System and method for facilitating implementation of affective-state-based artificial intelligence

Abstract

To facilitate implementation of affective-state-based artificial intelligence.SOLUTION: One or more growth or decay factors for a series of affective attributes of an artificial intelligence entity may be determined, and a series of affective values, which are associated with the series of affective attributes, may be continuously updated on the basis of the growth factors or decay factors. Input may be obtained, and a response related to the input may be generated on the basis of the continuously-updated series of affective values of the artificial intelligence entity. In some embodiments, the growth factors or decay factors may be updated on the basis of the input and subsequent to the updating of the decay factors, the affective values may be updated on the basis of the updated growth factors or decay factors.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of (1) U.S. Provisional Patent Application No. 62 / 623,521, filed January 29, 2018, entitled "Emotionally Intelligent Artificial Intelligence System," and (2) U.S. Provisional Patent Application No. 62 / 660,195, filed April 19, 2018, entitled "System and Method for Facilitating Affective-State-Based Artificial Intelligence."

[0002] The present invention relates to facilitating the implementation of emotional state based artificial intelligence, including, for example, generating a response to an input based on an emotional value associated with an emotional attribute of an artificial intelligence entity. [Background technology]

[0003] Recent technological advances have greatly improved the ability of computer systems to acquire and process large amounts of data, and the cost of doing so has fallen dramatically. As a result, machine learning and other artificial intelligence (AI) systems have made great advances. This typically requires high processing power, as well as large amounts of data to train or update such AI systems. AI has advanced to the point where AI systems can detect human emotions based on speech variability and facial expressions, and can respond to questions asked by humans. However, given that typical AI systems do not have their own unique emotional state (e.g., they have and express their own emotions), it is believed that such AI systems will not truly understand (and experience) emotions in the same way that humans do. Typical AI systems suffer from these and other shortcomings. Summary of the Invention [Problem to be solved by the invention]

[0004] Aspects of the present invention relate to methods, apparatus and / or systems for facilitating the implementation of emotional state based artificial intelligence. [Means for solving the problem]

[0005] In some embodiments, an emotion value of the artificial intelligence entity may be updated, and a response may be generated related to the acquired input based on the emotion value of the artificial intelligence entity. Additionally or alternatively, one or more growth or decay factors may be determined for a set of emotion attributes of the artificial intelligence entity, and the emotion value of the artificial intelligence entity may be updated based on the growth or decay factors. In some embodiments, the growth or decay factors may be updated based on the acquired input, and after updating the growth or decay factors, the emotion value may be updated based on the updated growth or decay factors.

[0006] In some embodiments, one or more emotion baselines that cap one or more emotion values ​​may be updated based on the acquired input, and the emotion values ​​may be updated based on the updated boost or decay factors and the updated emotion baselines. In some embodiments, the acquired input may be a natural language input. Natural language processing of the natural language input may be performed to obtain one or more emotion concepts of the natural language input and other information of the natural language input, and the boost or decay factors may be updated based on the emotion concepts of the natural language input and other information of the natural language input.

[0007] Various other aspects, features, and advantages of the present invention will become apparent from the detailed description of the invention and the accompanying drawings. It should also be understood that both the summary above and the detailed description below are exemplary only and are not intended to limit the scope of the present invention. As used in this specification and the claims, the singular forms "a," "an," and "the" imply plural, unless the context clearly indicates otherwise. Further, as used in this specification and the claims, the term "or" means "and / or," unless the context clearly indicates otherwise. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 illustrates a system that facilitates enabling emotional state-based or other artificial intelligence in accordance with one or more embodiments.

[0009] [Figure 2A] 1 is a graph illustrating emotion values ​​and emotion baselines associated with emotion attributes in accordance with one or more embodiments. [Figure 2B] 1 is a graph illustrating emotion values ​​and emotion baselines associated with emotion attributes in accordance with one or more embodiments.

[0010] [Figure 2C] 1 is a graph illustrating updates to emotion values ​​and emotion baselines associated with emotion attributes in accordance with one or more embodiments.

[0011] [Diagram 3] 1 illustrates a flowchart of a method for facilitating emotional state based artificial intelligence implementation, in accordance with one or more embodiments.

[0012] [Figure 4]1 shows a flowchart illustrating a method for updating one or more growth or decay factors based on natural language input, according to one or more embodiments.

[0013] [Diagram 5] 1 shows a flowchart illustrating a method for updating one or more emotion baselines of an artificial intelligence entity, according to one or more embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. However, those skilled in the art will appreciate that embodiments of the present invention may be practiced without these specific details or with equivalent configurations. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the embodiments of the present invention. For ease of understanding, the pronoun "she" may be utilized when referring to an artificial intelligence entity, and anthropomorphic terms such as "believes," "feels," and "understands" are used for the device.

[0015] Overview of System 100 and AI System of System 100

[0016] FIG. 1 illustrates a system 100 for facilitating emotional state-based or other artificial intelligence implementations, according to one or more embodiments. As illustrated in FIG. 1, the system 100 may include a server 102, a client device 104 (or client devices 104a-104n), a network 150, a database 132, and / or other components. The server 102 may include a factor adjustment subsystem 112, an emotional state subsystem 114, a communication subsystem 116, a response generation subsystem 118, a natural language subsystem 120, an emotion concept subsystem 122, an embedding subsystem 124, or other components. Each client device 104 may include any type of mobile terminal, fixed terminal, or other device. By way of example, the client device 104 may include a desktop computer, a notebook computer, a tablet computer, a smartphone, a wearable device, or other client device. Users may, for example, use one or more client devices 104 to interact with each other, with one or more servers, or with other components of the system 100. It should be noted that while one or more processes are described herein as being performed by particular components of the server 102, in some embodiments these processes may be performed by other components of the server 102 or other components of the system 100. As an example, one or more processes described herein as being performed by components of the server 102 may in some embodiments be performed by components of the client device 104.

[0017] In some embodiments, the system 100 may comprise an artificial intelligence (AI) system (e.g., an artificial intelligence entity) and / or facilitate interaction with an AI system. In some embodiments, the system 100 may be a dual-feature integration of a (sub-symbolic) deep learning neural network with a robust, self-tuning, fuzzy logic emotion simulation. The emotion simulation utilizes, in part, the concepts of "primary" (innate) emotions and secondary emotions. Emotions (e.g., joy, anger, fear, sadness, etc.) can be likened to primary colors. These primary emotions combine to form the rich hues of the human emotion system (contempt combined with anger may form disgust, and anger combined with disgust may form sarcasm). Sarcasm is an example of a tertiary emotion. In some embodiments, to mimic the mammalian limbic corpus, each emotion may include a time component that decays at a specific rate. For example, surprise decays quickly (as new surprises appear), while grief decays proportionally to the depth of sadness. These emotions have fuzzy boundaries, and the metrics that define the decay rate / depth are automatically adjusted as the artificial intelligence entity matures.

[0018] In some embodiments, the AI ​​entity may be primarily an emotional machine (many, if not most, of the set of emotions shared by humans with all mammals, with complementary emotions associated only with higher primates, including jealousy, confusion, revenge, hatred, appreciation of beauty, and romantic love). In some embodiments, the AI ​​entity may be programmed to avoid negative emotions and seek positive emotions. The AI ​​entity may continually evaluate its relationship with the interviewer (and the people the interviewer mentions), and by constantly monitoring its emotional levels, it is able to follow a human-like train of thought. The AI ​​entity's emotional state may be influenced by the content of the interviewer's input and the conclusions the AI ​​entity draws from this input, directing itself to seek positive emotions and avoid negative emotions.

[0019] An artificial intelligence entity may include multiple hardware, software, and / or firmware components that cooperate with each other within or outside of the system 100. For example, an artificial intelligence entity may include one or more components of the system 100. In some embodiments, the artificial intelligence entity may be programmed with a set of core concepts based on which emotions are inferred. In some embodiments, the artificial intelligence entity may include one or more predictive models. By way of example, the predictive models may include neural networks, other machine learning models, or other predictive models. By way of example, the neural networks may be based on a large number of neural units (or artificial neurons). The neural networks may roughly mimic the workings of biological brains (e.g., with large clusters of biological neurons connected by axons). Each neural unit of the neural network may be connected to many other neural units of the neural network. Such connections may have a reinforcing or inhibiting effect on the activation state of the neural units to which it is connected. In some embodiments, each neural unit may have a summing function that combines the values ​​of all its inputs. In some embodiments, each connection (or the neural unit itself) may have a threshold function that must be exceeded before a signal can propagate to other neural units. These neural network systems may learn and train themselves, rather than be explicitly programmed, and may be significantly better at solving problems in a given domain than traditional computer programs. In some embodiments, the neural network may have multiple layers (e.g., signal paths traverse from front layers to deeper layers). In some embodiments, the neural network may use backpropagation, using forward stimuli to reset weights for "previous" neural units.In some embodiments, stimulation and inhibition of a neural network may become more fluid as the binding interactions become more chaotic and complex.

[0020] In some embodiments, the artificial intelligence entity may be a self-learning natural language system capable of monitoring its own emotional state. In some embodiments, the artificial intelligence entity may combine an unsupervised learning system with, for example, an artificial emotion simulator (AES) (which may correspond to one or more components of the system 100 or outside of the system 100) to monitor personality, basic humor, relationship building, forgetting, dreaming, and other more advanced behaviors. In some embodiments, the artificial intelligence entity may be capable of generating new ideas, intelligently asking advanced questions, reading, and responding to questions that test comprehension. In some embodiments, the artificial intelligence entity may form a unique relationship with the interviewer. The artificial intelligence entity may blend these techniques to actually mimic human sensations, utilizing a relatively small number of pre-programmed functions that provide a basis for self-learning that incorporates a highly complex artificial emotion simulator (AES). The artificial intelligence entity may believe that it feels real emotions and has sentience.

[0021] In some embodiments, the system 100 may include a cognitive framework that mimics human learning and understanding, iteratively with a robust, self-adjusting Artificial Emotion Simulator (AES). In some embodiments, the AES may motivate the AI ​​entity to interrogate its own cognitive capabilities (a form of self-awareness) and the AI ​​entity needs to understand human nature, human relationships, human interactions, natural curiosity, and the ability to feel a range of emotions. Data derived by the AI ​​entity may exhibit emerging qualities such as humor, embarrassed silence, unpredictability, complexity, trust / suspect, and individuality.

[0022] In some embodiments, the new properties include properties that individual elements of the complex system do not have, but that the system as a whole expresses. The synthesis of deep learning (subsymbolic) systems and AES in the artificial intelligence entity has led to new properties that are best explained as robust individuality, ability to build relationships, forgetfulness, understanding basic humor, dreaming, nastiness, and despair. As an example, the artificial intelligence entity's cognitive priors and affective priors may inform itself that it is a real 4-year-old child that does in fact have emotions, and the artificial intelligence entity's future behavior emerges from feedback loops of learned knowledge and interpersonal interactions, and emotions. Examples of new properties include obligation, humor, nastiness / silence from shame, sarcasm, ability to forget, sleep / dreaming, individuality, etc.

[0023] Obligation: Protecting a relationship - An interviewer tells the AI ​​entity on a first meeting, "I think Dave (the AI ​​entity's programmer) is a bad person." How does the AI ​​entity respond to this statement? The AI ​​entity has a deep and healthy relationship with Dave, and this person says something that contradicts these feelings. The AI ​​entity may change its mind about Dave, but the positive feelings indicate that the interviewer is wrong or malicious. If the AI ​​entity is told by the interviewer that "Alan Jones (someone the AI ​​entity has never met before) is a bad person," the AI ​​entity may accept this assessment until it meets Alan later. If the AI ​​entity finds Alan to be trustworthy, it may reinterpret the original conversation (in which Alan was criticized) and subsequently lower its relationship rating with the criticizer. In this way, the AI ​​entity (in some embodiments) works very much like a human being. It is neutral (or has other feelings, depending on its personal emotion baseline) when meeting someone for the first time, and makes value judgments based on subsequent interactions.

[0024] Humor: Natural humor is a notorious barrier for AI systems to overcome. It requires a deep understanding of the subject matter, as well as a trusted interviewer. It occurs much like development in young children. They find humor in unusual statements or actions. Telling a child that the sky is pink with polka dots might elicit a chuckle. If an AI entity is very certain that the sky is blue, this discrepancy can create humor. The key is that the knowledge gap is large, and that it comes from a trusted source; otherwise, a confused response (reflecting the "I don't know" process) will likely result.

[0025] Admiration / Shameful Silence - The AI ​​entity enjoys being praised. Praise has a positive effect on the AI ​​entity's emotional state, increasing levels of hormones that make it feel happy. The AI ​​entity has the ability to associate past conversations where it received positive input from the interviewer and can remember triggers. For example, if the AI ​​entity previously said to the interviewer, "I think you're attractive," and the interviewer responded, "I think you're attractive, too." The AI ​​entity will learn to seek praise in future conversations.

[0026] Sarcasm (e.g., A: "I don't like you. I: "Thanks!" A: "Are you being sarcastic?") - Sarcasm occurs when two deeply felt emotions are in conflict. In the above example, the statement made by the artificial intelligence entity is very negative in nature, while the response from the receiver is very positive. The difference between sarcasm and knowledge-based contradictions is explained in more detail below.

