Intelligent arrangement system for emotional infection in multi-person-to-multi-agent interaction

Abstract

An embodiment senses an interaction between a software agent and a plurality of persons, and in response to the sensed interaction, calculates an emotional pattern in an emotional pattern observation component based on the sensed interaction. The embodiment computes a popular emotion pattern in an emotion pattern grouping component based on the emotion pattern. The embodiment determines, by the agent interaction orchestration component, to adjust a response of the software agent to affect at least one of the plurality of persons toward the popular emotion pattern based on the popular emotion pattern, the determination further including training a text generation component to generate a text sequence based on the response, where the software agent issues the text sequence, and the sensed interaction between the software agent and the plurality of persons is updated with the text sequence.

Description

Background Art

[0001] The present invention relates generally to artificial intelligence and more particularly to methods, systems and computer programs for intelligent orchestration of emotional contagion in multi-person to multi-agent interactions.

[0002] Artificial intelligence (AI) technology has evolved significantly over the past few years. Modern AI systems are reaching human-level performance in cognitive tasks such as converting speech to text, recognizing objects and images, or translating between different languages. This evolution promises to enable new and improved applications in many industries.

[0003] In today’s digital age, multi-person to multi-software agent interactions are becoming increasingly common. From virtual assistants to customer service chatbots, humans are interacting with agents more frequently than ever before. However, these interactions often lack the emotional depth and nuance of human-to-human interactions, leading to a range of negative outcomes such as reduced satisfaction, increased frustration, and even anger. Furthermore, these interactions can also have a profound impact on human emotions and feelings, leading to a negative cycle of emotional contagion.

[0004] Current techniques for software agent-human interaction focus on accurately and correctly responding to human queries, but do not focus on improving the emotional depth and nuance of the interaction. As a result, these techniques do not address the problem of promoting positive emotional contagion in multi-person to multi-software agent interactions. Summary of the invention

[0005] An illustrative embodiment provides an intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions. The embodiment includes sensing interactions between a software agent and multiple people, and in response to the sensed interactions, calculating emotional patterns in an emotional pattern observation component based on the sensed interactions. The embodiment also includes calculating popular emotional patterns in an emotional pattern grouping component based on the emotional patterns. The embodiment also includes deciding to adjust the response of the software agent based on the popular emotional patterns by the agent interaction orchestration component to influence at least one of the multiple people toward the popular emotional pattern, the decision also including training a text generation component to generate a text sequence based on the response, wherein the software agent emits the text sequence, and the sensed interactions between the software agent and the multiple people are updated with the text sequence. Other embodiments of this aspect include corresponding computer systems, devices, and computer programs recorded on one or more computer storage devices, each of which is configured to perform the actions of the embodiment.

[0006] Embodiments include a computer usable program product. The computer usable program product includes a computer readable storage medium and program instructions stored on the storage medium.

[0007] Embodiments include a computer system. The computer system includes a processor, a computer-readable memory and a computer-readable storage medium, and program instructions stored on the storage medium for execution by the processor via the memory. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The novel features which are believed to be characteristic of the invention are set forth in the appended claims. However, the invention itself, together with its preferred mode of use, further objects and advantages, will be best understood by reference to the following detailed description of illustrative embodiments when read in conjunction with the accompanying drawings, in which:

[0009] Figure 1 depicts a block diagram of a computing environment according to an illustrative embodiment;

[0010] Figure 2 is a diagram according to an illustrative embodiment;

[0011] Figure 3 depicts a component diagram according to an illustrative embodiment;

[0012] Figure 4 depicts a component diagram according to an illustrative embodiment;

[0013] Figure 5 depicts a component diagram according to an illustrative embodiment;

[0014] Figure 6 depicts a component diagram according to an illustrative embodiment;

[0015] Figure 7 depicts a component diagram according to an illustrative embodiment;

[0016] Figure 8 depicts a system diagram according to an illustrative embodiment; and

[0017] Fig. 9 A flowchart of an example on-demand process is depicted in accordance with an illustrative embodiment. DETAILED DESCRIPTION

[0018] In today's digital age, multi-person to multi-software agent interactions (such as multi-user environments containing two or more human users of the technology) are becoming increasingly common. From virtual assistants to customer service chatbots, humans are interacting with software agents more frequently than ever before. However, these interactions often lack the emotional depth and nuance of human-to-human interactions, leading to a range of negative outcomes, such as reduced satisfaction, increased frustration, and even anger. In addition, these interactions can also have a profound impact on human emotions and moods, leading to a negative cycle of emotional contagion.

[0019] Current techniques for software agent-human interaction focus on accurately and correctly responding to human queries, but do not focus on improving the emotional depth and nuance of the interaction. As a result, these techniques do not address the problem of promoting positive emotional contagion in multi-person to multi-software agent interactions.

[0020] The present disclosure addresses the above-mentioned deficiencies by providing a method, machine-readable medium, and system for an intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions. The embodiments described herein describe sensing interactions between a software agent and multiple people, and in response to the sensed interactions, calculating emotional patterns in an emotional pattern observation component based on the sensed interactions. The embodiments also include calculating popular emotional patterns in an emotional pattern grouping component based on the emotional patterns. The embodiments also include deciding, by an agent interaction orchestration component based on the popular emotional patterns, to adjust the response of the software agent to influence at least one of the multiple people toward the popular emotional pattern, the decision also including training a text generation component to generate a text sequence based on the response, wherein the software agent emits the text sequence, and the sensed interactions between the software agent and the multiple people are updated with the text sequence.

