Apparatus and method for managing depression in perinatal period

Abstract

The present disclosure relates to an apparatus and a method for managing depression in a perinatal period. The apparatus comprises: a memory that stores at least one instruction for managing depression in a perinatal period; and a processor that performs an operation according to the instruction, wherein the processor analyzes, through a cognitive therapy model, questionnaire information and speech information collected from a terminal of a mother, so as to identify negative thought patterns and emotions of the mother, and evaluates the mental health level of the mother according to the identified negative thought patterns and emotions, the cognitive therapy model learns a trigger keyword related to depression of the mother, and, when a word showing similarity greater than or equal to a preset level with the learned trigger keyword is detected from the questionnaire information or the speech information, the mental health level of the mother can be evaluated according to the analysis result of the detected keyword.

Description

Devices and methods for managing perinatal depression

[0001] The present disclosure relates to a device and method for managing perinatal depression in pregnant women, and more specifically, to a device and method for managing perinatal depression that performs the role of a digital treatment device for perinatal depression for managing the mental health of pregnant women in the perinatal period based on the results of analysis of mental level emotional information and speech information of the pregnant woman.

[0002] Unless otherwise indicated herein, the materials described in this section are not prior art to the claims of this application, and their inclusion in this section is not intended to be admitted as prior art.

[0003] Pregnancy and childbirth bring about numerous physical, emotional, and psychological changes for many women. While the changes that occur during pregnancy and the perinatal period, including childbirth, can sometimes be positive, they can also often be a source of stress and distress. During pregnancy and childbirth, stress increases due to physical and emotional changes, social and economic stress, fear of childbirth, and the burden of childcare, all of which negatively impact the mother's mental health.

[0004] For example, pregnancy brings with it hormonal changes, weight gain, and changes in body shape. These changes can cause pain, discomfort, and sleep problems, which can lead to stress. Furthermore, hormonal changes can trigger mood swings. This can lead to various emotional problems, including anxiety, depression, and a fear of uncertainty, which can be especially severe if a pregnancy has included complications or previous miscarriages. Furthermore, pregnancy and childbirth often bring significant changes to daily life, which can impact financial, professional, and social relationships. Furthermore, the fear and anxiety of the birth itself can contribute significantly to stress. Furthermore, after the birth of a baby, the onset of parenting and the resulting new responsibilities can be stressful. For first-time mothers, the lack of experience can be particularly stressful. Furthermore, the transition to parenthood typically involves changes in self-esteem, a variety of social supports, limited time for personal care, and changes in marital relationships, all of which can cause significant anxiety for expectant mothers.

[0005] According to studies reporting on pregnancy and childbirth-related distress, depression is a relatively common perinatal complication, occurring in approximately 12-17% of cases. Positive depression screening tests are reported to occur in 27.8% of cases during pregnancy and 16.6% after birth. Furthermore, assessing anxiety is increasingly important to fully understand the mental health of new parents.

[0006] Meanwhile, for perinatal depression, a condition that many pregnant women complain of, traditionally, pregnant women have visited hospitals and clinics to undergo screening and diagnosis. However, many pregnant women face challenges due to hospitals being far from their homes, transportation difficulties, limited accessibility, and the physical and mental burdens of pregnancy and postpartum. Furthermore, visiting a hospital or clinic is time-consuming and can be particularly burdensome for pregnant women with busy schedules. Waiting times for appointments, consultations, and tests can be lengthy. Furthermore, the social stigma surrounding mental health issues like depression remains negative, which can discourage pregnant women from seeking medical care, potentially preventing them from receiving timely treatment. Furthermore, the cost of mental health services can be burdensome if health insurance coverage is inadequate or not adequate. Furthermore, traditional approaches often rely on standardized approaches, often failing to adequately consider the specific needs and circumstances of each pregnant woman, which can reduce treatment effectiveness.

[0007] The purpose of the embodiments disclosed in this disclosure is to identify the unmet mental health needs of perinatal mothers and to provide a smart healthcare platform including a digital therapeutic device to satisfy such needs.

[0008] In addition, the embodiment disclosed in the present disclosure analyzes lifelog data, questionnaire information, and speech information collected from a maternal terminal using a cognitive treatment model for perinatal stress management, and determines the level of mental health of the mother based on the analysis results, thereby providing treatment information suitable for the mother.

[0009] In addition, the embodiment disclosed in this disclosure provides a scenario for cognitive therapy for each session, and adjusts the cognitive therapy process based on the results of the interaction with the mother, thereby more actively reflecting the individual condition and changes of the mother and thereby improving the treatment effect.

[0010] However, the problems to be solved according to one embodiment are not limited to those mentioned above.

[0011] In order to achieve the above-described technical problem, a device for managing perinatal depression according to the present disclosure includes a memory storing at least one command for managing perinatal depression; and a processor performing an operation according to the command, wherein the processor analyzes questionnaire information and speech information collected from a terminal of a mother through a cognitive therapy model to identify negative thought patterns and emotions of the mother, and evaluates the mental health level of the mother according to the identified negative thought patterns and emotions, and the cognitive therapy model learns trigger keywords related to depression of the mother, and when a word showing a similarity higher than a preset level with the learned trigger keyword is detected in the questionnaire information or speech information, the mental health level of the mother can be evaluated according to an analysis result of the detected keyword.