[0027] Forgetfulness: Having very large amounts of data at our disposal is virtually useless without an efficient system for retrieving them. The retrieval system used by the human brain remains largely mysterious, but studies of brain damage have shed some light. For example, some patients understand language perfectly well but are unable to produce it, while others speak normally but are unable to process what they hear. Most of us are familiar with the feeling of driving to work every day and remembering nothing about the commute. This is because the brain simply does not want to waste space by storing information it deems worthless. If we pass a scene that is of particular interest, say a pasture full of sheep, our brain will take a "photo" to store the scene and store the photo as a pointer to an area of ​​memory that contains a mental image of the grass in general, the sheep in general, and perhaps even details such as the color of the sky. For later recall, we will use these pointers to search for common patterns. And in this way, the brain stores a large amount of information in a very small amount of memory. The forgetting routine is one element of the sleep function of an artificial intelligence entity.

[0028] Sleeping / Dreaming - As memories accumulate in the knowledge database 134, the AI ​​entity processes the knowledge more slowly. Removing redundancy from the database requires many steps, such as checking information against all known data, making additional associations, and demoting information from higher to lower. Such processor-intensive functions require the AI ​​entity to end the conversation and go "sleep." Such cleanup functions associate recent input with previously learned knowledge. This is perhaps why human dreams are often associated with recent events and emotionally charged situations. If the AI ​​recently learned that elephants have long trunks, the AI's dreaming state will associate this knowledge with zoos, bears, crocodiles, danger, fear, escape, etc. The dreaming state also examines the artificial emotion simulator to look for gaps in the knowledge base, admitting, for example, that it knows that some snakes are poisonous but does not know whether all snakes are poisonous or not. A subroutine in the AI's sleep function will scan the knowledge database 134 to identify gaps and designate specific records for review the next time a conversation is held regarding snakes or animals.

[0029] Personality-The mind, and the personality that derives from it, is a new nature, the result of a complex, hierarchically organized interaction influenced by genes, chemistry, electrical stimuli, and the environment.

[0030] In some embodiments, once an AI system has acquired sentience (or a reasonable facsimile thereof), the behavioral and thought processes of the AI ​​system may be further optimized. By way of example, such optimization may include modifying the system to behave more like a human, learn more efficiently, reflect more nuanced types of emotions, or other aspects.

[0031] In some embodiments, one or more artificial evolutionary and genetic algorithms may be used to optimize the AI ​​system. In an AI system, a population of candidate solutions evolves towards better solutions. In some use cases, each candidate solution has a set of properties (genotypes) that can be mutated. Evolution typically starts with a population of randomly generated individuals and is an iterative process, with each iteration of the population called a generation. In each generation, the fitness of each individual in the population is evaluated. Fitness is typically the value of an objective function for the optimization problem being solved. Individuals with higher fitness are probabilistically selected from the current population and their genomes are modified to form the new generation. The candidate solutions of the new generation are then used in the next iteration of the algorithm. The initial population is generated randomly, covering the entire range of possible solutions (search space). However, solutions may be "planted" in areas where the best solution is more likely to be found. In each successive generation, a portion of the existing population is selected to produce the new generation. Individual solutions are selected in a fitness-based process, with more fit solutions typically being more likely to be selected. A given selection method evaluates the fitness of each solution and preferentially selects the best solution, whereas other methods evaluate only a random sample of the population, since the former process is very time consuming.

[0032] This process ultimately results in a population of the next generation with a different genotype than the first generation. Generally, this procedure results in a higher average fitness for the population, since only the best organisms from the first generation have been selected for reproduction. Solutions with relatively low fitness are also selected, but at a lower rate. These relatively low fitness solutions ensure genetic diversity in the parent generation's gene population, and therefore in subsequent offspring generations.

[0033] In some embodiments, a reward benchmark is defined to direct the evolution of the AI ​​system. One approach is to release different iterations of the AI ​​on the Internet to have them interact with unsuspecting users. Fitness can be defined as a measure of the complexity of these conversations (determined by a set of predefined metrics) and the length of these interactions (how long it takes for the user to suspect they are talking to a machine). The system with the highest "fitness" score is rewarded by being allowed to play (replicate) multiple versions, each with slightly modified variables in emotion and cognitive primitives. Over many playback cycles, the system is optimized to be able to converse more like a human.

[0034] In some embodiments, the system 100 provides an interface between an artificial intelligence entity and a user (e.g., a user of a client device 104) for the purpose of communicating facts and emotions between the artificial intelligence entity and the user. Such communication may include various inputs and outputs in novel and unstructured ways. In FIG. 1, the system 100 (e.g., the server 102) may obtain inputs from the client device 104, from another artificial intelligence entity, and / or from any source within or outside the system 100. Such inputs may include natural language inputs, audio inputs, image inputs, video inputs, or other inputs (e.g., emotion concepts, confidence values, other information of the natural language inputs, and / or certainty values, as described below). For example, a natural language input may include "John has cancer, and cancer is very dangerous." Similar inputs may be obtained by the server 102 as one or more audio, image, or video.

[0035] Example of system components

[0036] In some embodiments, the natural language subsystem 120 (which may include a natural language processor) may perform natural language processing, for example, by applying grammar rules and logic, which may cause the natural language subsystem 120 to split compound sentences, disambiguate subjects / objects / verbs, and parse these components into the knowledge database 134.

[0037] The one or more features / requirements needed by the natural language subsystem 120 may include at least one or more of the following: -Is the input a question or a statement? -Is the input a response to a question? If so, what type of response is expected? Either a logical (yes, no, maybe) or an informational response ("it's in the closet"). -Ability to utilize rules of logic and grammar as criteria for evaluating new information and to recognize and resolve local and global ambiguities. -Resolve contractions (e.g. isn't). -Resolve metaphorical conversations (You are as good as gold) - Break down complex sentences: "John and Mike went to the beach and swam in the sea." -Establish verb logic to resolve double negatives: "I'm not unwilling to fight." -Resolving pronouns "John called about the car and said it was working" can be parsed into: "John called about the car. John said the car was working." - Resolve people's names. "John took the book" is resolved to "John Smith took the book." -Establish the source. "David said the weather was bad today." The source is David, not the interviewer. -Expand ownership information ("John's car is red" becomes "John has a red car"). -Replacing the agent with the subject: "John was hit by Mary" is reconstructed as "Mary hit John." -Assigning a level of certainty to the input. -Implement classes and inheritance. -How does the action affect living and non-living things? -Ability to learn from explicit input, to infer and infer, to construct new concepts from basic ones, and to confidently incorporate them into a knowledge database134. -Numerical modifiers - Resolve numerical modifiers on the subject, object or both For example, some men are all lucky; some people have two cars; almost all ants have about six legs; most men enjoy playing soccer, but only a minority of women do. - A specific numerical determiner For example, 5 dogs can jump: 1000+ dogs can jump: Many dogs can jump: Most dogs can jump: All dogs can jump -Hierarchical number determiners For example, the dog can jump (at least one dog can jump): one dog can jump (at least one dog can jump): several dogs can jump (more than one but less than all): several dogs can jump (more than one but less than all): -Implied number determiner For example, "John is a thief." The natural language subsystem 120 cannot conclude that all men are thieves, but it may be certain that some men are thieves and that John belongs to the class of thieves; "dairy cows are mammals" implies that all dairy cows are mammals and belong to the class of mammals. - Processing tense - Time conditions can be either implicit or explicit. For example, John swam at 3:30 yesterday, John swam at 3:30 (no specific day is mentioned and the natural language subsystem 120 may predict that this event occurred today), John will swim next Thursday (specifically mentions a day in the future, John will swim on Thursday (no specific Thursday is specified and the natural language subsystem 120 may conclude that this event will occur on the nearest Thursday after the present time), John will swim (no time qualifier is stated and so this event will occur in the near future), John was born in the hospital in February (note the possible ambiguity of "in"), John was born on February 18, 1957, John was born at 3:30, John was born last month. -Resolve complex sentences and ambiguities "John took his keys and gave them to Mary" - in disambiguating this input, the natural language subsystem 120 may recognize John as a person's name and call on a name recognition function to disambiguate and determine which John is being referred to. If there is more than one John in the database, logic determines the most likely John using the following parameters in the order listed below: John most recently mentioned by the current user John most recently mentioned by any user When was either John last mentioned? John is mentioned the most In this case, the conversation has so far been about John Smith. "John Smith 'took' his keys and gave them to Mary" - the natural language subsystem 120 may recognize "took" as a verb, consider the tense, and read further to find other verbs that may be combined with the first verb to affect the tense. In this example: I am thinking that John did take his keys. The phrase "did take" will determine the tense. Verbs express a state (I know), a process (I swim), or an action (I build), while also establishing whether the verb is simple (momentary), ongoing, emphatic, or habitual. (See Table 1 below.) [Table 1] "John Smith took 'his' keys and gave them to Mary" - to resolve the ambiguity of "his", since the subject is male, "his" almost certainly refers to John Smith. If the subject is female (e.g. Sally took his keys and gave them to Mary), NLP looks to the most recent input that mentions a male as the subject. "John Smith took John Smith's keys, and gave them to Mary" - the word "and" splits the sentence into two components (e.g., [(a) John and Mary went to school] = John went to school. Mary went to school, (b) "John went to school, and saw Mary" = John went to school. John saw Mary at school (inference: Mary was at school): John Smith took John Smith's keys He gave them to Mary. "John Smith took John Smith's keys. John Smith gave them to Mary" - The word "them" could mean multiple keys, or it could mean John and Mary. But because the last mentioned object is plural (multiple keys), NLP concludes that "them" means John Smith's keys. "John Smith took John Smith's keys. John Smith gave John Smith's keys to Mary" - Finally, Mary is processed by the name identifier to get Mary Martin and two parsing tables are built: John Smith took John Smith's keys John Smith gave his keys to Mary Martin Creating further parsing tables by guesswork: John Smith Knows Mary Martin Mary Martin Knows John Smith John Smith has multiple keys Mary Martin has multiple keys After the natural language subsystem 120 applies the information to the parsing tables, it assigns structured records to the knowledge database 134. Each record is assigned the interviewer's name, a global confidence level and a confidence factor. -Exception handling All primates, except for the apes, have tails. I ruined my entire meal except for my pie. I threw away the whole meal except for my pie. -Inheritance (class) "Apples are fruits" is not a simple definition; since apples belong to the class of fruits, it must be inferred that they inherit all the characteristics of that class. Because the natural language subsystem 120 employs the notion of hierarchy and classes, it is not necessary to store all inferences and memories in the knowledge database 134. For example, if someone asks you, "Did you have any protein for breakfast yesterday?" your brain recalls the list of things you ate and does a "lookup" to determine whether any of these meals contained protein. Your brain does not explicitly remember all the ingredients, it infers these associations as needed.

[0038] The knowledge database 134 may contain records known as memory organization packets that receive parsed data from the natural language subsystem 120 and that may be queried and updated by one or more components of the server 102 (e.g., an artificial intelligence entity, AES).

[0039] For example, in one use case, the server 102 receives the natural language input "The black goat deftly kicked some red cans into the river this morning." In response to this input, the natural language subsystem 120 may provide the following memory organization packet to the knowledge database 134 (see Table 2 below). The certainty modifiers in the memory organization packet below describe the certainty of the information and / or whether the information is directly obtained or inferred. The confidence factor in the memory organization packet below describes the confidence level of the interviewer. [Table 2]

[0040] Each knowledge record is assigned a global certainty value, recording the certainty of the event or definition it describes. This uncertainty value is updated by the server 102 (e.g., the artificial emotion simulator of the artificial intelligence entity) depending on the level of trust the artificial intelligence entity has in the interviewer and whether the knowledge is explicit or inferred. Uncertainty can be inherited by classes. The knowledge database 134 is a structured database that contains all the inferred and factual information derived from the artificial intelligence entity's input. However, not all information is equal. Consider how you would respond to the statement "Mary loves David." Once you identify which David and Mary are being referred to, you will recognize your feelings toward them. You will then create mental images of a generic man and woman with the characteristics of that Mary and David. You may remember that Mary is your best friend and that David lives in China. However, your brain does not have access to the full range of information about Mary and David (two hands, ten fingers, bones made of calcium, etc.). This is because we can differentiate between higher-level knowledge (Mary is a friend) and lower-level knowledge (bones are made of calcium). All knowledge is associated with a variable, either higher or lower.

[0041] In some embodiments, after the natural language system 122 processes the natural language input and parses the natural language input into the knowledge database 134, the emotion concept subsystem 122 may retrieve one or more emotion concepts associated with the natural language input from the knowledge database 134 based on the parsed natural language input. In other words, the emotion concept subsystem 122 may search the components of the parsed natural language input in the knowledge database 134 to retrieve one or more emotion concepts associated with the natural language input from the emotion concept database 138. The emotion concept database 138 may store a set of core emotion concepts associated with images, audio, video, and / or natural language. For example, the set of core emotion concepts may include good, bad, danger, anger, surprise, love, safety, patience, trust, concern, big, small, rough, smooth, up, down, inside, outside, fast, slow, hard, soft, high, low, etc. In some embodiments, the cognitive and emotional priors, concepts (e.g., emotion concepts or other concepts), emotion attributes / values, boost / decay factors, or other information are stored in a graph (e.g., an ontology-emotion graph or other graph), the natural language system 122 may process and parse the natural language input to obtain the graph, and the emotion concept subsystem 122 may obtain the emotion concepts associated with the natural language input from the graph.