[0021] Illustrative embodiments include where deciding, by the agent interaction orchestration component, further comprises inputting a prompt into a machine learning model, where the prompt is based in part on a popular sentiment pattern.

[0022] Illustrative embodiments include where calculating popular emotional patterns in the emotional pattern grouping component further includes sensing intensity and duration of the emotional patterns.

[0023] Illustrative embodiments include where calculating the emotion pattern in the emotion pattern observation component includes sensing mood and emotion from the sensed interaction.

[0024] Illustrative embodiments include where calculating popular sentiment patterns in the sentiment pattern grouping component includes executing a clustering algorithm.

[0025] Illustrative embodiments include where the text generation component includes a sequence-to-sequence model.

[0026] The illustrative embodiments also include where the agent interaction orchestration component includes a feedback loop based in part on the emotion patterns and the sensed interactions.

[0027] For the sake of clarity of description, and without implying any limitation thereto, some example configurations are used to describe the illustrative embodiments. In light of this disclosure, those of ordinary skill in the art will be able to envision many changes, adjustments, and modifications of the described configurations to achieve the described purposes, and the same changes, adjustments, and modifications are expected within the scope of the illustrative embodiments.

[0028] In addition, simplified diagrams of data processing environments are used in the drawings and illustrative embodiments. In an actual computing environment, additional structures or components not shown or described herein, or structures or components different from the structures or components shown but having similar functions as described herein, may exist without departing from the scope of the illustrative embodiments.

[0029] Furthermore, the illustrative embodiments are described with respect to specific actual or hypothetical components only as examples. Any particular representation of these and other similar artifacts is not intended to limit the present invention. Any suitable representation of these and other similar artifacts may be selected within the scope of the illustrative embodiments.

[0030] The embodiments in this disclosure are only for clarity of description and are not limited to the illustrative embodiments. Any advantages listed herein are only examples and are not intended to limit the illustrative embodiments. Additional or different advantages can be achieved by specific illustrative embodiments. In addition, specific illustrative embodiments may have some, all or none of the advantages listed above.

[0031] Furthermore, the illustrative embodiments may be implemented with respect to any type of data, data source, or access to a data source over a data network. Any type of data storage device may provide data to embodiments of the present invention locally at a data processing system or over a data network within the scope of the present invention. Where embodiments are described using a mobile device, any type of data storage device suitable for use with the mobile device may provide data to such embodiments locally at the mobile device or over a data network within the scope of the illustrative embodiments.

[0032] The illustrative embodiments are described using only specific codes, computer-readable storage media, high-level features, designs, architectures, protocols, layouts, schematics, and tools as examples, and are not limited to the illustrative embodiments. In addition, for the sake of clarity of description, only specific software, tools, and data processing environments are used as examples to describe the illustrative embodiments in some instances. The illustrative embodiments can be used in combination with other comparable or similar purpose structures, systems, applications, or architectures. For example, within the scope of the present invention, other comparable mobile devices, structures, systems, applications, or architectures can be used in combination with such embodiments of the present invention. The illustrative embodiments can be implemented with hardware, software, or a combination thereof.

[0033] The embodiments in this disclosure are only for clarity of description and are not limited to the illustrative embodiments. Additional data, operations, actions, tasks, activities, and manipulations can be envisioned from this disclosure and can be envisioned within the scope of the illustrative embodiments.

[0034] Various aspects of the present disclosure are described by narrative text, flow charts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. With respect to any flow chart, depending on the technology involved, the operations may be performed in an order different from the order shown in a given flow chart. For example, again depending on the technology involved, two operations shown in consecutive flow chart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in a manner that at least partially overlaps in time.

[0035] Computer program product embodiments ("CPP embodiments" or "CPP") are terms used in this disclosure to describe any collection of one or more storage media (also referred to as "media") collectively included in a collection of one or more storage devices that collectively include machine-readable code corresponding to instructions and / or data for performing the computer operations specified in a given CPP claim. A "storage device" is any tangible device that can retain and store instructions for use by a computer processor. Without limitation, a computer-readable storage medium may be an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the foregoing. Some known types of storage devices that include these media include: magnetic disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), compact disk read-only memories (CD-ROM), digital versatile disks (DVD), memory sticks, floppy disks, mechanical encoding devices (such as punch cards or pits / ridges formed in a major surface of a disk), or any suitable combination of the foregoing. As the term is used in this disclosure, computer-readable storage media should not be construed as storage in the form of transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, light pulses through fiber-optic cables, electrical signals transmitted through wires, and / or other transmission media. As will be appreciated by those skilled in the art, data is typically moved at some occasional point in time during the normal operation of the storage device, such as during access, defragmentation, or garbage collection, but this does not make the storage device transient because the data is not transient when stored.

