Method, device, and system for predicting anxiety-related indicator on basis of virtual reality

Abstract

A method for predicting an anxiety-related indicator, according to exemplary embodiments of the present invention, is executed by at least one processor and may comprise the steps of: acquiring behavior data and anxiety score data of a subject, which are acquired while the subject performs an anxiety evaluation process including virtual reality content; and generating an anxiety characteristic indicator of the subject on the basis of the behavior data and the anxiety score data of the subject.

Description

Method, device, and system for predicting anxiety-related indicators based on virtual reality

[0001] The present invention relates to a method, apparatus, and system for predicting anxiety-related indicators based on virtual reality.

[0002] Anxiety disorder is a mental health disorder characterized primarily by excessive or persistent anxiety and fear. While anxiety is generally a normal reaction to danger or stressful situations, in anxiety disorders it manifests excessively and can have a negative impact on daily life.

[0003] Examples of anxiety disorders include Generalized Anxiety Disorder (GAD), Panic Disorder, Social Anxiety Disorder (SAD), Specific Phobia, Obsessive-Compulsive Disorder (OCD), and Post-Traumatic Stress Disorder (PTSD).

[0004] There are various traditional scales for evaluating anxiety disorders. For example, there is the GAD-7 for generalized anxiety, the LSAS for social anxiety, the IUS for anxiety about uncertainty, the ASI for anxiety susceptibility, the BFNE for fear of negative evaluation, and the PSWQ for chronic anxiety.

[0005] Meanwhile, methods for evaluating a subject's anxiety disorder or predicting indicators related to the disorder (i.e., anxiety-related indicators) based on virtual reality (VR) are being provided. For example, Korean Published Patent Application No. 10-2023-0084361 discloses a method for predicting the severity of a subject's anxiety disorder based on virtual reality. However, conventional methods have limitations in that they are anxiety assessment (i.e., prediction) tools based on the subject's subjective experience.

[0006] One objective of the present invention is to provide a method, device, and system capable of more objectively predicting anxiety-related indicators for a subject.

[0007] A method for predicting anxiety-related indicators according to exemplary embodiments of the present invention may include a method executed by at least one processor, comprising: (S1) obtaining behavioral data and anxiety score data of a subject obtained while the subject performs an anxiety assessment process including virtual reality content; and (S2) generating an anxiety characteristic indicator of a subject based on the behavioral data and anxiety score data of the subject.

[0008] In one embodiment, the behavior data may include at least one of skeletal data and facial expression data.

[0009] In one embodiment, step (S1) may further include acquiring the subject's biosignal data acquired while the subject performs the anxiety assessment process. Step (S2) may include generating an anxiety characteristic index of the subject based on the subject's behavior data, anxiety score data, and biosignal data.

[0010] In one embodiment, the biosignal data may include brainwave data.

[0011] In one embodiment, step (S2) may include: a step of extracting behavioral characteristic information of the subject based on the subject's behavioral data using a trained artificial intelligence model; and a step of generating an anxiety characteristic index of the subject based on the subject's behavioral characteristic information and anxiety score data. The trained artificial intelligence model may be one in which expression learning is performed using a contrastive learning method with a behavioral data set obtained from the virtual reality content.

[0012] In one embodiment, the virtual reality content includes a mission that requires a specific action from the subject, and the virtual reality content includes a mission waiting section, a mission execution section, and a mission completion section, and the trained artificial intelligence model may have performed representation learning in a contrastive learning manner using a behavior data set obtained in each section of the virtual reality content.

[0013] In one embodiment, the virtual reality content includes requiring at least one action from the subject, and the action data may include action data acquired at multiple points in time while the virtual reality content is being performed.

[0014] (S2) The step may include: generating at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data for the virtual reality content based on the subject’s behavior data; and generating an anxiety characteristic index of the subject based on at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data and anxiety score data.

[0015] In one embodiment, the behavior intensity data may include data quantifying the subject's behavior performed according to a request in the virtual reality content based on speed or magnitude. The conscientiousness data may include data quantifying the subject's behavior performed according to a request in the virtual reality content based on time or frequency. The compliance data may include data quantifying the degree of agreement between the behavior required by the virtual reality content and the subject's behavior performed according to the request; or the degree of similarity between the behavior required by the virtual reality content and the subject's behavior performed according to the request. The activeness data may include data quantifying the subject's behavior during the performance of the virtual reality content based on time, speed, frequency, or magnitude.

[0016] In one embodiment, the virtual reality content includes a mission that requires a specific action from the subject, and the virtual reality content includes a mission waiting section, a mission execution section, and a mission completion section, and the action data may include at least one action data obtained in each section of the virtual reality content.

