Method and apparatus for providing digital therapeutics for smoking cessation by using ai chatbot

Abstract

The present invention relates to a method and an apparatus for providing digital therapeutics for smoking cessation. The method for providing digital therapeutics for smoking cessation comprises steps in which a computing device: converses with a participant through an AI-based chatbot; generates a smoking cessation therapeutics scenario for smoking cessation therapeutics of the participant on the basis of chatbot data obtained from the conversation with the chatbot; and provides smoking cessation digital therapeutics content to the participant on the basis of the generated smoking cessation therapeutics scenario.

Description

Method and device for providing digital treatment for smoking cessation using AI chatbot

[0001] The present invention relates to a method and device for providing digital therapy for smoking cessation.

[0002] Smoking has numerous negative health consequences, so various efforts are being made to help people quit smoking at both the individual and societal levels. Quitting smoking through personal willpower alone is not easy. Recently, so-called digital therapeutics (DTx) have been introduced to prevent, manage, and treat disorders and diseases. Attempts are being made to apply digital therapeutics to smoking cessation, and digital therapeutics can be suitable as a smoking cessation treatment because they can foster close communication with users. In particular, the use of AI-based chatbots, which are widely used in various fields, is expected to enhance the effectiveness of digital therapeutics for smoking cessation.

[0003] The matters described in the technical background of this invention are written to enhance understanding of the background of the invention and may include matters that are not already known in the field to which this technology belongs.

[0004] - Prior art document: Republic of Korea Patent Publication No. 10-2566741

[0005] The problem that the present invention seeks to solve is to provide effective digital smoking cessation treatment by conducting continuous conversations with smoking cessation treatment participants using an artificial intelligence chatbot and performing digital smoking cessation treatment based on the conversations.

[0006] The technical problems to be solved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0007] A method for providing a digital treatment for smoking cessation according to an embodiment of the present invention comprises: a step in which a computing device conducts a conversation with a participant through an AI-based chatbot; a step in which the computing device generates a smoking cessation treatment scenario for the participant's smoking cessation treatment based on chatbot data obtained from the conversation with the chatbot; and a step in which the computing device provides smoking cessation digital treatment content to the participant based on the generated smoking cessation treatment scenario.

[0008] The above chatbot may be configured to provide at least one of a small talk function for building intimacy with the participant, a user information collection function for collecting information about the participant, an education schedule coordination function for providing the smoking cessation digital therapy content to the participant according to a designed education schedule, and a daily check function for checking the daily events of the participant.

[0009] A method for providing digital treatment for smoking cessation according to another embodiment of the present invention may further include a step of predicting the likelihood of the participant failing to quit smoking based on the collected data, and a step of performing early intervention in smoking cessation treatment for the participant based on the likelihood of the participant failing to quit smoking by the computing device.

[0010] The collected data may include one or more of biometric data collected through a wearable device worn by the participant, health information data including basic health information of the participant, and chatbot data collected through a conversation with the participant by the chatbot.

[0011] The above prediction of the possibility of failure in quitting smoking can be made by the Catboost model, an AI model.

[0012] A device for providing digital therapy for smoking cessation according to an embodiment of the present invention comprises a memory for storing commands; and a processor configured to execute the commands. The processor performs a smoking cessation digital therapy process, including the steps of conducting a conversation with a participant through an AI-based chatbot, generating a smoking cessation treatment scenario for the participant's smoking cessation treatment based on chatbot data obtained from the conversation by the chatbot, and providing smoking cessation digital therapy content to the participant based on the generated smoking cessation treatment scenario.

[0013] The above smoking cessation digital treatment process may further include a step of predicting the possibility of the participant failing to quit smoking based on the collected data, and a step of performing early intervention in smoking cessation treatment for the participant based on the possibility of failing to quit smoking.

[0014] According to the present invention, it is possible to provide effective digital smoking cessation treatment by conducting continuous conversations with smoking cessation treatment participants using an artificial intelligence chatbot and performing digital smoking cessation treatment based on the conversations.

[0015] In addition, various effects that can be obtained or expected due to embodiments of the present invention are disclosed directly or implicitly in the detailed description of the embodiments of the present invention.