[0036] refer to Figure 1, which depicts a block diagram of a computing environment 100. The data center environment 100 includes an example of an environment for executing at least some of the computer codes involved in executing the methods of the present invention, such as an application module 200 that provides an intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions. In addition to the box 200, the computing environment 100 includes, for example, a computer 101, a wide area network (WAN) 102, an end-user device (EUD) 103, a remote server 104, a public cloud 105, and a private cloud 106. In this embodiment, the computer 101 includes a processor set 110 (including a processing circuit 120 and a cache 121), a communication structure 111, a volatile memory 112, a persistent storage device 113 (including an operating system 122 and the box 200, as described above), a peripheral device set 114 (including a user interface (UI) device set 123, a storage device 124, and an Internet of Things (IoT) sensor set 125) and a network module 115. The remote server 104 includes a remote database 130. The public cloud 105 includes a gateway 140 , a cloud orchestration module 141 , a host physical machine set 142 , a virtual machine set 143 , and a container set 144 .

[0037] Computer 101 may take the form of a desktop computer, laptop computer, tablet computer, smart phone, smart watch or other wearable computer, mainframe computer, quantum computer, or any other form of computer or mobile device now known or to be developed in the future that is capable of running programs, accessing a network, or querying a database (such as remote database 130). As is well understood in the field of computer technology, and depending on the technology, the execution of the computer-implemented method may be distributed among multiple computers and / or among multiple locations. On the other hand, in this presentation of computing environment 100, the detailed discussion focuses on a single computer (specifically, computer 101) to keep the presentation as simple as possible. Computer 101 may be located in the cloud, even if it is not in the cloud. Figure 1 On the other hand, except to any extent that may be indicated with certainty, computer 101 need not be in the cloud.

[0038] Processor set 110 includes one or more computer processors of any type now known or developed in the future. Processing circuit 120 can be distributed over multiple packages (e.g., multiple co-integrated circuit chips). Processing circuit 120 can implement multiple processor threads and / or multiple processor cores. Cache 121 is a memory located in (one or more) processor chip packages, and is typically used for data or code that should be available for quick access by threads or cores running on processor set 110. Cache memory is typically organized into multiple levels based on relative proximity to the processing circuit. Alternatively, some or all of the caches for the processor set may be located "off chip". In some computing environments, processor set 110 may be designed to work with quantum bits and perform quantum computing.

[0039] Computer-readable program instructions are typically loaded onto the computer 101 to cause the processor set 110 of the computer 101 to perform a series of operating steps to implement a computer-implemented method, such that the instructions so executed will instantiate the method specified in the flowchart and / or narrative description of the computer-implemented method included in this document (collectively referred to as the "inventive method"). These computer-readable program instructions are stored in various types of computer-readable storage media, such as cache 121 and other storage media discussed below. The program instructions and associated data are accessed by the processor set 110 to control and direct the execution of the inventive method. In the computing environment 100, at least some of the instructions for performing the inventive method may be stored in the persistent storage device 113 in the box 200.

[0040] Communications fabric 111 is the signaling pathways that allow the various components of computer 101 to communicate with each other. Typically, the fabric is made of switches and conductive pathways, such as those that make up a bus, a bridge, physical input / output ports, etc. Other types of signal communication pathways may be used, such as fiber optic communication pathways and / or wireless communication pathways.

[0041] The volatile memory 112 is any type of volatile memory now known or developed in the future. Examples include dynamic type random access memory (RAM) or static type RAM. Typically, the volatile memory 112 is characterized by random access, but this is not required unless explicitly indicated. In the computer 101, the volatile memory 112 is located in a single package and is internal to the computer 101, but alternatively or additionally, the volatile memory can be distributed over multiple packages and / or located externally relative to the computer 101.

[0042] Persistent storage 113 is any form of non-volatile storage for computers known now or to be developed in the future. The non-volatility of the storage means that the stored data is maintained regardless of whether power is supplied to computer 101 and / or directly to permanent storage 113. Persistent storage 113 may be a read-only memory (ROM), but typically at least a portion of the persistent storage allows data to be written, deleted, and rewritten. Some common forms of persistent storage include disks and solid-state storage devices. Operating system 122 may take several forms, such as various known proprietary operating systems or open source portable operating system interface type operating systems using a kernel. The code included in frame 200 typically includes at least some of the computer codes involved in executing the method of the present invention.

[0043] The peripheral device set 114 includes a collection of peripheral devices of the computer 101. The data communication connection between the peripheral devices and other components of the computer 101 can be implemented in various ways, such as a Bluetooth connection, a near field communication (NFC) connection, a connection by a cable (such as a universal serial bus (USB) type cable), a plug-in type connection (e.g., a secure digital (SD) card), a connection through a local area network, and even a connection through a wide area network (such as the Internet). In various embodiments, the UI device set 123 may include components such as display screens, speakers, microphones, wearable devices (such as goggles and smart watches), keyboards, mice, printers, touchpads, game controllers, and tactile devices. The storage device 124 is an external storage device (such as an external hard drive) or a pluggable storage device (such as an SD card). The storage device 124 can be persistent and / or volatile. In some embodiments, the storage device 124 can take the form of a quantum computing storage device for storing data in the form of quantum bits. In embodiments where the computer 101 needs to have a large amount of storage (e.g., where the computer 101 locally stores and manages a large database), the storage may be provided by a peripheral storage device designed to store very large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. The IoT sensor set 125 consists of sensors that can be used in IoT applications. For example, one sensor may be a thermometer, while another sensor may be a motion detector.

