System to manifest a cognitive identity

Abstract

Apparatus and associated methods relate to a synthetic cognitive system (SCS). In an illustrative example, the SCS may include a performance quantifier engine (PQE) configured to generate an action signal based on input data received from a user / agent experience. The SCS may, for example, include a synthetic cognitive identity (SCI). The SCI may, for example, include cognitive biases associated with an agent. The SCI may, for example, include goals associated with an agent. The SCI may, for example, include observations and inferences associated with an agent. The SCI may, for example, include hypotheses associated with an agent. The SCI may, for example, dynamically and independently update in real-time in response to the input data, such that the SCS generates responses dynamically to match with an evolution process of the user / agent experience. Various embodiments may advantageously simulate human-like cognitive and emotional processes, enabling personalized and adaptive interactions across multiple domains.

Description

SYSTEM TO MANIFEST A COGNITIVE IDENTITYCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application is a non-pro visional application and claims the benefit of U.S. Application Serial No. 63 / 641,545, titled “SYSTEM TO MANIFEST A COGNITIVE IDENTITY,” filed by Luke Michael Du Pont and Duane Edward Kealoha Bridges on May 2, 2024.

[0002] This application incorporates the entire contents of the foregoing application herein by reference.TECHNICAL FIELD

[0003] Various embodiments relate generally to synthetic cognitive systems capable of performing complex tasks across multiple domains.BACKGROUND

[0004] Artificial General Intelligence (AGI) refers to the development of intelligent systems with the capacity to understand, learn, and apply knowledge in a manner comparable to human intelligence across a wide variety of tasks and domains. Unlike narrow artificial intelligence (Al) systems, which are designed for specific, predefined functions, AGI aspires to achieve flexibility, adaptability, and autonomy in problem-solving and reasoning. AGI could mark a transformative milestone in the field of artificial intelligence, with far-reaching implications for science, society, and technology.

[0005] Closely related to AGI are synthetic cognitive systems. Synthetic cognitive systems are artificial constructs designed to emulate aspects of human cognition. These systems draw upon interdisciplinary research across cognitive science, neuroscience, Al, and robotics. Their aim is to develop systems that can understand and interact with the world in a flexible, adaptive manner.SUMMARY

[0006] Apparatus and associated methods relate to a synthetic cognitive system (SCS). In an illustrative example, the SCS may include a performance quantifier engine (PQE) configured to generate an action signal based on input data received from a user / agent experience. The SCS may, for example, include a synthetic cognitive identity (SCI). The SCI may, for example, include cognitive biases associated with an agent. The SCI may, for example, include goals associated with an agent. The SCI may, for example, include observations and inferences associated with an agent. The SCI may, for example, include hypotheses associated with an agent. The SCI may, for example, dynamically and independently update in real-time in response to the input data, such that the SCS generates responses dynamically to match with an evolution process of the user / agentexperience. Various embodiments may advantageously simulate human- like cognitive and emotional processes, enabling personalized and adaptive interactions across multiple domains.

[0007] Various embodiments may achieve one or more advantages. For example, some embodiments may advantageously enable more engaging and relatable interactions with users. Some implementations may, for example, advantageously create tailored responses and outputs, enhancing user experience. Some embodiments may, for example, advantageously evolves over time through dynamic updates, learning from new information and interactions to improve performance and relevance. Some implementations may, for example, advantageously optimize decision-making processes. Some embodiments may, for example, advantageously dynamically adjust behavior and outputs based on user inputs, goals, and evolving contexts, creating an engaging and tailored experience that closely mimics human interaction.

[0008] Some implementations may, for example, advantageously process inputs sequentially through modules, ensuring comprehensive and context-aware outputs. Some embodiments may, for example, advantageously enable users to author and adjust SCIs without extensive programming expertise. Some implementations may, for example, advantageously interpret a moral definition document to guide behaviors and decision-making processes to be morally upright. Some embodiments may, for example, advantageously generate various types of media outputs tailored to a selected SCI. Some implementations may, for example, advantageously operate in portable or remote applications, making an SCS suitable for diverse environments. Some embodiments may, for example, advantageously collect and exchange data autonomously with Internet of Things (loT) devices, enabling seamless connectivity and data flow.

[0009] The details of various embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG. 1 depicts an exemplary synthetic cognitive system (SCS) employed in an illustrative use-case scenario.

[0011] FIG. 2 is a block diagram depicting an exemplary emotional circuit module.

[0012] FIG. 3 is a flowchart illustrating an exemplary synthetic cognitive identity (SCI) authoring method.

[0013] FIG. 4 is a flowchart illustrating an exemplary synthetic cognitive interactive output generation method.100141 FIG. 5 depicts a block diagram depicting exemplary definitions incorporated in a SCI to define personality, temperament, and other personal psychometrically identifying factors associated with a target cognitive identity (TCI).

[0015] FIGS. 6A, 6B, and 6C shows an exemplary SCI system (SCI Engine) in one embodiment.

[0016] Like reference symbols in the various drawings indicate like elements.DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS

[0017] FIG. 1 depicts an exemplary synthetic cognitive system (SCS 100) employed in an illustrative use-case scenario. In this example, the SCS 100 receives input 105 to generate a media output 110. Various embodiments may apply a synthetic cognitive identity to the input 105 to generate output files as a function of an emotional response characteristic with the synthetic cognitive identity.

[0018] For example, the input 105 may include data generated from physical interactions between the SCS 100 with the real world. In this example, the input 105 may be generated from an exercise device 1 15. For example, the input 105 may include audio, a heart rate, and / or other biometric information of a user of the exercise device 115.

[0019] In some implementations, the SCS 100 may process the input 105 based on a currently selected (e.g., user-selected) synthetic cognitive identity to generate the media output 110. As an illustrative example without limitation, the synthetic cognitive identity may identify with having an overarching personality such as a trainer or a workout buddy for the user of the exercise device 115. For example, the media output 110 may include a video / audio response (e.g., response of a drill instructor, a response of a workout buddy) to the user. For example, the media output 110 may correspond to empathy, temperament, integrity, worth appraisal, mood from system state, and / or emotions of the synthetic cognitive identity.