[0012] In addition, a method for managing perinatal depression performed by a processor of a device according to the present disclosure for achieving the above-described technical task may include a step of analyzing questionnaire information and speech information collected from a terminal of a mother by the processor through a cognitive therapy model to identify negative thought patterns and emotions of the mother; and a step of evaluating the mental health level of the mother according to the identified negative thought patterns and emotions by the processor, wherein the cognitive therapy model learns trigger keywords related to depression of the mother, and when a word showing a similarity higher than a preset level with the learned trigger keyword is detected in the questionnaire information or speech information, the mental health level of the mother may be evaluated according to an analysis result of the detected keyword.

[0013] According to the aforementioned problem solving means of the present disclosure, a depression treatment platform is configured with a digital treatment device consisting of a chatbot using artificial intelligence, so that not only the presence or absence of depression is determined, but also the corresponding depression symptoms are specified in each algorithmic step to suggest a treatment method, and for users in need of immediate help, it provides a search function for easily accessible emergency room information and counseling service information, thereby providing the effect of enabling early diagnosis of maternal depression and rapid treatment.

[0014] In addition, according to the aforementioned problem solving means of the present disclosure, when a pregnant woman feels emotional ups and downs, including feeling depressed, she can easily receive a test for the relevant part anytime and anywhere, and receive a step-by-step diagnosis and treatment based on artificial intelligence, thereby providing the effect of maintaining the mental health of the mother.

[0015] Furthermore, the aforementioned problem-solving method of the present disclosure allows for the analysis of lifelog data, questionnaire information, and speech information collected from pregnant women to accurately identify their individual mental health status and needs, thereby enabling the development of a customized treatment plan. This allows for the provision of the most appropriate treatment for each pregnant woman, maximizing therapeutic effectiveness.

[0016] In addition, according to the aforementioned problem solving means of the present disclosure, by utilizing a digital therapeutic device and platform, it provides the effect of providing great help, especially to pregnant women who are subject to geographical or time constraints, by enabling pregnant women to easily access therapeutic resources anytime and anywhere.

[0017] In addition, according to the aforementioned problem solving means of the present disclosure, changes in the mother's condition can be continuously monitored by collecting and analyzing data in real time, thereby preventing the mother's condition from worsening in advance and enabling immediate response.

[0018] In addition, the aforementioned problem-solving means of the present disclosure provides the effect of enabling the mother to more actively participate in her own treatment process and practice self-management, thereby increasing the mother's awareness of her own health status and enabling her to achieve better health outcomes through active participation in treatment.

[0019] Furthermore, according to the aforementioned problem-solving method of the present disclosure, access to treatment through a digital platform reduces social stigma compared to mothers visiting a hospital in person. This is particularly beneficial for mothers who are reluctant to seek treatment due to negative perceptions of mental health issues.

[0020] The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the detailed description of the present invention or the composition of the invention described in the claims.

[0021] Figure 1 is a diagram showing a perinatal depression management system according to an embodiment.

[0022] Figure 2 is a drawing showing the configuration of a perinatal depression management device according to an embodiment.

[0023] Figure 3 is a diagram showing the results of the mental level assessment of the mother according to an embodiment.

[0024] Figures 4 to 7 are diagrams showing scenarios for cognitive therapy provided in the embodiment.

[0025] Figure 8 is a diagram showing the perinatal depression management process according to an embodiment.

[0026] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably only for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, a detailed description thereof will be omitted. In addition, the attached drawings are only intended to make it easier to understand the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0027] Terms that include ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used solely to distinguish one component from another.

[0028] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0029] In this application, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0030] In this specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Furthermore, a single unit may be realized using two or more pieces of hardware, and two or more units may be realized by a single piece of hardware.

[0031] Some of the operations or functions described herein as being performed by a terminal, apparatus, or device may instead be performed by a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described herein as being performed by a server may also be performed by a terminal, apparatus, or device connected to the server.

[0032] Hereinafter, the present invention will be described in detail with reference to the attached drawings.

[0033] Figure 1 is a diagram showing a perinatal depression management system according to an embodiment.

[0034] Referring to FIG. 1, a perinatal depression management system according to an embodiment may be configured to include a perinatal depression management device (100) and a maternal terminal (200).

[0035] The perinatal depression management device (100) identifies the unmet mental health needs of perinatal mothers and provides digital therapeutic devices to address these unmet needs. Furthermore, the perinatal depression management device (100) functions as a digital therapeutic device and provides a smart healthcare platform to the mothers.