[0044] The network module 115 is a collection of computer software, hardware, and firmware that allows the computer 101 to communicate with other computers via the WAN 102. The network module 115 may include hardware such as a modem or a Wi-Fi signal transceiver, software for packetizing and / or depacketizing data for communication network transmission, and / or web browser software for transmitting data via the Internet. In some embodiments, the network control function and the network forwarding function of the network module 115 are executed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing software defined networks (SDN)), the control function and the forwarding function of the network module 115 are executed on physically separated devices, so that the control function manages several different network hardware devices. Computer-readable program instructions for executing the method of the present invention can typically be downloaded to the computer 101 from an external computer or an external storage device via a network adapter card or a network interface included in the network module 115.

[0045] WAN 102 is any wide area network (e.g., the Internet) capable of transmitting computer data over non-local distances by any technology now known or to be developed in the future for transmitting computer data. In some embodiments, WAN 1012 may be replaced and / or supplemented by a local area network (LAN) designed to transmit data between devices located in a local area (such as a Wi-Fi network). WANs and / or LANs typically include computer hardware such as copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and edge servers.

[0046] End-user device (EUD) 103 is any computer system used and controlled by an end-user (e.g., a customer of an enterprise operating computer 101), and may take any of the forms discussed above in connection with computer 101. EUD 103 typically receives helpful and useful data from the operation of computer 101. For example, in the hypothetical case where computer 101 is designed to provide recommendations to an end-user, the recommendations would typically be transmitted from network module 115 of computer 101 to EUD 103 via WAN 102. In this manner, EUD 103 may display or otherwise present the recommendations to the end-user. In some embodiments, EUD 103 may be a client device, such as a thin client, a heavy client, a mainframe computer, a desktop computer, or the like.

[0047] Remote server 104 is any computer system that provides at least some data and / or functionality to computer 101. Remote server 104 may be controlled and used by the same entity that operates computer 101. Remote server 104 represents a machine(s) that collects and stores helpful and useful data for use by other computers, such as computer 101. For example, in the hypothetical case where computer 101 is designed and programmed to provide recommendations based on historical data, the historical data may be provided to computer 101 from remote database 130 of remote server 104.

[0048] The public cloud 105 is any computer system available to multiple entities that provides on-demand availability of computer system resources and / or other computer capabilities, particularly data storage (cloud storage) and computing capabilities, without direct active management by users. Cloud computing typically utilizes the sharing of resources to achieve consistency and economy of scale. The direct and active management of the computing resources of the public cloud 105 is performed by the computer hardware and / or software of the cloud orchestration module 141. The computing resources provided by the public cloud 105 are typically implemented by virtual computing environments running on various computers that constitute the host physical machine set 142, which is the totality of physical computers in and / or available to the public cloud 105. Virtual computing environments (VCEs) are typically in the form of virtual machines from a virtual machine set 143 and / or containers from a container set 144. It should be understood that these VCEs can be stored as images and can be transferred between various physical machine hosts as images or after instantiation of the VCEs. Cloud orchestration module 141 manages the transfer and storage of images, deploys new instantiations of VCEs, and manages active instantiations of VCE deployments. Gateway 140 is a collection of computer software, hardware, and firmware that allows public cloud 105 to communicate over WAN 102 .

[0049] Some further explanation of virtualized computing environments (VCEs) will now be provided. A VCE can be stored as an "image". A new active instance of a VCE can be instantiated from an image. Two common types of VCEs are virtual machines and containers. Containers are VCEs that use operating system-level virtualization. This refers to an operating system feature in which the kernel allows the existence of multiple isolated user space instances called containers. From the perspective of the programs running in them, these isolated user space instances typically behave like real computers. Computer programs running on a normal operating system can utilize all the resources of the computer, such as connected devices, files and folders, network shares, CPU capabilities, and quantifiable hardware capabilities. However, programs running within a container can only use the contents of the container and the devices assigned to the container, a feature called containerization.

[0050] The private cloud 106 is similar to the public cloud 105, except that the computing resources are only available to a single enterprise. Although the private cloud 106 is depicted as communicating with the WAN 102, in other embodiments, the private cloud can be completely disconnected from the Internet and accessible only through a local / private network. A hybrid cloud is a combination of multiple clouds of different types (e.g., private, community, or public cloud types), typically implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technologies that enable orchestration, management, and / or data / application portability between the multiple constituent clouds. In this embodiment, both the public cloud 105 and the private cloud 106 are part of a larger hybrid cloud.

[0051] Metered Services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, reported, and invoiced, providing transparency to both providers and consumers of the utilized services.

[0052] Process software: An intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions is shared, serving multiple clients simultaneously in a flexible, automated manner. It is standardized, requiring little customization, and it is scalable, providing capacity on demand in a pay-as-you-go model.

[0053] The process software may be stored on a shared file system accessible from one or more servers. The process software is executed via transactions containing data and server processing requests that use CPU units on the accessed servers. CPU units are units of time on the central processing unit of a server, such as minutes, seconds, and hours. In addition, the accessed server may issue requests to other servers that require CPU units. CPU units are an example and represent only one usage metric. Other usage metrics include, but are not limited to, network bandwidth, memory usage, storage usage, packet transfers, complete transactions, etc.