[0020] The SCS 100 includes a processor 120. The processor 120 may, for example, include one or more processing units. In some implementations, the processor 120 may be operably coupled to a communication module (not shown). The communication module may, for example, include wired communication. The communication module may, for example, include wireless communication. In some examples, the communication module may be operably coupled to the exercise device 115.

[0021] The processor 120 is operably coupled to a memory module 125. The memory module 125 may, for example, include one or more memory modules (e.g., random-access memory (RAM)). The processor 120 is further operably coupled to a data store 130. In some implementations, the memory module 125 and the data store 130 may, for example, combine into one data store. Insome implementations, the memory module 125 and the data store 130 may, for example, combine into one memory module.

[0022] As shown, the data store 130 includes synthetic cognitive identities (SCI) 135. A SCI 135 may, for example, define personality, temperament, and other personal psychometrically identifying factors associated with a target cognitive identity (TCI). In some implementations, the SCI 135 may define emotion associated with TCI. The SCI 135 may, for example, include hypotheses definitions 140 associated with the TCI. For example, the SCI 135 may include goal definitions 145 associated with the TCI. The SCI 135 may, for example, include cognitive bias definitions (CBD 150) associated with the TCI. The SCI 135 may, for example, include observations and inferences history 152 associated with the TCI.

[0023] In some embodiments, the SCI 135 may be represented in a human-readable programming language. For example, the SCI 135 may be programmed in list processing (LISP) languages. For example, once an SCI is created, the SCI may be embodied in a LISP file. For example, the LISP file may be configured to define a range of identifiable personal psychometric traits, decisionmaking behaviors, and cognitive biases that the media output 110 should exhibit. For example, the LISP file may include the hypotheses definitions 140, the goal definitions 145, and the CBD 150.

[0024] In some implementations, the SCI 135 may be configured to include predefined functions to direct an external module based on a programmed identity. In various embodiments, the SCI 135 may be configured to be dynamically updated as the SCI is used and / or is further trained. For example, the dynamic updating may advantageously allow for evolution of the SCS 100 over time in response to new information and / or interactions. In some implementations, the SCI 135 may be manually configured using a graphical user interface (GUI). For example, the GUI may allow a user to author and / or adjust a SCI without extensive programming expertise.

[0025] In this example, the memory module 125 includes a cognitive engine 155. For example, the cognitive engine 155 may apply the hypotheses definitions 140, the goal definitions 145, and the CBD 150 of a selected SCI to operate upon the input 105. As shown, the cognitive engine 155 includes a cognitive bias module(s) (CBM 160), an emotional circuit module (ECM 165), a system state module (SSM 170), and a temperament module (TM175).

[0026] The cognitive engine 155, for example, may adjust the CBM 160 according to the selected SCI. In some implementations, the cognitive engine 155 may apply the cognitive modules (e.g., the CBM 160, the ECM 165, the SSM 170, and the TM175) in a sequence. In this example, one or more sequences may be described. In other embodiments, other sequential applications may be possible.

[0027] The cognitive engine 155 may, for example, receive the input 105 from physical interactions with the real world. For example, the input 105 may include data, audio files, videofiles, numerical inputs, gesture identifying and tracking, eye tracking, temperature, or some combination thereof. For example, the cognitive engine 155 may sequentially operate on the input 105 by each of the cognitive modules (e.g., the CBM 160, the ECM 165, the SSM 170, and the TM175). In some implementations, the cognitive engine 155 may generate the media output 110 corresponding to one of the selected SCIs (e.g., a response of a drill instructor, a response of a workout buddy).

[0028] As an illustrative example without limitation, the cognitive engine 155 may process the input 105 by the CBM 160. Based on the SCI 135, the CBM 160 may apply a current bias state to the input 105 to generate, for example, preliminary biases. In some implementations, the cognitive engine 155 may apply the preliminary biases to the ECM 165 and the TM175.

[0029] The ECM 165 may, for example, apply emotional circuits (e.g., seeking, lust, anger, care, disgust, happiness, sadness, fear, rage, contempt, play, grief, etc.) to generate an emotional data output. The TM 175 may, for example, apply one or more of a predetermined number (e.g., 5, 10) and personal psychometric identifiers (e.g., openness, narcissism, conscientiousness, etc.) to generate a psychometric output.

[0030] In some implementations, when the input 105 is received initially by the SCS 100 (e.g., as an interaction with the physical world begins), the emotional circuits of the ECM 165 may be at a neutral state. For example, personality factors in the ECM 165 may be static. As the interaction continues, for example, the ECM 165 may be updated to drift the emotional circuits as a function of the SCI 135 and the input 105.

[0031] In some implementations, the SSM 170 may receive output from the ECM 165 (e.g., dynamically shifting based on input) and the TM 175 (e.g., more static psychometric attributes). The SSM 170 may, for example, apply a matrix to generate a selection of one or more cognitive biases or other heuristic to activate.

[0032] In some implementations, the SSM 170 may assign a relative worth to each of the active cognitive biases. For example, the relative worth may be generated during a machine learning process (e.g., using reinforcement learning, supervised learning). In some examples, the relative worth may be generated using heuristic methods. For example, the relative worth may be generated by applying optimization techniques. In some implementations, the relative worth may be generated using Bayesian updating. In some examples, a combination approach may be used.

[0033] In this example, the CBM 160 receives input from the SSM 170. For example, the CBM 160 may select a currently active bias (e.g., perception-related biases, goal-related biases) based on an output of the SSM 170. For example, the cognitive biases may advantageously to speed up decision making. In some implementations, the CBM 160 may apply the currently active bias to apply a weight to an output decision generated.100341 In some embodiments, output of the CBM 160 may include other heuristics. The output of the CBM 160, in some implementations, may extend beyond the traditionally recognized cognitive biases. For example, some heuristics may be designed to modulate the emphasis on, and / or de-emphasis of, various aspects of sensory and cognitive processing in the cognitive engine 155. For example, the CBM 160 may include heuristics affecting a perception of the input 105 (e.g., an incoming data), the inference drawn from the input 105, calculations based on the input 105, and the desires or goals that are pursued.

