Artificial intelligence chatbot system for quarantined people

Abstract

A chatbot system according to an embodiment of the present invention is an artificial intelligence chatbot system for an isolated person comprising a conversation controller that classifies the type of a query sentence and an output unit, wherein the conversation controller comprises an extraction module that extracts the isolated person's query intent and entities through morphological analysis, a type classification module that classifies the type of query using the extracted intent and entities, and an answer module that provides an answer to the isolated person's query based on a knowledge base, and the output unit outputs an answer to the isolated person.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence chatbot system for quarantined individuals, and more specifically, to a chatbot system for prescribing and treating symptomatic patients who are self-quarantining due to COVID-19 or the like. Background Technology

[0002] As the spread of COVID-19 continues, concerns about a downturn in the global IT industry are growing. This is because there are forecasts of a potential recurrence of the global supply chain constraints seen in the first half of the year, centered on Asia including China, and a widening decline in global demand. Although South Korea's IT exports performed relatively well, recording only a 1.2% year-on-year decline through July of this year despite the impact of COVID-19, future improvement cannot be guaranteed due to increasing global uncertainty stemming from the prolonged pandemic and the escalating conflict between the U.S. and China. Meanwhile, positive aspects are also emerging, such as the increase in demand for non-face-to-face and online services and the acceleration of the transition to a digital society.

[0003] As the contactless trend becomes widespread, the global IT industry is expected to see changes in its consumption and competitive product structures. With global companies seeking to stabilize their supply chains, signs of deglobalization and a restructuring of the division of labor are also emerging. Major companies in the U.S., China, and other regions are responding closely to these changes and preparing for the post-COVID market. Competition between Korea and China is projected to expand beyond existing IT product markets into new, promising areas of IT products for the post-COVID era.

[0004] Korea's IT industry must actively utilize the current situation as an opportunity for a new leap forward. Product differentiation and premium leadership are required through continuous innovation to respond to changes in global value chains and IT product structures, as well as the digital era. Furthermore, it is necessary to expand the foundation for the future growth of the domestic IT industry, including fostering downstream industries and building the infrastructure required for the post-COVID-19 era.

[0005] Positive changes resulting from the spread of the novel infectious disease COVID-19 are also emerging. First, as previously observed in the smart home market, online services are becoming more active as non-face-to-face indoor activities, such as remote work and the expansion of remote learning, have significantly increased. While demand for offline consumption is decreasing to avoid the risk of COVID-19 infection, digitalization is being accelerated as non-face-to-face online transactions surge instead.

[0006] For individuals in self-quarantine due to COVID-19 or other reasons, it may be impossible or difficult to speak with a counselor via voice call, making chat-based counseling essential. However, since chatbot-based counseling mostly involves answering questions based on pre-defined scenarios, there is a high likelihood of merely repeating the guidelines provided to patients in self-quarantine, and there is a problem in that it fails to respond in a patient-specific manner to various environments. The problem to be solved

[0007] The objective of the present invention is to provide a chatbot response system that can respond to diseases or symptoms in a customized manner for patients during self-isolation. means of solving the problem

[0008] A chatbot system according to an embodiment of the present invention is an artificial intelligence chatbot system for an isolated person comprising a conversation controller that classifies the type of a query sentence and an output unit, wherein the conversation controller comprises an extraction module that extracts the isolated person's query intent and entities through morphological analysis, a type classification module that classifies the type of query using the extracted intent and entities, and an answer module that provides an answer to the isolated person's query based on a knowledge base, and the output unit outputs an answer to the isolated person.

[0009] As an example, the knowledge base includes a dataset that stores data related to self-quarantine, a scenario DB and a scenario bot for providing answers to questions related to self-quarantine, and a plugin DB that stores call value information of a call consultation AP and an integrated platform.

[0010] As an example, the plugin DB is connected to an external institution's knowledge base that is connected to an external institution's system and can provide answers to the quarantiner's queries.

[0011] As an example, the data set includes a self-quarantine guidance DB that provides guidance information regarding self-quarantine, an FAQ DB that stores questions and answers regarding self-quarantine, a self-quarantine scenario DB that stores questions and answers related to self-quarantine, and a self-quarantine DB that stores information about self-quarantine persons.

[0012] As an example, the type classification module classifies a query into any one type selected from the group consisting of rule bases, scenarios, and plugins.

