Dual artificial intelligence (AI) agent system for virtual environments
A dual AI agent system with roleplay and feedback agents enhances virtual learning environments by providing interactive scenarios and real-time feedback, addressing the need for effective soft skill training.
Patent Information
- Application Number
- PCT/US2026/028214
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-14
- Filing Date
- 2026-05-14
- Publication Date
- 2026-11-19
AI Technical Summary
Existing virtual learning environments lack effective methods to teach soft skills such as negotiation, teamwork, and conflict resolution, and there is a need for systems that can provide interactive and feedback-driven learning experiences.
A dual artificial intelligence (AI) agent system is implemented, comprising a roleplay agent and a feedback agent, embodied as virtual avatars, to facilitate interactive virtual sessions and provide real-time feedback on learner performance.
The system enhances the learning experience by allowing learners to practice soft skills through role-playing scenarios and receive personalized feedback, thereby improving their proficiency in these skills.
Smart Images

Figure US2026028214_19112026_PF_FP_ABST
Abstract
Description
DUAL ARTIFICIAL INTELLIGENCE (Al) AGENT SYSTEM FOR VIRTUAL ENVIRONMENTS CROSS REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 805,802, filed on May 14, 2025, and entitled “DUAL ARTIFICIAL INTELLIGENCE (Al) AGENT SYSTEM FOR VIRTUAL ENVIRONMENTS,” which is herein incorporated by reference in its entirety.BACKGROUND
[0002] A software agent (also referred to as an agent) may be a computer program that can perform a range of tasks or services for a user. In some examples, a software agent may perform tasks or services autonomously (or semi-autonomously) on behalf of a user or another program. A user may interact or engage with the software agent by providing user input (e.g., commands, questions, conversational dialogue, prompt responses, etc.) and the software agent may perform a corresponding task or service based on the user input.
[0003] The discussion above is merely provided for general background information and is not intended to be used as an aid in determining the scope of the claimed subject matter.SUMMARY
[0004] Various aspects of the present disclosure relate to a dual artificial intelligence (Al) agent system for virtual environments, and in particular, to providing a dual Al agent system to teach soft skills (e.g., negotiation, teamwork, conflict resolution, etc.) in a virtual learning environment, such as, e.g., an eLearning course, an eWorkshop, or another type of online educational session or environment. In some configurations, the dual Al agent system may implement a roleplay agent and a feedback agent. The roleplay agent may roleplay with an entity (e.g., a learner entity) and the feedback agent may monitor the interaction between the roleplay agent and the learner entity and provide feedback to the learner entity. In some examples, each agent may be embodied by a virtual avatar that the learner entity may interact with in a virtual environment, such as, e g., a virtual learning environment.
[0005] Some configurations provide a system. The system may include a processing system including one or more electronic processors. The processing system may be configured to receive an agent-integrated data packet for a virtual session, wherein the agent-integrated data packet includes a plurality of artificial intelligence (Al) agents developed for a virtual session. The processing system may be configured to provide a prompt that identifies a plurality7of characteristics for a virtual entity. The processing system may be configured to determine aQB\102526408.1Attorney Docket No. 186391.00003subset of characteristics of the plurality of characteristics based on a response to the prompt. The processing system may be configured to provide the subset of characteristics to a first artificial intelligence (Al) agent, where the first Al agent may be configured to emulate the virtual entity using the subset of characteristics. The processing system may be configured to initiate a virtual experience related to the virtual session, where the virtual experience may be based on an objective of the virtual session, where the virtual experience may include an interaction between an entity participating in the virtual session and the virtual entity as emulated by the first Al agent using the subset of characteristics. The processing system may be configured to receive data related to the interaction between the virtual entity’ and the entity. The processing system may be configured to provide the data related to the interaction to a second Al agent, the second Al agent configured to generate feedback data based on a criterion linked to the objective of the virtual session, where the feedback data may relate to a performance of the entity during the interaction. The processing system may be configured to receive, from the second Al agent, the feedback data. The processing system may be configured to execute an action related to the virtual session based on the feedback data.
[0006] Some configurations provide a method. The method may include receiving, with a processing system including one or more electronic processors, an agent-integrated data packet for a virtual session, where the agent-integrated data packet may include a plurality of artificial intelligence (Al) agents developed for a virtual session. The method may include providing, with the processing system, a prompt that identifies a plurality of characteristics for a virtual entity. The method may include determining, with the processing system, a subset of characteristics of the plurality of characteristics based on a response to the prompt. The method may include providing, with the processing system, the subset of characteristics to a first artificial intelligence (Al) agent, where the first Al agent may be configured to emulate the virtual entity using the subset of characteristics. The method may include initiating, with the processing system, a virtual experience related to the virtual session, where the virtual experience may be based on an objective of the virtual session, where the virtual experience may involve an interaction between an entity participating in the virtual session and the virtual entity as emulated by the first Al agent using the subset of characteristics. The method may include receiving, with the processing system, data related to the interaction between the virtual entity’ and the entity. The method may include providing, with the processing system, the data related to the interaction to a second Al agent, the second Al agent configured to generate feedback data based on a criterion linked to the objective of the virtual session, where the 2QB\102526408.1Attorney Docket No. 186391.00003feedback data may relate to a performance of the entity during the interaction. The method may include receiving, with the processing system, from the second Al agent, the feedback data. The method may include executing, with the processing system an action related to the virtual session based on the feedback data.
[0007] Some configurations provide a system. The system may include a processing system including one or more electronic processors. The processing system may be configured to receive, over a communication network, a data packet representing a virtual session, where the data packet may include electronic content of the virtual session. The processing system may be configured to determine context data related to the virtual session, where the context data may be associated with an objective to be achieved via the virtual session. The processing system may be configured to provide the context data to a plurality of artificial intelligence (Al) agents, where each Al agent of the plurality of Al agents may be specifically trained for the virtual session using the context data. The processing system may be configured to embed the plurality of Al agents into the data packet as an agent-integrated data packet. The processing system may be configured to transmit, over the communication network, the agent-integrated data packet to a remote computing platform, where the remote computing platform may control access to the agent-integrated data packet.
[0008] Some configurations provide a method. The method may include receiving, over a communication network, with a processing system including one or more electronic processors, a data packet representing a virtual session, where the data packet may include electronic content of the virtual session. The method may include determining, with the processing system, context data related to the virtual session, where the context data is associated with an objective to be achieved via the virtual session. The method may include providing, with the processing system, the context data to a plurality’ of artificial intelligence (Al) agents, where each Al agent of the plurality of Al agents may be specifically trained for the virtual session using the context data. The method may include embedding, with the processing system, the plurality of Al agents into the data packet as an agent-integrated data packet. The method may include transmitting, over the communication network, with the processing system, the agent-integrated data packet to a remote computing platform, where the remote computing platform may control access to the agent-integrated data packet.
[0009] Some configurations provide a system. The system may include a processing system including one or more electronic processors. The processing system may be configured 3QB\102526408.1Attorney Docket No. 186391.00003to receive, over a communication network, a data packet representing a virtual session, where the data packet may include electronic content of the virtual session. The processing system may be configured to embed a plurality of Al agents into the data packet as an agent-integrated data packet, where each Al agent of the plurality of Al agents may be specifically trained using context data associated w ith an objective to be achieved via the virtual session. The processing system may be configured to access the agent-integrated data packet. The processing system may be configured to provide the virtual session to an entity. The processing system may be configured to initiate, based on the agent-integrated data packet, a virtual experience related to the virtual session, where the virtual experience may be based on the objective of the virtual session and involves an interaction between the entity and a virtual entity', where a first Al agent of the plurality of Al agents may be configured to emulate the virtual entity using one or more selected characteristics. The processing system may be configured to receive data related to the interaction between the virtual entity and the entity. The processing system may be configured to generate, using a second Al agent, feedback data related to a performance of the entity during the interaction, where the second Al agent may be configured to generate the feedback data based on a enterion linked to the objective of the virtual session. The processing system may be configured to execute an action related to the virtual session based on the feedback data.