[0017] (S2) The step may include: generating at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data for the virtual reality content based on the subject’s behavior data; and generating an anxiety characteristic index of the subject based on at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data and anxiety score data.

[0018] The behavioral intensity data may include data quantifying the subject's behavior during the mission completion section based on speed or magnitude. The conscientiousness data may include data quantifying the subject's behavior for performing the action required by the mission during the mission execution section based on time or frequency. The compliance data may include data quantifying the degree of agreement between the action required by the mission and the subject's behavior during the mission execution section; or the degree of similarity between the action required by the mission and the subject's behavior. The activeness data may include data quantifying the subject's behavior during the mission waiting section based on time, speed, frequency, or magnitude.

[0019] In one embodiment, step (S2) includes fusing the subject's behavior data and anxiety score data to generate the subject's anxiety characteristic index, and the fusion may include concatenation.

[0020] In one embodiment, the method for predicting the aforementioned anxiety-related indicator may further include the step of predicting the subject's anxiety-related indicator based on the subject's anxiety characteristic indicator using a preset rule-based model or a trained artificial intelligence model.

[0021] In one embodiment, the anxiety-related indicator may include at least one of severity, risk, treatment response at a given time point, and expected duration of treatment.

[0022] A method for predicting anxiety-related indicators according to exemplary embodiments of the present invention may include, as a method executed by at least one processor, the step of providing an anxiety assessment process including virtual reality content to a subject; the step of acquiring behavioral data and anxiety score data of the subject while the subject performs the anxiety assessment process; and the step of generating an anxiety characteristic indicator of the subject based on the behavioral data and anxiety score data of the subject.

[0023] An apparatus for predicting anxiety-related indicators according to exemplary embodiments of the present invention may include at least one memory; and at least one processor that executes instructions stored in the at least one memory.

[0024] The above at least one processor can control the acquisition of behavioral data and anxiety score data of the subject obtained while the subject performs an anxiety assessment process including virtual reality content, and to generate an anxiety characteristic index of the subject based on the behavioral data and anxiety score data of the subject.

[0025] According to exemplary embodiments of the present invention, an application program stored on a recording medium may be provided to execute a method for predicting the aforementioned anxiety-related indicator when operated by at least one processor.

[0026] According to exemplary embodiments of the present invention, an anxiety characteristic indicator capable of more objectively predicting the subject's anxiety-related indicators can be provided by utilizing the subject's behavioral data obtained through a virtual reality-based anxiety assessment process.

[0027] According to exemplary embodiments of the present invention, by utilizing behavioral data and biosignal data of a subject obtained through a virtual reality-based anxiety assessment process together, an anxiety characteristic indicator capable of more objectively predicting the subject's anxiety-related indicators can be provided.

[0028] According to exemplary embodiments of the present invention, by utilizing behavioral data of a subject obtained through a virtual reality-based anxiety assessment process, anxiety-related indicators for the subject can be predicted more objectively.

[0029] According to exemplary embodiments of the present invention, by utilizing behavioral data and biosignal data of a subject obtained through a virtual reality-based anxiety assessment process, anxiety-related indicators for the subject can be predicted more objectively.

[0030] FIG. 1 shows a block diagram of a system for predicting anxiety-related indicators based on virtual reality according to one embodiment of the present invention.

[0031] FIG. 2 shows a block diagram of a virtual reality providing system according to one embodiment of the present invention.

[0032] FIG. 3 is a flowchart illustrating a process for predicting anxiety-related indicators according to one embodiment of the present invention.

[0033] FIG. 4 is a flowchart illustrating the process of virtual reality content according to one embodiment of the present invention.

[0034] FIG. 5 is a flowchart illustrating a process for predicting anxiety-related indicators according to one embodiment of the present invention.

[0035] FIGS. 6 and 7 show conceptual diagrams of a model for predicting anxiety-related indicators according to one embodiment of the present invention.

[0036] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms.

[0037] To clearly explain the embodiments of the present invention, parts unrelated to the description may be omitted. Additionally, in describing the embodiments of the present invention, if it is determined that a detailed description of related known components or functions could obscure the essence or description of the present invention, such detailed description may be omitted.

[0038] In this specification, the terms “…part,” “…unit,” and “…module” may refer to a unit that processes at least one function or operation. The “…part,” “…unit,” and “…module” may be implemented in hardware, software, or a combination of hardware and software.

[0039] The classification of components in this specification is merely based on the primary function each component is responsible for. That is, two or more components may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Additionally, each component may perform some or all of the functions of other components in addition to its primary function, and some of the primary functions of each component may be exclusively performed by other components.