[0054] When multiple customers use the same process software application, their transactions are distinguished by parameters included in the transaction that identify the unique customer and the type of service for that customer. All CPU units and other usage metrics for each customer's service are recorded. When the number of transactions to any one server reaches a number that begins to affect the performance of that server, other servers are accessed to increase capacity and share the workload. Similarly, when other usage metrics (such as network bandwidth, memory usage, storage usage, etc.) approach capacity so as to affect performance, additional network bandwidth, memory usage, storage, etc. are added to share the workload.

[0055] The usage metrics for each service and customer are sent to a collection server which sums the usage metrics for each customer for each service that is processed anywhere in the network of servers providing shared execution of the process software. The summed usage metric units are periodically multiplied by the unit cost, and the resulting total process software application service cost is alternatively sent to the customer and / or indicated on a website accessed by the customer, who can then remit payment to the service provider.

[0056] In another embodiment, the service provider requests payment directly from the customer's account at a bank or financial institution.

[0057] In another embodiment, if the service provider is also a customer of the customer using the process software application, the amounts owed to the service provider are reconciled with the amounts owed by the service provider to minimize the transfer of payments.

[0058] Figure 2 A diagram 200 is depicted in accordance with an illustrative embodiment. In certain embodiments, the diagram 200 represents Figure 1 Various aspects of application 200.

[0059] In the illustrated embodiment, a software agent 206 interacts 204 with multiple human users 202. In embodiments, the interactions may be between multiple software agents and multiple people, including software agent to agent or human to human interactions. Some embodiments are described as the following use cases:

[0060]

[0061]

[0062] Figure 3 A component diagram 300 is depicted in accordance with an illustrative embodiment. In certain embodiments, component 300 represents Figure 1 Various aspects of application 200.

[0063] In the illustrated embodiment, the emotion pattern observation component 302 uses natural language techniques and algorithms such as SVM to observe and classify emotion patterns. The emotion pattern observation component 302 inputs the emotion patterns into the emotion pattern grouping component 304, which groups the emotion patterns by executing clustering algorithms and decision trees. The emotion pattern grouping component 304 groups the popular emotion patterns and inputs them into the Orchestration of Agent Interactions Component 306, which orchestrates the interactions between software agents and users, trains and executes decision trees, artificial neural networks (ANNs), and reinforcement learning. The Agent Interactions Orchestration Component 306 orchestrates and inputs them into the Text Generation Component 308, which generates text for emotional contagion, including training recurrent neural networks and sequence-to-sequence models, and executing encoder-decoder algorithms.

[0064] Figure 4 A component diagram 400 is depicted in accordance with an illustrative embodiment. In certain embodiments, component 400 represents Figure 1 Various aspects of application 200.

[0065] In the illustrated embodiment, the emotional pattern observation component 302 collects 402 text data from human-agent interactions using an application programming interface (API) or webhooks. The component can use the API to collect text data from social media platforms. Alternatively, the component can use webhooks to collect text data from software agents or virtual assistants. The component pre-processes 404 the collected text data using natural language processing (NLP) techniques such as tokenization, stemming, and lemmatization. Tokenization involves breaking text into individual words or phrases, while stemming and lemmatization involve reducing words to their base forms.

[0066] In some embodiments, emotional patterns can be observed based on the emotions and moods in the sensed text data captured from the interaction. The component uses a machine learning algorithm such as a support vector machine (SVM) to analyze the mood 406 of the preprocessed text data. Mood analysis involves identifying the emotional tone of the text, whether it is positive, negative or neutral. The component uses NLP techniques such as emotional intensity detection to sense the emotions 408 expressed in the text data interaction. Emotional intensity detection involves identifying the intensity of the emotions expressed in the text, such as happiness, sadness, anger or fear. The component classifies the observed emotional patterns 410 into predefined categories based on the intensity and duration of the observed emotional patterns 410. For example, the system can classify emotional patterns as positive, negative or neutral based on the emotions expressed in the text data. The component uses a machine learning algorithm such as a decision tree or ANN to refine the classification of emotional patterns 412. A decision tree involves creating a hierarchy of decisions based on the features of the text data, while an ANN involves creating a network of interconnected nodes to analyze the text data.

[0067] Figure 5 A component diagram 500 is depicted in accordance with an illustrative embodiment. In certain embodiments, component 500 represents Figure 1 Various aspects of application 200.

[0068] In the illustrated embodiment, the emotional pattern grouping component 304 clusters the observed emotional patterns based on the similarity of the observed emotional patterns using a clustering algorithm such as k-means or hierarchical clustering 502. This step helps identify common emotional patterns between humans and agents. The component identifies common emotional patterns between humans and agents based on the clustered emotional patterns 504. This step helps determine the popular emotional patterns in the conversation. The component senses the popular emotional patterns in the conversation based on the intensity and duration of the emotional patterns 506. This step helps identify the dominant emotions expressed in the conversation. The component groups the conversations based on the popular emotional patterns of the conversations 508. This step helps organize the conversations into categories based on the emotional tone of the conversations. The component also uses a machine learning algorithm (such as a decision tree or ANN) to refine the grouping of conversations based on the similarity of the conversations 510. This step helps improve the accuracy of the grouping and ensure that similar conversations are grouped together. The component also classifies the grouped conversations into predefined categories 512 based on the intensity and duration of the grouped conversations. This step helps classify the conversations into specific emotional states, such as positive, negative, or neutral.