[0010] Some configurations provide a method. The method may include receiving, over a communication network, with a processing system including one or more processors, a data packet representing a virtual session, where the data packet may include electronic content of the virtual session. The method may include embedding, with the processing system, a plurality of Al agents into the data packet as an agent-integrated data packet, w here each Al agent of the plurality' of Al agents may be specifically trained using context data associated with an objective to be achieved via the virtual session. The method may include accessing, with the processing system, the agent-integrated data packet. The method may include providing, with the processing system, the virtual session to an entity. The method may include initiating, with the processing system, based on the agent-integrated data packet, a virtual experience related to the virtual session, where the virtual experience may be based on the objective of the virtual session and may involve an interaction between the entity and a virtual entity, where a first Al agent of the plurality of Al agents may be configured to emulate the virtual entity using one or more selected characteristics. The method may include receiving, with the processing system, data related to the interaction between the virtual entity and the entity. The method may include 4QB\102526408.1Attorney Docket No. 186391.00003generating, with the processing system, using a second Al agent, feedback data related to a performance of the entity during the interaction, wherein the second Al agent is configured to generate the feedback data based on a criterion linked to the objective of the virtual session. The method may include executing, with the processing system, an action related to the virtual session based on the feedback data.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] FIG. 1 schematically illustrates a system for implementing a dual artificial intelligence (Al) agent system for virtual environments according to some examples.
[0012] FIG. 2 schematically illustrates an example client device according to some examples.
[0013] FIG. 3 schematically illustrates an example server according to some examples.
[0014] FIG. 4 is a flowchart illustrating an example method for implementing a dual Al system for virtual environments according to some examples.
[0015] FIG. 5 is a flowchart illustrating another example method for implementing a dual Al system for virtual environments according to some examples.
[0016] FIG. 6 is a flowchart of an example workflow in accordance with some configurations.
[0017] FIG. 7 is a flowchart of a learning module example in accordance with some configurations.DETAILED DESCRIPTION OF THE PRESENT DISCLOSURE
[0018] The disclosed technology' is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the following drawings. Other examples of the disclosed technology are possible and examples described and / or illustrated here are capable of being practiced or of being carried out in various ways.
[0019] A plurality of hardware and software-based devices, as well as a plurality of different structural components can be used to implement the disclosed technology’. In addition, examples of the disclosed technology can include hardware, software, and electronic components or modules that, for purposes of discussion, can be illustrated and described as if the majority7of the components were implemented solely in hardware. However, in at least one example, the electronic based aspects of the disclosed technology can be implemented in software (for example, stored on non-transitory computer-readable medium) executable by at least one processor. Although certain drawings illustrate hardware and software located within 5QB\102526408.1Attorney Docket No. 186391.00003particular devices, these depictions are for illustrative purposes only. In some examples, the illustrated components can be combined or divided into separate software, firmware, hardware, or combinations thereof. As one example, instead of being located within and performed by a single electronic processor, logic and processing can be distributed among multiple electronic processors. Regardless of how they are combined or divided, hardware and software components can be located on the same computing device or can be distributed among different computing devices connected by at least one network or other suitable communication link.
[0020] As described above, a software agent (or an agent) may be a computer program that can perform a range of tasks or services for a user. In some examples, a software agent may perform tasks or services autonomously (or semi-autonomously) on behalf of a user or another program. A user may interact or engage with the software agent by providing user input (e.g., commands, questions, conversational dialogue, prompt responses, etc.) and the software agent may perform a corresponding task or service based on the user input.
[0021] As described in greater detail herein, the technology disclosed herein may implement software agents within a virtual environment, such as. e.g., a virtual learning environment. A virtual learning environment may facilitate (or otherwise provide) a virtual session, such as, e.g., an eLearning course, an eWorkshop, another type of online or virtual educational session, etc. In some instances, a virtual session may include a series of interdependent modules or segments (e.g., a series of 2-5 minute, interdependent modules). Such modules may include, e.g.. lectures, videos, animations, exercises, quizzes, another type or form of educational (or training) content, etc. The skills targeted by such virtual sessions may be divided into various objectives or skillsets, such as, e.g., “Technical Skills” and “Soft Skills.” Technical skills may generally pertain to specific professional functions or roles, such as, e.g., providing information about legal code to lawyers, Java scripting for information technology (IT) professionals, etc. Soft skills may generally refer to interpersonal skills that pertain to anyone, regardless of their function or role.
[0022] For example, an objective of a soft skills virtual session may include teaching one or more conceptual frameworks (e.g., a predetermined framework). As one specific example, an eWorkshop on “Difficult Conversations” may teach a “Balanced Communication” framework (e.g., as a means of successfully broaching and navigating a difficult conversation.). As another specific example, an eWorkshop on “Habits of Highly Effective People” may teach an “Effective Habit” framework.6QB\102526408.1Attorney Docket No. 186391.00003
[0023] In some instances, learning objectives may include behavioral change(s) resulting from the introduction of conceptual models or frameworks and other lessons introduced by the virtual session (e.g., an eWorkshop).
[0024] Generally, virtual environments (e.g., eWorkshops) are designed based on a set of technical standards, such as the sharable content objective reference model (SCORM). SCORM is a set of technical standards for eLearning content that ensures the eLearning content can work across different learning management systems (LMSs). For instance, SCORM allows courses to be created once and used on any SCORM-compliant LMS without modification. In some configurations, the technology disclosed herein provides a SCORM-compliant solution. As such, in some configurations, the technology disclosed herein may be incorporated as an add-on to any SCORM-compliant eLearning course.
[0025] An LMS is a software platform that helps organizations create, deliver, manage, or track training programs or educational content. An LMS is widely used in corporate training, online education, or compliance training to facilitate learning in a structured and scalable way. Many companies also use their LMS to track data related to their eLeamers, such as. e.g., enrollment, engagement, performance, etc.
[0026] Accordingly, in some examples, the technology disclosed herein provides a dual artificial intelligence (Al) agent system for virtual environments, and in particular, to provide a dual Al agent system to teach soft skills (e.g., negotiation, teamwork, conflict resolution, etc.) in a virtual environment (e.g., via a virtual session or virtual learning session). In some configurations, the dual Al agent system may implement a roleplay agent and a feedback agent. The roleplay agent may roleplay with an entity (e.g., a learner entity) and the feedback agent may monitor the interaction between the roleplay agent and the learner entity and provide feedback to the learner entity. In some examples, each agent may be embodied by a virtual avatar that the learner entity may interact with in a virtual environment, such as, e.g., an eWorkshop environment or session.
[0027] FIG. 1 illustrates a system 100 for implementing a dual Al agent system for virtual learning experiences (or sessions) according to some examples. As illustrated in the example of FIG. 1, the system 100 can include a server 105, a client device 110, and a database 115. In some examples, the system 100 can include fewer, additional, or different components in different configurations than illustrated in FIG. 1. For example, as illustrated, the system 100 includes one server 105, one client device 110, and one database 115. However, in some examples, the system 100 can include fewer or additional servers 105, client devices 110,7QB\102526408.1Attorney Docket No. 186391.00003databases 115, or a combination thereof. As another example, components of the system 100 can be combined into a single device (e.g.. the database 115 and the client device 110), divided among multiple devices, or a combination thereof. As one example, in some configurations, the functionality described herein (or a portion thereof) of the server 105 may be performed by the client device 110.
[0028] The server 105, the client device 110, and the database 115 can communicate over wired or wireless communication networks 130. Portions of the communication networks 130 can be implemented using a wide area network, such as the Internet, a local area network, such as a Bluetooth™ netw ork or Wi-Fi, and combinations or derivatives thereof. In some examples, the communication network 130 represents a direct wireless link between two components of the system 100 (e.g., via a Bluetooth™ or Wi-Fi link). Alternatively, or in addition, in some examples, two or more components of the system 100 can communicate through an intermediary device of the communication netw ork 130 not illustrated in FIG. 1.