[0040] In describing the components in this specification, terms such as "first," "second," etc., may be used. These terms are intended for convenience of explanation to distinguish one component from another, and unless otherwise specifically stated, the nature, order, etc., of the components are not limited by these terms.

[0041] In each step mentioned in this specification, the steps may proceed differently from the specified order unless the context clearly indicates a specific order. That is, the steps may be performed in the same order as specified, substantially simultaneously, or in the reverse order.

[0042] In this specification, "and / or" may mean each of the listed components and a combination of two or more of the components. For example, "A, B and / or C" may be used with the same meaning as "at least one of A, B and C."

[0043] In this specification, "predetermined" may be a concept encompassing "pre-configured." For example, "pre-configured" may be performed by a provider, manager, operator, etc. of a device, system, or service.

[0044] According to exemplary embodiments of the present invention, a method, apparatus, and system for predicting anxiety-related indicators based on virtual reality (VR) may be provided.

[0045] According to some embodiments of the present invention, an anxiety-related indicator of a subject can be predicted based on behavioral data of the subject obtained while the subject performs a virtual reality-based anxiety assessment process. For example, the anxiety-related indicator may refer to an indicator related to an anxiety disorder.

[0046] According to some embodiments of the present invention, an anxiety feature indicator of a subject may be generated based on behavioral data of the subject obtained while the subject performs a virtual reality-based anxiety assessment process. For example, the anxiety feature indicator may include various information related to anxiety behavior, and anxiety-related indicators may be predicted based on the anxiety feature indicator.

[0047] FIG. 1 illustrates a block diagram of a system (10; hereinafter abbreviated as anxiety-related indicator prediction system) for predicting anxiety-related indicators based on virtual reality according to an embodiment of the present invention. FIG. 2 illustrates a block diagram of a virtual reality providing system (100) according to an embodiment of the present invention.

[0048] Referring to FIG. 1, the anxiety-related indicator prediction system (10) may include a virtual reality providing system (100) and a server device (200).

[0049] The virtual reality providing system (100) may be a system for providing a virtual reality-based anxiety assessment process (hereinafter abbreviated as anxiety assessment process) including virtual reality content to an anxiety assessment subject (hereinafter abbreviated as subject). The virtual reality providing system (100) may be a system built by the provider of the anxiety assessment process. For example, the virtual reality providing system (100) may provide the anxiety assessment process to the subject and, while the subject performs the anxiety assessment process, collect and acquire data regarding the subject (e.g., behavioral data, anxiety score data, biosignal data, etc.). The virtual reality providing system (100) may perform processing, such as processing or converting the collected and acquired data, as needed. The virtual reality providing system (100) may interact with a server device (200) via a network. The virtual reality providing system (100) may transmit data regarding the subject to the server device (200) and receive predicted anxiety-related indicators of the subject from the server device (200).

[0050] A virtual reality providing system (100) may include at least one device, and at least one of the at least one device may be a display device for providing virtual reality content to a subject. In some examples, the virtual reality providing system (100) may include a display device that can be worn on the subject's skin or in close proximity to the subject's skin. For example, the virtual reality providing system (100) may include a head-mounted display (HMD) device; an optical head-mounted display (OHMD) device; a device such as goggles or a headset having a display, sensor, and computing functions; etc.

[0051] A virtual reality providing system (100) may include a control unit (101), a storage unit (102), a communication unit (103), a sensor (104), and a display (105).

[0052] The control unit (101) can control the overall functions and operations of the virtual reality providing system (100). The control unit (101) can control the components of the virtual reality providing system (100). That is, the control unit (101) can provide information or data necessary for the operation of the components of the virtual reality providing system (100) and can perform operations based on the information or data generated or managed by the components. The control unit (101) may include at least one processor, at least one circuit, etc. The at least one processor may include at least one of a central processing unit (CPU), a graphics processing unit (GPU), and a neural network processing unit (NPU). The control unit (101) can perform the necessary control to operate the virtual reality providing system (100) according to various embodiments described in this specification. For example, the control unit (101) can control the operation of the virtual reality providing system (100) by executing software, programs, or instructions stored in the storage unit (102).

[0053] The storage unit (102) can store data used in the virtual reality providing system (100) and software, programs, and commands for the operation of the virtual reality providing system (100). The storage unit (102) can provide the stored data according to the control of the control unit (101). The storage unit (102) can store applications, drivers, etc. to be driven by the control unit (101). For example, the storage unit (102) can store virtual reality content provided to a subject. For example, the storage unit (102) can store artificial intelligence models such as a body keypoint extraction model, a body motion recognition model, a face keypoint extraction model, and an expression recognition model for acquiring behavioral data of a subject. The storage unit (102) may include at least one memory. For example, the storage unit (102) may include RAM such as DRAM, SRAM, etc.; ROM; EEPROM; HDD; SSD; flash storage means, etc.