[0036] To this end, the perinatal depression management device (100) according to the embodiment analyzes questionnaire information, speech information, etc. transmitted from the maternal terminal (200) to assess the mental health level of the mother and provides treatment content to the user. In addition, the perinatal depression management device (100) according to the embodiment collects life log data from the maternal terminal (200) and analyzes the collected life log data to manage the perinatal stress of the mother. In addition, the perinatal depression management device (100) according to the embodiment learns a cognitive model for managing the stress and mental health of the mother, determines the mental health level of the mother through the learned cognitive model, and provides treatment information to maintain the mental health of the mother during the perinatal period. In addition, the perinatal depression management device (100) according to the embodiment may be linked with a medical staff terminal to provide a medical staff screen that can be viewed by the medical staff.

[0037] In an embodiment, the maternal terminal (200) may include a terminal such as a smartphone or wearable device worn or carried by the mother. In an embodiment, the maternal terminal (200) transmits questionnaire information, speech information, and life log data answered by the mother to a perinatal depression management device (100).

[0038] In an embodiment, the life log data is systematically recorded and collected data that includes various data occurring in the daily life of the pregnant woman. The life log data represents the daily life of the pregnant woman, and generally includes data related to at least one of people's activities, behaviors, locations, and health conditions. In an embodiment, the life log data may be automatically collected through at least one of an application, a wearable device, and a digital assistant installed on the pregnant woman's terminal (200).

[0039] In an embodiment, the perinatal depression management device (100) collects life log data from the maternal terminal (200) and analyzes the collected life log data to more accurately identify changes in the mental health of the mother. Through this, the quality of life of the mother is improved and the data can be utilized for at least one of health management, time management, and behavioral pattern analysis. For example, the perinatal depression management device (100) tracks and manages at least one of the number of steps and sleep patterns in the life log data to help manage health, thereby managing the physical health of the mother, which affects her mental health.

[0040] Figure 2 is a block diagram of a perinatal depression management device according to an embodiment.

[0041] In the embodiment, the perinatal depression management device (100) may be implemented as a server. A server is a computing system that provides services to other computers or devices in a computer network or stores and manages data. The perinatal depression management device (100) accepts requests from clients (the maternal terminal) and other computers or devices, and provides responses or data in response to the requests. The configuration of the perinatal depression management device (100) illustrated in FIG. 2 is merely a simplified example.

[0042] The communication module (110) can be configured regardless of the communication mode, such as wired or wireless, and can be configured with various communication networks, such as a personal area network (PAN) and a wide area network (WAN). In addition, the communication module (110) can operate based on the known World Wide Web (WWW), and can be configured with infrared (IrDA: Infrared Data Association) or Bluetooth. TM (Bluetooth TM ) may also be used for short-distance communication. For example, the communication module (110) may be responsible for transmitting and receiving data required to perform a technique according to an embodiment of the present disclosure.

[0043] The memory (120) may refer to any type of storage medium. For example, the memory (120) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk. Such a memory (120) may also constitute a database as illustrated in FIG. 1.

[0044] The memory (120) can store at least one instruction that can be executed by the processor (130). In addition, the memory (120) can store any type of information generated or determined by the processor (130) and any type of information received by the server (200). For example, the memory (120) stores RM data and RM protocols according to the user, as will be described later. In addition, the memory (120) stores various types of modules, instruction sets, and models.

[0045] The processor (130) may perform technical features according to embodiments of the present disclosure, which will be described later, by executing at least one instruction stored in the memory (120). In one embodiment, the processor (130) may be configured with at least one core and may include a processor for data analysis and / or processing, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of a computer device.

[0046] This processor (130) can train a neural network or model designed using machine learning or deep learning methods. To this end, the processor (130) can perform calculations for neural network training, such as processing input data for training, extracting features from the input data, calculating errors, and updating the weights of the neural network using backpropagation. In addition, the processor (130) can also perform inference for a predetermined purpose using a model implemented using an artificial neural network method.

[0047] In the embodiment, the processor (130) analyzes the questionnaire and speech information collected from the maternal terminal (200) using a cognitive therapy model to identify the mother's negative thought patterns and emotions. The mother's mental health level is then assessed based on the identified negative thought patterns and emotions. All operations performed by the cognitive therapy model described below can be controlled by the processor (130).

[0048] Here, cognitive therapy is an approach that focuses on how an individual's negative thoughts and cognitive patterns influence their emotions and behavior, and aims to treat mental health issues by modifying these patterns. Cognitive therapy has been proven effective for a variety of mental health conditions, including depression, anxiety disorders, and stress-related issues. In the embodiment, the cognitive therapy model is an artificial intelligence model that provides cognitive therapy processes through a trained artificial neural network.

[0049] The core of cognitive therapy is to help individuals identify their thoughts and beliefs, assess how closely these thoughts align with reality, and then replace unrealistic or distorted thoughts with more appropriate and realistic ones. Accordingly, the cognitive therapy model analyzes questionnaire and speech data provided by pregnant women using natural language analysis and a language model. Based on the analysis results, it identifies the mother's mental health level and provides treatment information to improve the identified mental health level.