[0035] In some implementations, the cognitive engine 155 may be configured to dynamically adjust these heuristics in response to changing environmental conditions or objectives. For example, the cognitive engine 155 may be configured to increase the emphasis on calculated inferences in situations where empirical data is abundant and reliable to advantageously enhance the decision-making accuracy. In some examples, the cognitive engine 155 may be configured to prioritize desires in scenarios where immediate action is necessary, optimizing for speed over precision. These adjustments may, for example, be realized through the modification of relative worth assigned to each heuristic, enabling the SCS 100 to adapt its processing approach in realtime based on the context of operation.

[0036] The memory module 125, in this example, includes a performance quantifier engine (PQE 180) and an inference engine (IE 185). The IE 185 may receive the output decision from the cognitive engine 155. For example, the IE 185 may select one of the SCI 135 from the data store 130 based on the hypotheses definitions 140 being most aligned with the output decision of the cognitive engine 155. The PQE180, for example, may include a Markov Blanket calculator. For example, the PQE 180 may be configured to receive as an input the output of the IE 185.

[0037] In some implementations, the PQE 180 may be configured to minimize a confidence value (e.g., associated with a Markov Blanket) calculated of a course of action (e.g., an ambiguous outcome, a curiosity outcome, a risk outcome - such as an action misaligned with the goals defined, a value outcome). The output of the IE 185, for example, may be used to generate the media output 110 (e.g., an audio file, a video file, a text file) as a function of the sequential processing in the cognitive engine 155 according to a currently applied SCI 135. In various embodiments, each of the cognitive modules (e.g., the CBM 160, the ECM 165, the SSM 170, and the TM 175) may dynamically adjust worth and weightings according to the currently selected SCI. In some examples, the SCI 135 may be dynamically adjusted (e.g., selections, weightings, worth, integrity, purposes, focus) as a function of outputs of the cognitive engine 155.

[0038] In some implementations, the PQE180 may evaluate potential actions against the minimization of uncertainty and surprise. For example, the PQE180 may consider multiple factors (e.g., ambiguity, curiosity, risk, value). For example, the PQE180 may use the Markov Blanketcalculator to select one or more actions that align with the hypotheses definitions 140, the goal definitions 145, and the CBD 150 of the SCI 135.

[0039] Various embodiments may advantageously generate artificial general intelligence (AGI) that is “human-like”. For example, the SCS 100 may generate a cognitive intelligence that may advantageously demonstrate emotion and personality. For example, the cognitive engine 155 may adaptively adjust parameters of the CBM 160, the ECM 165, the SSM 170, and the TM 175 to model emotions of a TCI. For example, the cognitive engine 155 may be configured to adjust the parameters to better the user of the media output 110. For example, in a game application, the SCS 100 may be configured to learn a goal of a user of the game. For example, the goal may be enjoyment (e.g., regardless of winning or losing the game). For example, the cognitive engine 155 may select weighting, worth, focus and parameters to generate the media output 110 to match the goal (e.g., a fun factor) over time.

[0040] FIG. 2 is a block diagram depicting an exemplary emotional circuit module. In this example, the ECM 165 receives a cognitive bias 205 and generates an emotion output 210. In various examples, human emotions may be created by cells releasing chemicals. For example, the chemicals may be released based on an instantaneous feeling, resting on a person’s personal psychometric identifiers, personality and temperament. In one embodiment, the ECM 165 may include a set of mathematical functions 215 configured to simulate a physiological correlation.

[0041] For example, the set of mathematical functions 215 may generate the emotion output 210 based on a current state of worth and / or integrity factors 220 and a current state of temperament 225. For example, the worth and / or integrity factors 220 and the temperament 225 may be represented in a digital format.

[0042] As shown, the ECM 165 also includes an update module 230. For example, the update module may update the worth and / or integrity factors 220 and the temperament 225 based on a feedback input 235. For example, the feedback input 235 may include the output of the cognitive engine 155 and the input 105. For example, the worth and / or integrity factors 220 and the temperament 225 may be updated to simulate a TCI.

[0043] FIG. 3 is a flowchart illustrating an exemplary synthetic cognitive identity (SCI) authoring method 300. In a step 305, entitled “Rotes,” an author defines the activities that an SCI (e.g., SCI 135) may perform. The activities may, for example, effect the outside world. The activities may, for example, effect an internal state of the SCI.

[0044] In a step 310, entitled “Knowledge,” the author defines the quasi-static data that the SCI may have, specifying those that may come from the outside world. In a step 315, entitled “Perceivable,” the author defines the dynamic data that the SCI may receive from the outside world.100451 In a step 320, entitled “Calculables,” the author defines the data that the SCI may calculate from known data. The known data may, for example, include dynamic data. The known data may, for example, include quasi-static data.

[0046] In a step 325, entitled “Inferables,” the author defines the dynamic data that the SCI may calculate using math associated with inference. In a step 330, entitled “Hypotheses,” the author defines the models that correlate received data to that which may be inferred. In a step 335, entitled “Ambitions,” the author defines the desirable world states that might result from activities. In a step 340, entitled “Worth,” the author defines a model to correlate outcomes of activities with desired outcomes. In a step 345, entitled “Moral Integrity,” the author defines a model to correlate outcomes of activities with a moral framework.

[0047] In a step 350, entitled “Temperament & Plasticity,” the author defines a model of the personality of the SCI. The rough model may, for example, include how the SCI might drift. In a step 355, entitled “Emotions,” the author defines a model of dynamic feelings. The dynamic feelings may, for example, include visceral changes in the internal state of the SCI due to things that occur.

[0048] In a step 360, entitled “Bias & Heuristics,” the author defines a variety of rules-of-thumb. The variety of rules-of-thumb may, for example, apply weights to many aspects within the engine. In a step 365, entitled “System State,” the author defines how temperament, emotion, and other aspects come together to represent the overall internal state of the SCI and from there select heuristics to apply. In a step 370, entitled “Tags,” the author defines labels for data, hypotheses, ambitions, and other aspects which mark things as being associated with particular heuristics. As the engine processes tags, the engine may, for example, attach weights to the tags.