[0016] The accompanying drawings, which are intended to aid in understanding the present invention, provide embodiments of the present invention along with a detailed description. However, the technical features of the present invention are not limited to any specific drawings, and the features disclosed in each drawing may be combined to form new embodiments. The embodiments of the present specification may be better understood by referring to the following description in conjunction with the accompanying drawings, in which similar reference numerals designate identical or functionally similar elements.

[0017] FIG. 1 is a schematic diagram illustrating a device providing digital treatment for smoking cessation according to an embodiment of the present invention.

[0018] FIG. 2 is a diagram showing a smoking cessation treatment server to which a device providing digital treatment for smoking cessation according to an embodiment of the present invention is applied, and a user terminal connected to the smoking cessation treatment server via a communication network.

[0019] FIG. 3 is a diagram showing an example of a conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant, i.e., an initial conversation.

[0020] FIG. 4 is a diagram showing an example of a conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant, i.e., a conversation regarding data collected by a wearable device.

[0021] FIG. 5 is a diagram showing an example of a conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant, i.e., a conversation in a daily check-up situation regarding the participant's situation.

[0022] FIG. 6 illustrates an example of a conversation screen by a chatbot using a device that provides digital treatment for smoking cessation according to an embodiment of the present invention.

[0023] It should be understood that the drawings referenced above are not necessarily drawn to scale and are intended to provide brief representations of various features that illustrate the fundamental principles of the present invention. For example, specific design features of the present invention, including specific dimensions, orientations, positions, and shapes, will be determined in part by the specific intended application and usage environment.

[0024] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the described embodiments.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present invention. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the terms "comprises" and / or "comprising," as used herein, indicate the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. The term "coupled" indicates a physical relationship between two components in which the components are directly connected to one another or are indirectly connected through one or more intervening components.

[0026] When describing components of the present invention, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and the nature, order, or sequence of the components are not limited by the terms. When a component is described as being "connected," "coupled," or "connected" to another component, it should be understood that the component may be directly connected, coupled, or connected to the other component, but that another component may also be "connected," "coupled," or "connected" between each component.

[0027] Figure 1 is a schematic diagram illustrating a device providing digital therapy for smoking cessation according to an embodiment of the present invention. Referring to Figure 1, the device (100) providing digital therapy for smoking cessation can be implemented as a computing device capable of processing, calculating, and storing data.

[0028] A computing device may include at least one of a processor, memory, a user interface input device, a user interface output device, and a storage device that communicate via a bus. The processor may be a central processing unit (CPU) or a semiconductor device that executes instructions stored in the memory or storage device. The processor may be configured to implement the functions and methods described above. The memory and storage device may include various types of volatile or non-volatile storage media. For example, the memory may include read-only memory (ROM) and random access memory (RAM). In embodiments of the present invention, the memory may be located internally or externally to the processor and may be connected to the processor via various known means. The memory of the computing device stores instructions, and the processor is configured to execute the instructions, thereby performing a process for providing a digital treatment for smoking cessation according to an embodiment of the present invention.

[0029] Accordingly, embodiments of the present invention may be implemented as a computer-implemented method or as a non-transitory computer-readable medium storing computer-executable instructions. In embodiments of the present invention, when executed by a processor, the computer-readable instructions may perform a method according to at least one aspect of the present disclosure.

[0030] FIG. 1 illustrates a functional block diagram of a device (100) providing digital treatment for smoking cessation. The device (100) may include a chatbot (110) providing digital treatment. Furthermore, the device (100) may include a scenario management unit (120) for managing digital treatment scenarios, and a chatbot gateway (130) for external communication.

[0031] The chatbot (110) may be designed using AI (artificial intelligence) and may be capable of natural language processing, which analyzes information collected through conversations with users and converts it into a storable form. It may also be designed to generate its own conversation scenarios based on conversations with users, basic scenarios, and scenario generation rules. For example, the chatbot (110) may include a conversation management (111) for managing conversations with users, a natural language processing (112) for natural language processing, a chatbot engine (113), and a plug-in management (114).

[0032] The database (200) may store data for providing digital treatment for smoking cessation. For example, the database (200) may include a corpus dictionary (201), a metadata database (202), an ontology base (KB) (203), a scenario repository (204), and a smoking cessation DTx database (205).