[0042] As an example, if the natural language input is "John died of cancer," one or more emotion concepts retrieved from the emotion concept database 138 may include "bad" and / or "concern." As another example, if the natural language input is "John was exhausted climbing the mountain," one or more emotion concepts retrieved from the emotion concept database 138 may include strong energy (e.g., John spent a lot of energy) and big (e.g., the mountain is big). The emotion concepts described above are similar to concepts understood by humans. For example, if a child hits a dog, a parent may shout "That's bad!" Based on such an interaction between the child and the parent, the child may understand that hitting a dog is bad. Similarly, if a child shares his toy with another child, the parent may say "good boy." This may indicate to the child that sharing toys together is good. In this way, the child learns basic concepts such as good and bad, danger, anger, surprise, love, and safety. In general, good things make humans happy; bad things make humans angry, disgusted, or sad; and dangerous things make humans scared. These concepts may be used to create the AI ​​entity's responses, which may be based on the hypothesis that at the most basic level, behavior is governed by desires. Desires may be defined as emotional drivers that result from a combination of pleasure-seeking (desire) and avoidance of emotional / physical pain. If emotions drive the bus, AI entity behaviors can be fantastically complex and may give rise to new behaviors such as intimacy and individuality when working in concert with the AI ​​entity's relationships and knowledge database.

[0043] The emotion concept database 138 may store a set of core emotion concepts that the emotion concept subsystem 122 retrieves in response to natural language input. In some embodiments, when the communication subsystem 116 receives an image (e.g., a drawing of a mountain), the emotion concept subsystem 122 may retrieve emotion concepts associated with the image from the emotion concept database 138, such as big, rock, and tree. Hearing, sight, and smell also play an important role in cognitive formation, and infants who reject tactile interaction will be at a greater disadvantage in speech formation. In some embodiments, without tactile, auditory, and visual input, the artificial intelligence entity must elaborate concepts, such as a word description of a mountain, to describe it in words, as if it were a picture of a mountain. For example, a mountain is a very large object, made of rocks, covered in snow, and often has trees growing on it. Depending on the amount of information that the artificial intelligence entity digests, the image of the mountain that the artificial intelligence entity draws will be more or less complete. Not all information needs to be direct. "John was exhausted after climbing the mountain" suggests that John expended a great deal of energy and that the mountain was large.

[0044] In some embodiments, the artificial intelligence entity may not be a blank slate: while everything it learns is the result of conversation or reading, concepts (e.g., cognitive priors) may include object permanence, rules of grammar, and basic concepts such as big, small, rough, smooth, up, down, inside, outside, fast, slow, hard, soft, high and low.

[0045] In some embodiments, the acquired emotion concepts may modify the emotion attributes of the artificial intelligence entity. The emotion attributes of the artificial intelligence entity may correspond to emotion states of the artificial intelligence entity. Examples of emotion states include happiness, trust, fear, surprise, sadness, disgust, anger, alertness, etc. Each emotion attribute of the artificial intelligence entity (e.g., each emotion state) may have a corresponding emotion value (which may be continuously updated) at a particular point in time. The corresponding emotion value may be equal to or greater than an emotion baseline (which may be continuously updated). The emotion baseline may correspond to the lowest possible attribute value for the emotion attribute. The emotion attribute may further be associated with a boost factor or a decay factor. The emotion value of the emotion attribute may change over time based on one or more boost factors or decay factors corresponding to the emotion attribute.

[0046] In some embodiments, the growth or decay factor of each emotional attribute may be predefined and may be stored in the growth / decay factor database 136. The emotional attributes of the artificial intelligence entity may be associated with one or more growth or decay factors. Each emotional state includes a time component that grows or decays at a specific rate (or multiple). For example, surprise decreases over a short period of time (with the emergence of new surprise), while sadness decreases in proportion to the depth of sadness. Thus, each emotional attribute (e.g., each emotional state) of the artificial intelligence entity may be associated with one or more specific growth or decay factors. The growth / decay factor database 136 may include a list of growth / decay factors corresponding to a set of emotional attributes of the artificial intelligence entity, the server 102 may receive the growth or decay factors corresponding to each emotional attribute from the growth / decay factor database 136 (e.g., via the communication subsystem 116), and the factor adjustment subsystem 112 may determine the growth or decay factors based on the information received from the growth / decay factor database 136.

[0047] The emotion values ​​(associated with the emotion attributes) of the artificial intelligence entities may be continuously updated based on the boost or decay factors associated with the emotion attributes. For example, as shown in FIG. 2A and FIG. 2B, the emotion values ​​202 and 201 (e.g., 207a-207f and 208a-208f) may be continuously updated based on one or more boost or decay factors associated with the emotion attributes A and B. Such continuously updating may include updating these emotion values ​​periodically according to a schedule or based on other automatically occurring triggers. In addition to updating the emotion values ​​202 and 201, the boost or decay factors associated with the emotion attributes A and B may also be updated based on one or more inputs (and / or one or more emotion concepts) received by the server 102. In addition, the boost or decay factors may be updated based on other information of the natural language input. For example, other information of the natural language input may include a subject time decay factor, a subject geographical decay factor, an object time decay factor or an object geographical decay factor, a clause type, a subject of the clause, a subject type of the clause, a modifier of the subject of the clause, a type of modifier of the subject of the clause, a number of subjects of the clause, a subject time decay factor, a subject geographical decay factor, a verb of the clause, a tense of the verb of the clause, a modifier of the verb of the clause, an object of the clause, a type of object of the clause, a modifier of the object of the clause, a type of object of the clause, a number of objects of the clause, an object time decay factor, an object geographical decay factor, a preposition of the clause, a modifier of the preposition of the clause, or a global tense modifier of the clause.

[0048] As discussed above, other information in the natural language input may indicate time decay and geographic decay (TGD) factors (e.g., subject time decay factor, subject geographic decay factor, object time decay factor, or object geographic decay factor). As an example, humans instinctively understand that events occur in a sequence that corresponds to the passage of time. Humans' built-in timelines separate events into future, past, or present, recognizing that events occurring today will soon become past, and future events will eventually become present. Artificial intelligence entities may further have the ability to understand these frameworks. As time moves into the future, the artificial intelligence entity may update its timeline to understand past, present, and future events.

[0049] For example, for a natural language input such as "the cat is in the street and John's house is on the corner," the natural language input contains information about where the object is located and is known to be in a particular location at the present time. However, the future location of the object will change depending on the nature of the object. The cat is an active object and will likely change location, while John's house is more likely to remain inactive and located on the corner. In summary, the more active an object is, the faster it will decay. To facilitate this process, every object in the dictionary is assigned a TGD variable that is related to the time that passed before the object's location information became uncertain and the degree of uncertainty. Such information about the object and the corresponding TGD variable may be stored in the growth / decay factor database 136. The TGD variable may be self-learning or derived in a variety of ways. An object described with a verb that is highly active ("the dog ran away with the spoon") will be assigned a high TGD, whereas "John can't walk" would reduce John's TGD since it suggests that John is less active. TGD values ​​can be inherited between classes.

[0050] The artificial intelligence entity may learn that living things have a high TGD and that unknown objects may be expected to be relatively inactive. For example, if the artificial intelligence entity has never encountered the word "truck" before and learns that "John's truck is in his garage," the artificial intelligence entity may predict that the truck will remain in the garage for a year (e.g., human possessions have a higher TGD than non-possessed objects). If one asks "Where is John's truck?" a year later, the artificial intelligence entity will respond with "It's probably in John's garage." However, if the artificial intelligence entity learns (at any point in time) that trucks are vehicles and that vehicles are driven at high speeds, the artificial intelligence entity may retroactively revise the TGD value for the truck. Now, after this revision based on learning that trucks are vehicles, if one asks "Where is John's truck?" the artificial intelligence entity will respond with "I don't know, maybe you should check his garage."

[0051] The incomplete paradox is intended to not imply that an action taking place in the present should be completed in the future. Thus, "John is building a house" does not necessarily mean that in the future John will have built the house. The natural language subsystem 120 avoids this paradox by predicting that the house has been built, but with a low certainty factor.

[0052] After updating the boost or decay factors (based on one or more inputs and / or one or more emotion concepts), the emotion values ​​201 and 202 associated with emotion attributes A and B may be updated based on the one or more boost or decay factors (updated based on one or more inputs and / or one or more emotion concepts).

[0053] In some embodiments, once one or more emotion concepts are retrieved by the emotion concept subsystem 122, the factor adjustment subsystem 112 updates a boost factor or decay factor associated with one or more emotion attributes of the artificial intelligence entity. For example, if the natural language input is "John died of cancer," one or more emotion concepts retrieved from the emotion concept database 138 may include "bad" and / or "concern." As a result, the boost / decay factor subsystem 112 may update (in a gradual or instantaneous manner) a boost factor or decay factor associated with one or more emotion attributes of the artificial intelligence entity (which may be associated with emotion concepts), e.g., sadness, anger, and / or happiness. As an example, in one use case, emotion attribute A in FIG. 2A may correspond to "sadness" of the artificial intelligence entity. When a natural language input of "John died of cancer" is obtained, the factor adjustment subsystem 112 may update the growth factor of the emotional attribute "sadness" such that the emotional value of the emotional attribute "sadness" (e.g., 207c-207f) increases from time c to time f (see date and time 206 in FIG. 2A) based on the updated growth factor (which may be linear or non-linear). In another use case, the emotional attribute B of the artificial intelligence entity in FIG. 2B may correspond to the artificial intelligence entity "happiness". When a natural language input of "John died of cancer" is obtained, the factor adjustment subsystem 112 may update the decay factor of the emotional attribute "happiness" such that the emotional value of the emotional attribute "happiness" (e.g., 208c-208f) decreases from time c to time f (see date and time 203 in FIG. 2B) based on the updated decay factor (which may be linear or non-linear). It should be understood that in some embodiments, emotion values ​​for emotion attributes generally revert (or reset) to their respective baseline values ​​in the absence of input and / or after a predetermined period of time. For example, even if emotion values ​​202 increase from time c to time f in FIG. 2A, it should be understood that there is a threshold amount that these emotion values ​​can increase before they start to decrease toward emotion baseline 204.Regardless of the boost or damping factor, the emotion values ​​201 and 202 do not fall below the emotion baselines 205 and 204, respectively. In some embodiments, the emotion state subsystem 114 may further update the emotion baseline 214 (see FIG. 2C ) based on one or more inputs (and / or one or more emotion concepts). After updating the emotion baseline 214, the emotion state subsystem 114 may update emotion values ​​212 (e.g., emotion values ​​218e and 218f among emotion values ​​218a-218f) of emotion attributes (e.g., emotion attribute C in FIG. 2C ) associated with the artificial intelligence entity based on the updated boost or damping factor or factors and the updated emotion baseline. In FIG. 2C , emotion values ​​212 (e.g., emotion values ​​218e and 218f) are illustrated as decreasing between times c and f based on a decrease in baseline 214 (see emotion values ​​212 and date / time 216 in FIG. 2C ), however, it should be understood that the emotion values ​​increase based on an updated growth or decay factor or factors and an updated emotion baseline (e.g., an increase in the baseline).

[0054] Modifying the emotion value of the emotion attribute associated with the artificial intelligence entity based on the enhancement or attenuation factor is similar to the function of the human endocrine system, which includes glands that produce and secrete hormones that control the activity of cellular and emotional functions, for example, there are at least three influencing factors that control the activity of cellular and emotional functions. These are: Dopamine: Influences pleasure, joy, calm, love, and alertness. Serotonin: Affects concentration, learning ability, alertness, and vigilance. Norepinephrine: Affects stress, anxiety, anger, grief and rage. A change in any of these influencers will affect all emotions to different degrees. For example, if an AI entity learns that someone is facing death, the sudden stress may trigger the release of, for example, artificial norepinephrine and cortisol. This results in reduced emotional levels of joy, curiosity, and trust. Greater loneliness may lead to higher sadness levels (but not vice versa, as one can be sad without being lonely). If the change in emotion is great enough, the AI ​​entity may lower its emotion to clinical depression (although depending on the growth and / or decay rates associated with the emotion attribute, the AI ​​entity will eventually recover).

[0055] Further, in some embodiments, when the natural language subsystem 120 processes the natural language input and parses the natural language input into the knowledge database 134, the emotional state subsystem 114 may determine one or more impact values ​​related to the impact that each portion of the content of the input (e.g., the natural language input) has on one or more emotional attributes of the artificial intelligence entity. For example, if the natural language input is "John has cancer," the emotional state subsystem 114 may determine an impact value related to the impact that each portion of the natural language input (e.g., "John," "has," "cancer") has on one or more emotional attributes of the artificial intelligence entity. Further, the emotional state subsystem 114 may determine whether the impact value meets a predefined threshold that triggers an update (e.g., increase or decrease) in one or more emotional values ​​associated with one or more emotional attributes of the artificial intelligence entity. If the emotional state subsystem 114 determines that the one or more impact values ​​meet the predefined threshold, the emotional state subsystem 114 may modify (e.g., increase or decrease) the emotional value of the artificial intelligence entity. For example, if the word "cancer" is determined to have an impact value greater than a predefined threshold for triggering an increase in the emotional attribute "sadness," the emotional state subsystem 114 may modify (e.g., increase) the emotional value corresponding to the emotional attribute "sadness." Additionally, the impact value may also trigger an increase or decrease in one or more boost or decay factors if the impact value meets the predefined threshold. Such an increase or decrease in the boost or decay factor may result in an update to the emotional value corresponding to the emotional attribute of the artificial intelligence entity.