[0049] In some embodiments, the SCS 100 an author engine configured to take inputs to generate an authored cognitive identity (ACI). For example, the ACI may describe when and where something is more pertinent to that personality. In one embodiment, the SCS 100 may receive parameters from the ACI. For example, the parameters may include psychometric factors. For example, the parameters may include personal emotion. For example, the parameters may include hypotheses (e.g., the hypotheses definitions 140). For example, the parameters may include goals (e.g., the goal definitions 145). For example, the parameters may include cognitive biases.

[0050] For example, an author may give a human-like input to generate the ACI (e.g., designating a factor is more important than another factor). For example, the author may give a priority list and a feedback loop to the ACI. In some embodiments, the SCS 100 may generate the set of mathematical functions 215 to represent an emotion circuit of the ACI. For example, the SCS 100 may include mathematical relationships between the worth and / or integrity factors 220 and the temperament 225.10051 1 FIG. 4 is a flowchart illustrating an exemplary synthetic cognitive interactive output generation method 400. For example, the cognitive engine 155 may use the method 400 to generate the media output 110 based on a selected SCI. In this example, the 400 begins in step 405 when a synthetic cognitive identity (SCI) is retrieved from a data store. For example, the cognitive engine 155 may retrieve the SCI 135 from the data store 130. In some implementations, the SCS 100 may include a preselected SCI. For example, the SCS 100 may be configured to use a workout buddy instead of retrieving a trainer SCI.

[0052] In step 410, cognitive modules are initialized based on the SCI. For example, the cognitive engine 155 may initialize parameters in the CBM 160, the ECM 165, the SSM 170, and the TM 175. In some examples, the ECM 165 may be initiated into a neutral state. Next, input is received in step 415. For example, the cognitive engine 155 may receive the input 105. For example, the input may include audio and / or heart rate of a user of the input 105. After input is received, in step 420, a current bias state is applied to the input to generate a preliminary bias. For example, the CBM 160 may process the input 105 to generate the preliminary bias.

[0053] In step 425, the preliminary bias is processed with an emotional circuit and a worth and / or integrity factor module. For example, the output of the CBM 160 may be processed by the ECM 165 and the TM 175. Next, in step 430, a derivation is applied to outputs of the emotional circuit and the worth and / or integrity factor module to generate a new cognitive state. For example, the cognitive engine 155 may process the input 105 in sequence to generate a cognitive state based on the SCI 135.

[0054] In step 435, parameters of the cognitive modules are updated based on the input and the new cognitive state. For example, the update module 230 of the ECM 165 may update the worth and / or integrity factors 220 and the temperament 225 based on the feedback input 235. A decision is generated based on the current cognitive state in step 440. For example, the IE 185 may be applied to generate the decision based on the input 105 and the cognitive state. For example, the PQE180 may include a Markov blanket to determine a decision based on the SCI 135.

[0055] In a decision point 445, it is determined whether an output media is to be generated. For example, the decision generated in the step 440 may include generating a voice output. For example, the decision generated in the step 440 may include generating a video output. If it is determined that an output media is to be generated, in step 450, an output media is generated at an output port, and the step 415 is repeated. If an output media is not to be generated, the step 415 is repeated. For example, the cognitive engine 155 may continue to receive the input 105 and update the cognitive modules.

[0056] FIG. 5 depicts a block diagram 500 depicting exemplary definitions incorporated in a SCI 135 to define personality, temperament, and other personal psychometrically identifying factorsassociated with a target cognitive identity (TCI). The SCI 135 may, for example, include hypotheses definitions 140 associated with the TCI. The hypotheses definitions 140 may, for example, include a proposed explanation formulated to fill identified gaps in knowledge. For example, the hypotheses definitions 140 may be based on incomplete knowledge and include a method for gaining more complete knowledge.

[0057] For example, the SCI 135 may include goal definitions 145 associated with the TCI. For example, goal definitions 145 may include purpose-driven objective or desired outcomes that an SCI 135 strives to achieve within a SCS (e.g., SCS 100). Goals definitions 145 may, for example, be appraised for their worth and alignment with a subject's identity, purpose, and understanding. For example, the appraisal of goals definitions 145, may involve assessing risks, potential threats, and the probability of achieving expectations, ensuring that the pursuit of goals contributes to the system's overall good and purpose.

[0058] The SCI 135 may, for example, include cognitive bias definitions (CBD 150) associated with the TCI. For example, CBD 150 may include subjective inclinations or predispositions that influence the SCI’s 135 perception, appraisal, or decision-making process. For example, CBD 150 may manifest as cognitive tendencies, cultural norms, or personal perspectives that shape how the SCI 135 interprets meaning, assigns worth, or interacts with the SCI’s 135 environment.

[0059] The SCI 135 may, for example, include observations and inferences history 152 associated with the TCI. For example, observations may refer to the observed findings of the SCI 135. Inferences may, for example, include conclusions or deductions made from these observations. Both the observation and inferences of the SCI 135 may, for example, be stored in the observations and inferences history 152. The observations and inferences history 152 may, for example, advantageously enable an SCS (e.g., SCS 100) to make full use of the computing platform by storing data and evolving over a period.

[0060] The SCI 135 may, for example, include appraisals definitions 505 associated with the TCI. Appraisals definitions 505 may, for example, include the process by which an SCI 135 interprets and evaluates the worth, meaning, or purpose of perceivable within an SCS (e.g., SCS 100). Appraisals definitions 505 may, for example, involve identifying problems or questions, forming insights, and analyzing these through cognitive modulators or social interactions to confirm or deny their contextual value.

[0061] The SCI 135 may, for example, include modeled affect definitions 510 associated with the TCI. Modeled affect definitions 510 may, for example, include the neuroscience definition of modeled affect. For example, modeled affect definitions 510 may include something’s ability to influence the SCI 135 in a way that is linked to an SCS (e.g., SCS 100).100621 The SCI 135 may, for example, include veracity calibration definitions 515 associated with the TCI. Veracity calibration definitions 515 may, for example, include the dynamic ability of the SCI 135 to adapt its actions and responses based on internal or external stimuli. Veracity calibration definitions 515 may, for example encompass both contextual changes, where existing mechanisms are activated, and developmental changes, where past experiences shape current behavior through new neuronal pathways. This adaptability may, for example, reflect the SCI’s 135 capacity to adjust to threats, challenges, and evolving environments.