[0029] The client device 110 can be a computing device, such as, e.g., a desktop computer, a laptop computer, a tablet computer, an all-in-one computer, a notebook computer, a terminal, a smart telephone, a smart television, a smart speaker, a smart imaging device, or another suitable computing device that interfaces with a user. A user (also referred to herein as an entity) may interact with the client device 110 via text (e.g., text-based communication or input), voice (e.g., audio-based communication or input), image (e.g., visual or image-based communication or input), etc. Based on the input provided by a user, the client device 110 may provide (or otherwise perform) a task or service for the user, as described in greater detail herein. In some configurations, a user may participate (or otherwise attend) a virtual session using the client device 110, as described in greater detail herein. Alternatively, or in addition, in some configurations, a user may interact in a virtual experience related to a virtual session using the client device 110, as described in greater detail herein.
[0030] A virtual session may be a virtual learning or educational experience, such as, e.g., an eLearning course, an eWorkshop, etc. As such, a virtual session may be an online learning or educational experience. A virtual session may be associated with one or more topics, disciplines, subjects, etc. A virtual session may be directed to or otherwise focus on one or more objectives (also referred to herein as learning objectives). A learning objective may represent, e.g., a target skillset, a skillset proficiency, a target behavioral change, etc. In some instances, the learning objective may be a technical learning objective (e.g., an objective related to technical skills). Alternatively, or in addition, in some configurations, the learning objective 8QB\102526408.1Attorney Docket No. 186391.00003may be a soft skills learning objective (e.g., an objective related to soft skills). In some instances, the learning objective of a virtual session may be related to (or otherwise based on) a topic, discipline, or subject of the virtual session. As one specific example, when a topic relates to effective negotiations, the learning objective may relate to navigating difficult conversations, active listening, conflict resolution, decision-making, etc.
[0031] A virtual session may include electronic content related to a topic of the virtual session. Such electronic content may present (or otherwise be based on) a framework or model for achieving an objective of the corresponding topic (e.g., a conceptual framework or model). For example, the electronic content of a virtual session may provide instruction as to how to achieve a learning objective, where the electronic content may follow (or be based on) a framework or model for achieving the learning objective. The electronic content may include data or information in various forms or formats, such as, e.g., lectures, videos, animations, exercises, quizzes, assessments, other types of interactive content, etc. In some configurations, a virtual session may include a series of interdependent modules, such as, e.g., a series of 2-5 minute, interdependent modules. In such configurations, a module can include one or more lectures, videos, animations, exercises, quizzes, other interactive components, etc.
[0032] As noted above, in some instances, a virtual session may be related to (or otherwise associated with) a virtual experience. In some cases, a virtual experience may be a separate component from the virtual session. Alternatively, in some instances, a virtual experience may be included as part of (or a component of) the virtual session.
[0033] A virtual experience may be an interactive experience or exercise related to a virtual session. In some instances, an entity may engage (or otherwise participate) in a virtual experience after completing a virtual session (e.g., after being taught the electronic content of the virtual session). As such, in some instances, a virtual experience may be an assessment or evaluation of the entity with respect to the learning objective of the virtual session (e.g., an assessment of how much an entity learned or how proficient an entity is with respect to the learning objective of the virtual session). For example, the virtual experience may be a roleplaying exercise between the entity and the virtual entity.
[0034] As described in greater detail herein, a virtual experience may involve an interaction between a virtual entity and the entity (e.g., a conversation, a dialogue, etc.), where the interaction is based on a prompt or example scenario related to a learning objective of the corresponding virtual session. Further, as described in greater detail herein, the entity may receive feedback data related to a performance of the entity with respect to the interaction. Such 9QB\102526408.1Attorney Docket No. 186391.00003feedback data may indicate a performance of the entity, and, ultimately, how much the entity learned or how proficient the entity is with respect to the learning objective of the virtual session.
[0035] As illustrated in FIG. 2, the client device 110 may include a client device electronic processor 200, a client device memory 205, a client device communication interface 210, and a human-machine interface (“HMF ) 215. The client device electronic processor 200, the user device memory 205, the client device communication interface 210, and the HMI 215 can communicate wirelessly, over at least one communication line or bus, or a combination thereof. The client device 110 can include additional, different, or fewer components than those illustrated in FIG. 2 in various configurations. The client device 110 can perform additional functionality other than the functionality described herein. Also, the functionality (or a portion thereof) described herein as being performed by the client device 110 can be performed by another component (e.g., a remote computing device, another computing device, or a combination thereof), distributed among multiple computing devices (e.g., as part of a cloud service or cloud-computing environment), combined with another component (e.g., a remote computing device, another computing device, another component of the system 100, or a combination thereof), or a combination thereof.
[0036] The client device communication interface 210 can include a transceiver that communicates with the server 105. the database 115, another device of the system 100, another device external or remote to the system 100. or a combination thereof over the communication network 130 and, optionally, at least one other communication network or connection. The client device electronic processor 200 may include a microprocessor, an application specific integrated circuit (ASIC), or another suitable electronic device for processing data, and the client device memory 205 may include a non-transilory. computer-readable storage medium. The client device electronic processor 200 is configured to retrieve instructions and data from the client device memory 205 and execute the instructions.
[0037] For example, as illustrated in FIG. 2, the client device memory 205 may store an application 230. The application 230 is a software application executable by the client device electronic processor 200 in the example illustrated and as specifically discussed herein, although a similarly purposed module can be implemented in other ways in other examples. In some configurations, the application 230 may be a dedicated software application locally stored in the client device memory 205 of the client device f 10. The application 230 (when executed by the client device electronic processor 200) may enable or facilitate interaction with agent- 10QB\102526408.1Attorney Docket No. 186391.00003integrated electronic content 235 in accordance with the technology disclosed herein. As described in greater detail herein, the agent-integrated electronic content 235 may include electronic content of a virtual session having one or more Al agents embedded (or otherwise integrated) therein. As one example, the application 230 (when executed by the client device electronic processor 200) may present (or otherwise provide) a virtual session (or electronic content thereof) to an entity, as described in greater detail herein. For instance, a user may participate (or otherwise attend) a virtual session via the application 230. As another example, the application 230 (when executed by the client device electronic processor 200) may facilitate (or otherwise provide) a virtual experience between an entity and a virtual entity, as described in greater detail herein. For example, a user may participate in a virtual experience related to a virtual session via the application 230.
[0038] The client device memory 205 may include additional, different, or fewer components in different configurations than illustrated in FIG. 2. Alternatively, or in addition, in some configurations, components of the client device memory 205 may be combined into a single component, distributed among multiple components, or the like. Alternatively, or in addition, in some configurations, a component of the client device memory 205 may be stored remotely from the client device 110, or, in a remote database, another ser er, a remote user device, an external storage device, or the like. For example, in some configurations, the agent-integrated electronic content 235 may be stored in the database 115, as illustrated in FIG. 1, such that the agent-integrated electronic content 235 is accessible to the client device 110.
[0039] As noted herein, in some instances, the functionality (or a portion thereof) described herein as being performed by the client device 110 can be performed by another component (e.g., a remote computing device, another computing device, or a combination thereof), distributed among multiple computing devices (e.g., as part of a cloud service or cloudcomputing environment), combined with another component (e.g., a remote computing device, another computing device, another component of the system 100, or a combination thereof), or a combination thereof. For example, in some instances, the application 230, the agent-integrated electronic content 235, or a combination thereof may be stored and executed by another component, distributed among multiple computing devices, combined with another component, or a combination thereof.
[0040] As illustrated in FIG. 2, the client device 110 can also include the HMI 215 for interacting with a user (or an entity). The HMI 215 can include at least one input device, at least one output device, or a combination thereof. Accordingly, in some examples, the HMI 11QB\102526408.1Attorney Docket No. 186391.00003215 allows a user to interact with (e.g., provide input to and receive output from) the client device 110. For example, the HMI 215 can include a keyboard, a cursor-control device (e.g., a mouse), a touch screen, a scroll ball, a mechanical button, a display device (e.g., a liquid crystal display (“LCD”)), a printer, a speaker, a microphone, or a combination thereof.