[0054] The communication unit (103) can perform the function of transmitting and receiving signals with other devices. The communication unit (103) performs wired communication or wireless communication and can process signals according to the control of the control unit (101). The communication unit (103) may include at least one network interface. For example, the communication unit (103) may include an RF circuit, an antenna, etc. for wireless communication, or a connection terminal, a modem, a driver module, etc. for wired communication. For example, the communication unit (103) may support at least one of various communication protocols, such as cellular communication like LTE and 5G, short-range wireless communication like WiFi and Bluetooth, and short-range wired communication like Ethernet.

[0055] The sensor (104) may include at least one sensor that collects specific data about the subject while the subject performs an anxiety assessment process. In some examples, the sensor (104) may include a motion recognition sensor (such as an optical sensor-based motion recognition sensor, an IMU-based motion recognition sensor, etc.) for recognizing the subject's motion. In some examples, the sensor (104) may include an optical sensor that captures (or scans) the subject to collect image data (or scan data). For example, the optical sensor may refer to an RGB camera, an IR camera, a LiDAR, etc. In some examples, the sensor (104) may include a biosignal measurement sensor for collecting the subject's biosignal data. For example, the biosignal data may be collected by measuring the subject's biosignal. For example, the biosignal measurement sensor may include a dry electroencephalogram (EEG) measurement sensor, etc. In some examples, the sensor (104) may include an IMU sensor such as an accelerometer, a gyroscope, or a magnetometer. In some examples, the sensor (104) may include an audio sensor. The sensor (104) may include additional sensors other than the aforementioned sensor as needed.

[0056] The display (105) may include at least one display that outputs virtual reality to a subject. That is, the display (105) may include at least one display that projects virtual reality onto the subject's field of view (FOV). For example, the display (105) may include an LCD, LED, OLED, etc.

[0057] A subject performing an anxiety assessment process may interact with virtual reality through various types of input. For example, a virtual reality providing system (100) may require the subject to respond to a predetermined survey (e.g., anxiety score), and the subject may respond to the survey through various types of input. In some examples, various types of input may include motion recognition-based input (e.g., gestures using hands, arms, or head), manipulation of an input unit (not shown), etc.

[0058] A virtual reality providing system (100) according to one example may include a wearable device (110), an optical sensor device (120), and a computing device (130), as illustrated in FIG. 2. The virtual reality providing system (100) may further include an input device (not shown), such as a controller, as needed. The wearable device (110), the optical sensor device (120), the computing device (130), and the input device (not shown) may be connected via a network and interact with each other.

[0059] Some of the components of the aforementioned virtual reality providing system (100) may be included in a wearable device (110), an optical sensor device (120), or a computing device (130). Some of the components of the aforementioned virtual reality providing system (100) may be included in a wearable device (110), an optical sensor device (120), and a computing device (130), respectively.

[0060] The wearable device (110) may be a device including a display that provides virtual reality content accompanying the anxiety assessment process to the subject (e.g., an HMD device, etc.). The wearable device (110) may be a device including a sensor for collecting certain data (e.g., biosignal data) from the subject performing the anxiety assessment process (e.g., a biosignal measurement sensor device).

[0061] In some examples, the wearable device (110) may include a control unit, a storage unit, a communication unit, a sensor, a display, etc. However, the control unit, the storage unit, and the communication unit may be applied as described above in relation to the virtual reality providing system (100), but may be applied according to the purpose and function of the device.

[0062] In some examples, the wearable device (110) may be an HMD device, and the storage of the HMD device may store virtual reality content to be provided to the subject. In other examples, the storage of the HMD device may store some data related to the virtual reality content (e.g., cache data, etc.), and the virtual reality content may be stored in the storage of the computing device (130). In this case, the virtual reality content may be rendered in the computing device (130) and output from the HMD device.

[0063] In some examples, the sensor of the wearable device (110) may include an optical sensor that captures (or scans) at least a portion of the subject's face to collect image data (or scan data). For example, the optical sensor may refer to an RGB camera, IR camera, LiDAR, etc., installed inside or outside the wearable device (110). For example, the optical sensor may collect image data (or scan data) at a predetermined time point or continuously collect it in predetermined time units within a predetermined time interval. In some examples, the sensor of the wearable device (110) may include a biosignal measurement sensor (e.g., a brainwave measurement sensor, etc.) for collecting the subject's biosignal data. In some examples, the sensor of the wearable device (110) may include an IMU sensor-based motion recognition sensor. In some examples, the sensor of the wearable device (100) may include an audio sensor, etc.