[0063] FIGS. 6A, 6B, and 6C show an exemplary SCI system (SCI Engine) in one embodiment. An SCI engine may, for example, provide downloadable computer software for use in creating interactive individual or interactive multiples of corporeal or incorporeal or digital or virtual: animals, appliances, artificial assistants, artificial intelligence systems, artificial personalities, automated chal'mt systems, chatbots, conversational agents, creatures, dialogue systems, fictional characters, non-fictional characters, objects, operating systems, people, places, and tools, with capabilities of: understanding and or displaying cognitive and non-cognitive emotional and logical and non-logical distinguishing and or idiosyncratic and or anomalous personality characteristics and behaviors and manners and reactions and responses and social qualities and traits with distinguishing and or idiosyncratic and or anomalous individual or multiple cognitive and non- cognitive identities.

[0064] Although various embodiments have been described with reference to the figures, other embodiments are possible. In some implementations, the input 105 may be a speech to text input in a car navigation system.

[0065] In some embodiments, the heuristic may include a moral integrity heuristic. In one embodiment, the SCS 100 may be configured to interpret a moral definition document (MDD) to define standards of moral integrity. For example, the SCS 100 may include a tool to process the moral definition document and generate a specification of behaviors, actions, and / or decisionmaking processes guided to be morally upright based on the defined standards. For example, the MDD may be structured in a human-readable format (e.g., using a markup language, a programming language).

[0066] In some implementations, the SCS 100 may be configured as a Markov blanket. For example, each of the cognitive modules (e.g., the CBM 160, the ECM 165, the SSM 170, and the TM 175) may be implemented in the Markov blanket. The cognitive engine may, for example, be configured as a Markov blanket applied to one or more Markov blankets.

[0067] Although an exemplary system has been described with reference to FIG. 1, other implementations may be deployed in other industrial, scientific, medical, commercial, and / or residential applications.|0068| In some embodiments, the SCS 100 may, for example, be employed as a customer service bot. For example, the SCS 100 may, for example, advantageously respond to customer inquiries empathetically, improving customer experience. For example, the SCS 100 may, for example guide a customer into picking from options with a particular focus related to specialty. For example, the SCS 100 may, guide a customer in picking pizza toppings. The SCS 100 may, for example, guide a customer in picking a type of screw.

[0069] In some embodiments, the SCS 100 may, for example, be employed as a personal assistant. For example, the SCS 100 may understand and predict a user’s needs. The SCS 100 may, for example, advantageously understand the emotional states of the user. For example, the SCS 100 may, for example, be employed as a coaching bot such that the SCS 100 guides a user in activities such as exercise or meal preparation doing so with the right amount of energy and specific focus. The SCS 100 may, for example, be employed as a leisure guide such that the SCS 100 guides a user in leisure activity such as movies or books, restaurants or clubs, or sight-seeing and doing so with specific focus an attention to user's tastes.

[0070] In some embodiments, the SCS 100 may, for example, be employed in content creation. For example, the SCS 100 may create high-quality media content, that resonates with human emotions or has a specific style. For example, the media content may include articles. The media content may, for example include art. The media content may, for example include music. The media content may, for example include video games.

[0071] In some implementations, the SCS 100 may, for example, be employed in mental health therapy. For example, the SCS 100 may, for example, provide therapeutic conversations, understand human emotions, and provide comfort with a specific style or methodology. The SCS 100 may, for example, supplement counselors, therapists, life coaches, and child protective services interviewers.

[0072] In some embodiments, the SCS 100 may, for example, be employed in education. For example, the SCS 100 may provide personal tutors, adapting to the emotional state and learning style of the student to provide personalized education. For example, the SCS 100 may provide personal tutors to disabled students or students that are having trouble with traditional school.

[0073] In some implementation, the SCS 100 may, for example be employed in social care. For example, the SCS 100 may assist in caring for the elderly or people with disabilities, providing companionship and understanding their emotional needs.

[0074] In some embodiments, the SCS 100 may, for example, be employed in negotiation or diplomacy. For example, the SCS 100 may be used in complex negotiations or diplomatic situations, understanding and navigating human emotions and cultural nuances. For example, the SCS 100 may advise police officers or journalists while investigating subjects. The SCS 100 may,for example, assist in fact checking by identifying cognitive biases or logical fallacies in the news or other types of presentations, including, for example, orations and debates.

[0075] In some implementations, the SCS 100 may, for example, be employed in marketing and advertising. For example, the SCS 100 may generate personalized marketing campaigns that resonate with the emotions of the target audience. Additionally, the SCS 100 may, for example, analyze consumer behavior and emotions to predict market trends.

[0076] In some embodiments, the SCS 100 may, for example, be employed in recruitment. For example, the SCS 100 may understand roles and candidates’ personalities to make matches for companies or persons. For example, the SCS 100 may be used in job interviews. The SCS 100 may, for example, be used in dating.

[0077] In some implementations, the SCS 100 may, for example, be employed in posthumous interactions. For example, the SCS 100 may use extensive data about deceased individuals to recreate their personalities, allowing interactions with virtual representations of the departed.

[0078] In some embodiments the SCS 100 may, for example, be employed in gaming. For example, the SCS 100 may be used to develop emotionally rich opposition, allies, obstacles, and resources within a gaming environment.

[0079] Although an exemplary system has been described with reference to FIG. 1, other implementations may be deployed in other industrial, scientific, medical, commercial, and / or residential applications.

[0080] In various embodiments, some bypass circuits implementations may be controlled in response to signals from analog or digital components, which may be discrete, integrated, or a combination of each. Some embodiments may include programmed, programmable devices, or some combination thereof (e.g., PLAs, PLDs, ASICs, microcontroller, microprocessor), and may include one or more data stores (e.g., cell, register, block, page) that provide single or multi-level digital data storage capability, and which may be volatile, non-volatile, or some combination thereof. Some control functions may be implemented in hardware, software, firmware, or a combination of any of them.