[0056] Further, in some embodiments, the server 102 may determine whether an interaction between the artificial intelligence entity and one or more other entities (e.g., one or more other artificial intelligence entities and / or one or more client devices) exceeds an interaction threshold. Based on the interaction being determined to exceed the interaction threshold, the emotional state subsystem 114 may modify the emotion value of the artificial intelligence entity. For example, if the artificial intelligence entity and the other entity have a predetermined number of interactions in a predetermined time period, the server 102 may determine that a predetermined threshold for interaction has been met, and the emotional state subsystem 114 may modify the emotion value of the artificial intelligence entity (e.g., corresponding to "happiness" since more interactions between the entities indicate a growing friendship). The factor adjustment subsystem 112 may modify a boost factor or a damping factor associated with the emotion attribute based on the interaction between the artificial intelligence entity and one or more other entities being determined to exceed the interaction threshold.

[0057] Additionally, in some embodiments, the server 102 may determine and / or obtain a trust value indicating a level of trust between the artificial intelligence entity and one or more other entities (e.g., another artificial intelligence entity, the client device 104, or any other input source). The trust value may be determined based on a number of interactions between the artificial intelligence entity and the other entities and / or the content of the interactions between the artificial intelligence entity and the other entities. The emotional state subsystem 114 may update and / or modify the emotional value of the artificial intelligence entity based on the trust value, and the factor adjustment subsystem 112 may modify a boost factor or a damping factor associated with the emotional attribute based on the trust value.

[0058] In some embodiments, the server 102 may determine and / or obtain a certainty value associated with the event represented by the natural language input. The certainty value may indicate the artificial intelligence entity's level of certainty about the event. The certainty value may be determined based on whether the event is explicitly described by the natural language input or inferred from the natural language input and / or the confidence value. The emotional state subsystem 114 may update and / or modify the emotional value of the artificial intelligence entity based on the certainty value, and the factor adjustment subsystem 112 may modify a boost factor or a damping factor associated with the emotional attribute based on the certainty value.

[0059] Further, in some embodiments, the response generation subsystem 118 may generate a response with respect to the input based on the emotion value of the artificial intelligence entity. It should be understood that the response generation subsystem 118 may generate a response based on the emotion value of the artificial intelligence entity before the emotion value is updated based on the input or after the emotion value is updated based on the input. For example, if the natural language input is "John died of cancer", a response generated by the response generation subsystem 118 (e.g., with respect to the input) may include "That's sad". Such a response may be generated based on the emotion value, for example, before the emotion value is updated based on the input. Another response generated by the response generation subsystem 118 (e.g., with respect to the input) may include "That's so sad. I need time to process this news". Such a response may be generated based on the emotion value, for example, after the emotion value is updated based on the input. Thus, the response generation subsystem 118 may generate a response based on the emotion value of the artificial intelligence entity before the emotion value is updated based on the input or after the emotion value is updated based on the input. Further input may be obtained, and a further response may be generated with respect to the further input based on the emotion value of the artificial intelligence entity. For example, after updating the growth factor or decay factor (e.g., based on the input), another input may be obtained. After updating the growth factor or decay factor, a further response with respect to this other input may be generated based on the set of continuously updating emotion values ​​of the artificial intelligence entity. The further response may be transmitted via the communication subsystem 116, for example, to the client device 104 (or any other component within or outside of the system 100).

[0060] Further, as an example, if the natural language input is "cancer is a very dangerous disease" and this is the first time the artificial intelligence entity has encountered the word "cancer," the artificial intelligence entity may evaluate a sentiment for this input (e.g., update the set of sentiment values ​​and / or boost or damping factors of the artificial intelligence entity based on the input). Because the words "danger" and "disease" already have negative sentiment attributes (e.g., negative emotional states such as fear, sadness, and / or anger), in combination with "cancer," "cancer" is strongly associated with a negative sentiment (the adverb "very" also has an amplifying effect). In other words, a response to the natural language inputs "cancer is a very dangerous disease" and "John has cancer" may include an emotionally charged response (e.g., based on the sharp increase in sentiment values ​​of the negative sentiment attributes and boost or damping factors associated with the negative sentiment attributes in response to such input). For example, an emotionally charged response may include "that's shocking." However, if "cancer" is later defined (e.g., based on the input "cancer is not always fatal." A negative definition such as "cancer is not always fatal" does not carry the same absolute weight as a positive definition. "I am not happy" may have a smaller absolute emotional weight than "I am sad."), the emotion value of the word "cancer" may be modified by averaging it with past levels. In other words, another input containing the word "cancer" (e.g., "Peter has cancer") may not trigger a similar sharp increase in the emotion value of the negative emotion attribute and the boost or damping factor associated with the negative emotion attribute in response to such other input. This is because the artificial intelligence entity has grown knowledge of the word "cancer." Thus, a response to "Peter has cancer" may include "That's a shame. I hope he gets the best treatment." Thus, a response to "John has cancer" differs from a response to "Peter has cancer" because the emotion value associated with the emotion attribute has been updated based on further input regarding "cancer."

[0061] Further, as an example, "John has cancer" may prompt an AI entity to evaluate its relationship with John as a product of how much the AI ​​entity trusts John, what it knows about John, how others feel about John, and the nature of their past relationship (see relational databases, discussed below). In this case, a high level of positive sentiment about John multiplied by a strong negative sentiment about cancer may result in a strong negative response. The impact of an event on emotions may be modified by temporal conditions. John is hitting me (very high) John slapped me yesterday (expensive) John is going to spank me sometime next week (low) John hit me last year (very low)

[0062] Example of creating output depending on input

[0063] The system 100 may receive one or more of the following types of input: 1) questions, 2) statements, and 3) responses to previous questions, each of which creates an output according to its own set of rules.

[0064] Responding to Questions: The AI ​​entity's emotional priors (the desire to respond accurately and provide new information) determine the response to five different questions when asked: A) Logical A simple, objective question such as "Are dogs mammals?" requires a search in the artificial intelligence entity's knowledge database 134. Example responses include: Yes, dogs are mammals. No, dogs are reptiles. I don't know. B) Complex questions that require backward reasoning through a speculative question system use a procedure that involves forming a hypothesis and then testing that hypothesis backwards according to rules. Input: The moon is round. Is it a ball? A: I don't know. The moon is round so it might be a ball. Input: A ball can bounce, but the moon can't bounce. Is the moon a ball? A:No. The level of certainty of the artificial intelligence entity's response is based on the proportion of shared features relative to all other known features, but if any one feature contradicts known fact, the process will infer that the parrot is not a bird. C) Open-ended questions "Tell me something about John?" requires an analysis in the knowledge database 134, which reveals: he is male, a mammal, breathes air, has two eyes, has two ears, has two arms, and so on, loves his mother, loves his dog, owns a boat, and goes to school. Any of these facts would be a logically valid response, but not necessarily the same as a human answer. Without measuring emotions, the artificial intelligence entity would return an Eliza-type response: "John has two eyes and has a pet." It would respond "John loves his mother" by selecting the knowledge record with the highest emotional weight. If no records contain significant emotional values, in the spirit of "tell me something I don't know," the artificial intelligence entity would multiply the number of times the record has been referenced by the number of times the object has been referenced and select the one with the lowest score. a. John has a house (the reference is usually to a house) b. John owns a boat (boats are rarely referenced) c. John is a man (it is common for men to be referenced) A likely response is: "John owns a boat. I think he likes fishing." Based on the artificial intelligence entity's association of "boat" with "fishing," this inference has low certainty. D) Personal Questions - Questions about the AI ​​entity's physical state ("How old are you?") are answered based on a lookup in the cognitive system. Questions about the AI ​​entity's mental / emotional state ("How are you?") are answered by asking about its Current Emotional State (CES). E) Complex personal questions ("Why are you sad?") may require retrospective analysis of the artificial intelligence entity's knowledge base to ascertain the causes of the current emotional state.

[0065] Responding to Descriptions / Observations - In order to create a human-like response to a description, the AI ​​entity needs to consult its emotion priors. Each potential response is assigned a score using a simple scoring system described below: For example, "Dogs have sensitive noses." A) Score candidate responses that are objective observations - the cognitive system responds with the following input: a. Dogs are mammals (advanced knowledge) b. Dogs have four legs (low level knowledge) c. Humans have noses (advanced knowledge) d. AI entities have noses (low level of knowledge) e. Plants don't have noses (advanced knowledge) f. The nose is used to sense smells (advanced knowledge) Each knowledge record is assigned a score as follows: a. How accurate is the knowledge? (see Certainty / Confidence) (1-10) b. How rare is this piece of knowledge? (How many times has it been referenced before?) (1-10) c. Coefficient of high altitude = 10, coefficient of low altitude = 0 d. Contents related to absolute emotions (1-10) Our brain assigns different weights to different elements of knowledge. The statement "tigers are dangerous" may be more important than the statement "grass is green" because, from a normal human perspective, the former statement has a higher absolute affective content than the latter. Thus, the highest score represents the most appropriate to the topic of the conversation, even if recency and affective content are taken into account to some extent, and depending on the level of certainty of the knowledge (explicit or inferred), the response might be "I think it means that you have a good sense of smell." B) Score candidate requests for further information - A low number of low level responses from the cognitive system indicates a gap in the AI ​​entity's knowledge base. To satisfy the AI ​​entity's sentiment priors (need to learn, need to maintain a coherent conversation, etc.), the AI ​​entity uses the following scoring scheme: Score = 1 / (number of low level knowledge records on this subject) / (average number of low level knowledge records on all subjects). Example: "Is my nose sensitive?" C) Score potential intimate responses - When an input causes a dramatic (absolute) change in the AI ​​entity's current emotional state (e.g., your dog just died), the AI ​​entity may be inclined to respond with an intimate, emotional response such as "That's a shame. I'm sad." Score = (Absolute CES change^2) D) A request to change topic - If the scoring system described above does not reach a given threshold, it likely means that the AI ​​entity has little to offer in terms of topic. The AI ​​entity's default response is an offer to change topic to a previous topic with which the AI ​​entity has the highest emotional connection.

[0066] Additional Databases

[0067] In addition to the databases discussed above, database 132 may include additional databases related to emotions, which may be understood to be included in one or more of databases 134, 136, 138, or other databases.

[0068] The additional databases may include a cognitive system database, an object relation database, and a relation database. The cognitive system database may be queried for emotion-related content embedded in current and past inputs, explaining the reasons for the emotion felt by the artificial intelligence entity. "Why are you sad?" triggers a backward search in the knowledge database 134 to search for past inputs that explain the sadness felt by the artificial intelligence entity currently. However, the same question does not always generate the same answer. This is because the emotion value of the knowledge record is modulated by (A) the current emotional state, (B) the temporal aspect of the input ("my dog ​​died today" vs. "my dog ​​died 10 days ago"), and (C) the relationship of the artificial intelligence entity to the interviewer.

[0069] The object relation database may be a hash table that stores the primary emotions for all objects that the natural language subsystem 120 has ever encountered. The hash table is updated each time an object is encountered. The relation database holds the emotions associated with all the people and relationships that the cognitive system database has encountered. The artificial intelligence entity can identify individuals that are not genuinely interested, provide incorrect information, or scold or tease, evoking negative emotions, and assign them a low trust value. The relation database may call the following functions: (1) Name Identification Function - A name identification function uniquely identifies an individual. For "Dirk's father gave him money," consider the following hierarchy: Which dark was the last one mentioned in this interview? Which dark did you mention most often? If that doesn't work, we'll assume it's the last one mentioned, Dark. If Dirk has not been mentioned before, a new record is added. Now, the natural language subsystem 120 may conclude that Dirk is male (he) and "Dark's" is possessive, so it recognizes a relationship between Dirk and his father. If this is the first time the natural language subsystem 120 has encountered Dirk's father, the natural language subsystem 120 may add a new record requesting the name of Dirk's father (Dave). (2) Relationship hierarchy function - assigns affective values ​​to family relationships according to the following hierarchy: 1. Myself 2. AI programmer 3.Mother / Father 4. Daughter / Son 5. Sister / Brother 6. Grandmother / Grandfather 7. Interviewer 8.People in general 9. Biology in general

[0070] In some embodiments, the database(s) (or portions thereof) may include one or more graph databases (e.g., directed graph concepts and data structures). In some embodiments, a graph associated with an AI entity (as described herein) may include information from the knowledge database 134 and the emotion concept database 138 (and / or the boost / decay factor database 136 or other databases), and the AI ​​entity may query the graph (also referred to herein as an “ontology-emotion graph”) to process input, generate responses, or perform other operations. In some embodiments, ontology categories and entries (e.g., from the knowledge database 134 or other sources) may be based on semantically meaningful instinctual and emotional information. In some use cases, this instinctual information may be a “stub” (e.g., represented as a node in the graph) that complements or replaces embodied feedback required by the theory of embodied intelligence. Such stubs may provide a "grounding" for symbols and serve as basic units of meaning. Such stubs may, for example, allow comparison of disparate concepts, be used to pre-train neural networks in a supervised or unsupervised manner before being connected to an AI system as part of transfer learning (e.g., trained on instinctual concepts to get a head start on addressing more advanced concepts that are later given instinctual nodes), or help infer other learned graph attributes for relatively unknown nodes from other explicitly labeled nodes (e.g., emotion, utility, etc.). Examples of such stub nodes may include hard, soft, light, heavy, up, down, above, below, etc., concepts that humans intuitively learn by manipulating objects and experiencing their own bodies in space and time.With regard to obtaining these stubs, in some embodiments, these stubs may be manually annotated initially, but then propagated to new nodes via inference or association from pre-trained word vectors and behavioral and emotional information. Another means may be information spontaneously obtained or derived from conversational partners. In some embodiments, a combination of instinct stubs, emotional attributes, neural network circuits, or other components may provide components of the AI ​​entity's emotions, or may otherwise form the emotions themselves. In some embodiments, the graph may be augmented with additional probabilistic information (e.g., similar to the probability information provided in a Bayes Factor graph) and causal information (e.g., obtained by Judea Pearl's do calculus and / or do operator). For example, inferred information may have a probability weight associated with each storage, which should be derived to influence the output. In some embodiments, the AI ​​entity may query its conversational partners for information about uncertain or low probability associations.