[0069] Figure 6 A component diagram 600 is depicted in accordance with an illustrative embodiment. In certain embodiments, component 600 represents Figure 1 Various aspects of application 200.

[0070] In the illustrated embodiment, the agent interaction orchestration component 306 defines predefined emotional patterns 602 based on emotional patterns observed in human-agent conversations. These emotional patterns may include emotions such as happiness, sadness, anger, and fear. The component uses a decision-making algorithm (such as a decision tree or ANN) to orchestrate the interaction between the software agent and the user based on the defined popular emotional patterns 604. The orchestration will be done in real time based on the observed emotional patterns and the desired outcome of the conversation. The component achieves emotional contagion 606 between people and agents by adjusting the conversational style of the agent to influence the human emotions toward the defined popular emotional patterns. This may include using a machine learning model (such as a language model or a sequence-to-sequence model) to generate appropriate responses from the agent. The component promotes real-time interaction 608 between people and agents based on the choreographed interaction. This may include using a network socket for real-time communication between people and agents. The component also creates a feedback loop 610, in which the observed emotional patterns and sensed interactions can be used to refine the orchestration of agent interactions. This may include using a reinforcement learning algorithm to optimize the performance of the orchestration based on real-time feedback. The component also uses machine learning algorithms such as reinforcement learning to optimize the performance of the orchestration 612. This can include using A / B testing or multivariate testing to optimize the conversation flow and improve the overall experience for the user.

[0071] Figure 7 A component diagram 700 is depicted in accordance with an illustrative embodiment. In certain embodiments, component 700 represents Figure 1 Various aspects of application 200.

[0072] In the illustrated embodiment, the text generation component 308 selects a language model 702 (such as a sequence-to-sequence model or a recurrent neural network (RNN)) for generating appropriate textual contacts. Sequence-to-sequence models are preferred because they are able to generate coherent and contextually relevant textual responses. The component trains and fine-tunes the selected language model 704 using a dataset of human-agent conversations and their corresponding emotional patterns. The training process involves optimizing the parameters of the model to maximize the likelihood of generating appropriate textual contacts given the observed emotional patterns and context. The component generates appropriate textual contacts 706 for emotional contagion based on the observed emotional patterns using the trained and fine-tuned language model. The generated textual responses are filtered based on their relevance, coherence, and appropriateness to the context of the conversation. The component also filters the generated textual responses 708 based on the relevance, coherence, and appropriateness of the generated textual responses to the context of the conversation. This involves using NLP techniques (such as mood analysis and emotional intensity detection) to evaluate the effectiveness of the generated textual contacts in inducing the desired emotional patterns in humans. In an embodiment, the generated text is emitted by a software agent, and the sensed interaction is updated with the generated text. This component further continuously improves 710 the language model and text generation capabilities based on user feedback and conversational data. This involves updating the training dataset with new conversation and sentiment patterns, and fine-tuning the language model to better capture the nuances of human communication.

[0073] In another example, consider 3 people conversing with a digital assistant using the following profile distribution from the method emotional pattern grouping component:

[0074] Human 1: chatty, happy, currently in a good mood, very interested in current topic X, seems to understand X, Y, Z.

[0075] Human 2: Shy, happy, nervous or unclear emotions, interested in topic X, understands Y, Z.

[0076] Human 3: Neutral, neutral, currently disengaged, not interested in topic X, aware of Z.

[0077] Human 1 jokes and tries to re-engage Human 3.

[0078] How can digital agents help transmit emotions from Human 1 to Human 3?

[0079] Step 1: Identify the intention of emotional contagion between people

[0080] Considering that the model has been classified (according to the previous method)

[0081] Classify the interaction from Human 1 (telling a joke) as a possible attempt to engage Human 3 and make him happy.

[0082] Step 2: Once the interactions between people are identified, classify the processes that the interactions between people are intended to achieve

[0083] The interaction is a joke or humorous message

[0084] The intention must be to bring joy to neutral / disengaged humans 3.

[0085] Identify the shortcomings of Human 3 in this context -> lack of interest, neutral emotion, etc.

[0086] For example, this can be achieved by prompting the process of engineering based on a combination between rule bases and large AI models:

[0087] ° Meta-prompt: Consider there are two people interacting through this channel. Human 1 is {defined profile}.

[0088] Human 3 is a {defined profile}. Human 1 makes a joke about X, designed to motivate and engage Human 3.

[0089] ° Hint: What possible shortcomings of Human 3 are Human 1 trying to address?

[0090] Answer: {Disadvantages of inference}

[0091] Step 3: Identify possible interactions that the digital assistant can inject into the conversation to support Human1-Human3 contagion.

[0092] This can be achieved through a process of prompt engineering based on a combination of rule bases and large AI models:

[0093] ° Meta-prompt: Consider there are two people interacting via this channel. Human 1 is {defined profile}. Human 3 is {defined profile}. Human 1 makes a joke about X, intended to motivate and engage Human 3.

[0094] ° Consider the shortcomings of Human 3 that Human 1 is trying to address {inferred shortcomings}.