[0041] In the illustrated example of FIG. 2, the HMI 215 includes at least one display device 240 (referred to herein collectively as “the display devices 240” and individually as “the display device 240”). The display device 240 can provide (or output) a media signal to a user. As one example, the display device 240 can display a user interface (e.g., a graphical user interface (GUI)) associated with the application 230, such as, e.g., a GUI providing electronic content related to a virtual session, a GUI providing a virtual experience related to a virtual session (or objective thereol). a GUI providing a report or summary of a performance of an entity with respect to the virtual session, the virtual experience, or the like, etc. The display device 240 can be included in the same housing as the client device 110 or can communicate with the client device 110 over a wired or wireless connection. As one example, the display¬ device 240 can be a touchscreen included in a cellular phone, a smart wearable, a laptop computer, a tablet computer, a smart speaker, another type of portable smart device, etc. As another example, the display device 240 can be a monitor, a television, or a projector coupled to a terminal, desktop computer, or the like via a cable.
[0042] The HMI 215 can also include at least one imaging device 245 (referred to herein collectively as “the imaging devices 245” and individually as “the imaging device 245”). The imaging device 245 can be a component associated with the client device 110 (e g., included in the client device 110 or otherwise communicatively coupled with the client device 110). In some examples, the imaging device 245 can be internal to the client device 110 (e.g., a built-in webcam or camera). Alternatively, or in addition, the imaging device 245 can be external to the client device 110 (e.g., an external webcam or camera positioned on the client device 110 or proximate to the client device 110, e.g., on a desk, table, shelf, wall, ceiling, etc.).
[0043] The imaging device 245 can electronically capture or detect a visual image (as an image data signal or data stream). A visual image can include, e.g., a still image, a movingimage. a video stream, other data associated with providing a visual output, and the like. The imaging device 245 can include a camera, such as, e g., a webcam, an image sensor, or the like. For example, the imaging device 245 can detect image data associated with a physical surrounding or environment of the client device 110. In some examples, the imaging device 245 may detect image data associated with a user (or a feature thereof) using the client device 12QB\102526408.1Attorney Docket No. 186391.00003110. A feature of a user may include, e.g., an eye, a mouth, a body, a head, a hand, a finger, a limb. etc.
[0044] The HMI 215 can also include at least one microphone 250 (referred to herein collectively as ‘'the microphones 250” and individually as “the microphone 250”). The microphone 250 may capture (or otherwise record) audio data (also referred to herein as “voice data”). In some examples, the microphone 250 may capture audio data continuously in realtime (or near real-time). In some configurations, the audio data may be time series data or a data stream of audio data (e.g., an audio datastream). In some instances, the audio data captured by the microphone 250 may be user input provided by a user using the client device 110.
[0045] The HMI 215 can also include at least one speaker 255 (referred to herein collectively as “the speakers 255” and individually as “the speaker 255”). The speaker 255 may output (or otherwise provide) audio data. As described in greater detail herein, in some configurations, the speaker 255 may provide audio data responsive to input received from a user using the client device 110 (e.g., the audio data captured by the microphone 445, image data collected by the imaging device 245, text data received via an input device of the HMI 215, such as a keyboard, a touchscreen, etc.).
[0046] The HMI 215 can also include at least one sensor 260 (referred to herein collectively as “the sensors 260” and individually as “the sensor 260”). The sensor(s) 260 may collect data related to the client device 110, an environment or surroundings of the client device 110, a user of the client device 110, etc. As one example, the sensor(s) 260 may include one or more biometric sensors, such as, e.g., a heart rate monitor, a respiration rate sensor, an electrocardiogram (ECG) sensor, a pupil dilation sensor, a blood pressure monitor, etc. Accordingly, in some cases, the sensor(s) 260 may collect biometric data of a user of the client device 110, such as, e.g., biometric data of the user while the user is participating in a virtual experience (e.g., an interaction between the user and a virtual entity). Biometric data may represent a physical or emotional state of a user given a particular situation, such as, e.g., whether a user is stressed, anxious, relaxed, focused, etc.
[0047] Returning to FIG. 1, the system 100 may also include the server 105. The server 105 may be a computing device. The server 105 may host or otherwise provide at least one platform or environment that implements or facilitates a multi-AI agent system, as described herein. Accordingly, in some examples, the server 105 is associated with a multi-AI agent architecture or platform (e.g., included as a component, device, or subsystem of a system providing or hosting a multi-AI agent platform or service). Alternatively, or in addition, in 13QB\102526408.1Attorney Docket No. 186391.00003some examples, the functionality (or a portion thereof) described herein as being performed by the client device 110 may be locally performed by the server 105.
[0048] As illustrated in FIG. 3, the server 105 may include an electronic processor 300, a memory 305, and a communication interface 310. The electronic processor 300, the memory7305, and the communication interface 310 can communicate wirelessly, over a communication line or bus, or a combination thereof. The server 105 may include additional, different, or fewer components than those illustrated in FIG. 3 in various configurations. The server 105 can perform additional functionality other than the functionality described herein. Also, the functionality' (or a portion thereof) described herein as being performed by the server 105 can be performed by another component (e.g., the database 115, the client device 110, a remote computing device, another computing device, or a combination thereof), distributed among multiple computing devices (e.g., as part of a cloud service or cloud-computing environment), combined with another component (e.g., the database 115, a remote computing device, another computing device, another component of the system 100, or a combination thereof), or a combination thereof.
[0049] The communication interface 310 can include a transceiver that communicates with the client device 110, the database 115, another device of the system 100, another device external or remote to the system 100, or a combination thereof over the communication network 130 and, optionally, at least one other communication network or connection. The electronic processor 300 may include a microprocessor, an ASIC, or another suitable electronic device for processing data, and the memory 305 may include a non-transitory, computer-readable storage medium. The electronic processor 300 is configured to retrieve instructions and data from the memory 305 and execute the instructions.
[0050] For example, as illustrated in FIG. 3, the memory 305 may store an agent database 345. The agent database 345 may store at least one agent 350 (referred to herein collectively as ‘‘the agents 350” and individually as “the agent 350”). The agent(s) 350 may be a software agent. The agent(s) 350 may be artificial intelligence (Al) agents. For instance, the agent(s) 350 may be a software application executable by the electronic processor 300 in the example illustrated and as specifically discussed herein, although a similarly purposed module can be implemented in other ways in other examples. In some instances, the agent 350 may7be a single agent tailored to a particular virtual session. Alternatively, or in addition, the agent 350 may be multiple agents tailored to a particular virtual session. Accordingly, as described in greater detail herein, in some configurations, the agent(s) 350 may be specifically developed for a 14QB\102526408.1Attorney Docket No. 186391.00003particular virtual session, a domain or topic of the virtual session, an objective of the virtual session, electronic content of the virtual session, a conceptual framework or model employed (or otherwise associated with) the virtual session, etc.
[0051] In one specific configuration, the agents 350 may include a roleplay agent (e.g., as a first Al agent) and a feedback agent (e.g., as a second Al agent), as described in greater detail herein. In some examples, the roleplay agent may emulate a virtual entity based on one or more characteristics (e.g., personality or behavioral traits) during a virtual experience. The feedback agent may monitor a virtual experience, such as an interaction between an entity and the virtual entity, and generate feedback data based on the monitored virtual experience. In some instances, the feedback data may indicate (or otherwise include) a performance of the entity during the virtual experience.
[0052] In some configurations, the agent(s) 350 may include one or more large language models (LLMs). Generally, an LLM may include a deep Al or machine learning model that can comprehend and generate human language text. The LLM(s) may be an artificial neural network that is trained using self-supervised learning, semi-supervised learning, or a combination thereof. For instance, an LLM may be configured to determine meanings (or context) from a sequence of words and understand relationships between those words and, ultimately, perform a task based on that understanding. For instance, an LLM may perform a variety of natural language processing (NLP) related tasks to produce content based on input prompts in human language. Such tasks may generally include (or otherwise relate to) answering questions (e.g., responding to a user query), translating text, text generation, content summary', sentiment analysis (e.g., rhythm of speech, speech patterns, tonality' recognition, etc.), speech-to-text, speech recognition, context awareness (e.g., speech patterns), social cues, etc. Accordingly, in some configurations, the agent(s) 350, such as, e.g., the roleplay agent, the feedback agent, etc., may perform NLP functions or functionality for speech recognition, speech to text, sentiment analysis, context awareness, social cues, etc.