[0033] Referring to FIG. 2, the device (100) providing the above-described digital treatment can be mounted on a smoking cessation digital treatment server (300), and a smoking cessation treatment app control unit (310) for controlling a digital treatment app installed on a user terminal (400) can be installed on the smoking cessation digital treatment server (300). The device (100) providing the digital treatment and the smoking cessation treatment app control unit (310) can communicate with the user terminal (400) via a communication network and perform digital treatment for smoking cessation.

[0034] The digital treatment for smoking cessation according to the present invention provides therapeutic digital program content for improving nicotine addiction disorder based on Cognitive Behavioral Therapy (CBT) and Habit Reversal Training (HRT), representative evidence-based treatments for addiction. CBT emphasizes cognitive function among the three interconnected elements of cognition, emotion, and behavior, and suggests cognitive and behavioral strategies as strategies for changing behavior. Furthermore, to promote smoking cessation through cognitive and behavioral strategies, MET (Motivation Enhancement Therapy) is utilized to provide motivational content in the early stages of treatment. Focusing on a cognitive approach, it modulates interpersonal relationships and motivated behaviors to reduce smoking behavior and increase motivation and participation in healthcare services.

[0035] A method for providing a digital treatment for smoking cessation according to an embodiment of the present invention can be performed by the above-described device (100), and includes a step of introducing a digital treatment and evaluating a participant's motivation stage for smoking cessation, a step of providing motivational reinforcement content to continuously arouse motivation for smoking cessation according to the motivation stage for smoking cessation, a step of differentiating a start module according to a smoking cessation treatment design algorithm and motivation stage and establishing a behavior change plan based on the reinforcement principle, a step of performing cognitive restructuring for dysfunctional thoughts about smoking, and a step of providing training for coping with cravings through relaxation training.

[0036] The method for providing digital treatment for smoking cessation according to the embodiment of the present invention described above can interact with a participant through a smoking cessation treatment app installed on the participant's user terminal (400), and can provide digital treatment for smoking cessation through a process including, for example, a membership registration step, a smoking information input step, a mission performance step, a mission status step, a craving overcoming step, a craving recording step, a craving status step, etc.

[0037] According to an embodiment of the present invention, a conversation with a participant is facilitated through an AI-based chatbot (110), and information collected through the participant's conversation is reflected in smoking cessation treatment. The chatbot (110) performs small talk functions, user information collection functions, training schedule coordination functions, and daily check-in functions.

[0038] Small talk function

[0039] The chatbot (110) is configured to exchange small talk with participants, such as about the weather, time, and light jokes, through the small talk function, thereby forming a sense of intimacy with the participants.

[0040] User information collection function

[0041] The chatbot (110) can collect basic information, such as the participant's age, occupation, health, lifestyle, and smoking habits, through conversation, for example, through questions. The chatbot (110) can incorporate the collected information into the smoking cessation monitoring and treatment process, thereby enabling personalized smoking cessation treatment, enabling optimal smoking cessation treatment tailored to each individual's circumstances.

[0042] Training schedule coordination function

[0043] Based on participant information collected by the chatbot (110), personalized smoking cessation treatment digital therapeutic content and training schedules can be designed and generated. The generated content can be provided to users according to the planned training schedule.

[0044] Daily check function

[0045] Through conversations with participants conducted by a chatbot (110), users' emotional management and smoking cessation status can be tracked. To achieve this, daily conversations with participants allow for regular monitoring of their events, mood, and smoking cessation success. The collected information can be utilized for patient monitoring and personalized smoking cessation treatment.

[0046] Figures 3 to 5 illustrate examples of conversations between a chatbot (110) and a participant. Figure 3 illustrates an example of an initial conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant. Figure 4 illustrates an example of a conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant regarding data collected by a wearable device. Figure 5 illustrates an example of a conversation between a chatbot of a device providing digital treatment for smoking cessation according to an embodiment of the present invention and a participant regarding a daily check-up on the participant's condition.

[0047] As illustrated in Figure 3, the first conversation may include a brief introduction and confirmation of the participant's basic information. At this time, the chatbot (110) may present two or more example responses to facilitate easier responses for the participant, and allow the user to select one or more of the suggested responses.

[0048] Meanwhile, in an embodiment of the present invention, a sensor in the form of a wearable device can be utilized to detect the status of a participant, and as illustrated in FIG. 4, a chatbot (110) can be configured to present information received from a wearable device to a participant and lead a conversation based on the information.