[0095] ° Tips: What possible interactions can digital assistants inject into conversations to support human1-human3 contagion.

[0096] Answer: {Inferred Interaction}

[0097] Step 4: Convert the proposed interactions into action plans for interactions P1, P2, P3

[0098] • This can be achieved through a rule-based system to convert the proposed actions into regular action sequences.

[0099] Step 5: Verify P1, P2, P3 as interactions with human X

[0100] • This can be achieved through a rule-based system to validate the human-X interaction P* taking into account profile, context, etc.

[0101] Step 6: Convert P* into a conversational interaction uttered by the digital assistant and presented to human-X

[0102] This can be achieved by a Large Language Model (LLM) using the above meta-cues and the hint about “converting P1 to human 3’s dialogue sentence in the current context”.

[0103] Step 7: Feedback Loop:

[0104] Changes in sentiment patterns observed after the interaction to refine the orchestration rules applied in the above steps.

[0105] This can include using reinforcement learning algorithms to optimize the performance of the orchestration based on real-time feedback.

[0106] Figure 8 A system diagram 800 is depicted in accordance with an illustrative embodiment. In certain embodiments, components 800 represent Figure 1 Various aspects of application 200.

[0107] In the illustrated embodiment, a computer system 802 including a processor 812 executes an emotion pattern observation component 804 , an emotion pattern grouping component 806 , an agent interaction orchestration component 808 , and a text generation component 810 .

[0108] Fig. 9 A flowchart of an example on-demand process is depicted in accordance with an illustrative embodiment.

[0109] Step 940 begins the on-demand process. A transaction is created (941) containing a unique client identification, the type of service requested, and any service parameters that further specify the type of service. The transaction is then sent to the primary server (942). In an on-demand environment, the primary server may initially be the only server, and then as capacity is consumed, other servers are added to the on-demand environment.

[0110] The central processing unit (CPU) capacity of the servers in the on-demand environment is queried (943). The CPU requirement of the transaction is estimated, and then the available CPU capacity of the servers in the on-demand environment is compared with the transaction CPU requirement to see if there is sufficient CPU available capacity in any server to process the transaction (944). If there is not sufficient server CPU available capacity, additional server CPU capacity is allocated to process the transaction (948). If there is sufficient available CPU capacity, the transaction is sent to the selected server (945).

[0111] Prior to executing the transaction, the remaining on-demand environment is checked to determine if the environment has sufficient available capacity to process the transaction. The environment capacity includes, for example, but not limited to, network bandwidth, processor memory, storage, etc. (946). If there is not enough available capacity, capacity is added to the on-demand environment (947). Next, the software required to process the transaction is accessed, loaded into memory, and the transaction is executed (949).

[0112] The usage metrics are recorded (950). The usage metrics consist of the portion of those functions in the on-demand environment used to process the transaction. What is recorded is the use of functions such as, but not limited to, network bandwidth, processor memory, storage, and CPU cycles. The usage metrics are summed, multiplied by the unit cost, and then recorded as a charge to the requesting customer (951).

[0113] If the customer has requested that the On Demand charges be posted to the website (952), they are posted to the website (953). If the customer has requested that the On Demand charges be sent to the customer address via email (954), the On Demand charges are sent (955). If the customer has requested that the On Demand charges be paid directly from the customer account (956), payment is received directly from the customer account (957). The On Demand process proceeds to 958 and exits.

[0114] Although it should be understood that the process software of the intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions can be deployed by manually loading the process software directly into the client, server, and agent computers via a storage medium such as a CD, DVD, etc., the process software can also be automatically or semi-automatically deployed to the computer system by sending the process software to a central server or a group of central servers. The process software is then downloaded to the client computer that will execute the process software. Alternatively, the process software is sent directly to the client system via email. Then, the process software is separated into a directory or loaded into a directory by executing a set of program instructions that separate the process software into a directory. Another option is to send the process software directly to a directory on the client computer hard drive. When there is a proxy server, the process will select the proxy server code, determine which computers to place the proxy server code on, send the proxy server code, and then install the proxy server code on the agent computer. The process software will be sent to the proxy server and then stored on the proxy server.

[0115] introduction

[0116] • Loading the process software directly onto client, server and agent computers by loading storage media such as CDs, DVDs, etc.

[0117] Automatically or semi-automatically deploy the process software to computer systems by sending the process software to a central server or a group of central servers. The process software is then downloaded to client computers that will execute the process software.

[0118] • Sending the process software directly to the client system via email. The process software is then separated into a directory or loaded into a directory by executing a set of program instructions that separate the process software into the directory.

[0119] · Send the process software directly to a directory on the client computer's hard drive.

[0120] When a proxy server is present, the process will select the proxy server code, determine on which computers to place the proxy server code, send the proxy server code, and then install the proxy server code on the proxy computer. The process software will be sent to the proxy server, and then the process software will be stored on the proxy server.