[0053] Alternatively, or in addition, in some configurations, the agent(s) 350 may perform functions or functionality related to computer vision and facial recognition, such as, e.g., facial recognition, emotion recognition, gesture recognition, etc. For example, the agent(s) 350 may detect, interpret, or analyze human facial expressions or cues, human gestures, read emotions, detect gestures, etc., such as, with respect to the entity during the virtual expression (e.g., the interaction between the entity and the virtual entity).15QB\102526408.1Attorney Docket No. 186391.00003
[0054] In some configurations, the memory 305 may store a learning engine 360. In some configurations, the learning engine 360 develops a model using an Al or machine learning function. Machine learning functions are generally functions that allow a computer application to leam without being explicitly programmed. In particular, the learning engine 360 is configured to develop a model based on training data. As one example, to perform supervised learning, the training data includes example inputs and corresponding desired (for example, actual) outputs, and the learning engine 360 progressively develops a model that maps inputs to the outputs included in the training data. As another example, to perform self-supervised learning (“SSL”), a model is trained on a task using the data itself to generate supervisory signals (e.g., unlabeled training data), rather than relying on, e.g., external labels provided by a user (e.g., labeled training data). As yet another example, to perform semi-supervised learning, the training data may include desired output values for a subset of the training data (e.g., labeled training data) while the remaining training data may be unlabeled or imprecisely labeled (e.g., unlabeled training data). Machine learning performed by the learning engine 360 may be performed using various types of methods and mechanisms including but not limited to decision tree learning, association rule learning, artificial neural networks, inductive logic programming, support vector machines, clustering, Bayesian networks, reinforcement learning, representation learning, similarity' and metric learning, sparse dictionary7learning, and genetic algorithms. These approaches allow the learning engine 330 to ingest, parse, and understand data and progressively refine models.
[0055] In some configurations, the learning engine 360 may develop one or more of the models described herein, including, e.g., one or more machine learning or Al models of the agents 350 described herein. For example, in some instances, the learning engine 360 may develop the agent(s) 350, including, e.g., the roleplay agent, the feedback agent, etc. In some configurations, the learning engine 360 may develop the agent(s) 350 based on training data, a particular domain or context (e.g., context data), etc. As one specific example, the learning engine 360 may develop the agent(s) 350 using context data specific to a particular virtual session. Following this example, the context data may include a domain or topic of the virtual session, an objective of the virtual session, electronic content of the virtual session, a conceptual framework or model employed (or otherwise associated with) the virtual session, etc. Accordingly, in some configurations, the learning engine 360 may develop one or multiple models that may be utilized by the technology described herein.16QB\102526408.1Attorney Docket No. 186391.00003
[0056] In some configurations, the memory 305 may store an agent integration application 365. The agent integration application 365 is a software application executable by the electronic processor 300 in the example illustrated and as specifically discussed herein, although a similarly purposed module can be implemented in other ways in other examples. In some configurations, the agent integration application 365 may be a dedicated software application locally stored in the memory 305 of the server 105. The agent integration application 365 (when executed by the electronic processor 300) may enable or facilitate the integration of one or more Al agents 350 into electronic content of a virtual session (e.g., to produce the agent-integrated electronic content 235) in accordance with the technology disclosed herein. As described in herein, the agent-integrated electronic content 235 may include electronic content of a virtual session having one or more Al agents 350 embedded (or otherwise integrated) therein. As such, in some configurations, the agent integration application 365 (when executed by the electronic processor 300) may access (or otherwise retrieve) a data packet related to a virtual session (e.g., electronic content of a virtual session), facilitate the development (or training) of the agent(s) 350 for the virtual session (e.g., using the learning engine 360), and integrate (or otherwise embed) the agent(s) 350 into the data packet to generate the agent-integrated electronic content 235, as described in greater detail herein.
[0057] As noted herein, the server 105 (or component(s) thereof) can include additional, different, or fewer components than those illustrated in FIG. 3 in various configurations. Also, the functionality (or a portion thereof) described herein as being performed by the server 105 (or component(s) thereof) can be performed by another component (e g., a remote computing device, another computing device, or a combination thereof), distributed among multiple computing devices (e.g., as part of a cloud service or cloud-computing environment), combined with another component (e.g., a remote computing device, another computing device, another component of the system 100, or a combination thereof), or a combination thereof. For example, in some instances, the agent database 345 (or the agent(s) 350 thereof), the learning engine 360, the agent integration application 365, or a combination thereof may be stored and executed by another component (e.g.. either local to the server 105 or external to the server 105, such as, e.g., the client device 110), distributed among multiple computing devices, combined with another component, or a combination thereof.
[0058] Returning to FIG. 1, in some configurations, the system 100 may also include the database 115. As illustrated in FIG. 1, in some instances, the database 115 may store data or information related to a virtual session, such as. e.g., electronic content 380, the agent- 17QB\102526408.1Attorney Docket No. 186391.00003integrated electronic content 235, etc. The electronic content 380 may represent a version of the electronic content for the virtual session without agents integrated therein (e.g., an original version of electronic content for a virtual session). In some configurations, the database 115 may be (or otherwise be included in) a learning management system (LMS).
[0059] FIG. 4 is a flowchart illustrating a method 400 for integrating Al agents (e.g., the agent(s) 350) into a virtual session according to some examples. The method 400 is described as being performed by the server 105 and, in particular, the electronic processor(s) 300. However, as noted above, the functionality described with respect to the method 400 can be performed by other devices, such as the client device 110, another remote server or computing device, another component of the system 100, or a combination thereof, or distributed among a plurality of devices, such as a plurality of servers included in a cloud service (e.g., a webbased service executing software or applications). Further, although generally described as begin performed by a processor (e.g., the electronic processor 300), this processor may include multiple processors (e.g., as a part of a distributed processor system or group of cooperating processors, such as a processing system).
[0060] As illustrated in FIG. 4, the method 400 may include receiving, with the electronic processor 300, a data packet representing a virtual session (at block 405). The data packet may include (or otherwise represent) the electronic content of the virtual session (e.g., the electronic content 380). In some configurations, the electronic processor 300 may receive the data packet over the communication network 130. The electronic processor 300 may receive (or otherwise retrieve the data packet from the database 115 (e.g., the electronic content 380), the client device 110, or another component of the system.
[0061] The electronic processor 300 may determine context data related to the virtual session (at block 410). The context data may identify (or otherwise indicate) one or more objectives of the virtual session, a conceptual framework or model of the virtual session, additional data or information related to the virtual session, etc. As one specific example, the context data may include one or more key performance indicators (KPIs) or learning objectives related to the virtual session. As described herein, learning objectives may include behavioral change(s) resulting from the introduction of conceptual models or frameworks and other lessons introduced in the virtual session (e g., an eWorkshop). In some instances, the context data may be generated by an entity or user and provided to the electronic processor 300.
[0062] The electronic processor 300 may provide the context data to the agent(s) 350 (at block 415). In some configurations, the context data may be utilized as training data for the 18QB\102526408.1Attorney Docket No. 186391.00003agent(s) 350. For instance, in some configurations, the electronic processor 300 may provide the context data to the learning engine 360 such that the learning engine 360 may develop one or more agents 350 (e.g., a roleplay agent, a feedback agent, etc.) using the context data. Accordingly, in some configurations, the roleplay agent, the feedback agent, or another agent may be specifically trained for a particular virtual session using the context data (e.g., the KPIs or key learning objectives related to the virtual session).
[0063] The electronic processor 300 may embed (or otherwise integrate) the agent(s) 350 (e.g., the roleplay agent, the feedback agent, etc.) into the data packet as the agent-integrated data packet (e.g., the agent-integrated electronic content 235) (at block 420). The electronic processor 300 may then transmit, over the communication network 130, the agent-integrated data packet (e.g.. the agent-integrated electronic content 235) to a remote device (at block 425). In some configurations, the remote device may be the database 115. In some examples, the remote device may be a component of a remote computing platform, such as, e.g., a remote computing platform that controls access to the agent-integrated data packet (e.g., the agent-integrated electronic content 235). As one example, the remote device may be an LMS.