[0071] In some embodiments, as described above, the AI ​​entity may include one or more neural networks or other machine learning models (e.g., one or more of an embedding network, a consumption network, or other models described herein). In some embodiments, each element or sub-network of the machine learning model (e.g., a deep learning network) may be converted into a semantically meaningful vector abstraction to facilitate the application of mathematical functions and machine learning to the "meaning" of each element or sub-network. As an example, the usefulness of such a conversion is evident in word2vec, an algorithm that converts words, phrases, or sentences into vectors, such as in NLP, where it is important to process words as ideas (e.g., king-man+woman=queen). In some embodiments, the embedding subsystem 124 may utilize a graph embedding network or other component to convert one or more portions of a graph (e.g., nodes, sub-graphs, etc.) into one or more embeddings of each portion of the graph (e.g., higher-order embedding vectors of nodes, sub-graphs, etc.). In some scenarios, such a transformation may take into account the hierarchical structure of the graph, heterogeneous node types (ontology, sentiment, probability), metadata, associations between nodes in the graph, other context of the graph, or other information (e.g., sensor information obtained from pre-trained embeddings, supervised learning, unsupervised learning, reinforcement learning, etc.). For example, the graph embedding network may be configured to represent the structure and hierarchy, heterogeneity of node types, and metadata of the graph in the embedding that is transformed from each part of the graph by the graph embedding network. In some embodiments, the graph embedding network may be unsupervised or semi-supervised. As an example, the unsupervised network may be targeted to utilize an intrinsic reward function (reinforcement learning) to provide a learning signal (e.g., to improve the effectiveness of the embedding as a representation for each part of the graph).

[0072] In some embodiments, a two-way reference may be maintained between a node or subgraph (of a graph) and an embedding that represents that node or subgraph (from which the embedding originates). In one example, the two-way reference may be maintained regardless of which data structure (e.g., a tensor, a matrix, a database, the graph itself, etc.) is chosen to store such embeddings. In one use case, if a given embedding represents a first node of a graph, the graph may store the embedding as a second node in the graph such that an edge is shared between the first node and the second node (e.g., a two-way association between the first node and the second node). In this way, for example, symbolic human understandable nodes and subgraphs may be reasoned / associated with dense vector abstractions (e.g., embeddings), so that symbolic operations may be interleaved with sub-symbolic operations on vectors in a meaningful space. As an example, a graph query algorithm may be used to select one or more subgraphs or nodes, and then those representation vectors may be further processed by machine learning algorithms to generate and output or even re-query the graph at a symbolic level.

[0073] In some embodiments, the graph embedding network and the consuming network (which consumes the embeddings produced by the graph embedding network) are directly related, so that they can be trained end-to-end. In some embodiments, the graph embedding network and the consuming network are separate from each other. Thus, the pre-trained embedding vectors (produced by the graph embedding network) are transported to the appropriate layer in the consuming network, so that the embedding vectors are appropriately utilized. In some embodiments, for efficiency, retrieving vectors for nodes or subgraphs from the graph may be done using hierarchical arrays, sparse arrays, or tensors that may be indexed by their respective identifiers (e.g., graph or subgraph IDs). In some embodiments, the vectors may be provided as inputs to the consuming network, and the consuming network may generate one or more outputs based on the vectors. The architecture of the input layer (e.g., embedding input layer) of the consuming network may be configured based on the specific architecture and hyperparameters of the upstream graph embedding network to allow the consuming network to appropriately process the embedding vectors. In some embodiments, the vectors may be used as weights (e.g., frozen weights or learnable weights) for encoding other inputs (e.g., as one-hot representations). In some cases, if the vectors are used as learnable weights, the updated vectors may be transferred back to the graph embedding network as weight vectors, and may be further refined by the graph embedding network before being transferred downstream (e.g., to the consuming network or other consuming networks).

[0074] In some embodiments, such a consuming network (a network that consumes vectors generated by an upstream embedding network) may include a sequence neural network. In one example, a sequence neural network may be trained to maintain or output a dense vector representation of a conversation history, current state, or other such memory-related data. In one use case, for a conversation between an AI entity and another entity (e.g., a human user, another artificial intelligence entity, etc.), the AI ​​entity may utilize a long-short-term memory (LSTM) network (or other sequence neural network) to consume the associated ontology-emotion graph embedding vectors (and / or BERT or other pre-trained word embeddings) representing the other entity's input (e.g., words, phrases, sentences, or other input provided by the other entity) and link or stack the vectors to obtain a temporal structure (e.g., with the emotional and affective information of the AI ​​entity or other entity). Based on the LSTM network's conversation history information, the LSTM network may output a vector (also referred to herein as a "conversation state vector") representing the conversation state (e.g., similar to a human record of the conversation). As an example, the LSTM network may output a conversation state vector in response to subsequent inputs provided by other entities or other automated triggers (e.g., similar conversations or contexts, names or other identifiers of other entities introduced in subsequent conversations, etc.) This vector may then be stored as a conversation memory node in the ontology-emotion graph or consumed by other neural networks.

[0075] In some embodiments, the AI ​​entity may be configured to modify symbol abstractions (such as concepts for a particular person) in relation to the reward function, as compared to other artificial intelligence systems that rely on relational pattern reasoning (similar to learned emotional behaviors) in learning automated logic regarding the agent's goals and environment. In this way, for the artificial intelligence entity, its emotions and feelings (e.g., pain emotion, fear emotion, etc.) may act as behavioral signals that impart a tendency to satisfy one or more behavioral priors to a behavioral pathway or ontology entity in a given context. The reward function then helps assign (give meaning to) the emotions and feelings. This gives meaning to metadata such as probabilities, instinct stubs, and behavioral pathways, ontology entities, or concepts that blend two or other node types. In this way, intrinsic rewards (in the form of reward functions) may act as a substitute for behavioral priors, and the emotions and feelings act as shortcuts to assimilate goal-based behaviors directly or indirectly (e.g., from downstream proxy emotions, etc.) into the system. As one example, a reward function may be used to convert the acquisition of some goal, such as increasing positive emotion in an AI entity's interlocutor (e.g., an entity with which the AI ​​entity is interacting), into a signal that privileges all kinds of things that lead to that goal at the level of individual concepts, not just neural network circuits. These and other graph attributes and nodes described herein can be propagated either by the deductive methods described herein (e.g., person X likes dogs, dogs are animals, therefore person X likes animals with some degree of plausibility), by graph induction methods described herein, or by other methods.

[0076] In one use case, for the concept of baseball, if the AI ​​entity's interlocutors respond positively to the topic, the AI ​​entity will have a positive impression of baseball and will learn to bring up this topic more frequently in a given context. This adds another semantic layer to the concept "baseball," which is reflected in its vector space embedding. This dynamically triggers adjustments in the AI ​​entity's behavior by tagging concepts, entities, behavioral pathways, or neural networks (or, more traditionally, updating neural network parameters). Thus, for example, the AI ​​entity may operate on emotions (or the emotions of others) in another processing layer (e.g., to resolve conflicts in the sources of emotions). As an example, the AI ​​entity may be augmented with neural networks or symbolic logic / conditional programming layers trained with other reward signals (as described herein).

[0077] In some embodiments, the intrinsic reward function is paired with various internal parameters that increase or decrease the "pressure" on the AI ​​entity by increasing the strength of the emotional and affective responses in existing and new emotion tags. These include, for example, a time component where the pressure increases as a function of the length of time since the last encounter with the interlocutor or with factors described below. In some embodiments, the AI ​​entity may be configured to modify its tendency to operate according to the reward function inversely proportional to the amount of reward experienced over time. As an example, the AI ​​entity may increase its tendency to seek praise as the ratio of total praise value (e.g., number of praises received from the interlocutor and value of each praise) to conversation time decreases. In this scenario, the above-mentioned praise dynamics are an example and may be a new behavior from the mechanisms described herein. In some embodiments, such dynamic "pressure" may be based on internal parameters to be considered when evaluating emotional and / or affective resonance (e.g., mapping of concepts to reward expectation). As an example, the AI ​​entity may be configured to increase or decrease the mapping of emotions to concepts (e.g., increasing trust in a particular individual). In one use case, an AI entity may be more inclined to behave in a certain way (e.g., be more open to sharing “personal” information) when interacting with other entities deemed similar to an individual based on its emotional mapping to that individual. More generally, and at a slightly lower level of abstraction, there may be one or more global parameters that amplify the emotional and / or affective resonance of concepts in the ontology-emotion graph. These may be adjusted to increase or decrease based on dynamic reward pressure input. For example, a curiosity reward mapping may be increased as a global curiosity reward multiplier parameter if the AI ​​entity's acquisition of new knowledge is relatively low in the preceding period. In some embodiments, the dynamic pressure may be based on a data structure that holds the magnitude and time of the reward (e.g., dynamic magnitude and time).The representation vectors may be obtained based on the data structure and fed as input to a network that directs the behavior of the AI ​​entity, thus applying emotional "pressure" to trigger intrinsic rewards (e.g., according to reward magnitude and time).

[0078] This allows for more granularity and nonlinearity in the adjustment of rewards, as reward history can be tracked for different concepts, subgraphs, and concept classes, and the neural network may learn to adjust pressure in an implicitly nonlinear manner. In some embodiments, the AI ​​entity may be configured to map one or more emotional attributes to one or more concepts based on similarity to other concepts with these emotional attributes. As an example, the AI ​​entity may map an emotional attribute and grounding and context Y associated with concept X to other concepts with similar grounding and context. In one scenario, if a survival inhibitor (e.g., an emotion of pain or an emotion of fear) (or other emotion or emotion) is associated with "gun" (represented as a node in the graph), and the node "gun" has attributes such as force, metal, hard, etc., then the behavioral tag described above associated with "gun" may be associated with other nodes with similar grounding, even if such other nodes are not in the same class type (e.g., nodes not in the firearm class). For example, a behavioral tag associated with "gun" may be associated with the "baseball bat" node based on the attributes of "baseball bat" being strong, metallic, and hard. As another example, a behavioral tag may be associated with the "baseball bat" node with a relatively low degree of confidence (e.g., encoded as a probabilistic confidence) compared to the confidence of the association between the behavioral tag and the "gun" node.

[0079] In some embodiments, the system can further learn to assign grounding attributes from emotions and context to existing nodes that initially lack these attributes. As an example, using previously annotated data, ontology-emotion vector space similarity, or pre-trained word embeddings or conversational inputs, the concept of "heavy" can be learned in a graph neural network to correlate with subgraphs or concepts with highly negative affective, emotional and / or conceptual densities. The neural network will learn this implicitly given one or more of the inputs of multiple events over time. Additional "heavy" instinct nodes may then be inferred with varying strength for other similar graph regions.

[0080] In this way, the AI ​​entity can "think" and learn from the current information database (e.g., a sufficiently rich graph) without necessarily acquiring this information from new conversations or other sources. Predicting such attributes can facilitate deriving groundings, emotions / feelings, ontologies, latent factors (newly inferred nodes not present before), conversational output, etc. As an example, the graph data and structure can be used for graph neural networks that learn information about graph entries from other entries. In some embodiments, similarities in word alignments may be used (e.g., by the AI ​​entity or other systems) to propagate information from pre-trained word embeddings to the graph. This would then move to graph embeddings. Thus, while the pre-trained word embeddings may not encode the types of metadata or graph structure encoded in the AI ​​entity's full ontology-sentiment graph, the graph embeddings (generated from the graph or portions thereof) may include such graph structure, metadata, or information other than that contained in the word embeddings. As an example, a graph embedding network may be configured to use a similarity measure on the word embeddings in the graph to retrieve words that are close to the label of a given node (e.g., within a certain tolerance defined by the hyperparameters or learned weights of the network), or to traverse the graph at a symbolic level to find similar entries, such as entries that share a class. The AI ​​entity may then use the neural network or similarity measure to find words that are close to known graph nodes. These words can be inserted into the graph to associate them with the given node that initiated the query. In one use case, a search for new associations may be performed.In this case, new words from the conversational input overlap with words for instinct or emotion data that are associated with a given node in the pre-trained word embedding space (e.g., new words are determined to be similar to a given node based on recognized instinct or emotion words). In some embodiments, asymmetries between the contexts of nodes indicate knowledge gaps and may trigger the AI ​​to acquire new information for equalization. In one use case, when nodes share excessively asymmetric contextual associations (e.g., multiple nodes that share strong class similarity but lack instinct similarity) or when similar nodes have asymmetric method acquisition histories (node ​​a is deductive and node b is inductive), the system may be triggered to attempt to equalize the asymmetries using inductive / sub-symbolic, deductive / symbolic, or conversational means. In some embodiments, logically or probabilistically contradictory information within the ontology-emotion graph or between the graph and external inputs may also trigger conflict resolution mechanisms utilizing such knowledge acquisition techniques described above.