[0064] In some examples, a plurality of wearable devices (110) may be provided. In this case, the plurality of wearable devices (110) may include a display device for outputting virtual reality to a subject (e.g., an HMD device, etc.) and a sensor device for measuring the subject's biosignals (e.g., a biosignal measurement sensor device, etc.).

[0065] The optical sensor device (120) can capture (or scan) the subject's body, face, etc., and collect image data (or scan data) of the subject. For example, the optical sensor device (120) can collect image data (or scan data) at a predetermined time point or continuously collect it in predetermined time units over a predetermined time interval. For example, the optical sensor device (120) may include an RGB camera, an IR camera, a lidar, etc.

[0066] In some examples, the optical sensor device (120) may include an optical sensor, a control unit, a storage unit, and a communication unit. However, the control unit, storage unit, and communication unit may be applied as described above in relation to the virtual reality providing system (100), but may be applied according to the purpose and function of the device. In some examples, the optical sensor device (120) may provide an optical sensor-based motion recognition function.

[0067] In some examples, the optical sensor device (120) may be an edge computing device. In this case, an artificial intelligence model, such as a body keypoint extraction model, a body motion recognition model, a face keypoint extraction model, and a facial expression recognition model, may be stored in the storage unit of the optical sensor device (120). The optical sensor device (120) may collect image data (or scan data) of a subject and obtain behavioral data (i.e., skeletal data and facial expression data) of the subject using the artificial intelligence model. In some other examples, the optical sensor device (120) may collect image data (or scan data) of a subject and transmit it to a computing device (130), and the computing device (130) may obtain behavioral data (e.g., skeletal data and facial expression data) of the subject using the artificial intelligence model based on the image data (or scan data) of the subject. In this case, an artificial intelligence model, such as a body keypoint extraction model, a body motion recognition model, a face keypoint extraction model, and a facial expression recognition model, may be stored in the storage unit of the computing device (130).

[0068] The computing device (130) may be a device that exists separately from the wearable device (110). For example, the computing device (130) may include a smartphone, tablet, laptop, PC, etc.

[0069] In some examples, the computing device (130) may include a control unit, a storage unit, and a communication unit. However, the control unit, storage unit, and communication unit may be applied according to the purpose and function of the device, although the above-mentioned details may apply in relation to the virtual reality providing system (100). For example, virtual reality content may be stored in the storage unit of the computing device (130).

[0070] The computing device (130) can acquire data about a subject collected from the sensor and optical sensor device (120) of the wearable device (110) and store the acquired data. The computing device (130) can perform processing such as processing or converting the acquired data about the subject as needed. The computing device (130) can transmit data about the subject to the server device (200) via a network and receive anxiety characteristic indicators and / or anxiety-related indicators of the subject from the server device (200).

[0071] The server device (200) may be a device of a provider that provides a service for predicting anxiety-related indicators (hereinafter abbreviated as anxiety-related indicator prediction service). The server device (200) may interact with the virtual reality providing system (100) via a network. For example, the server device (200) may receive data regarding a subject (e.g., behavioral data, anxiety score data, biosignal data, etc.) from the virtual reality providing system (100) and, based on the received data, determine the subject's anxiety characteristic indicators and / or predict anxiety-related indicators. The server device (200) may provide the subject's anxiety characteristic indicators and / or anxiety-related indicators upon request from the virtual reality providing system (100). In some examples, the server device (200) may provide the anxiety-related indicator prediction service in the form of a platform.

[0072] The server device (200) may include a control unit (201), a storage unit (202), and a communication unit (203).

[0073] The control unit (201) can control the overall functions and operations of the server device (200). The control unit (201) can control the components of the server device (200). That is, the control unit (201) can provide information or data necessary for the operation of the components of the server device (200) and can perform operations based on the information or data generated or managed by the components. The control unit (201) may include at least one processor, at least one circuit, etc. The at least one processor may include at least one of a central processing unit (CPU), a graphics processing unit (GPU), and a neural network processing unit (NPU). The control unit (201) can perform the necessary controls to enable the server device (200) to operate according to various embodiments described in this specification. For example, the control unit (201) can control the operation of the server device (200) by executing software, programs, or instructions stored in the storage unit (202).

[0074] The storage unit (202) can store data used in the server device (200) and software, programs, and commands for the operation of the server device (200). The storage unit (202) can provide the stored data under the control of the control unit (201). The storage unit (202) can store applications, drivers, etc. to be driven by the control unit (201). For example, the storage unit (202) can store a rule-based model or a trained artificial intelligence model used for generating anxiety characteristic indicators, predicting anxiety-related indicators, etc. The storage unit (102) may include at least one memory. For example, the storage unit (102) may include RAM such as DRAM, SRAM, etc.; ROM; EEPROM; HDD; SSD; flash storage means, etc.