[0050] The above cognitive therapy is conducted in conversational sessions, where the therapist helps the client clearly recognize their thoughts and beliefs and understand how they influence their emotional state and behavior. Consequently, the patient learns how to apply this new cognitive approach to address problematic situations in their daily lives. Accordingly, the cognitive therapy model, which provides cognitive therapy, provides a session-by-session cognitive therapy process based on the results of questionnaires and speech analysis completed by the mother, using a chatbot or generative artificial intelligence. The mother's interactions during each session are then recorded to derive treatment outcomes. In one embodiment, the questionnaire includes various psychological assessment tools, such as depression and anxiety tests, and the mother's responses to these. The speech data may include text and voice information generated by the mother while conversing with the chatbot.

[0051] In an embodiment, the processor (130) learns trigger keywords related to maternal depression to implement the cognitive therapy model. In an embodiment, the trigger keywords used as learning data for the cognitive therapy model are words or phrases that people experiencing depression may frequently use, and include keywords related to worthlessness, fatigue, loss of interest, despair, sleep problems, death, and suicide. In an embodiment, the cognitive therapy model can learn by using the trigger keywords as input data and the type and level of mental illness corresponding to the input trigger keywords as output data. Specifically, keywords related to worthlessness among the trigger keywords include "I'm nothing," "I'm a useless person," and "I'm a failure," and keywords related to fatigue include "I'm always tired," "I have no energy at all," and "My body feels heavy."

[0052] Keywords related to loss of interest include "I don't want to do anything," "I don't feel pleasure anymore," and "Things I used to enjoy no longer appeal to me." Keywords related to despair include "I feel like I have no way out," "Things will never get better," and "I see no hope." Keywords related to sleep problems include "It's so hard," "I can't sleep properly," "I'm up all night," and "I sleep too much." Keywords related to death and suicide include "I want to die," "I wish I wasn't here," and "I wish it would all end." The aforementioned trigger keywords are examples and not limitation.

[0053] In the embodiment, when the questionnaire information and speech information of the mother are input, the cognitive treatment model analyzes the input and determines whether a word showing a similarity level higher than a preset level with the learned trigger keyword is detected in the questionnaire information or speech information.

[0054] Thereafter, the cognitive therapy model assesses the mental health level of the mother based on the analysis results of keywords that exhibit a similarity level above the preset level with the trigger keyword. For example, the cognitive therapy model can calculate the total similarity between words extracted from the mother's questionnaire and speech information and the trigger keyword, and assess the mother's mental health level based on the range within which the calculated total similarity falls.

[0055] Additionally, the cognitive therapy model identifies which group of keywords contained in the mother's questionnaire and speech data are most closely related to: worthlessness, fatigue, loss of interest, despair, sleep problems, death, and suicide. The similarity between the keywords contained in the questionnaire and speech data and the trigger keywords can then be measured separately. The mental health level of each trigger keyword group can then be assessed based on the measured similarity between the groups.

[0056] In addition, the cognitive therapy model according to the embodiment quantifies the mental health level of the mother as a score and provides the mother with necessary treatment information according to the range of the quantified score. For example, the cognitive therapy model can quantify the mental health level of the mother as a score using the total similarity between the trigger keyword and the keywords included in the mother's questionnaire and speech information. Specifically, the cognitive therapy model can convert the score proportional to the total similarity and express the mental health level of the mother as a score.

[0057] In this embodiment, the cognitive therapy model presets the maternal mental health level based on a range of scores. For example, the cognitive therapy model sets the maternal mental health level score as good if converted to a score of 0 to 9, mild if converted to a score of 9 to 15, severe if converted to a score of 15 to 24, and severe if converted to a score of over 24.

[0058] Additionally, the cognitive therapy model pre-establishes the necessary information required for each stage and provides information tailored to the mother's mental health stage. For example, the cognitive therapy model recommends that pregnant women with severe or higher symptoms visit a mental health clinic for consultation with medical staff. Furthermore, for users in need of immediate assistance, the model provides a function to search for a nearby emergency room based on their current location.

[0059] Additionally, the example provides guidance on the services of an infertility and depression counseling center, which provides mental health counseling for women and their families from pregnancy preparation through postpartum. In addition to the central center, there are regional infertility and depression counseling centers in Seoul, northern Gyeonggi Province, Gyeonggi Province, Incheon Metropolitan City, South Jeolla Province, North Gyeongsang Province, and Daegu Metropolitan City. Therefore, the example can provide guidance on services at an infertility and depression counseling center located near the expectant mother's location.

[0060] Additionally, in the embodiment, the processor (130) stores a scenario for improving perinatal mental health. In the embodiment, the scenario is a scenario for conducting cognitive therapy provided to the mother, and the scenario may include at least one of the processes of emotion recognition, acceptance, reality recognition, and value discovery.

[0061] In an embodiment, the processor (130) classifies the scenario into multiple treatment sessions and provides a scenario corresponding to each of the classified treatment sessions to the maternal terminal. In an embodiment, the scenario may be pre-configured as a scenario for providing cognitive therapy according to the psycho-emotional level.

