provide additional output for conversational interaction with the customer.

13. The entertainment venue as claimed in claim 12, wherein: The initial output includes a first animation, the additional output includes a second animation, and the second animation is larger than the first animation.

14. The entertainment venue as claimed in claim 12, wherein: The initial output includes a first sound, the additional output includes a second sound, and the first sound is quieter than the second sound.

15. The entertainment venue as claimed in claim 12, wherein: The controller is configured to analyze the imagery to identify one or more characteristics of the customer, and the initial output, the additional output, or both are based on the one or more characteristics of the customer.

16. The entertainment venue as claimed in claim 12, wherein: Such behavior includes: the customer turns their head toward the display, the speaker, or both; the customer focuses their gaze on or near the display, the speaker, or both; The customer utters a word or phrase associated with the initial output; or Any combination thereof.

17. The entertainment venue of claim 12, comprising a communication device communicatively coupled to the controller; in, the communication device being configured to communicate with a portable object carried by the customer to retrieve an identifier from the portable object; wherein the controller is configured to use the identifier to search a database for an achievement associated with the identifier; Wherein the initial output, the additional output, or both are based on the achievement associated with the identifier.

18. The entertainment venue as claimed in claim 12, wherein: The controller is configured to perform the conversational interaction using the one or more artificial intelligence algorithms.

19. A method of operating an interactive portrait system in an entertainment venue, the method comprising: using one or more processors to analyze images captured by the camera to identify customer behavior; evaluating the behavior of the patron using the one or more processors and one or more artificial intelligence algorithms to determine whether the patron shows signs of interest in an interactive area of ​​the entertainment venue; as well as In response to determining that the patron is showing an indication of interest in the interactive area of ​​the casino and using the one or more processors, an output device is directed to provide an initial output in an attempt to interact with the patron.

20. The method of claim 19, comprising: analyzing the imagery using the one or more processors to identify one or more characteristics of the customer; as well as Based on the one or more characteristics of the customer, the one or more processors are used to instruct the output device to provide the initial output.

Images