[0064] Alternatively, or in addition, in some configurations, the electronic processor 300 may transmit the agent-integrated data packet (e.g., the agent-integrated electronic content 235) to the client device 110, such that, e.g., an entity of the client device 110 may interact with or otherwise access the agent-integrated data packet (e.g., the agent-integrated electronic content 235). For example, as described in greater detail herein, in some configurations, the client device 110 may provide the electronic content 380 of the virtual session to an entity of the client device 110 and, subsequent to the entity engaging with the electronic content 380 of the virtual session (e g., participating in an eWorkshop, an eLearning course, etc.), the client device 110 may provide a virtual experience based on the objective of the virtual session to an entity of the client device 110, where the agent(s) 350 embedded in the agent-integrated electronic content 235 are executed during the virtual experience, as described in greater detail herein.
[0065] FIG. 5 is a flowchart illustrating a method 500 for implementing a dual Al agent system for virtual environments according to some examples. The method 500 is described as being performed by the client device 110 and, in particular, the client device electronic processor(s) 200. However, as noted above, the functionality described with respect to the method 500 can be performed by other devices, such as the server 105, another remote server or computing device, another component of the system 100, or a combination thereof, or distributed among a plurality of devices, such as a plurality of servers included in a cloud 19QB\102526408.1Attorney Docket No. 186391.00003sen-ice (e.g., a web-based service executing software or applications). Further, although generally described as being performed by a processor (e.g., the client device electronic processor 200), this processor may include multiple processors (e.g., as a part of a distributed processor system or group of cooperating processors, such as a processing system).
[0066] In some configurations, the method 500 may be performed subsequent to one or more steps of method 400. Accordingly, in some configurations, the method 500 may be a continuation of the method 400.
[0067] As illustrated in FIG. 5, the client device electronic processor 200 may receive an agent-integrated data packet (e.g., the agent-integrated electronic content 235) for a virtual session (at block 505). As described herein, the agent-integrated data packet may include, e.g., one or more agent(s) 350 (developed for the virtual session), the electronic content 380, etc. In some configurations, the client device electronic processor 200 may receive (or otherwise retrieve) the agent-integrated data packet responsive to a request from a user (or entity) of the client device 110.
[0068] In some configurations, the client device electronic processor 200 may provide a prompt that identifies a plurality of characteristics for a virtual entity (at block 510). The client device electronic processor 200 may determine a subset of characteristics of the plurality of characteristics based on a response to the prompt (at block 515).
[0069] In some configurations, the client device electronic processor 200 may generate the prompt and output the prompt to a user of the client device 110, such as, e.g., as a GUI that includes or otherwise indicates the plurality of characteristics for a virtual entity (e.g., a list of characteristics or traits). In some configurations, a user may interact with the prompt by selecting one or more characteristics for a virtual entity. In some examples, the characteristics selected by the user may be characteristics for the virtual entity that the user wants emulated during the virtual experience.
[0070] The client device electronic processor 200 may provide the subset of characteristics to a first Al agent (e.g., the roleplay agent) (at block 520). As described herein, the roleplay agent may be configured to emulate a virtual entity. As such, in some configurations, the roleplay agent may emulate a virtual entity based on the subset of characteristics such that the virtual entity' exhibits the subset of characteristics during the virtual experience (e.g., an interaction between the entity and the virtual entity).
[0071] The client device electronic processor 200 may initiate a virtual experience related to the virtual session (at block 525). As described herein, the virtual experience may be based 20QB\102526408.1Attorney Docket No. 186391.00003on an objective of the virtual session. For example, the virtual experience may involve a prompt or a realistic context (e.g.. a written narrative, a narrated story, etc.) in which the entity may apply (or practice) what the entity learned during the virtual session. As one specific example, in a “Difficult Conversations” eWorkshop, the eLeamer (e.g., the entity) may be presented with a situation in which the eLeamer is asked to share a performance review with their direct report, including notifying the direct report that they will not receive a raise or promotion and, instead, are being put on a performance improvement plan. Accordingly, in some configurations, the virtual experience may involve an interaction between the entity and the virtual entity (as emulated by the roleplay agent using the subset of characteristics).
[0072] The client device electronic processor 200 may receive data related to the interaction between the virtual entity and the entity (at block 530). In some configurations, the data related to the interaction between the virtual entity and the entity may text data, audio data, image data, biometric data, or the like for the entity that was collected during the interaction. The data related to the interaction may indicate or describe a behavior of an entity during the interaction. As one example, the data related to the interaction may include a transcription of a conversation between the virtual entity and the entity. As another example, the data related to the interaction may include a video stream of the interaction between the virtual entity and the entity. As yet another example, the data related to the interaction may include an audio recording of the interaction between the virtual entity and the entity. In some configurations, the data related to the interaction between the virtual entity and the entity may be collected using one or more components of the client device 110, such as, e g., the imaging device(s) 245, the microphone(s) 250, the sensor(s) 260, etc.
[0073] The client device electronic processor 200 may provide the data related to the interaction to a second Al agent (e.g., a feedback agent) (at block 535). As described in greater detail herein, the feedback agent may be configured to generate feedback data based on a criterion linked to the objective of the virtual session (e.g., one or more KPI or key learning objectives associated with the virtual session). For instance, in some configurations, the criterion may be a performance indicator specific to the obj ective of the virtual session. In some configurations, the feedback data may relate to a performance of the entity during the interaction, as described herein.
[0074] In some configurations, the feedback agent may generate (or otherwise determine) the feedback data based on a behavioral characteristic, a speech characteristic, a gesture, or a combination thereof of the entity during the interaction. In some examples, the feedback agent 21QB\102526408.1Attorney Docket No. 186391.00003may determine a behavioral characteristic, a speech characteristic, a gesture, or a combination thereof of the entity based on the data related to the interaction (e.g., the text data, the audio data, the image data, the biometric data, etc.). For instance, the feedback agent may receive the data related to the interaction and determine a behavioral characteristic, a speech characteristic, a gesture, etc. of the entity using, e.g., NLP techniques (e.g., speech recognition, sentiment analysis, context awareness, social cues, etc.) computer vision and facial recognition techniques (e.g., facial recognition, gesture detection and recognition, emotion recognition, facial expression recognition, gesture recognition, etc ), or a combination thereof.
[0075] As one specific example, the feedback agent may perform NLP on the data related to the interaction to classify a sentiment of the entity during the interaction, based on, e.g., rhythm of speech, speech patterns, tonality recognition, etc. of the entity during the interaction. The feedback agent may compare the behavioral characteristic, the speech characteristic, the gesture, etc. to the criterion linked to the objective of the virtual session (e.g., the KPIs or key learning objectives) in order to determine a performance of the entity during the interaction. In some instances, when the behavioral characteristic, the speech characteristic, the gesture, etc. align with one or more of the KPIs or key learning objectives of the virtual session, the feedback agent may determine that the entity performed well. In contrast, when the behavioral characteristic, the speech characteristic, the gesture, etc. do not align with one or more of the KPIs or key learning objectives of the virtual session, the feedback agent may determine that the entity did not performed well.
[0076] In some instances, the performance of an entity may be represented using various ratings, rankings, or scorings techniques. As one example, the performance of an entity may be pass / fail. As another example, the performance of an entity may be a percentage that may be based on how aligned the entity was with the criterion (e.g., the KPIs or key learning objectives).
[0077] The client device electronic processor 200 may receive, from the second Al agent, the feedback data (at block 540) and may execute an action related to the virtual session based on the feedback data (at block 545).
[0078] In some configurations, the client device electronic processor 200 may execute the action by generating a report that indicates (or otherwise includes) the feedback data (e.g., how the entity performed during the interaction with the virtual entity). For example, the report may indicate successes, missed opportunities, etc. of the entity. The client device electronic processor 200 may provide the report for display. In some examples, the client device 22QB\102526408.1Attorney Docket No. 186391.00003electronic processor 20 may output the report to the entity via the display device 240 of the client device. Alternatively, or in addition, in some configurations, the client device electronic processor 200 may transmit the report to another device, such as, e.g., a computing device of an administrator or supervisor of the entity, a database (or LMS) of a corporate entity that employs the entity, etc.