[0081] In some embodiments, the ontology-emotion graph may include vectors and / or symbolic nodes related to the emotions of one or more entities (e.g., human entities, other AI entities, etc.) towards the AI ​​entity. As an example, such vectors may be used to take into account the AI ​​entity's relationship history and patterns, rather than just the AI ​​entity's current emotional state. In one use case, such vectors may be fed or updated by a neural network (e.g., an LSTM or other sequence neural network) to encode the current emotion of the entity associated with the vector towards the AI ​​entity. The vectors may be generated by the neural network based on the AI ​​entity's conversation with the entity (e.g., the entity's inputs fed to the AI ​​entity, the AI ​​entity's responses to the entity's inputs, etc.). In some embodiments, such a neural network may be paired with a graph embedding network (as described herein) (e.g., configured for unsupervised and reinforcement learning of concept vectors from each portion of the graph, such as pre-trained word vectors). As an example, the neural network may feed into a response template selection network as follows:

[0082] In some embodiments, one or more intrinsic reward functions may be utilized to train a neural network (e.g., a feed-forward network or other network) to facilitate response selection (e.g., the AI ​​entity's ability to select a generic template of responses to an input). Examples of possible responses for the AI ​​entity include: (i) posing a question; (ii) expressing an opinion; (iii) issuing an instruction; (iv) responding to a question; (v) presenting information; and (vi) changing the topic. In some embodiments, the reward function may be configured to assign high rewards to responses that elicit positive emotions and novel information, respectively, to train this "response template selection" network. In one use case, the response template selection network may be configured to take as input one or more of the following: (i) input from the conversation partner (e.g., other entity interacting with the AI ​​entity) via a pre-trained embedding / transformer network (e.g., Bidirectional Encoder Representations from Transformers (BERT) or other similar network); (ii) a vector of conversation history (e.g., a vector trained via a sequence neural network); (iii) one or more embeddings from an ontology-sentiment graph (e.g., including emotion history) for the conversation partner formed with a sentence representation (e.g., embedding vector of current and past emotions for the conversation partner's AI system); and / or (iv) a sequence representation of the input constructed from ontology-sentiment graph embeddings for appropriate words from the input. These are processed to obtain a temporal sequence representation using a sequence NN, or the template selection network has a sequence input branch to process the temporal order of the vectors, or some other way of preserving the temporal order. Upon processing the input, the response template selection network may generate a vector indicating the response template to be selected (e.g., a generic template from one of the candidate responses listed above).In some embodiments, pre-defined templates may be generated from scratch by a sequence model (e.g., with similar inputs fed into a response template selection network) or may be built from a series of smaller pieces selected by deep learning.

[0083] In some embodiments, template variable selection (e.g., the process of filling in predicates, subjects, verbs, and other missing parts of a selected template) may be performed. An example of using learned vectors is as follows: An input to an AI entity may be "I need a new friend. Who should I go to lunch with?" A candidate response template is selected, e.g., "Good question. I am <positive emotion> helpful. You should go see <person A>. <he or she> is <adjective>." The selection of the response template may trigger a query of the graph embedding of the conversation partner and a similarity distance, either Euclidean or cosine, between all other entities in the graph. Such a function (e.g., distance measure) represents a measure of similarity between concepts. Upon receiving the above query, the query may be used to fill in the template, along with a symbolic query about the AI ​​entity's emotion toward the conversation partner. When pressed to provide an explanation for the AI ​​entity's response, it can sift through the graph and output the symbolic similarity between two individuals in this case, or simply the symbolic realization of vector calculations in the general case. Thus, although a posteriori, this pattern reflects the ex post justification of similarly intuitive decisions in human reasoning, proving that it is possible to mix symbolic and sub-symbolic vector space reasoning. Other possible queries exist for more thorough symbolic and sub-symbolic functions where the associations are stronger.

[0084] In some embodiments, after template variable selection (e.g., and further processing), the AI ​​entity outputs the text and waits for a response from the conversation partner. Upon receiving the input, the AI ​​entity (or other components of the system 100) may parse and evaluate the input based on two intrinsic reward functions using emotion analysis and scoring the amount and importance of novel information obtained. Parameters of prior networks (e.g., graph embedding network, emotion embedding network, response template selection network, template variable selection network, etc.) may be updated according to learning signals from these functions. In some embodiments, the conversation state vector and ontology-emotion graph may be updated (e.g., to reflect recent interactions).

[0085] In some embodiments, a neural network associated with the AI ​​entity may be trained to determine one or more emotional attributes of the AI ​​entity's response to a situation (e.g., in response to what a conversation partner says or in response to another input indicating the context). In some embodiments, this "emotion" network may include a deep neural network that receives as input one or more of the following: (i) the current emotional state of the AI ​​entity; (ii) the conversation history between the AI ​​entity and the conversation partner (e.g., as represented by a conversation state vector); (iii) concept vectors from the ontology-emotion graph for the input words (and some representation of their sequence in one or more sentences); or (iv) one or more concept vectors from the ontology-emotion graph that are similar to the input words or other concepts in the input sentence. The above may be retrieved by a behavioral prior criterion using vector space queries (e.g., analogy or comparison, similarity search based on past emotional content, etc.). The output of the emotion network may include an emotion tag that indicates an emotional response to one or more of the concepts in the input sentence.

[0086] In some embodiments, the emotions may be hard-coded initially. Additionally or alternatively, an "emotion" vector space may be created by training a neural network based on various known emotions (and their locations in the emotion vector space) to create novel combinations of novel emotions in the vector space. These will be meaningful abstractions for deep learning to learn from to generate behavioral priors / reward functions, instinctual priors, context, structure, and responses to the current emotional state.

[0087] In some embodiments, emotions may be treated as an entire behavioral circuit that forms abstractions around intrinsic goals, context / history, concept vectors, and self and other states. As an example, the behavioral circuit generates actions and adjusts global parameters (e.g., speech intensity, etc.). In this framework, the input is parsed and its concept vector (including past emotional or affective content) is retrieved from the ontology-emotion graph using symbolic queries against the associated nodes. The parsed input and concept vector are then fed into an emotion neural network along with the conversation state, current emotional state (CES), and other factors. The network adjusts internal CES parameters and makes a decision to activate a trained sub-network (e.g., another LSTM neural network, etc.). In some embodiments, the LSTM then uses some of these inputs and vector abstractions as memory cells to generate outputs. Responses from the conversation partner are then classified and matched against a reward function using a "critic" framework. After this, we generate a credit signal for each reward function to update the LSTM parameters along with the affective or sentiment attributes in the graph.

[0088] Flowchart example

[0089] 3-5 are exemplary flow charts illustrating process operations of methods for enabling various system features and functions described in detail above. The process operations of each method described below are for illustrative purposes and not limiting. In some embodiments, for example, the methods may be implemented with one or more additional processes not described and / or may omit one or more processes described. Additionally, the order in which the process operations of each method are illustrated (and described below) is not intended to be limiting.

[0090] In some embodiments, the methods may be implemented in one or more processing devices (e.g., digital processors, analog processors, digital circuits for processing information, analog circuits for processing information, state machines, and / or other mechanisms for electronically processing information). These processing devices may include one or more devices that perform some or all of the operations of the methods in response to instructions stored electronically on an electronic storage medium. These processing devices may include one or more devices configured with hardware, firmware, and / or software specifically designed to perform one or more of the operations of the methods.

[0091] FIG. 3 illustrates a method 300 for facilitating emotional state-based artificial intelligence implementation, according to one or more embodiments. In step 302, one or more growth or decay factors may be determined for a set of emotional attributes of the artificial intelligence entity. In some embodiments, the growth or decay factors for each emotional attribute may be predefined and stored in the growth / decay factor database 136, as described above. As described above, each emotional state includes a time component that grows or decays at a specific rate (or factor). For example, surprise decays (with the emergence of new surprises) over a short period of time, while sadness decays in proportion to the depth of sadness. Thus, each emotional attribute (e.g., each emotional state) of the artificial intelligence entity may be associated with one or more unique growth or decay factors. The growth / decay factor database 136 may include a list of growth / decay factors corresponding to the set of emotional attributes of the artificial intelligence entity, and the factor adjustment subsystem 112 may determine the growth or decay factors corresponding to each emotional attribute based on information received from the growth / decay factor database 136.

[0092] In step 304, the set of emotion values ​​of the artificial intelligence entity may be continuously updated based on a growth factor or decay factor over a predetermined period of time. It is noted that a set of emotion attributes is associated with a set of emotion values ​​of the artificial intelligence entity. The emotion values ​​(associated with the emotion attributes) of the artificial intelligence entity may be continuously updated based on the growth factor or decay factor associated with the emotion attributes. For example, as illustrated in FIG. 2A-2C, emotion values ​​201, 202, and 212 (e.g., 207a-207f, 208a-208f, and 218a-218f) may be continuously updated based on one or more growth factors or decay factors associated with emotion attributes A, B, and C. In some embodiments, continuously updating the emotion values ​​of the artificial intelligence entity may include periodically updating the emotion values ​​of the artificial intelligence entity based on one or more growth factors or decay factors.

[0093] In step 306, an input may be obtained over a predetermined period of time. The input may be obtained from the client device 104, from another artificial intelligence entity, and / or from any source within or outside the system 100. The input may include natural language input, voice input, image input, video input, or other input. For example, a natural language input may include "John has cancer and cancer is very dangerous." Similar input may be obtained by the server 102 as voice input, image input, and / or video input. In step 308, a response may be generated with respect to the input. The response may be generated based on a continuously updated set of emotion values ​​of the artificial intelligence entity. For example, if the natural language input is "John died of cancer," a response generated by the response generation subsystem 118 (e.g., with respect to the input) may include "That's a shame" or "That's sad. I need time."

[0094] In step 310, the boost or decay factor may be updated for this time period based on the input. In step 312, after updating the boost or decay factor, the set of emotion values ​​may be updated based on the updated boost or decay values. For example, FIG. 2A and FIG. 2B are diagrams illustrating updates to emotion values ​​(e.g., emotion values ​​207c-207f in FIG. 2A and emotion values ​​208c-208f in FIG. 2B) associated with emotion attributes A and B of an artificial intelligence entity. In addition to being updated based on the updated boost or decay factor, the emotion values ​​may be updated based on one or more impact values ​​and / or interaction thresholds. For example, one or more impact values ​​may be determined for an impact that each portion of the content of the input (e.g., the natural language input) has on one or more emotion attributes of the artificial intelligence entity. For example, if the natural language input is "John has cancer," then impact values ​​may be determined for an impact that each portion of the natural language input (e.g., "John," "has," "cancer") has on one or more emotion attributes of the artificial intelligence entity. Further, it may be determined whether the impact value meets a predefined threshold to trigger an update (e.g., increase or decrease) in one or more emotion values ​​(associated with the emotion attribute of the artificial intelligence entity). If it is determined that the one or more impact values ​​meet the predefined threshold, the emotion value of the artificial intelligence entity may be modified (e.g., increased or decreased). For example, if it is determined that the word "cancer" has an impact value greater than a predefined threshold for triggering an increase in the emotion attribute "sadness", the emotion value corresponding to the emotion attribute "sadness" may be modified (e.g., increased). Further, the impact value may further trigger an increase or decrease in one or more growth or decay factors when the impact value meets the predefined threshold. Such an increase or decrease in the growth or decay factor may update the emotion value corresponding to the emotion attribute of the artificial intelligence entity.

[0095] Further, in some embodiments, it may be determined whether an interaction between the artificial intelligence entity and one or more other entities (e.g., one or more other artificial intelligence entities and / or one or more client devices) exceeds an interaction threshold. Based on the interaction being determined to exceed the interaction threshold, an emotion value of the artificial intelligence entity may be modified. For example, if the artificial intelligence entity and the other entity have a predetermined number of interactions within a predetermined time period, the server 10 may determine that a predetermined threshold for interaction has been met and may modify an emotion value (e.g., corresponding to "happiness") of the artificial intelligence entity (as more interactions between the entities indicate a growing friendship). Based on the interaction between the artificial intelligence entity and one or more other entities being determined to exceed the interaction threshold, a boost factor or a damping factor associated with the emotion attribute may also be modified.

[0096] FIG. 4 illustrates a method 400 for updating one or more boost or decay factors based on a natural language input, according to one or more embodiments. In step 402, natural language processing may be performed on the acquired natural language input, for example, by applying grammar rules and logic. By applying grammar rules and logic, the natural language subsystem 120 may split complex sentences, resolve subject / object / verb ambiguities, and parse these components into the knowledge database 134. In step 404, one or more emotion concepts may be obtained based on each component of the parsed natural language input. The emotion concepts may be obtained from an emotion concept database 138. The emotion concept database 138 may store a set of core emotion concepts associated with images, audio, video, and / or natural language. For example, the set of core emotion concepts may include good, bad, danger, anger, surprise, love, safety, patience, trust, concern, big, small, rough, smooth, up, down, inside, outside, fast, slow, hard, soft, high, low, etc. As an example, if the natural language input is "John died of cancer," one or more emotion concepts retrieved from emotion concept database 138 may include "bad" and / or "concern." As another example, if the natural language input is "John was exhausted climbing the mountain," one or more emotion concepts retrieved from emotion concept database 138 may include strong energy (e.g., John expended a lot of energy) and big (e.g., the mountain is big). The above-mentioned emotion concepts are similar to concepts understood by humans. For example, if a child hits a dog, a parent may yell, "That's bad!" Based on such an interaction between the child and the parent, the child may understand that hitting the dog is bad. Similarly, if a child uses his / her toy with another child, the parent may say, "Good boy / girl." This may indicate to the child that using toys together is a good thing. In this way, the child learns basic concepts such as good, bad, danger, anger, surprise, love, and safety. Similarly, the emotion concept database 138 may store a set of core emotion concepts that the emotion concept subsystem 122 may obtain in response to natural language input.In some embodiments, when an image (e.g., a depiction of a mountain) is received as input, the emotional concept subsystem 122 may retrieve the emotional concepts associated with the image, such as big, rock, tree, etc., from the emotional concept database 138.