[0081] Computer program products may contain a set of instructions that, when executed by a processor device, cause the processor to perform prescribed functions. These functions may be performed in conjunction with controlled devices in operable communication with the processor. Computer program products, which may include software, may be stored in a data store tangibly embedded on a storage medium, such as an electronic, magnetic, or rotating storage device, and may be fixed or removable (e.g., hard disk, floppy disk, thumb drive, CD, DVD).100821 Although an example of a system, which may be portable, has been described with reference to the above figures, other implementations may be deployed in other processing applications, such as desktop and networked environments.

[0083] Temporary auxiliary energy inputs may be received, for example, from chargeable or single use batteries, which may enable use in portable or remote applications. Some embodiments may operate with other DC voltage sources, such as (nominal) batteries, for example. Alternating current (AC) inputs, which may be provided, for example from a 50 / 60 Hz power port, or from a portable electric generator, may be received via a rectifier and appropriate scaling. Provision for AC (e.g., sine wave, square wave, triangular wave) inputs may include a line frequency transformer to provide voltage step-up, voltage step-down, and / or isolation.

[0084] Although particular features of an architecture have been described, other features may be incorporated to improve performance. For example, caching (e.g., LI, L2, . . .) techniques may be used. Random access memory may be included, for example, to provide scratch pad memory and or to load executable code or parameter information stored for use during runtime operations. Other hardware and software may be provided to perform operations, such as network or other communications using one or more protocols, wireless (e.g., infrared) communications, stored operational energy and power supplies (e.g., batteries), switching and / or linear power supply circuits, software maintenance (e.g., self-test, upgrades), and the like. One or more communication interfaces may be provided in support of data storage and related operations.

[0085] Some systems may be implemented as a computer system that can be used with various implementations. For example, various implementations may include digital circuitry, analog circuitry, computer hardware, firmware, software, or combinations thereof. Apparatus can be implemented in a computer program product tangibly embodied in an information carrier, e.g., in a machine-readable storage device, for execution by a programmable processor; and methods can be performed by a programmable processor executing a program of instructions to perform functions of various embodiments by operating on input data and generating an output. Various embodiments can be implemented advantageously in one or more computer programs that are executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a data storage system, at least one input device, and / or at least one output device. A computer program is a set of instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.|0086| Suitable processors for the execution of a program of instructions include, by way of example, both general and special purpose microprocessors, which may include a single processor or one of multiple processors of any kind of computer. Generally, a processor will receive instructions and data from a read-only memory or a random-access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memories for storing instructions and data. Generally, a computer will also include, or be operatively coupled to communicate with, one or more mass storage devices for storing data files; such devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including, by way of example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, ASICs (applicationspecific integrated circuits).

[0087] In some implementations, each system may be programmed with the same or similar information and / or initialized with substantially identical information stored in volatile and / or nonvolatile memory. For example, one data interface may be configured to perform auto configuration, auto download, and / or auto update functions when coupled to an appropriate host device, such as a desktop computer or a server.

[0088] In some implementations, one or more user-interface features may be custom configured to perform specific functions. Various embodiments may be implemented in a computer system that includes a graphical user interface and / or an Internet browser. To provide for interaction with a user, some implementations may be implemented on a computer having a display device. The display device may, for example, include an LED (light-emitting diode) display. In some implementations, a display device may, for example, include a CRT (cathode ray tube). In some implementations, a display device may include, for example, an LCD (liquid crystal display). A display device (e.g., monitor) may, for example, be used for displaying information to the user. Some implementations may, for example, include a keyboard and / or pointing device (e.g., mouse, trackpad, trackball, joystick), such as by which the user can provide input to the computer. For example, the display device may, for example, include an OLED (Organic Light Emitting Diodes) display. A display device may, for example, include an AMOLED (Active-Matrix Organic Light- Emitting Diode) display. A display device may, for example, include a Plasma display. A display device may, for example, feature an E-Ink (Electronic Ink) display. A display device may, for example, include a QLED (Quantum Dot Light Emitting Diode) display. In various examples, the display device may be configured to display information to a user in different ways and withdifferent characteristics, such as brightness, contrast, color gamut, power consumption, and / or refresh rate.

[0089] In various implementations, the system may communicate using suitable communication methods, equipment, and techniques. For example, the system may communicate with compatible devices (e.g., devices capable of transferring data to and / or from the system) using point-to-point communication in which a message is transported directly from the source to the receiver over a dedicated physical link (e.g., fiber optic link, point-to-point wiring, daisy-chain). The components of the system may exchange information by any form or medium of analog or digital data communication, including packet-based messages on a communication network. Examples of communication networks include, e.g., a LAN (local area network), a WAN (wide area network), MAN (metropolitan area network), wireless and / or optical networks, the computers and networks forming the Internet, or some combination thereof. Other implementations may transport messages by broadcasting to all or substantially all devices that are coupled together by a communication network, for example, by using omni-directional radio frequency (RF) signals. Still other implementations may transport messages characterized by high directivity, such as RF signals transmitted using directional (i.e., narrow beam) antennas or infrared signals that may optionally be used with focusing optics. Still other implementations are possible using appropriate interfaces and protocols such as, by way of example and not intended to be limiting, USB 2.0, Firewire, ATA / IDE, RS-232, RS-422, RS-485, 802.11 a / b / g, Wi-Fi, Ethernet, IrDA, FDDI (fiber distributed data interface), token-ring networks, multiplexing techniques based on frequency, time, or code division, or some combination thereof. Some implementations may optionally incorporate features such as error checking and correction (ECC) for data integrity, or security measures, such as encryption (e.g., WEP) and password protection.

[0090] In various embodiments, the computer system may include Internet of Things (loT) devices. loT devices may include objects embedded with electronics, software, sensors, actuators, and network connectivity which enable these objects to collect and exchange data. loT devices may be in-use with wired or wireless devices by sending data through an interface to another device. loT devices may collect useful data and then autonomously flow the data between other devices.