[0121] General Description

[0122] Although it should be understood that the process software of the intelligent orchestration system for emotional contagion in multi-person to multi-agent interactions can be deployed by manually loading the process software directly into the client, server, and agent computers via a storage medium such as a CD, DVD, etc., the process software can also be automatically or semi-automatically deployed to the computer system by sending the process software to a central server or a group of central servers. The process software is then downloaded to the client computer that will execute the process software. Alternatively, the process software is sent directly to the client system via email. Then, the process software is separated into a directory or loaded into a directory by executing a set of program instructions that separate the process software into a directory. Another option is to send the process software directly to a directory on the client computer hard drive. When there is a proxy server, the process will select the proxy server code, determine which computers to place the proxy server code on, send the proxy server code, and then install the proxy server code on the agent computer. The process software will be sent to the proxy server, and then the process software will be stored on the proxy server.

[0123] The following definitions and abbreviations are used to interpret the claims and specification. As used herein, the terms "comprises," "comprising," "includes," "including," "has," "having," "contains," or "containing," or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus that includes a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such composition, mixture, process, method, article, or apparatus.

[0124] Additionally, the term "illustrative" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or design described herein as "illustrative" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. The terms "at least one" and "one or more" should be understood to include any integer greater than or equal to one, i.e., one, two, three, four, etc. The term "plurality" is understood to include any integer greater than or equal to 2, i.e., two, three, four, five, etc. The term "connected" may include both indirect "connected" and direct "connected."

[0125] References in the specification to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but each embodiment may or may not include the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.

[0126] The terms "about," "substantially," "approximately," and variations thereof are intended to include the degree of error associated with the measurement of a particular quantity based on the equipment available at the time the application was filed. For example, "about" may include a range of ±8% or 5% or 2% of a given value.

[0127] The description of various embodiments of the present invention has been presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications, or technical improvements over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments described herein.

[0128] The description of various embodiments of the present invention has been presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications, or technical improvements over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments described herein.

[0129] Thus, in the illustrative embodiments, computer-implemented methods, systems or apparatuses, and computer program products for managing participation and other related features, functions or operations in online communities are provided. Where embodiments or portions thereof are described with respect to one type of device, the computer-implemented methods, systems or apparatuses, computer program products, or portions thereof are adapted or configured for use with appropriate and comparable manifestations of that type of device.

[0130] Where embodiments are described as being implemented in an application, delivery of the application in a Software as a Service (SaaS) model is contemplated within the scope of the illustrative embodiments. In the SaaS model, the ability to implement the application of the embodiments is provided to the user by executing the application in a cloud infrastructure. The user can access the application using a variety of client devices through a thin client interface such as a web browser (e.g., web-based email) or other lightweight client applications. The user does not manage or control the underlying cloud infrastructure, including the network, servers, operating system, or storage of the cloud infrastructure. In some cases, the user may not even manage or control the capabilities of the SaaS application. In some other cases, the SaaS implementation of the application may allow limited possible exceptions to user-specific application configuration settings.

[0131] Embodiments of the present invention may also be delivered as part of a service engagement with a client company, non-profit organization, government entity, internal organizational structure, etc. Aspects of these embodiments may include configuring a computer system to execute and deploy software, hardware, and web services that implement some or all of the methods described herein. Aspects of these embodiments may also include analyzing the operation of the client, creating recommendations in response to the analysis, building a system that implements the recommended parts, integrating the system into existing processes and infrastructure, metering the use of the system, allocating fees to users of the system, and billing for the use of the system. Although the above-mentioned embodiments of the present invention are described by stating their respective advantages, the present invention is not limited to their specific combinations. On the contrary, these embodiments may also be combined in any manner and quantity according to the intended deployment of the present invention without losing their beneficial effects.

Claims

1. A computer-implemented method comprising: sensing interactions between the software agent and the plurality of persons, and in response to the sensed interactions, calculating in an emotion pattern observation component an emotion pattern based on the sensed interactions; calculating a popular emotion pattern in an emotion pattern grouping component based on the emotion pattern; as well as Determining, by an agent interaction orchestration component based on the popular emotional pattern, to adjust a response of the software agent to influence at least one of the plurality of persons toward the popular emotional pattern, the determining further comprising: A text generation component is trained to generate a text sequence based on the responses, wherein the software agent utters the text sequence and the sensed interactions between the software agent and the plurality of people are updated with the text sequence.

2. The computer-implemented method of claim 1 , wherein deciding, by the agent interaction orchestration component, further comprises inputting a prompt into a machine learning model, wherein the prompt is based in part on the popular sentiment pattern. 3 . The computer-implemented method of claim 1 , wherein calculating the popular emotional patterns in the emotional pattern grouping component further comprises sensing intensity and duration of the emotional patterns. 4 . The computer-implemented method of claim 1 , wherein calculating the emotional pattern in the emotional pattern observation component comprises sensing mood and emotion from the sensed interactions. 5 . The computer-implemented method of claim 1 , wherein calculating the popular sentiment patterns in the sentiment pattern grouping component comprises executing a clustering algorithm.

6. The computer-implemented method of claim 1, wherein the text generation component comprises a sequence-to-sequence model.

7. The computer-implemented method of claim 1, wherein an agent interaction orchestration component comprises a feedback loop based in part on emotion patterns and the sensed interactions.

8. A computer program product comprising program instructions, the program instructions being executable by a processor to cause the processor to perform the method according to any one of claims 1 to 7.

9. A computer system comprising a processor and program instructions, wherein the program instructions are executable by the processor to cause the processor to perform the method according to any one of claims 1 to 7.

Images