[0049] Referring to Figure 5, in order to check the participant's daily smoking cessation status, the participant's mood, activities, etc. can be checked and a conversation can be conducted to induce the participant's active participation accordingly.

[0050] Conversations between a chatbot (110) and a participant can be conducted through a smoking cessation app installed on the participant's terminal. Figure 6 illustrates an example of a conversation screen displayed on the participant's terminal. Various conversations described above can be conducted through the smoking cessation app.

[0051] The Catboost model can be used to predict smoking cessation failure. The Catboost model is a gradient boosting-based machine learning model that boasts superior performance compared to existing boosting algorithms such as XGBoost and LightGbm. It offers fast learning speed and high predictive power for datasets with a large number of categorical variables. The Catboost model employs a level-wise tree structure using the BFS method. The algorithm starts at a vertex, first exploring all adjacent nodes, and then visits distant vertices later. Furthermore, the Catboost model employs an ordered-boosting structure. It calculates residuals using only a portion of the training data, regenerates the model based on these results, and then uses the model's predictions for the residual data. Random permutation is used to shuffle the training data, preventing the overfitting problem inherent in boosting models. Catboost also employs ordered target encoding, a categorical variable encoding technique. Categorical variables are encoded as the mean of the label data, and one-hot encoding is performed when the set size (cardinality) is low.

[0052] Additionally, according to an embodiment of the present invention, hyperparameter tuning (Optuna) is used to predict smoking cessation failure. Optuna is a framework that automates hyperparameter tuning of ML algorithms. It searches for optimal parameters by changing parameters for each trial by specifying parameter ranges and setting a list.

[0053] According to an embodiment of the present invention, an early intervention algorithm for predicting smoking cessation failure is derived and used. The prediction of smoking cessation failure can be determined based on the identified failure factors and collected data, and if failure is expected, early intervention can be implemented to increase the success of smoking cessation. For example, failure factors can be identified based on the results of questionnaires and assessments (smoking / quitting, amount smoked when smoking, triggers and cravings, nicotine dependence, motivation for change, medication information (medication level, side effects, etc.), and conversational information through chatbot-based small talk, etc.). By applying the smoking cessation failure prediction algorithm, if the probability of smoking cessation failure exceeds a certain level, early intervention can be implemented to support smoking cessation success. Furthermore, if the participant's motivation to quit smoking decreases or a certain level of change occurs in compliance with digital therapeutics, the early intervention algorithm can be implemented.

[0054] According to the present invention, patient data is analyzed to predict the likelihood of smoking cessation failure. For example, patient data may include biometric data collected through wearable devices worn by participants, health information data from external databases containing the participant's basic health information, such as MyData data, and chatbot data collected through a chatbot. Using such patient data, the likelihood of a patient's smoking cessation failure can be predicted.

[0055] According to an embodiment of the present invention, a smoking cessation treatment program can be personalized to an individual based on the participant's biometric information, information collected by a chatbot (110), survey data obtained through a questionnaire, etc., and thereby individualization of a smoking cessation treatment scenario can be achieved according to individual conditions, characteristics, etc. Based on the collected data, patient cluster classification can be performed using k-means clustering, which is an unsupervised learning. K-means clustering is an algorithm that groups data into k clusters, and is a representative clustering technique that groups data with similar characteristics together and clusters them into k clusters.

[0056] According to an embodiment of the present invention, a threshold for a smoking cessation failure prediction value is set, and the smoking cessation failure prediction value is calculated and updated based on collected data such as biometric data and chatbot data. If the smoking cessation failure prediction value exceeds the set threshold, a corresponding smoking cessation treatment, such as a craving scenario, can be executed.

[0057] According to the present invention, AI is utilized to generate and use scenarios in addition to the base smoking cessation treatment scenario. Since the existing base smoking cessation treatment scenario and entities alone are not sufficient to handle all patient conversations, AI learning is utilized to process natural language data and analyze it to automatically construct scenarios. A method for automatically constructing scenarios is implemented that recommends optimal scenarios based on the meaning and context of sentences. By linking a chatbot and an RDBMS, the natural language data collected by the chatbot can be loaded and transferred to AI, automating the process of generating scenarios through natural language processing and analysis.

[0058] The natural language processing process may include preprocessing, document similarity extraction and clustering, and dictionary building with entities and scenarios.