[0079] In some configurations, the client device electronic processor 200 may determine a recommendation based on the feedback data. A recommendation may include, e.g., a remedial action or content (e.g., additional electronic content directed toward an aspect of the entity’ performance that could be improved), a promotion in role or level of the entity, a certificate or accreditation for the entity, etc. In some instances, the client device electronic processor 200 may include the recommendation in a report that indicates (or otherwise includes) the feedback data (e.g., how the entity performed during the interaction with the virtual entity).
[0080] In some configurations, the client device electronic processor 200 may generate a digital representation for one or more of the agent(s) 350. For example, the client device electronic processor 200 may generate a first digital representation (e.g.. an avatar) for the roleplay agent, a second digital representation (e.g., another avatar) for the feedback agent, or a combination thereof. In some examples, the client device electronic processor 200 may facilitate display of the graphical representation(s) of the agent(s) 350, such as, e.g., during the virtual experience. As one specific example, the client device electronic processor 200 may generate and display an avatar (e.g., a graphical representation) of the roleplay agent while the entity interacts with the virtual entity, where the avatar of the roleplay agent emulates the virtual entity7(e.g., using the subset of characteristics, as selected by the entity). Accordingly, during the interaction between the virtual entity and the entity, the client device electronic processor 200 may control the digital representation of the virtual entity (e.g., the roleplay agent) using the subset of characteristics such that the digital representation emulates (or otherwise exhibits) the subset of characteristics.
[0081] In some configurations, the client device electronic processor 200 may control the digital representation(s) to provide the feedback data. For example, in some instances, the client device electronic processor 200 may control the digital representation of either the roleplay agent or the feedback agent to provide the feedback data. In some instances, the client device electronic processor 200 may control the digital representation of the roleplay agent or the feedback agent based on the performance of the entity such that the digital representation behaves in a manner that is consistent with how the entity performed during the virtual 23QB\102526408.1Attorney Docket No. 186391.00003experience. As one example, when the entity performed well (e.g., in alignment with the criterion), the digital representation may exhibit positive characteristics when providing the feedback data to the entity. As another example, when the entity did not perform well (e.g., not in alignment with the criterion), the digital representation may exhibit negative or empathetic characteristics when providing the feedback data to the entity.
[0082] FIG. 6 is a flowchart of an example workflow 700 in accordance with some configurations. At 605, a client may enter into a licensing agreement with a Company. The license may allow licensee to integrate the dual Al agent solution ("‘the Solution”) into one or more of licensee's eLearning courses (“eWorkshops”), over the term of the license. At 610, the Company may integrate the Solution into one or more of licensee's eWorkshops. For each eWorkshop, this may involve back-end coding that integrates licensee-supplied key learning objectives into one or more agents of the Solution. Accordingly, licensee may provide the Company access to subject eWorkshop(s), and may consult with the Company to define learning objectives. At 615, upon completion of the integration of the Solution into licensee’s preexisting eWorkshop, the newly integrated eWorkshop may be saved to licensee’s LMS for the duration of the license term. At 620, the licensee may make the integrated eWorkshop available to its users via its LMS. At 625, the eLeamer may access a self- paced eLearning course via a learning platform / leaming management system (LMS). Users may access and “attend” the eWorkshop at their convenience from their device (computer, tablet, phone, etc.). At 630. the eLeamer may complete instructional components of eWorkshop (e.g., the licensee supplied modules).
[0083] FIG. 7 is a flowchart of a learning module example in accordance with some configurations. At 705, the eLeamer may be presented with a realistic context (e g., on screen as a written narrative, as a narrated story, etc.) in which they will apply what they learned in the eWorkshop. For example, in a “Difficult Conversations” eWorkshop, the eLeamer might be presented with a situation in which they must share a critical performance review with their direct report, including notifying the direct report that they will not receive a raise / promotion and, instead, are being put on a performance improvement plan. At 710, the eLeamer may be prompted to choose personality and behavioral traits (i.e., from a list) to describe the counterpart they prefer to interact with. This way, they will interface with a counterpart “agent” that is realistic to them. At 715, a roleplay agent is a foil in the role play of the case study and assumes the personality and communication traits selected by eLeamer. At 720, the eLeamer may begin conversation (e.g., “Hi. How are you?”). At 725, the roleplay agent may respond.24QB\102526408.1Attorney Docket No. 186391.00003At 730, the eLeamer may respond. At 735, the eLeamer completes the role-play. At 740, a feedback agent may track the eLeamer’ s performance an application of key performance indicators (KPIs). The feedback agent may generate and share feedback with the eLeamer.
[0084] In some examples, aspects of the technology, including computerized implementations of methods according to the technology', can be implemented as a system, method, apparatus, or article of manufacture using standard programming or engineering techniques to produce software, firmware, hardware, or any combination thereof to control a processor device (e.g., a serial or parallel processor chip, a single- or multi-core chip, a microprocessor, afield programmable gate array, any variety of combinations of a control unit, arithmetic logic unit, and processor register, and so on), a computer (e.g., a processor device operatively coupled to a memory), or another electronically operated controller to implement aspects detailed herein. Accordingly, for example, examples of the technology can be implemented as a set of instructions, tangibly embodied on a non-transitory computer-readable media, such that a processor device can implement the instructions based upon reading the instructions from the computer-readable media. Some examples of the technology can include (or utilize) a control device such as an automation device, a computer including various computer hardware, software, firmware, and so on, consistent with the discussion below. As specific examples, a control device can include a processor, a microcontroller, a field-programmable gate array, a programmable logic controller, logic gates etc., and other typical components that are known in the art for implementation of appropriate functionality (e.g., memory, communication systems, power sources, user interfaces and other inputs, etc.).
[0085] Certain operations of methods according to the technology7, or of systems executing those methods, can be represented schematically in the FIGS, or otherwise discussed herein. Unless otherwise specified or limited, representation in the FIGS, of particular operations in particular spatial order can not necessarily require those operations to be executed in a particular sequence corresponding to the particular spatial order. Correspondingly, certain operations represented in the FIGS., or otherwise disclosed herein, can be executed in different orders than are expressly illustrated or described, as appropriate for particular examples of the technology. Further, in some examples, certain operations can be executed in parallel, including by dedicated parallel processing devices, or separate computing devices configured to interoperate as part of a large system.
[0086] As used herein in the context of computer implementation, unless otherwise specified or limited, the terms "‘component,” “system,” “module,” “block,” and the like are 25QB\102526408.1Attorney Docket No. 186391.00003intended to encompass part or all of computer-related systems that include hardware, software, a combination of hardware and software, or software in execution. For example, a component can be, but is not limited to being, a processor device, a process being executed (or executable) by a processor device, an object, an executable, a thread of execution, a computer program, or a computer. By way of illustration, both an application running on a computer and the computer can be a component. A component (or system, module, and so on) can reside within a process or thread of execution, can be localized on one computer, can be distributed between two or more computers or other processor devices, or can be included within another component (or system, module, and so on).
[0087] Also as used herein, unless otherwise limited or defined, “or” indicates a nonexclusive list of components or operations that can be present in any variety of combinations, rather than an exclusive list of components that can be present only as alternatives to each other. For example, a list of “A, B, or C” indicates options of: A; B; C; A and B; A and C; B and C; and A, B, and C. Correspondingly, the term “or” as used herein is intended to indicate exclusive alternatives only when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.” Further, a list preceded by “one or more” (and variations thereon) and including “or” to separate listed elements indicates options of one or more of any or all of the listed elements. For example, the phrases “one or more of A, B, or C” and “at least one of A, B, or C” indicate options of: one or more A; one or more B; one or more C; one or more A and one or more B; one or more B and one or more C; one or more A and one or more C; and one or more of each of A, B, and C. Similarly, a list preceded by “a plurality of” (and variations thereon) and including “or” to separate listed elements indicates options of multiple instances of any or all of the listed elements. For example, the phrases “a plurality of A, B, or C” and “two or more of A, B, or C” indicate options of: A and B; B and C; A and C: and A, B, and C. In general, the term “or” as used herein only indicates exclusive alternatives (e.g., “one or the other but not both”) when preceded by terms of exclusivity, such as “either,” “one of,” “only one of,” or “exactly one of.”