[0091] Various examples of modules may be implemented using circuitry, including various electronic hardware. By way of example and not limitation, the hardware may include transistors, resistors, capacitors, switches, integrated circuits, other modules, or some combination thereof. In various examples, the modules may include analog logic, digital logic, discrete components, traces and / or memory circuits fabricated on a silicon substrate including various integrated circuits (e.g., FPGAs, ASICs), or some combination thereof. In some embodiments, the module(s) may involveexecution of preprogrammed instructions, software executed by a processor, or some combination thereof. For example, various modules may involve both hardware and software.

[0092] In an illustrative aspect, a system may include a data store (e.g., memory module 125 or data store 130) that may, for example, include a program of instructions. For example, the system may include a processor (e.g., processor 120) operably coupled to the data store such that, when the processor executes the program of instructions, the processor causes operations to be performed to automatically manage a synthetic cognitive system (e.g., SCS 100).

[0093] For example, the operations may include obtain input data (e.g., input 105) from a user / agent experience comprising physical interactions between the user / agent with a real world. For example, the operations may include retrieve a synthetic cognitive identity (e.g., SCI 135) from the data store based on the input data by determining cognitive biases definitions (e.g., cognitive bias definitions 150), goals definitions (e.g., goals definitions 145), observations and inferences history (e.g., observations and inferences history 152), and hypotheses definitions (e.g., hypothesis definitions 140) such that the SCI is dynamically updated in real-time to match an evolution of the user / agent experience. For example, the operations may include apply the SCI to a performance quantifier engine (e.g., PQE 180) to generate an action signal (e.g., media output 110) comprising a feedback to a user as a function of the dynamically updated SCI and the input data.

[0094] For example, the operations may include transmit the input data from the user / agent experience to a cognitive engine (e.g., cognitive engine 155), the cognitive engine including: a cognitive bias module (e.g., cognitive bias module 160) configured to process the input data to generate a preliminary bias state; an emotional circuit module (e.g., emotion circuit module 165) configured to process the preliminary bias state to generate emotional outputs; and a temperament module (e.g., temperament module 175) configured to process the preliminary bias state to generate psychometric outputs; and, a system state module (e.g., system state module 170) configured to receive and apply a matrix to the emotional and psychometric outputs to generate a new cognitive state, such that parameters of the cognitive bias module, emotional circuit module, temperament module, and system state module are updated based on the input and the new cognitive state. For example, the operations may include generate a new cognitive state via the cognitive engine. For example, the operations may include retrieve the new cognitive state generated by the cognitive engine and retrieve the SCI from the data store based on the hypotheses definitions, the goals definitions, observations and inferences history, and the cognitive bias definitions that align most closely with the new cognitive state via an inference engine (e.g., IE 185) such that the SCI selected by the IE is sent to the PQE, such that the PQE and the IE work in conjunction to generate the action signal.100951 For example, the system may include one or more of below features:• For example, the action signal may include a media output (e.g., media output 110).• For example, the action signal may be generated by applying a Markov blanket to a current cognitive state dynamically determined from the SCI.• For example, the action signal may be generated based on, in addition to the SCI, a set of predetermined factors identified from the input data including risk, value, and ambiguity.• For example, the retrieved SCI may be further based on determining appraisal definitions (e.g., appraisal definitions 505), modeled affect definitions (e.g., modeled affect definitions 510), and veracity calibration definitions (e.g., veracity calibration definitions 515).

[0096] In an illustrative aspect, a computer program product may include a program of instructions tangibly embodied on a computer readable medium wherein when the instructions are executed on a processor (120), the processor causes operations to be performed to automatically manage a synthetic cognitive system (e.g., SCS 100). For example, the operations may include obtain input data (e.g., input 105) from a user / agent experience comprising physical interactions between the user / agent with a real world. For example, the operations may include retrieve a synthetic cognitive identity (e.g., SCI 135) from a data store (e.g., ., memory module 125 or data store 130) based on the input data. For example, the operations may include determine cognitive biases definitions (e.g., cognitive bias definitions 150), goals definitions (e.g., goals definitions 145), observations and inferences history (e.g., observations and inferences history 152), and hypotheses definitions (e.g., hypothesis definitions 140) such that the SCI may be dynamically updated in real-time to match an evolution of the user / agent experience. For example, the operations may include determine a potential action signal that corresponds to a minimization of uncertainty and surprise. For example, the operations may include, based on the retrieved SCI and the determined potential action signal, generate an action signal (e.g., media output 110) including a feedback to a user as a function of the dynamically updated SCI and the input data.100971 For example, the operations may include retrieve the input data from the user / agent experience. For example, the operations may include generate a preliminary bias state based on the retrieved input data. For example, the operations may include retrieve the preliminary bias state and generate an emotional output and a psychometric output. For example, the operations may include retrieve and apply a matrix to the emotional output and the psychometric output to generate a new cognitive state, such that parameters of the preliminary bias state, the emotional output, and the psychometric output are updated based on the input data and the new cognitive state. For example, the operations may include retrieve the SCI from the data store based on the hypotheses definitions, the observations and inferences history, the goals definitions, and the cognitive bias definitions that align most closely with the generated new cognitive state. For example, theoperations may include determine the potential action signal that corresponds to the minimization of uncertainty and surprise. For example, the operations may include, based on the retrieved SCI and the determined potential action signal, generate the action signal comprising the feedback to the user as the function of the dynamically updated SCI and the input data.

[0098] For example, the computer program product may include one or more of below features:• For example, the action signal may include a media output (e.g., media output 110).• For example, the action signal may be generated by applying a Markov blanket to a current cognitive state dynamically determined from the SCI.• For example, the action signal may be generated based on, in addition to the SCI, a set of predetermined factors identified from the input data including risk, value, and ambiguity.• For example, the retrieved SCI may be further based on determining appraisal definitions (e.g., appraisal definitions 505), modeled affect definitions (e.g., modeled affect definitions 510), and veracity calibration definitions (e.g., veracity calibration definitions 515).

[0099] A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made. For example, advantageous results may be achieved if the steps of the disclosed techniques were performed in a different sequence, or if components of the disclosed systems were combined in a different manner, or if the components were supplemented with other components. Accordingly, other implementations are contemplated within the scope of the following claims.