[0075] The communication unit (203) can perform the function of transmitting and receiving signals with other devices. The communication unit (203) performs wired communication or wireless communication and can process signals according to the control of the control unit (201). The communication unit (203) may include at least one network interface. For example, the communication unit (203) may include an RF circuit, an antenna, etc. for wireless communication, or a connection terminal, a modem, a driver module, etc. for wired communication. For example, the communication unit (103) may support at least one of various communication protocols, such as cellular communication like LTE or 5G, short-range wireless communication like WiFi or Bluetooth, and short-range wired communication like Ethernet.

[0076] FIG. 1 shows only one virtual reality providing system (100). However, multiple virtual reality providing systems may connect to a server device (200) to use the anxiety-related indicator prediction service.

[0077] The relationship between the virtual reality providing system (100) and the server device (200) as shown in FIG. 1 can be established when an anxiety-related indicator prediction service is provided in the form of a platform. In another embodiment of the present invention, the virtual reality providing system (100) and the server device (200) may be integrated so that the functions of the server device (200) are performed independently within the virtual reality providing system (100). In this case, the description of the components and functions of the server device (200) described above may be applied to the virtual reality providing system (100).

[0078] For example, the anxiety-related indicator prediction service may be provided in the form of a non-network-based program rather than a platform. In this case, unlike as illustrated in FIG. 1, the anxiety-related indicator prediction service may be provided by a program or application installed on a virtual reality providing system (100), for example, a computing device (130), without a server device (200). That is, the virtual reality providing system (100) may predict the anxiety-related indicators of a subject based on data regarding the subject. In this case, the server device (200) may be the entity providing the program or application.

[0079] FIGS. 3 and FIGS. 5 are flowcharts illustrating a process for predicting anxiety-related indicators according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating a process of virtual reality content according to an embodiment of the present invention. The process for predicting anxiety-related indicators can be performed by an anxiety-related indicator prediction system (10).

[0080] In some examples, S301 and S302 illustrated in FIG. 3 may be performed by a virtual reality providing system (100), and S303 and S304 may be performed by a server device (200). In this case, the server device (200) may obtain the subject's behavior data, anxiety score data, and biosignal data from the virtual reality providing system (100). In other examples, as described above, the server device (200) and the virtual reality providing system (100) may be integrated. In this case, the process illustrated in FIG. 3 may be performed by the virtual reality providing system (100). The process illustrated in FIG. 4 may be performed by the virtual reality providing system (100). Hereinafter, the process illustrated in FIG. 3 will be described as an example in which it is performed by the virtual reality providing system (100).

[0081] Referring to FIG. 3, the virtual reality providing system (100) can provide the subject with an anxiety assessment process including virtual reality content (e.g., S301).

[0082] In some examples, virtual reality content may include content for anxiety-related assessment, training, etc. For example, virtual reality content may include content related to anxiety stimuli or experiences, relaxation training, etc.

[0083] In some examples, the anxiety assessment process may include multiple virtual reality contents. The multiple virtual reality contents may be provided to the subject sequentially according to the order selected by the subject or according to a pre-set order.

[0084] In some examples, virtual reality content may include requiring at least one specific action from a subject. For example, virtual reality content may include a mission that requires a specific action from a subject. For example, 'action' may include activities, movements, postures, facial expressions, etc.

[0085] With reference to FIG. 4, the process of virtual reality content according to one embodiment will be described in more detail.

[0086] Referring to FIG. 4, the virtual reality providing system (100) may provide a pre-anxiety related questionnaire to the subject (e.g., S3011). The pre-anxiety related questionnaire may be provided to assess the subject's pre-anxiety (e.g., anxiety felt before a mission is provided or while waiting for a mission). 'Pre-anxiety' may be a concept that includes 'anticipatory anxiety'.

[0087] In some examples, the prior anxiety questionnaire may include at least one item and at least one answer option for each item. For example, the prior anxiety questionnaire may include a questionnaire related to anxiety symptoms. For example, the prior anxiety questionnaire may include a questionnaire that directly asks the subject to rate their current level of anxiety on a scale of 0 to 100.

[0088] The virtual reality providing system (100) can obtain prior anxiety score data based on the subject's answers to a prior anxiety-related survey (e.g., S3012). For example, a predetermined score may be set for each answer option, and the prior anxiety score may be calculated by simply summing or weighting the set scores. For example, the weights may be pre-set by the provider, manager, operator, etc. of the virtual reality providing system (100).