[0013] As an example, it further includes a knowledge set that generates a list by analyzing and storing classification information of the query content input to the conversation controller, and constructs knowledge data by tagging the data.

[0014] As an example, the knowledge set generates a query intent list by matching the morphemes analyzed in the extraction module with the extracted query intents. Effects of the invention

[0015] According to the artificial intelligence chatbot system for isolated individuals according to an embodiment of the present invention, consultation is possible through chat in situations where voice communication is difficult.

[0016] In addition, customized treatment and diagnosis are possible for those in isolation.

[0017] In addition, counseling tailored to the isolated individual's situation is available. Brief explanation of the drawing

[0018] Figure 1 is an artificial intelligence chatbot processing process according to an embodiment of the present invention. FIG. 2 is a diagram of an interactive artificial intelligence chatbot configuration according to an embodiment of the present invention. Figure 3 is a process for building an interactive artificial intelligence chatbot according to an embodiment of the present invention. Figure 4 is a process for constructing a conversational artificial intelligence chatbot knowledge set according to an embodiment of the present invention. FIG. 5 is a scenario editor prosys and scenario configuration screen according to an embodiment of the present invention. Specific details for implementing the invention

[0019] Specific structural or functional descriptions regarding embodiments according to the concept of the present invention disclosed herein are provided merely for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described herein.

[0020] Embodiments according to the concept of the present invention may be subject to various modifications and may take various forms; therefore, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes all modifications, equivalents, or substitutions that fall within the spirit and scope of the present invention.

[0021] Terms such as "first" or "second" may be used to describe various components, but said components should not be limited by said terms. For the sole purpose of distinguishing one component from another, for example, without departing from the scope of rights according to the concept of the present invention, the first component may be named the second component and similarly the second component may be named the first component.

[0022] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions describing the relationships between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.

[0023] The terms used herein are used merely to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described herein, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0025] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached to this specification. However, the scope of the patent application is not limited or restricted by these embodiments. Identical reference numerals in each drawing indicate identical components.

[0026] FIG. 1 is a conceptual diagram of an artificial intelligence chatbot system for isolated individuals according to an embodiment of the present invention.

[0027] As illustrated in FIG. 1, the AI ​​chatbot system (10) for quarantined individuals receives a query from a quarantined individual (20) via voice or text, and connects with a self-quarantine platform (30) that can provide necessary information to the quarantined individual (20) or help the quarantined individual regarding the query.

[0028] Information reception from external agencies and agency linkage can be made possible by the self-quarantine platform (30) shown in FIG. 1. Of course, the chatbot system (10) can provide its own answers to the questions.

[0029] The chatbot system (10) according to an embodiment of the present invention is a system for providing necessary services to patients or suspected patients for whom self-quarantine due to COVID-19 or the like is essential. Furthermore, beyond the function of a chatbot that simply provides information, it is a system that predicts and monitors the condition of a self-quarantined person through outbound communication, and enables the self-quarantined person to understand their health condition through the content of the query input through the chatbot without having to directly disclose their health condition.

[0030] In addition, as shown in FIG. 1, a system is implemented that is connected to a self-isolation platform (30) so that the self-isolating person (20) can receive measures from an external agency, such as a public health center, a district office, or an emergency rescue center.

[0031] FIG. 2 is a functional block diagram of a chatbot system according to an embodiment of the present invention.

[0032] As illustrated in FIG. 2, a chatbot system (10) according to an embodiment of the present invention includes a conversation controller (100) that classifies the type of a query sentence and an output unit (200) that outputs an answer to an isolated person.

[0033] When a query is input into the conversation controller (100), processing to find an answer to the query begins. That is, when a query is input via voice, the process of converting it into text through STT and classifying and analyzing the sentence through an artificial intelligence-based natural language processing process is performed. Specifically, the natural language processing process is carried out through machine learning algorithms such as the BERT algorithm or GPT-3. Furthermore, the morphemes of the query are analyzed, and the entities and intentions are analyzed to classify the types of queries for providing answers.

[0034] A conversation controller (100) according to an embodiment of the present invention may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device constituting the conversation controller (100) may be described as being used as a single unit, but a person of ordinary knowledge in the art will know that the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. The processing device may include a plurality of processors or a single processor and a single controller. In addition, other processing configurations, such as a parallel processor, are also possible.

[0035] FIG. 3 is a detailed functional block diagram of a conversation controller according to an embodiment of the present invention.