[0062] In addition, the processor (130) can collect cognitive treatment scenarios for mental health, such as depression, from an external server via an API and provide them to the maternal terminal. In an embodiment, the scenarios can be composed of 1 to 8 sessions. In an embodiment, session 1 can be composed of a treatment start stage, session 2 can be composed of a thought understanding stage, session 3 can be composed of a thought handling stage, session 4 can be composed of an action stage, session 5 can be composed of a daily life recovery stage, session 6 can be composed of a vicious cycle breaking stage, session 7 can be composed of an antidepressant behavior finding stage, and session 8 can be composed of a look-at-it-as-it-is stage.

[0063] In an embodiment, the cognitive therapy model tracks the progress of the depression of the pregnant woman based on the results of the mental health level assessment of the pregnant woman, and generates a treatment plan for each session based on the tracked depression progress. To this end, the cognitive therapy model transmits a standardized psychological assessment tool to the pregnant woman's terminal (200) to evaluate the mental health level of the pregnant woman, and receives and acquires questionnaire information and the pregnant woman's speech information regarding the transmitted psychological assessment tool from the pregnant woman's terminal (200). In an embodiment, the psychological assessment tool can quantitatively measure the level of depression of the pregnant woman by utilizing a tool such as the Edinburgh Postnatal Depression Scale (EPDS).

[0064] Additionally, the cognitive therapy model collects log data representing the mother's daily life, as well as psychological assessment results, questionnaire information, and speech information. In one embodiment, the log data is data recording daily life, indicating at least one of sleep patterns, activity levels, and nutritional status, and can be collected through a wearable device and / or an application on the maternal terminal (200).

[0065] Afterwards, the cognitive therapy model continuously tracks the progress of the mother's depression through regular assessments. Furthermore, the cognitive therapy model analyzes life log data to determine whether at least one of the mother's sleep duration, sleep patterns, and activity patterns is improving in a way that supports mental health. Through this, the cognitive therapy model according to the embodiment can determine whether the mother's depression is improving, worsening, or remaining unchanged.

[0066] In this embodiment, the cognitive therapy model provides treatment content for preventing and alleviating depression. The treatment content is designed to be completed in one session per week. While it is recommended to complete a session from beginning to end, it can be divided and tailored to individual circumstances. The treatment content provided in this embodiment may broadly include at least one of relaxation training, cognitive restructuring, behavioral activation, and mindfulness. The relaxation training is conducted for the purpose of relaxing a tense body and mind, and the cognitive restructuring treatment aims to explore, change, and restructure negative thoughts and beliefs into more rational and positive ones. The behavioral activation treatment aims to increase adaptive activities associated with enjoyable or fulfilling experiences and decrease participation in activities that maintain or exacerbate depression. The mindfulness treatment increases awareness of present-moment experiences and promotes openness and acceptance of present-moment self-experience, thereby fostering coping skills for coping with stress in life. Additionally, in the embodiment, monitoring can be done through the medical viewer to check the user's accumulated data, such as the results of the survey, frequency of treatment use, and access time.

[0067] Additionally, in the embodiment, the cognitive therapy model adjusts the treatment plan for each session based on the mental health assessment results for each session, and extracts scenarios to be output for each treatment session based on the adjusted treatment plan. To this end, the mother's mental health is assessed before and after each treatment session. This assessment can be conducted through various methods, such as questionnaires, direct counseling, and physiological indicator measurements.

[0068] The cognitive therapy model then analyzes the mental health assessment results to quantitatively assess the mother's current mental health status and any changes during the treatment process. In an example, data on changes during the treatment process may include the mother's depression, anxiety, and stress levels.

[0069] The cognitive therapy model then adjusts the existing treatment plan based on the mother's most recent mental health assessment results. In one embodiment, this adjustment involves determining whether more intensive intervention is necessary or less intensive intervention is possible based on the mother's needs and responses.

[0070] The cognitive therapy model then extracts an appropriate treatment scenario based on the adjusted treatment plan. In an embodiment, the treatment scenario may include specific treatment content, activities, and conversation scripts to be provided to the mother. For example, the scenario may include self-management skill training using cognitive behavioral therapy (CBT), positive thinking practice, and problem-solving techniques.

[0071] Thereafter, the cognitive treatment model transmits a scenario matching the adjusted treatment plan to the maternal terminal (200). This can be done through various digital media such as an app, web portal, or SMS, allowing the mother to access it anytime, anywhere.

[0072] In the embodiment, the treatment information includes, but is not limited to, counseling information, treatment linkage methods, and mental health data categorized by the mother's mental health level score range. Furthermore, the mental health data provided in the embodiment includes, but is not limited to, web pages, audio, text, chatbots, and communities that connect with other mothers.

[0073] In addition, the cognitive therapy model according to the embodiment interacts with the mother by reflecting the input speech information, text information, number of treatment sessions, and mental health level of the previous session when speech information or text information received from the maternal terminal (200) is input in real time. For example, the cognitive therapy model obtains speech information (voice data) or text information from the maternal terminal (200). In the embodiment, the data obtained by the cognitive therapy model may include content in which the mother describes her current condition, emotions, thoughts, experiences, etc. Thereafter, the cognitive therapy model analyzes the received data using speech recognition and natural language processing (NLP) technology. In this process, important keywords, emotions, intentions, etc. are extracted from the mother's speech or text. In addition, the cognitive therapy model analyzes the current input information by combining it with historical information, such as the number of treatment sessions of the mother, mental health level of the previous session, etc. In this process, the cognitive therapy model can help in a comprehensive understanding of the mental health state of the mother and track the progress.