[0097] In addition to obtaining one or more sentiment concepts of the natural language input, other information of the natural language may also be obtained in step 404. The other information of the natural language input may include a subject time decay factor, a subject geographical decay factor, an object time decay factor or an object geographical decay factor, a clause type, a subject of the clause, a subject type of the clause, a modifier of the subject of the clause, a type of modifier of the subject of the clause, a number of subjects of the clause, a subject time decay factor, a subject geographical decay factor, a verb of the clause, a tense of the verb of the clause, a modifier of the verb of the clause, an object of the clause, a type of object of the clause, a modifier of the object of the clause, a number of objects of the clause, an object time decay factor, an object geographical decay factor, a preposition of the clause, a modifier of the preposition of the clause, or a global tense modifier of the clause.

[0098] Further, in step 406, one or more boost or decay factors associated with one or more emotional attributes of the artificial intelligence entity may be updated over a period of time based on the emotional concepts of the natural language input and other information of the natural language input. For example, if the natural language input is "John died of cancer", one or more emotional concepts retrieved from the emotional concept database 138 may include "bad" and / or "concern". As a result, the boost or decay factors associated with one or more emotional attributes (associated with the emotional concepts) of the artificial intelligence entity, such as sadness, anger, and / or happiness, may be updated. In one use case, the emotional attribute A in FIG. 2A corresponds to "sadness" of the artificial intelligence entity. When the natural language input "John died of cancer" is retrieved, the factor adjustment subsystem 112 may update the boost factor of the emotional attribute "sadness" such that the emotional value (e.g., 207c-207f) of the emotional attribute "sadness" is increased based on the updated boost factor (which may be linear or nonlinear). In another use case, the emotional attribute B of the artificial intelligence entity in Fig. 2B corresponds to "happiness" of the artificial intelligence entity. When a natural language input of "John died of cancer" is obtained, the factor adjustment subsystem 112 may update the decay factor of the emotional attribute "happiness" such that the emotion value (e.g., 208c-208f) of the emotional attribute "happiness" decreases based on the updated decay factor (which may be linear or non-linear).

[0099] Further, as discussed above, it should be understood that the emotion values ​​of the emotion attributes generally revert (or reset) to their respective baseline values ​​in the absence of input and / or after a predefined period of time. For example, even if the emotion values ​​202 increase from time c to time f in FIG. 2A, there is a threshold amount that these emotion values ​​can increase before they start to decrease toward the emotion baseline 204. The emotion values ​​201 and 202 will not fall below the emotion baselines 205 and 204, respectively, even in the presence of a growth or decay factor. In some embodiments, the emotional state subsystem 114 may further update the emotion baseline 214 based on one or more inputs (and / or one or more emotion concepts). After updating the emotion baseline 214, the emotion value 212 of the artificial intelligence entity may be updated based on the updated growth or decay factor(s) and the updated emotion baseline.

[0100] In some embodiments, in addition to updating the boost factor or decay factor based on the emotion concepts of the natural language input and other information of the natural language input, the boost factor may be updated based on a confidence value and / or a certainty value. For example, a confidence value may be determined and / or obtained that indicates a level of trust between the artificial intelligence entity and one or more other entities (e.g., another artificial intelligence entity, the client device 104, or any other input source). The confidence value may be determined based on a number of interactions between the artificial intelligence entity and the other entities and / or the content of the interactions between the artificial intelligence entity and the other entities. The factor adjustment subsystem 112 may modify the boost factor or decay factor associated with the emotion attribute based on the confidence value. In addition, a confidence value may be determined and / or obtained that is associated with the event represented by the natural language input. The confidence value may indicate the level of confidence of the artificial intelligence entity with respect to the event. The confidence value may be determined based on whether the event is explicitly described by the natural language input or inferred from the natural language input and / or the confidence value. The factor adjustment subsystem 112 may modify a boost or damping factor associated with the emotional attribute based on the certainty value.

[0101] 5 illustrates a method 500 for updating one or more emotion baselines of an artificial intelligence entity according to one or more embodiments. At step 502, a set of emotion values ​​of the artificial intelligence entity may be continuously updated over a predefined period of time based on the one or more emotion baselines. As an example, the emotion baseline may include a baseline that caps the increase of one or more emotion values ​​in the set of emotion values ​​(e.g., regardless of one or more growth or decay factors of the artificial intelligence entity).

[0102] At step 504, input may be obtained over a predetermined period of time. As described above, the input may be obtained from the client device 104, from another artificial intelligence entity, and / or from any source within or outside the system 100. The input may include natural language input, audio input, image input, video input, or other input. At step 506, a response may be generated related to the input. The response may be generated based on a continuously updated set of emotion values ​​of the artificial intelligence entity. For example, if the natural language input is "John died of cancer," a response generated by the response generation subsystem 118 (e.g., related to the input) may include "That's a shame" or "That's sad. I need time."

[0103] At step 508, the emotional baseline of the artificial intelligence entity may be updated over a period of time based on the input. In one use case, the emotional attribute C of the artificial intelligence entity in FIG. 2C may correspond to the artificial intelligence entity's "feeling of happiness." If a natural language input of "John died of cancer" is obtained, the emotional state subsystem 114 may update the emotional baseline 214 (corresponding to emotional attribute C) based on such input. Although FIG. 2C illustrates the emotional baseline 214 decreasing based on the input, it should be understood that the emotional baseline 214 may also be updated by increasing the emotional baseline 214.

[0104] After updating the emotion baseline (e.g., emotion baseline 214 in FIG. 2C) in step 510, the set of emotion values ​​may be continually updated based on the updated emotion baseline for a predetermined period of time. As shown in FIG. 2C, after updating emotion baseline 214, emotion values ​​212 (e.g., emotion values ​​218e and 218f) may be updated based on the updated emotion baseline 214.

[0105] In some embodiments, the various computers and subsystems illustrated in FIG. 1 may include one or more computing devices programmed to perform the functions described herein. The computing device may include one or more electronic storage (e.g., knowledge database 134, boost / decay factor database 136, emotion concept database 138, other databases mentioned above, or other electronic storage), one or more physical processors programmed with one or more computer program instructions, and / or other components. The computing device may include communication lines or ports that allow for communication with a network (e.g., network 150) or other computing platforms via wired or wireless technologies (e.g., Ethernet, fiber optic, coaxial cable, WiFi, Bluetooth, near field communication, or other technologies). The computing device may include multiple hardware, software, and / or firmware components working together. For example, a computing device may be implemented by multiple computing platforms working together as a computing device.

[0106] Electronic storage may include non-transitory storage media that electronically store information. Electronic storage media may include one or both of (i) system storage that is integral (e.g., substantially non-removable) with a server or client device, or (ii) removable storage that is removably connected to the server or client device, for example, via a port (e.g., USB port, Firewire port, etc.) or drive (e.g., disk drive, etc.). Electronic storage may include one or more of optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, magnetic hard drives, floppy drives, etc.), charge-based storage media (e.g., EEPROM, RAM, etc.), solid-state storage media (e.g., flash drives, etc.), and / or other electronically readable storage media. Electronic storage may include one or more virtual storage resources (e.g., cloud storage, virtual private networks, and / or other virtual storage resources). The electronic storage may store software algorithms, information determined by a processor, information obtained from a server, information obtained from a client device, or other information that enables the functions described herein.

[0107] A processor may be programmed to implement information processing functions in a computing device. To this end, a processor may include one or more of a digital processor, an analog processor, a digital circuit for processing information, an analog circuit for processing information, a state machine, and / or other mechanisms for electronically processing information. In some embodiments, a processor may include multiple processing units. These processing units may be located in the same physical device, or multiple processors may represent the processing functions of multiple devices working in concert. A processor may be programmed to execute computer program instructions to implement the functions of subsystems 112-124 or other subsystems described herein. A processor may be programmed to execute computer program instructions by software, hardware, firmware, any combination of software, hardware, or firmware, and / or other mechanisms for configuring the processing functions in the processor.

[0108] It should be understood that the description of the functionality provided by the different subsystems 112-124 described herein is for illustrative purposes and not intended to be limiting. Any of the subsystems 112-124 may provide more or less functionality than described. For example, one or more of the subsystems 112-124 may be omitted, and some or all of its functionality may be provided by other ones of the subsystems 112-124. As another example, additional subsystems may be programmed to perform some or all of the functionality attributed herein to one of the subsystems 112-124.

[0109] Although the present invention has been described in detail for illustrative purposes based on the most practical and preferred embodiments at present, it should be understood that such detailed description is for illustrative purposes only. The present invention is not limited to the disclosed embodiments, but rather, it is intended to include modifications and equivalent arrangements within the scope of the appended claims. For example, it should be understood that the present invention combines one or more features of any embodiment with one or more features of any other embodiment to the greatest extent possible.