[0036] FIG. 4 is a schematic diagram of the operation of a chatbot system according to an embodiment of the present invention.

[0037] As illustrated in FIG. 3, a conversation controller (100) according to an embodiment of the present invention includes an extraction module (110) that extracts the query intent and entities of an isolator through morphological analysis, a type classification module (120) that classifies the type of query using the extracted intent and entities, and an answer module (130) that provides an answer to the query of an isolator based on a knowledge base.

[0038] The extraction module (110) classifies a predetermined query intent through morphological analysis and extracts a core entity. For example, when a quarantined person who has come into contact with a COVID-19 patient inputs a query through the chatbot system saying, “My body temperature is 38℃. Am I infected with COVID?”, the extraction module (110) checks through morphological analysis which of the predetermined classifications the query intent belongs to: (1) support (medical support, daily necessities support, medicine support, food support, etc.), (2) health check, (3) prescription, (4) emergency, (5) other, and extracts the classification corresponding to (2) health check, and extracts body temperature, 38℃, and COVID as entities.

[0039] The type classification module (120) classifies the type of query into one of the types selected from the group consisting of rule bases, scenarios, and plugins.

[0040] The answer module (130) provides an answer to a query from a knowledge base-based isolator.

[0041] As illustrated in FIG. 4, the chatbot system (10) according to an embodiment of the present invention classifies sentences through natural language processing and analyzes intentions through morphological analysis when a query is input. The chatbot system of the present invention analyzes five classified intentions targeting a person isolated with a disease or suspected disease to which it is applied, and classifies the type of query.

[0042] In particular, the dialogue controller (100) according to an embodiment of the present invention performs a natural language processing process, and the natural language processing undergoes query analysis, morphological analysis, syntactic analysis, named entity analysis, and semantic structure determination processes. The natural language processing process is a process performed through a general and publicly available algorithm, and a detailed description is omitted.

[0043] As illustrated in FIG. 4, the chatbot system (10) according to an embodiment of the present invention merely classifies the type of inquiry and provides an answer to the inquiry, wherein the answer includes not only a text response to the inquiry made by the quarantined person through the chatbot but also all connections with related organizations and instructions.

[0044] In addition, the chatbot system (10) according to an embodiment of the present invention performs the function of generating a reverse query through a conversation controller (100). The conversation controller (100) extracts the query intent and entity through the query of the isolated person (20), and additionally infers the state of the isolated person, that is, not only the physical health state but also the psychological state, and generates a reverse query to the isolated person through the chatbot system (10). In this process, the chatbot system can generate and output a reverse query suitable for the isolated person by detecting signs such as the isolated person’s response time being delayed differently than usual, or by checking for changes in STT conversion time and detecting that a change in speech tone has occurred.

[0045] FIG. 5 is a diagram of an interactive artificial intelligence chatbot configuration according to an embodiment of the present invention.

[0046] In providing answers to inquiries, as previously mentioned, answers are provided based on a knowledge base. As illustrated in FIG. 5, the knowledge base (300) according to an embodiment of the present invention includes a data set (310) that stores data related to self-quarantine, a scenario DB (320) for providing answers to questions related to self-quarantine, and a plugin DB (330) that stores call value information of a scenario bot, a call consultation AP, and an integrated platform.

[0047] The dataset (310) includes a self-quarantine guidance DB that provides guidance information for self-quarantine, an FAQ DB that stores questions and answers regarding self-quarantine, a self-quarantine scenario DB that stores questions and answers related to self-quarantine, and a self-quarantine DB that stores information about self-quarantine persons.

[0048] The scenario DB (320) is a database that stores conversation models, and stores conversation models obtained through deep learning, updates conversation models by utilizing data accumulated through calling information from a dataset or calling a plugin, and creates, updates, and stores conversation models capable of responding to various situations related to self-quarantined individuals.

[0049] The plugin DB (330) is connected to an external organization's knowledge base that can provide answers to the quarantiner's queries by connecting to an external organization's system.

[0050] The plugin DB (330) is connected to the external organization system when a call is made to connect to the conversation model applied to the query, so that it can provide an answer to the query of the isolated person.

[0051] In addition, the plugin DB (330) includes the scenario bot key value DB, call consultation AP key value DB, and integrated platform key value DB as shown in FIG. 5, thereby ensuring accessibility to the database.