[0074] The cognitive therapy model then generates personalized responses in real time based on the analyzed data and the mother's treatment history. For example, if the mother expresses depression, the cognitive therapy model can apply effective intervention methods used in previous sessions or offer new advice. In one embodiment, the cognitive therapy model conducts a preference survey after each relaxation training session to determine which intervention method was most effective. As user responses accumulate, preference information can be provided during review.

[0075] Additionally, the cognitive therapy model suggests appropriate cognitive therapy techniques to the mother and provides real-time feedback. This can be done via text message, voice message, or interactive app features.

[0076] The processor (130) assesses the mental health level of the mother in each treatment session through the cognitive therapy model described above, and identifies changes in the assessed mental health level compared to the previous test. For example, the processor (130) records the change in the score indicating the mental health level of the mother in the current session compared to the previous session, and provides feedback according to the change in the score. In an embodiment, if the score increases by a certain amount or more and the mental state of the mother changes negatively, the processor (130) provides a message and treatment information to respond to the changed state. In addition, if the score decreases by a certain amount or more and the mental state of the mother changes positively, praise, encouraging comments, and treatment information corresponding to the corresponding level may be provided to the mother's terminal.

[0077] Figure 3 is a diagram showing the results of the mental level evaluation of the mother according to an embodiment.

[0078] Referring to Fig. 3, a pregnant woman can have her mental health assessed through a questionnaire and conversation via a maternal terminal (200). In an exemplary embodiment, the maternal terminal (200) displays the pregnant woman's mental health level and the corresponding score as assessed by a perinatal depression management device, along with the mental health stage according to the range of scores. Furthermore, the terminal can display the necessary measures at each stage and the change in the pregnant woman's mental health score (30) between the previous test and the current test.

[0079] Figures 4 to 7 are diagrams showing scenarios for cognitive therapy provided in the embodiment.

[0080] Referring to FIGS. 4 and 7, the scenarios provided in the embodiment can be output as voice (40) or text (70) via a chatbot, and can be output together with a video. In the embodiment, scenarios corresponding to Sessions 1 to 8 can be provided based on the mother's treatment process and mental health assessment results.

[0081] Figure 5 is a diagram illustrating a psychological testing tool provided in an embodiment. In the embodiment, the psychological testing tool (50) includes a test for measuring a depression scale and an anxiety test, etc. In the embodiment, each psychological testing tool may be provided on a session-by-session basis. Figure 6 is a diagram illustrating a scenario for providing test result analysis information according to the embodiment. Referring to Figure 6, in the embodiment, the mental health level assessment results (60) provided in each session may be provided as depression interpretation guidelines and anxiety interpretation guidelines, and corresponding information regarding the analysis results may also be provided.

[0082] Hereinafter, let us examine Fig. 8. The automatic contract generation method illustrated in Fig. 8 can be performed by an automatic contract generation device (100) including a processor (130).

[0083] Meanwhile, Fig. 8 is merely exemplary, and the spirit of the present invention is not limited to what is illustrated in Fig. 8. For example, each step may be configured in a different order than that illustrated in Fig. 8, at least one of the steps illustrated in Fig. 8 may not be performed, or one or more steps not illustrated in Fig. 3 may be additionally performed.

[0084] Below, the management method for perinatal depression is sequentially described. Since the function of the management method for perinatal depression according to the embodiment is essentially the same as the function of the perinatal depression management device, any description overlapping with that in FIGS. 1 to 7 will be omitted.

[0085] Figure 8 is a diagram showing a process for managing perinatal depression according to an embodiment.

[0086] Referring to FIG. 8, in step S100, the processor (130) collects questionnaire and speech information from the maternal terminal (200), and analyzes the information collected in step S200. In an embodiment, the processor (130) may analyze the similarity between pre-stored trigger keywords and keywords included in the questionnaire results and speech. In step S300, the processor (130) determines the mental health level of the maternal body based on the analysis results, and in step S400, the processor (130) provides the determined result to the maternal terminal (200). In step S500, the processor (130) provides necessary treatment information based on the maternal body's mental health level. In an embodiment, the treatment information may include whether counseling is necessary, etc.

[0087] In this embodiment, a depression treatment platform is configured with a digital therapeutic device consisting of an AI-powered chatbot. This not only determines the presence or absence of depression, but also provides treatment methods by specifying the corresponding depression symptoms step by step through an algorithm, thereby providing the effect of early diagnosis and rapid treatment of depression in pregnant women. Furthermore, through this embodiment, when pregnant women experience emotional ups and downs, including feelings of depression, they can conveniently receive tests for relevant areas anytime and anywhere, and receive AI-based step-by-step diagnosis and treatment, thereby helping to maintain the mental health of pregnant women.