Claims

CLAIMSWhat is claimed is:

1. A system comprising: a data store (130) comprising a program of instructions; and, a processor (120) operably coupled to the data store (130) such that, when the processor (120) executes the program of instructions, the processor (120) causes operations to be performed to automatically manage a synthetic cognitive system (SCS 100), the operations comprising: obtain input data (105) from a user / agent experience comprising physical interactions between the user / agent with a real world; retrieve a synthetic cognitive identity (SCI 135) from the data store (130) based on the input data (105) by determining cognitive biases definitions (150), goals definitions (145), observations and inferences history (152), and hypotheses definitions (140) such that the SCI (135) is dynamically updated in real-time to match an evolution of the user / agent experience; and apply the SCI (135) to a performance quantifier engine (PQE 180) to generate an action signal (110) comprising a feedback to a user as a function of the dynamically updated SCI (130) and the input data (105).

2. The system of claim 1 wherein the operations further comprise: transmit the input data (105) from the user / agent experience to a cognitive engine (155), the cognitive engine (155) comprising: a cognitive bias module (160) configured to process the input data to generate a preliminary bias state; an emotional circuit module (165) configured to process the preliminary bias state to generate emotional outputs; a temperament module (175) configured to process the preliminary bias state to generate psychometric outputs; and, a system state module (170) configured to receive and apply a matrix to the emotional and psychometric outputs to generate a new cognitive state, such that parameters of the cognitive bias module (160), emotional circuit module (165), temperament module (175), and system state module (170) are updated based on the input and the new cognitive state; and, generate a new cognitive state via the cognitive engine (155); and,retrieve the new cognitive state generated by the cognitive engine and retrieve the SCI (135) from the data store (130) based on the hypotheses definitions (140), the goals definitions (145), observations and inferences history (152), and the cognitive bias definitions (150) that align most closely with the new cognitive state via an inference engine (IE 185) such that the SCI (135) selected by the IE (185) is sent to the PQE (180), such that the PQE (180) and the IE (185) work in conjunction to generate the action signal (110).

3. The system of claim 1, wherein the action signal comprises a media output (110).

4. The system of claim 2, wherein the action signal comprises a media output (110).

5. The system of claim 1, wherein the action signal (110) is generated by applying a Markov blanket to a current cognitive state dynamically determined from the SCI (135).

6. The system of claim 2, wherein the action signal (110) is generated by applying a Markov blanket to the new cognitive state dynamically determined from the SCI (135).

7. The system of claim 1 , wherein the action signal (110) is generated based on, in addition to the SCI (135), a set of predetermined factors identified from the input data comprising risk, value, and ambiguity.

8. The system of claim 2, wherein the action signal (110) is generated based on, in addition to the SCI (135), a set of predetermined factors identified from the input data comprising risk, value, and ambiguity.

9. The system of claim 1, wherein the retrieved SCI (135) is further based on determining appraisal definitions (505), modeled affect definitions (510), and veracity calibration definitions (515).

10. The system of claim 2, wherein the retrieved SCI (135) is further based on determining appraisal definitions (505), modeled affect definitions (510), and veracity calibration definitions (515).

11. A computer program product comprising: a program of instructions tangibly embodied on a computer readable medium wherein when the instructions are executed on a processor (120), the processor (120) causes operations to be performed to automatically manage a synthetic cognitive system (SCS 100) the operations comprising:obtain input data (105) from a user / agent experience comprising physical interactions between the user / agent with a real world; retrieve a synthetic cognitive identity (SCI 135) from a data store (130) based on the input data; determine cognitive biases definitions (150), goals definitions (145), observations and inferences history (152), and hypotheses definitions (140) such that the SCI (135) is dynamically updated in real-time to match an evolution of the user / agent experience; determine a potential action signal that corresponds to a minimization of uncertainty and surprise; and, based on the retrieved SCI and the determined potential action signal, generate an action signal (110) comprising a feedback to a user as a function of the dynamically updated SCI and the input data.

12. The computer program product of claim 11 , wherein the operations further comprise: retrieve the input data (105) from the user / agent experience; generate a preliminary bias state based on the retrieved input data (105); retrieve the preliminary bias state and generate an emotional output and a psychometric output; retrieve and apply a matrix to the emotional output and the psychometric output to generate a new cognitive state, such that parameters of the preliminary bias state, the emotional output, and the psychometric output are updated based on the input data and the new cognitive state; retrieve the SCI (135) from the data store (130) based on the hypotheses definitions (140), the observations and inferences history (152), the goals definitions (145), and the cognitive bias definitions (150) that align most closely with the generated new cognitive state; determine the potential action signal that corresponds to the minimization of uncertainty and surprise; and, based on the retrieved SCI (135) and the determined potential action signal, generate the action signal (1 10) comprising the feedback to the user as the function of the dynamically updated SCI (135) and the input data (105).

13. The computer program product of claim 11 , wherein the action signal comprises a media output (HO).

14. The computer program product of claim 12, wherein the action signal comprises a media output (HO).

15. The computer program product of claim 11, wherein the action signal (110) is generated by applying a Markov blanket to a current cognitive state dynamically determined from the SCI (135).

16. The computer program product of claim 12, wherein the action signal (110) is generated by applying a Markov blanket to the new cognitive state dynamically determined from the SCI (135).

17. The computer program product of claim 11 , wherein the action signal (110) is generated based on, in addition to the SCI (135), a set of predetermined factors identified from the input data comprising risk, value, and ambiguity.

18. The computer program product of claim 12, wherein the action signal (110) is generated based on, in addition to the SCI (135), a set of predetermined factors identified from the input data comprising risk, value, and ambiguity.

19. The computer program product of claim 11, wherein the retrieved SCI (135) is further based on determining appraisal definitions (505), modeled affect definitions (510), and veracity calibration definitions (515).

20. The computer program product of claim 12, wherein the retrieved SCI (135) is further based on determining appraisal definitions (505), modeled affect definitions (510), and veracity calibration definitions (515).

Images