[0089] In some cases, the reaction time taken by a subject to input answers to a pre-anxiety questionnaire can be obtained and reflected in the calculation of the pre-anxiety score according to pre-established rules. That is, in some cases, pre-anxiety score data can be obtained using a pre-established rule-based model or a trained artificial intelligence model based on the pre-anxiety questionnaire and the reaction time taken to input answers to the pre-anxiety questionnaire. For example, the trained artificial intelligence model may be trained using traditional anxiety assessment scales as labels.

[0090] The virtual reality providing system (100) can provide a mission to the subject (e.g., S3013). As described above, the mission may require the subject to perform at least one specific action.

[0091] In some examples, the mission may include behaviors for responding to anxiety stimuli (hyperventilation, lifting the head, etc.), behaviors for experiencing anxiety (e.g., giving an acceptance speech, experiencing an elevator ride, etc.), and behaviors for relaxation training (e.g., performing relaxation movements, maintaining a relaxation posture, etc.).

[0092] The virtual reality providing system (100) may provide an anxiety-related questionnaire to the subject (e.g., S3014). The anxiety-related questionnaire may be provided to assess the anxiety the subject feels during or after the mission is completed.

[0093] In some examples, the anxiety-related questionnaire may include at least one item and at least one answer option for each item. For example, the anxiety-related questionnaire may include a questionnaire related to anxiety symptoms. For example, the anxiety-related questionnaire may include a questionnaire that directly asks the subject to rate a score (e.g., 0 to 100) corresponding to the level of anxiety felt during or after the mission.

[0094] The virtual reality providing system (100) can obtain anxiety score data based on the subject's answers to an anxiety-related survey (e.g., S3015). For example, a predetermined score may be set for each answer option, and the anxiety score may be calculated by simply summing or weighting the set scores. For example, the weights may be pre-set by the provider, manager, operator, etc. of the virtual reality providing system (100).

[0095] In some examples, mission completion time and the reaction time taken by the subject to input answers to anxiety-related questionnaires can be obtained and reflected in the calculation of anxiety scores according to pre-established rules. That is, in some examples, anxiety score data can be obtained using a pre-established rule-based model or a trained artificial intelligence model based on anxiety-related questionnaires, reaction times taken to input answers to anxiety-related questionnaires, and mission completion time. For example, the trained artificial intelligence model may be trained using traditional anxiety assessment scales as labels.

[0096] The virtual reality providing system (100) can acquire behavioral data, anxiety score data, and biosignal data of the subject while the subject performs an anxiety assessment process including virtual reality content (e.g., S302).

[0097] In some examples, behavioral data may include at least one of skeletal data and facial expression data.

[0098] In some examples, skeletal data may include coordinate data of specific body part points. For example, specific body part points may include the head, spine, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, left hand, right hand, fingers, joints for each finger, left pelvis, right pelvis, left knee, right knee, left ankle, right ankle, etc.

[0099] In some examples, facial expression data may include coordinate data of specific facial area points. For example, facial area points may include eyebrows, eyes, eyelids, cheeks, mouth, chin, tongue, etc.

[0100] Image data (or scan data) may be collected by photographing (or scanning) the subject while the subject performs the anxiety assessment process. Skeletal data may be obtained using an artificial intelligence model that extracts specific body (or face) keypoints based on the image data (or scan data). Since body keypoint extraction models and face keypoint extraction models are already known, specific descriptions are omitted in this specification.

[0101] In some examples, behavioral data may be acquired at a predetermined number of points in time. In some examples, behavioral data may be acquired continuously over time. That is, behavioral data may be time-series data. For example, behavioral data may be acquired in predetermined time units. For example, virtual reality content may be divided into multiple segments according to a predetermined criterion, and behavioral data may be acquired in predetermined time units in at least one of the multiple segments.

[0102] In some examples, virtual reality content may include a mission waiting period, a mission execution period, and a mission completion period, and behavioral data may be acquired in at least one of the mission waiting period, the mission execution period, and the mission completion period. For example, behavioral data may be acquired in predetermined time units in at least one of the mission waiting period, the mission execution period, and the mission completion period. For example, behavioral data may be acquired in predetermined time units in each period.

[0103] In some examples, skeletal data and facial expression data may include motion-related data. For example, data related to a subject's body movements can be obtained by using an artificial intelligence model (e.g., a body motion recognition model) based on the subject's body part points. For example, data related to a subject's facial movements can be obtained by using an artificial intelligence model (e.g., a facial expression recognition model) based on the subject's face part points. Since body part point-based body motion recognition models and face part point-based facial expression recognition models are already known, specific descriptions are omitted in this specification.