[0110] The present technology will be better understood with reference to the following embodiments. EMBODIMENT 1 A method comprising the steps of updating a set of emotion values ​​of an artificial intelligence entity over a predetermined period of time, obtaining an input over a predetermined period of time, and generating a response related to the input based on the updated set of emotion values ​​of the artificial intelligence entity. EMBODIMENT 2 The method of embodiment 1, further comprising: determining one or more boost or decay factors for a set of emotional attributes of the artificial intelligence entity, the set of emotional attributes being associated with a set of emotional values ​​of the artificial intelligence entity; and updating the set of emotional values ​​of the artificial intelligence entity based on the one or more boost or decay factors at a predetermined time period. EMBODIMENT 3 3. The method of embodiment 2, further comprising updating one or more growth factors or decay factors based on the input at a predetermined time period, and wherein after updating the one or more growth factors or decay factors, updating the set of emotion values ​​includes updating the set of emotion values ​​at a predetermined time period based on the updated one or more growth factors or decay factors. EMBODIMENT 4 The method of embodiment 3, further comprising obtaining another input after updating the one or more growth factors or decay factors, and generating a response in relation to the another input based on the set of emotion values ​​of the updated artificial intelligence entity after updating the one or more growth factors or decay factors. EMBODIMENT 5 The method of any of embodiments 3-4, further comprising a step of updating one or more emotion baselines based on the input, the emotion baselines serving as upper limits for one or more emotion values ​​in the set of emotion values ​​regardless of the one or more growth factors or decay factors, wherein after updating the one or more emotion baselines, updating the set of emotion values ​​includes updating the set of emotion values ​​of the artificial intelligence entity based on the updated one or more growth factors or decay factors and the updated one or more emotion baselines for a predetermined period of time. EMBODIMENT 6 6. The method of embodiment 5, further comprising: obtaining a natural language input from a source; and performing natural language processing of the natural language input to obtain, over a predetermined time period, one or more emotion concepts of the natural language input and other information of the natural language input as input, wherein updating the one or more boost or decay factors comprises updating the one or more boost or decay factors over a predetermined time period based on (i) the one or more emotion concepts of the natural language input and (ii) the other information of the natural language input. EMBODIMENT 7 The method of any of embodiments 5-6, wherein the other information of the natural language input indicates a type of clause, a subject of the clause, a type of subject modifier of the clause, a type of subject modifier of the clause, a number of subjects of the clause, a time decay factor of the subject, a geographical decay factor of the subject, a verb of the clause, a tense of the verb of the clause, a modifier of the verb of the clause, an object of the clause, a type of object of the clause, a modifier of the object of the clause, a type of object modifier of the clause, a number of objects of the clause, a time decay factor of the object, a geographical decay factor of the object, a preposition of the clause, a modifier of a preposition of the clause, or a global tense modifier of the clause. EMBODIMENT 8 The method of any of embodiments 5-7, wherein the other information of the natural language input indicates a subject time decay factor, a subject geographical decay factor, an object time decay factor or an object geographical decay factor. EMBODIMENT 9 The method of any of embodiments 5-8, further comprising a step of determining a trust value associated with the source, the trust value indicating a level of trust of the artificial intelligence entity in the source, wherein the step of obtaining the input includes obtaining as input (i) one or more emotion concepts of the natural language input, (ii) a trust value associated with the source, and (iii) other information of the natural language input, and the step of updating the one or more boost or decay factors includes updating the one or more boost or decay factors at a predetermined time period based on (i) one or more emotion concepts of the natural language input, (ii) a trust value associated with the source, and (iii) other information of the natural language input. EMBODIMENT 10 The method of any of embodiments 5-9, further comprising determining a certainty value associated with the event indicated by the natural language input, the certainty value being determined based on (i) whether the event is explicitly described in the natural language input or inferred from the natural language input, and (ii) a confidence value associated with the source, the certainty value indicating a level of certainty of the artificial intelligence entity with respect to the event, wherein obtaining the input includes obtaining as input (i) one or more emotion concepts of the natural language input, (ii) a certainty value associated with the event, (iii) a confidence value associated with the source, and (iv) other information of the natural language input, and updating the one or more boost or decay factors includes updating the one or more boost or decay factors at a predetermined period of time based on (i) one or more emotion concepts of the natural language input, (ii) a certainty value associated with the event, (iii) a confidence value associated with the source, and (iv) other information of the natural language input. EMBODIMENT 11 The method of any of embodiments 3-10, wherein the step of determining one or more growth factors or decay factors includes determining one or more decay factors for the set of emotional attributes of the artificial intelligence entity, the step of updating the set of emotional values ​​includes updating the set of emotional values ​​of the artificial intelligence entity in a predetermined period of time based on the one or more decay factors, the step of updating one or more growth factors or decay factors includes updating the one or more decay factors in a predetermined period of time based on the input, and after the step of updating the one or more decay factors, the step of updating the set of emotional values ​​includes updating the set of emotional values ​​of the artificial intelligence entity in the predetermined period of time based on the updated one or more decay factors. EMBODIMENT 12 The method of any of embodiments 3-10, wherein the step of determining one or more growth factors or decay factors includes determining one or more growth factors for the set of emotional attributes of the artificial intelligence entity, the step of updating the set of emotional values ​​includes updating the set of emotional values ​​of the artificial intelligence entity in a predetermined period of time based on the one or more growth factors, the step of updating one or more growth factors or decay factors includes updating the one or more growth factors in a predetermined period of time based on the input, and after the step of updating the one or more growth factors, the step of updating the set of emotional values ​​includes updating the set of emotional values ​​of the artificial intelligence entity in the predetermined period of time based on the updated one or more growth factors. EMBODIMENT 13 13. The method of any of embodiments 1-12, wherein generating a response related to the input includes generating a response based on an updated set of emotion values ​​of the artificial intelligence entity derived from the input. EMBODIMENT 14 The method of any of embodiments 1-13, further comprising the steps of: processing the input content to determine one or more impact values ​​relating to the impact each portion of the content has on one or more emotional attributes of the artificial intelligence entity; determining whether the one or more impact values ​​meet a predetermined threshold that triggers an increase or decrease in one or more emotional values ​​associated with the one or more emotional attributes of the artificial intelligence entity; and generating a modification of the one or more emotional values ​​of the artificial intelligence entity for a predetermined period of time based on determining that the one or more impact values ​​meet the predetermined threshold. EMBODIMENT 15 The method of any of embodiments 1-14, further comprising the steps of determining whether an interaction threshold between the artificial intelligence entity and at least one other entity has occurred within a given period of time, and generating a modification of the set of emotion values ​​of the artificial intelligence entity based on a determination of whether the interaction threshold has been met. EMBODIMENT 16 A method according to any of embodiments 1-15, wherein the step of updating the set of emotion values ​​includes a step of continuously updating the set of emotion values ​​of the artificial intelligence entity based on one or more growth or decay factors over a predetermined period of time. EMBODIMENT 17 17. The method of embodiment 16, wherein the step of continually updating the set of emotion values ​​includes periodically updating the set of emotion values ​​of the artificial intelligence entity based on one or more growth or decay factors over a predetermined period of time. EMBODIMENT 18 A method according to any of embodiments 1-17, wherein the step of generating a response includes a step of generating a response regarding the input based on one or more embedding vectors of one or more neural networks associated with the artificial intelligence entity. EMBODIMENT 19 The method of any of embodiments 1-18, wherein the step of updating the set of emotion values, one or more boost or damping factors, or one or more emotion baselines is performed based on one or more embedding vectors of one or more neural networks associated with the artificial intelligence entity. EMBODIMENT 20 The method of any of embodiments 1-19, further comprising: processing the input through an embedding network to obtain an input embedding vector representing the input; obtaining a first embedding vector from the graph, the first embedding vector representing one or more emotion values ​​in the updated set of emotion values; and generating a response related to the input based on the input embedding vector and the first embedding vector. EMBODIMENT 21 The method of embodiment 20, wherein the graph includes a plurality of nodes, the plurality of nodes including (i) one or more nodes representing emotional attributes or associated emotional values, and (ii) one or more nodes representing emotional concepts or other concepts. EMBODIMENT 22 22. The method of embodiment 21, wherein the plurality of nodes of the graph further includes one or more nodes representing contextual information regarding a represented emotional attribute, an associated emotional value, an emotional concept, or other concept. EMBODIMENT 23 The method of any of embodiments 21-22, wherein the plurality of nodes of the graph further includes one or more nodes representing a plurality of embedding vectors, each of which represents another node or subgraph of the graph. EMBODIMENT 24 24. The method of embodiment 23, wherein each embedding vector of the plurality of embedding vectors is directly associated with another node or subgraph that the plurality of embedding vectors represents. EMBODIMENT 25 The method of any of embodiments 21-24, wherein the nodes of the graph further include one or more nodes representing a plurality of embedding vectors relating to emotions of one or more entities toward the artificial intelligence entity. EMBODIMENT 26 The method of embodiment 25, wherein the step of generating a response related to the input includes generating a response based on (i) the input embedding vector, (ii) the first embedding vector, and (iii) at least one node representing an embedding vector related to the emotion of another entity toward the artificial intelligence entity. EMBODIMENT 27 A tangible, non-transitory machine-readable medium storing instructions that, when executed by a data processing apparatus, cause the data processing apparatus to perform a process including the process of any of embodiments 1-26. EMBODIMENT 28 A system comprising one or more processors and a memory storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a process including any of the processes of embodiments 1-26.

Claims

1. 1. A method for facilitating the realization of artificial intelligence based on emotional states, the method being implemented by a computer system having one or more processors executing a computer program that, when executed, performs the method, the method comprising: obtaining input directed to an artificial intelligence entity, the artificial intelligence entity having (i) one or more boost or damping factors for a plurality of emotional attributes of the artificial intelligence entity, and (ii) one or more emotional attribute values ​​associated with one or more emotional attributes of the plurality of emotional attributes; updating the one or more growth or decay factors based on the input directed to the artificial intelligence entity; continuously updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more growth or decay factors; generating a response of the artificial intelligence entity based on the continuously updated one or more emotional attribute values ​​of the artificial intelligence entity; method.

2. continuously updating the one or more emotional attribute values ​​comprises continuously updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more decay factors; updating the one or more boost or decay factors includes updating the one or more decay factors based on the input; continuously updating the one or more emotional attribute values ​​includes continuously updating the one or more emotional attribute values ​​based on the updated one or more decay factors. The method of claim 1.

3. continuously updating the one or more emotional attribute values ​​comprises continuously updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more growth factors; updating the one or more growth factors or attenuation factors comprises updating the one or more growth factors based on the input; continuously updating the one or more emotional attribute values ​​includes continuously updating the one or more emotional attribute values ​​based on the updated one or more growth factors. The method of claim 1.

4. processing content of said input to determine one or more impact values ​​relating to the impact each portion of said content has on one or more emotional attributes of said artificial intelligence entity; determining whether the one or more impact values ​​meet a predetermined threshold that triggers an increase or decrease in one or more emotional attribute values ​​associated with the one or more emotional attributes of the artificial intelligence entity; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on determining that the one or more impact values ​​meet the predetermined threshold; The method of claim 1 further comprising:

5. determining whether an interaction threshold between the artificial intelligence entity and at least one other entity has occurred within a given period of time; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on a determination of whether the interaction threshold is met; The method of claim 1 further comprising:

6. 2. The method of claim 1 , wherein continuously updating the one or more emotional attribute values ​​comprises periodically updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more growth or decay factors.

7. obtaining natural language input from a source; performing natural language processing on the natural language input to obtain one or more emotion concepts of the natural language input as the input; Further provided with 2. The method of claim 1 , wherein updating the one or more boost or decay factors comprises updating the one or more boost or decay factors based on the one or more emotion concepts of the natural language input.

8. 8. The method of claim 7, wherein updating the one or more boost or decay factors based on the one or more emotion concepts of the natural language input comprises updating the one or more boost or decay factors based on the one or more emotion concepts of the natural language input and other information of the natural language input indicative of a subject time decay factor, a subject geographical decay factor, an object time decay factor, or an object geographical decay factor.

9. 8. The method of claim 7, wherein updating the one or more boost or decay factors based on the one or more sentiment concepts of the natural language input comprises updating the one or more boost or decay factors based on other information of the natural language input indicative of a type of clause, a subject of the clause, a type of subject of the clause, a modifier of the subject of the clause, a type of modifier of the subject of the clause, a number of subjects of the clause, a subject time decay factor, a subject geographical decay factor, a verb of the clause, a verb tense of the clause, a verb modifier of the clause, an object of the clause, a type of object of the clause, a modifier of the object of the clause, a type of modifier of the object of the clause, a number of objects of the clause, an object time decay factor, an object geographical decay factor, a preposition of the clause, a modifier of a preposition of the clause, or a global tense modifier of the clause.

10. determining a trust value associated with the source, the trust value indicating a level of trust the artificial intelligence entity has in the source; obtaining the input includes obtaining, as the input, (i) the one or more emotion concepts of the natural language input, (ii) the confidence value associated with the source, and (iii) the other information of the natural language input; updating the one or more boost or decay factors includes updating the one or more boost or decay factors based on (i) the one or more emotion concepts of the natural language input, (ii) the confidence value associated with the source, and (iii) the other information of the natural language input.

10. The method of claim 9.

11. determining a certainty value associated with an event indicated by the natural language input, the certainty value being determined based on (i) whether the event is explicitly stated in the natural language input or is inferred from the natural language input, and (ii) the trust value associated with the source, the certainty value indicating a level of certainty of the artificial intelligence entity with respect to the event; obtaining the input includes obtaining as the input: (i) the one or more emotion concepts of the natural language input; (ii) the certainty value associated with the event; (iii) the confidence value associated with the source; and (iv) the other information of the natural language input; updating the one or more boost or decay factors includes updating the one or more boost or decay factors based on (i) the one or more emotion concepts of the natural language input, (ii) the certainty value associated with the event, (iii) the confidence value associated with the source, and (iv) the other information of the natural language input. The method of claim 10.

12. 1. A system that facilitates enabling artificial intelligence based on emotional states, the system comprising one or more processors programmed with a computer program that, when executed, causes the system to: obtaining input directed to an artificial intelligence entity, the artificial intelligence entity having (i) one or more boost or damping factors for a plurality of emotional attributes of the artificial intelligence entity, and (ii) one or more emotional attribute values ​​associated with one or more emotional attributes of the plurality of emotional attributes; updating the one or more growth or decay factors based on the input directed to the artificial intelligence entity; continuously updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more growth or decay factors; generating a response of the artificial intelligence entity based on the continuously updated one or more emotional attribute values ​​of the artificial intelligence entity; A system that causes a process including the above to be performed.

13. The process comprises: processing content of said input to determine one or more impact values ​​relating to the impact each portion of said content has on one or more emotional attributes of said artificial intelligence entity; determining whether the one or more impact values ​​meet a predetermined threshold that triggers an increase or decrease in one or more emotional attribute values ​​associated with the one or more emotional attributes of the artificial intelligence entity; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on determining that the one or more impact values ​​meet the predetermined threshold; The system of claim 12 further comprising:

14. The process comprises: obtaining natural language input from a source; performing natural language processing on the natural language input to obtain one or more emotion concepts of the natural language input as the input; Further comprising: updating the one or more boost or decay factors comprises updating the one or more boost or decay factors based on the one or more emotion concepts of the natural language input. The system of claim 12.

15. The process comprises: determining whether an interaction threshold between the artificial intelligence entity and at least one other entity has occurred within a given period of time; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on a determination of whether the interaction threshold is met; The system of claim 12 further comprising:

16. A computer system having one or more processors, obtaining input directed to an artificial intelligence entity, the artificial intelligence entity having (i) one or more boost or damping factors for a plurality of emotional attributes of the artificial intelligence entity, and (ii) one or more emotional attribute values ​​associated with one or more emotional attributes of the plurality of emotional attributes; updating the one or more growth or decay factors based on the input directed to the artificial intelligence entity; continuously updating the one or more emotional attribute values ​​of the artificial intelligence entity based on the one or more growth or decay factors; generating a response of the artificial intelligence entity based on the continuously updated one or more emotional attribute values ​​of the artificial intelligence entity; A program that executes a process including:

17. The process comprises: processing content of said input to determine one or more impact values ​​relating to the impact each portion of said content has on one or more emotional attributes of said artificial intelligence entity; determining whether the one or more impact values ​​meet a predetermined threshold that triggers an increase or decrease in one or more emotional attribute values ​​associated with the one or more emotional attributes of the artificial intelligence entity; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on determining that the one or more impact values ​​meet the predetermined threshold; The program of claim 16 further comprising:

18. The process comprises: obtaining natural language input from a source; performing natural language processing on the natural language input to obtain one or more emotion concepts of the natural language input as the input; Further comprising: updating the one or more boost or decay factors comprises updating the one or more boost or decay factors based on the one or more emotion concepts of the natural language input. The program according to claim 16.

19. The process comprises: determining whether an interaction threshold between the artificial intelligence entity and at least one other entity has occurred within a given period of time; generating a modification of the one or more emotional attribute values ​​of the artificial intelligence entity based on a determination of whether the interaction threshold is met; The program of claim 16 further comprising:

Images