[0088] Furthermore, by analyzing lifelog data, questionnaire information, and speech information collected from pregnant women through examples, the system can accurately assess each mother's individual mental health status and needs, enabling the development of a personalized treatment plan. This allows for the provision of the most appropriate treatment for each individual mother, maximizing therapeutic effectiveness.

[0089] Furthermore, the perinatal depression management device (100) according to the embodiment utilizes digital therapeutic devices and platforms to enable mothers to easily access treatment resources anytime and anywhere, thereby providing significant assistance, particularly to mothers facing geographical or time constraints. Furthermore, by collecting and analyzing data in real time, the device enables continuous monitoring of changes in the mother's condition and allows for immediate adjustments to the treatment plan as needed, thereby preventing the deterioration of the mother's condition in advance and enabling prompt response.

[0090] Additionally, the method provides the effect of increasing awareness of the mother's health status and enabling her to achieve better health outcomes through active participation in treatment by enabling her to participate more actively in her treatment process and practice self-management.

[0091] Furthermore, the example demonstrates that accessing treatment through a digital platform reduces social stigma compared to in-person hospital visits. This is particularly beneficial for expectant mothers who are reluctant to seek treatment due to negative perceptions of mental health issues.

[0092] A model in the present disclosure may refer to any form of computer program that operates based on a network function, an artificial neural network, and / or a neural network. Throughout this specification, the terms "model," "neural network," "network function," and "neural network" may be used interchangeably. A neural network is a network in which one or more nodes are interconnected through one or more links to form input and output node relationships within the network. The characteristics of a neural network can be determined based on the number of nodes and links within the neural network, the correlation between the nodes and links, and the weight values ​​assigned to each link. A neural network may be composed of a set of one or more nodes. A subset of the nodes constituting the neural network may constitute a layer.

[0093] A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a generative adversarial network (GAN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, a generative adversarial network (GAN), a transformer, and the like. The description of the above-described deep neural network is merely an example, and the present disclosure is not limited thereto.

[0094] Neural networks can learn through at least one of the following methods: supervised learning, unsupervised learning, semi-supervised learning, self-supervised learning, or reinforcement learning. Neural network learning can be the process of applying knowledge to the neural network to perform a specific action.

[0095] Neural networks can be trained to minimize output errors. This process involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network to reduce the error. In supervised learning, labeled data is used for each training data, while unsupervised learning uses unlabeled data. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate can vary depending on the number of iterations in the neural network's training cycle. Additionally, to prevent overfitting, methods such as increasing the learning data, regularization, dropout that disables some nodes, and batch normalization layers can be applied.

[0096] In one embodiment, the model may borrow at least a portion of a transformer. The transformer may be composed of an encoder that encodes embedded data and a decoder that decodes the encoded data. The transformer may have a structure that receives a series of data and outputs a series of data of different types through encoding and decoding steps. In one embodiment, the series of data may be processed into a form operable by the transformer. The process of processing the series of data into a form operable by the transformer may include an embedding process. Expressions such as data tokens, embedding vectors, and embedding tokens may refer to data embedded in a form operable by the transformer.

[0097] To encode and decode a series of data, a transformer can utilize an attention algorithm to process the encoders and decoders within the transformer. An attention algorithm can refer to an algorithm that, for a given query, calculates the similarity for one or more keys, reflects this similarity in the values ​​corresponding to each key, and then weights and sums the values ​​to which the similarity is reflected to calculate an attention value.

[0098] Depending on how the query, key, and value are configured, various types of attention algorithms can be categorized. For example, if attention is obtained by setting the query, key, and value all to the same value, this could be a self-attention algorithm. If attention is obtained by reducing the dimensionality of the embedding vector to process a series of input data in parallel and then generating individual attention heads for each segmented embedding vector, this could be a multi-head attention algorithm.

[0099] In one embodiment, the transformer may be composed of modules that perform multiple multi-head self-attention algorithms or multi-head encoder-decoder algorithms. In one embodiment, the transformer may also include additional components other than attention algorithms, such as embedding, normalization, and softmax. Methods for constructing a transformer using attention algorithms may include methods disclosed in Vaswani et al., Attention Is All You Need, 2017 NIPS, which is incorporated herein by reference.

[0100] A transformer can be applied to various data domains, such as embedded natural language, segmented image data, and audio waveforms, to transform a series of input data into a series of output data. To transform data with various data domains into a series of data that can be input to a transformer, the transformer can embed the data. The transformer can process additional data that expresses the relative positional relationship or phase relationship between the series of input data. Alternatively, vectors expressing the relative positional relationship or phase relationship between the input data can be additionally reflected in the series of input data to embed the series of input data. In one example, the relative positional relationship between the series of input data may include, but is not limited to, word order within a natural language sentence, the relative positional relationship between each segmented image, and the time order of segmented audio waveforms. The process of adding information expressing the relative positional relationship or phase relationship between the series of input data may be referred to as positional encoding.

[0101] In one embodiment, the model may include, but is not limited to, at least one of a Recurrent Neural Network (RNN), a Long Short Term Memory (LSTM) network, a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN).