[0052] In addition, the conversational AI chatbot can be implemented with a structure as shown in Fig. 5, consisting of a conversation management (DM) module, a knowledge base for each conversation type, deep learning inference learning, and natural language processing (NLP) areas, and is built by linking with the self-quarantine platform system through a plugin DB.

[0053] The artificial intelligence chatbot system (10) according to an embodiment of the present invention implements a conversation processing function that evolves through deep learning-based natural language processing and inference learning.

[0054] The construction of an artificial intelligence chatbot system according to an embodiment of the present invention implements scenario creation and output through planning of chatbot provision scenarios, design of user response scenarios, and design of conversation models, and even after opening, ensures the accuracy of the conversation by adding bot blocks through analysis of conversation logs, etc.

[0055] As explained above, artificial intelligence learning through a knowledge base according to an embodiment of the present invention is performed using chatbot users, statistical periods, scenario utterance updates and conversation logs, conversation statistics, etc.

[0056] Figure 6 is a process for constructing a conversational artificial intelligence chatbot knowledge set according to an embodiment of the present invention.

[0057] The AI ​​chatbot knowledge set is built by collecting basic information by conversation type, such as rule bases, scenarios, and plugins, implementing a standardized dataset, configuring and verifying standard scenarios, applying them, and going through a testing process.

[0058] In particular, a list of query intentions is generated by matching the morphemes analyzed in the aforementioned extraction module with the extracted query intentions.

[0059] The AI ​​chatbot knowledge set creates a list by storing analysis and classification information of the query input into the conversation controller, and builds knowledge data by tagging the data.

[0060] Knowledge data is constructed using source data for the query and the generated query intent list by performing metadata correction, intent information tagging, entity name tagging, glossary (synonym) tagging, and knowledge base tagging, and field-specific knowledge information is built.

[0061] A device constituting an artificial intelligence chatbot system for isolated persons according to an embodiment of the present invention may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component.

[0062] The devices and components described in the embodiments of the present invention may be implemented using one or more general-purpose computers or special-purpose computers, such as a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions.

[0063] Software for operating a chatbot system according to an embodiment of the present invention may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over a networked computer system and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0064] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0065] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0066] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 An AI chatbot system for quarantined individuals comprising a dialogue controller and an output unit for classifying the type of a query sentence, wherein the dialogue controller includes: an extraction module that extracts the quarantined individual's query intent and entities through morphological analysis; a type classification module that classifies the type of query into one type selected from a group consisting of a rule base, a scenario, and a plugin using the extracted intent and entities; an answer module that provides an answer to the quarantined individual's query based on a knowledge base; and a reverse query generation module that extracts the query intent and entities through the quarantined individual's query, infers the quarantined individual's physical health status and psychological state, and generates a reverse query to the quarantined individual, wherein the knowledge base includes a dataset storing data related to self-quarantine; and a scenario DB for providing answers to questions related to self-quarantine. An artificial intelligence chatbot system for quarantined individuals, characterized by including a plugin DB connected to a knowledge base of an external agency that stores call value information of a scenario bot, a call consultation AP, and an integrated platform, and is connected to an external agency system to provide answers according to the quarantined individual's query, wherein the data set includes a self-quarantine guidance DB that provides guidance information regarding self-quarantine; an FAQ DB that stores question and answer information regarding self-quarantine; a self-quarantine scenario DB that stores questions and answers related to self-quarantine; and a self-quarantine DB that stores information about the self-quarantine individual, wherein the output unit outputs answers and reverse queries to the quarantined individual, and the reverse query generation module checks at least one of the quarantined individual's response time delay, change in STT conversion time, or change in tone of voice to detect signs of a change in the quarantined individual's state, and generates and outputs a reverse query suitable for the quarantined individual's state. Claim 2 delete Claim 3 An artificial intelligence chatbot system for quarantined individuals according to claim 1, characterized in that the extraction module classifies the query intent into any one selected from a group consisting of support, health check, prescription, emergency, and others. Claim 4 delete Claim 5 delete Claim 6 An artificial intelligence chatbot system for isolated individuals according to claim 1, further comprising a knowledge set that generates a list by storing analysis and classification information of query content input to the conversation controller and constructs knowledge data by tagging data. Claim 7 An artificial intelligence chatbot system for isolated individuals according to claim 6, characterized in that the knowledge set generates a list of query intentions by matching morphemes analyzed in the extraction module with extracted query intentions.

Images