[0059] For preprocessing, the mecab morphological analyzer can be used to separate morphemes from natural language data collected through the chatbot (110). To improve performance, the pykospacing and py-hanspell libraries can be used to verify spelling and spacing. Furthermore, stemming can be used to restore verbs to their original form and stopword processing can be used to remove meaningless words.

[0060] In document similarity extraction and clustering, for example, the Sentence Bert model can be used to extract sentence similarity and question-answer similarity, and then cluster question-answer data.

[0061] In entity and scenario dictionary construction, entity dictionary and scenario dictionary can be constructed based on keywords from clustering data and question-answer data.

[0062] In this regard, if interpretation rules exist, questions or answers in the same cluster can be mapped to questions and answers based on those rules. If interpretation rules are not available, clustering can be performed based on sentence similarity. Since the question or answer is not in the BaseScenario, the chatbot escape block can be executed and the corresponding primary scenario can be re-executed. Natural language without interpretation rules can be loaded into a database, and automatic labeling (clustering classification criteria) can be periodically checked before inputting chatbot response scenarios (chatbot scenario construction).

[0063] The Sentence-Bert model can be used to extract sentence similarity. The Sentence-Bert model fine-tunes the existing Bert model to modestly improve sentence embedding performance. Sentence embedding can be performed using the representation vector of the "CLS" token in the Bert model as a sentence representation, and the vector created by averaging the average representation vector of all Bert words as a sentence representation. For example, parameters can be added by combining the output values ​​of characters with the difference values, and training can be performed toward minimizing the mse of the cosine similarity and the scenario label values.

[0064] Although the embodiments of the present invention have been described above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims also fall within the scope of the present invention.

Claims

1. A method for providing digital treatment for smoking cessation, A step in which a computing device conducts a conversation with a participant through an AI-based chatbot; The step of the computing device generating a smoking cessation treatment scenario for the smoking cessation treatment of the participant based on chatbot data obtained from a conversation with the chatbot; and A method comprising the step of providing smoking cessation digital therapeutic content to the participant based on the generated smoking cessation treatment scenario by the computing device.

2. In paragraph 1, A method wherein the chatbot is configured to provide at least one of a small talk function for forming intimacy with the participant, a user information collection function for collecting information about the participant, an education schedule coordination function for providing the smoking cessation digital therapy content to the participant according to a designed education schedule, and a daily check function for checking the daily events of the participant.

3. In paragraph 1, The step of the computing device predicting the possibility of the participant failing to quit smoking based on the collected data; A method further comprising the step of the computing device performing early intervention in smoking cessation treatment of the participant based on the possibility of failure in smoking cessation.

4. In paragraph 3, A method wherein the collected data includes at least one of biometric data collected through a wearable device worn by the participant, health information data including basic health information of the participant, and chatbot data collected through a conversation with the participant by the chatbot.

5. In paragraph 4, The above prediction of the possibility of failure in quitting smoking is made by the Catboost model, an AI model.

6. In a device providing digital treatment for smoking cessation treatment, memory for storing commands; and comprising a processor configured to execute the above instructions; The above processor is a device that performs a smoking cessation digital treatment process including a step of conducting a conversation with a participant through an AI-based chatbot, a step of generating a smoking cessation treatment scenario for smoking cessation treatment of the participant based on chatbot data obtained from the conversation by the chatbot, and a step of providing smoking cessation digital treatment content to the participant based on the generated smoking cessation treatment scenario.

7. In paragraph 6, The above chatbot is a device configured to provide at least one of a small talk function for forming intimacy with the participant, a user information collection function for collecting information about the participant, an education schedule coordination function for providing the smoking cessation digital therapy content to the participant according to a designed education schedule, and a daily check function for checking the daily events of the participant.

8. In paragraph 6, The above smoking cessation digital treatment process further comprises a step of predicting the possibility of the participant failing to quit smoking based on the collected data, and a step of performing early intervention in smoking cessation treatment for the participant based on the possibility of failing to quit smoking.

9. In paragraph 8, The above collected data is a device including at least one of biometric data collected through a wearable device worn by the participant, health information data including basic health information of the participant, and chatbot data collected through a conversation with the participant by the chatbot.

10. In paragraph 9, The above prediction of the possibility of failure in quitting smoking is made by the Catboost model, an AI model.

Images