[0088] Although the present technology has been described by referring to preferred examples, workers skilled in the art will recognize that changes can be made in form and detail without departing from the scope of the discussion.26QB\102526408.1
Claims
Attorney Docket No. 186391.00003CLAIMSWhat is claimed is:
1. A system, comprising:a processing system including one or more electronic processors, the processing system configured to:receive an agent-integrated data packet for a virtual session, wherein the agent-integrated data packet includes a plurality of artificial intelligence (Al) agents developed for a virtual session;provide a prompt that identifies a plurality of characteristics for a virtual entity;determine a subset of characteristics of the plurality of characteristics based on a response to the prompt;provide the subset of characteristics to a first artificial intelligence (Al) agent, wherein the first Al agent is configured to emulate the virtual entity using the subset of characteristics;initiate a virtual experience related to the virtual session, wherein the virtual experience is based on an objective of the virtual session, wherein the virtual experience involves an interaction between an entity participating in the virtual session and the virtual entity as emulated by the first Al agent using the subset of characteristics;receive data related to the interaction between the virtual entity and the entity; provide the data related to the interaction to a second Al agent, the second Al agent configured to generate feedback data based on a criterion linked to the objective of the virtual session, wherein the feedback data relates to a performance of the entity during the interaction;receive, from the second Al agent, the feedback data; andexecute an action related to the virtual session based on the feedback data.
2. The system of claim 1, wherein the data related to the interaction includes at least one of: text data, audio data, image data, or biometric data.
3. The system of claim 1. wherein the data related to the interaction includes at least one of:27QB\102526408.1Attorney Docket No. 186391.00003a transcription of a conversation between the virtual entity and the entity;a video stream of the interaction between the virtual entity and the entity; or an audio recording of the interaction between the virtual entity and the entity.
4. The system of claim 1, wherein the second Al agent is configured to generate the feedback data based on at least one of:a behavioral characteristic of the entity during the interaction;a speech characteristic of the entity during the interaction; ora gesture of the entity during the interaction.
5. The system of claim 1. wherein the second Al agent is configured to perform natural language processing (NLP) on the data related to the interaction to classify a sentiment of the entity7during the interaction.
6. The system of claim 1, wherein the criterion is a performance indicator specific to the objective of the virtual session.
7. The system of claim 1, wherein the processing system is configured to execute the action by:generating a report that includes the feedback data; andproviding the report for display.
8. The system of claim 1, wherein the processing system is configured to execute the action by:determining a recommendation based on the feedback data; andgenerating a report that indicates the recommendation.
9. The system of claim 1, wherein the processing system is configured to:generate a digital representation of the virtual entity emulated by the first Al agent; andcontrol the digital representation of the virtual entity' using the subset of characteristics during the interaction between the virtual entity' and the entity such that the digital representation emulates the subset of characteristics.28QB\102526408.1Attorney Docket No. 186391.0000310. The system of claim 9, wherein the processing system is configured to execute the action by:controlling the digital representation of the virtual entity to provide the feedback data such that, while the digital representation of the virtual entity provides the feedback data, the digital representation of the virtual entity has one or more characteristics based on the performance of the entity.
11. A method, comprising:receiving, with a processing system including one or more electronic processors, an agent-integrated data packet for a virtual session, wherein the agent-integrated data packet includes a plurality’ of artificial intelligence (Al) agents developed for a virtual session; providing, w ith the processing system, a prompt that identifies a plurality of characteristics for a virtual entity;determining, with the processing system, a subset of characteristics of the plurality of characteristics based on a response to the prompt;providing, with the processing system, the subset of characteristics to a first artificial intelligence (Al) agent, wherein the first Al agent is configured to emulate the virtual entity using the subset of characteristics;initiating, with the processing system, a virtual experience related to the virtual session, wherein the virtual experience is based on an objective of the virtual session, wherein the virtual experience involves an interaction between an entity participating in the virtual session and the virtual entity as emulated by the first Al agent using the subset of characteristics;receiving, with the processing system, data related to the interaction between the virtual entity and the entity';providing, with the processing system, the data related to the interaction to a second Al agent, the second Al agent configured to generate feedback data based on a criterion linked to the objective of the virtual session, wherein the feedback data relates to a performance of the entity during the interaction;receiving, with the processing system, from the second Al agent, the feedback data; and29QB\102526408.1Attorney Docket No. 186391.00003executing, with the processing system an action related to the virtual session based on the feedback data.
12. A system, comprising:a processing system including one or more electronic processors, the processing system configured to:receive, over a communication network, a data packet representing a virtual session, wherein the data packet includes electronic content of the virtual session; determine context data related to the virtual session, wherein the context data is associated with an objective to be achieved via the virtual session;provide the context data to a plurality of artificial intelligence (Al) agents, wherein each Al agent of the plurality of Al agents are specifically trained for the virtual session using the context data;embed the plurality of Al agents into the data packet as an agent-integrated data packet; andtransmit, over the communication network, the agent-integrated data packet to a remote computing platform, wherein the remote computing platform controls access to the agent-integrated data packet.
13. The system of claim 12, wherein the remote computing platform includes a client device, the client device configured to:provide the electronic content of the virtual session to an entity of the client device; andprovide a virtual experience based on the objective of the virtual session; and execute the plurality of Al agents during the virtual experience.
14. The system of claim 12, wherein the plurality of Al agents includes at least one of:a first Al agent that emulates a virtual entity based on a set of characteristics during a virtual experience that involves the virtual entity and an entity; ora second Al agent that generates feedback data based on a performance of the entity during the virtual experience.30QB\102526408.1Attorney Docket No. 186391.0000315. The system of claim 12, wherein the remote computing platform is a learning management system (LMS).
16. The system of claim 12, wherein the electronic content of the virtual session provides a conceptual framework for achieving the objective.
17. The system of claim 12, wherein the plurality of Al models includes at least one large language model (LLM).
18. A method, comprising:receiving, over a communication network, with a processing system including one or more electronic processors, a data packet representing a virtual session, wherein the data packet includes electronic content of the virtual session;determining, with the processing system, context data related to the virtual session, wherein the context data is associated with an objective to be achieved via the virtual session;providing, with the processing system, the context data to a plurality of artificial intelligence (Al) agents, wherein each Al agent of the plurality of Al agents are specifically trained for the virtual session using the context data;embedding, with the processing system, the plurality of Al agents into the data packet as an agent-integrated data packet; andtransmitting, over the communication network, with the processing system, the agent-integrated data packet to a remote computing platform, wherein the remote computing platform controls access to the agent-integrated data packet.
19. A system, comprising:a processing system including one or more electronic processors, the processing system configured to:receive, over a communication network, a data packet representing a virtual session, wherein the data packet includes electronic content of the virtual session; embed a plurality of Al agents into the data packet as an agent-integrated data packet, wherein each Al agent of the plurality of Al agents are specifically trained using context data associated with an objective to be achieved via the virtual session;access the agent-integrated data packet;provide the virtual session to an entity;31QB\102526408.1Attorney Docket No. 186391.00003initiate, based on the agent-integrated data packet, a virtual experience related to the virtual session, wherein the virtual experience is based on the objective of the virtual session and involves an interaction between the entity and a virtual entity, wherein a first Al agent of the plurality of Al agents is configured to emulate the virtual entity using one or more selected characteristics;receive data related to the interaction between the virtual entity and the entity; generate, using a second Al agent, feedback data related to a performance of the entity during the interaction, wherein the second Al agent is configured to generate the feedback data based on a criterion linked to the objective of the virtual session; andexecute an action related to the virtual session based on the feedback data.
20. The system of claim 19, wherein the processing system is configured to:generate a digital representation of the virtual entity emulated by the first Al agent; andcontrol the digital representation of the virtual entity using the one or more selected characteristics during the interaction between the virtual entity and the entity such that the digital representation emulates the one or more selected characteristics.QB\102526408.1