[0102] In one embodiment, the model may be a model trained using transfer learning. Transfer learning, in this context, refers to a learning method that pre-trains a large amount of unlabeled training data using semi-supervised or self-learning methods to obtain a pre-trained model for a first task, then fine-tunes the pre-trained model to suit a second task, and trains it on labeled training data using supervised learning to implement a target model.

[0103] The disclosed content is merely an example, and various modifications and implementations can be made by a person skilled in the art without departing from the gist of the claims claimed in the patent, so the scope of protection of the disclosed content is not limited to the specific embodiments described above.

Claims

1. A memory storing at least one command for managing perinatal depression; and A processor comprising: a processor that performs an operation according to the above command; The above processor, The questionnaire and speech information collected from the mother's terminal are analyzed through a cognitive therapy model to identify the mother's negative thought patterns and emotions, and the mother's mental health level is assessed based on the identified negative thought patterns and emotions. The above cognitive therapy model is, A device for managing perinatal depression, which learns trigger keywords related to the maternal depression, and, when a word showing a similarity level higher than a preset level with the learned trigger keyword is detected in the questionnaire information or speech information, evaluates the mental health level of the maternal depression based on the analysis result of the detected keyword.

2. In paragraph 1, the cognitive therapy model, The mental health level of the mother is quantified into a score, A perinatal depression management device that provides necessary treatment information to the mother according to the range of the above scores.

3. In paragraph 2, The above treatment information includes counseling information, treatment linkage methods, and mental health data classified according to the range of the mental health level score of the mother. The above mental health resources include a perinatal depression management device that includes web pages, sound, text, chatbots, and a community that connects with other mothers.

4. In the first paragraph, the processor, Save scenarios for improving perinatal mental health, including the processes of emotional recognition, acceptance, reality recognition, and value discovery. The above scenarios are categorized into multiple treatment sessions, A perinatal depression management device that provides a scenario corresponding to each of the classified treatment sessions to the maternal terminal according to the mental health level and treatment process of the maternal terminal.

5. In the fourth paragraph, the processor, In each of the above treatment sessions, the mental health level of the mother is assessed, A device for managing perinatal depression that compares the above-mentioned mental health level with the results of previous tests and identifies changes compared to the previous test results.

6. In paragraph 5, the cognitive therapy model, A perinatal depression management device that interacts with the mother by considering speech information, text information, number of treatment sessions, and mental health level of the previous session received from the maternal terminal.

7. In paragraph 1, the cognitive therapy model, Track the progress of the mother's depression based on the results of the mental health level assessment of the mother. A perinatal depression management device that provides treatment content using treatment techniques including relaxation training, cognitive restructuring, behavioral activation, and mindfulness related to the depression, based on the results of the above tracking.

8. In a method for managing perinatal depression performed by a processor of a device, A step of analyzing the questionnaire information and speech information collected from the mother's terminal by the above processor through a cognitive therapy model to identify the mother's negative thought patterns and emotions; and A step of assessing the mental health level of the mother according to the identified negative thought patterns and emotions by the above processor, The above cognitive therapy model is, A method for managing perinatal depression, wherein trigger keywords related to the maternal depression are learned, and when words showing a similarity level higher than a preset level with the learned trigger keywords are detected in questionnaire information or speech information, the mental health level of the maternal depression is assessed based on the analysis results of the detected keywords.

9. In paragraph 8, the cognitive therapy model, The mental health level of the mother is quantified into a score, A method for managing perinatal depression, which provides the mother with necessary treatment information according to the range of the above scores.

10. In paragraph 9, The above treatment information includes counseling information, treatment linkage methods, and mental health data classified according to the range of the mental health level score of the mother. The above mental health resources include web pages, sound, text, chatbots, and communities that connect with other mothers to manage perinatal depression.

11. In paragraph 8, Step of saving a scenario for improving perinatal mental health, including the process of emotional recognition, acceptance, reality recognition and value discovery; A step of classifying the above scenario into multiple treatment sessions; and A method for managing perinatal depression, further comprising the step of providing a scenario corresponding to each of the classified treatment sessions to the maternal terminal according to the mental health level and treatment process of the maternal terminal.

12. In the 11th paragraph, the step of providing the scenario to the maternal terminal is: A step of assessing the mental health level of the mother in each of the above treatment sessions; and A method for managing perinatal depression, comprising a step of comparing the above-mentioned emotional level with the results of a previous test to determine a trend of change compared to the results of the previous test.

13. In paragraph 12, the cognitive therapy model, A method for managing perinatal depression, wherein the method interacts with the mother by considering speech information, text information, number of treatment sessions, and mental health level of the previous session received from the mother's terminal.

14. In the first paragraph, the cognitive therapy model, Track the progress of the mother's depression based on the results of the mental health level assessment of the mother. A method for managing perinatal depression, which provides treatment content using treatment techniques including relaxation training, cognitive restructuring, behavioral activation, and mindfulness related to the depression, based on the results of the above tracking.

Images