[0104] In some examples, motion-related data included in the skeletal data may include head movements, shoulder movements, elbow movements, wrist movements, hand movements, finger movements, pelvic movements, knee movements, ankle movements, etc.

[0105] In some examples, the motion-related data included in the facial expression data comprises: eyebrow-related movements (e.g., lowering the left eyebrow, lowering the right eyebrow, raising the inner part of the left eyebrow, raising the inner part of the right eyebrow, raising the outer part of the left eyebrow, raising the outer part of the right eyebrow, etc.); cheek-related movements (puffing out the left cheek, puffing out the right cheek, raising the left cheek, raising the right cheek, sucking in the left cheek, sucking in the right cheek, etc.); and jaw-related movements (e.g., raising the lower jaw, raising the upper jaw, dropping the lower jaw, moving the jaw to the left, moving the jaw to the right, protruding the jaw forward, etc.). Eye / eyelid related movements (e.g., closing the left eye, closing the right eye, looking down with the left eye, looking down with the right eye, looking left with the left eye, looking left with the right eye, looking right with the left eye, looking right with the left eye, looking up with the right eye, looking up with the left eye, tightening the right eyelid, raising the left upper eyelid, raising the right upper eyelid, etc.); lip related movements (e.g., lowering the left corner of the mouth, lowering the right corner of the mouth, pulling the left corner of the mouth up, pulling the right corner of the mouth up, gathering the lips forward, tightening the left lip, tightening the right lip, etc.); tongue related movements (e.g., the tip of the tongue being positioned between the front teeth, the tip of the tongue touching the upper gums, the front part of the tongue touching the roof of the mouth, etc.).

[0106] In some examples, the anxiety score data may include the anxiety score data obtained in the aforementioned S3015. In some examples, the anxiety score data may further include the prior anxiety score data obtained in the aforementioned S3012. In some examples, the anxiety score data may be obtained by fusing the prior anxiety score data obtained in the aforementioned S3012 and the anxiety score data obtained in the aforementioned S3015. For example, the fusion may include concatenation. Since details regarding the anxiety score data have been previously described, a redundant explanation is omitted.

[0107] In some examples, biosignal data may include brainwave data.

[0108] In some examples, biosignal data can be acquired continuously over time. That is, biosignal data can be time-series data. For example, biosignal data can be acquired in predetermined time units. For example, virtual reality content can be divided into multiple segments according to predetermined criteria, and biosignal data can be acquired in predetermined time units in at least one of the multiple segments.

[0109] A virtual reality providing system (100) can generate an anxiety characteristic index of a subject based on the subject's behavior data, anxiety score data, and biosignal data (e.g., S303).

[0110] For example, an anxiety characteristic index can be a scalar, a vector, a matrix, or a tensor. For example, an anxiety characteristic index can be a vector.

[0111] In some examples, anxiety characteristic indicators can be generated by fusing behavioral data, anxiety score data, and biosignal data. For example, preprocessing such as vectorization, matrixization, and tensorization can be performed on each of the behavioral data, anxiety score data, and biosignal data. Anxiety characteristic indicators can be generated by fusing the preprocessed data.

[0112] In some examples, fusion may include concatenation. In this case, preprocessing may further include, as necessary, adjusting and aligning data size and dimensions, setting the concatenation direction, etc.

[0113] In some examples, behavioral feature information of a subject can be extracted based on the subject's behavioral data using a trained artificial intelligence model (hereinafter referred to as a feature information extraction model). The feature information extraction model may have performed representation learning using a contrastive learning method with a behavioral data set acquired from virtual reality content.

[0114] Anxiety characteristic indicators for a subject can be generated based on the subject's behavioral characteristic information, anxiety score data, and biosignal data. For example, anxiety characteristic indicators can be generated by fusing behavioral characteristic information, anxiety score data, and biosignal data.

[0115] In some examples, virtual reality content may be divided into multiple sections according to predetermined criteria, as previously mentioned. The feature information extraction model may have performed representation learning using a contrastive learning method with behavioral data sets obtained from at least two of the multiple sections.

[0116] In some examples, as previously mentioned, virtual reality content may include a mission waiting section, a mission execution section, and a mission completion section. For example, the feature information extraction model may have performed representation learning using a contrastive learning method with behavioral data sets obtained from at least two of the mission waiting section, the mission execution section, and the mission completion section. For example, the feature information extraction model may have performed representation learning using a contrastive learning method with behavioral data sets obtained from each section.

[0117] For example, contrastive learning can be performed by setting pairs of behavioral data sets corresponding to the same interval as positive pairs and pairs of behavioral data sets corresponding to different intervals as negative pairs. In this case, the differences between intervals of the behavioral data can be clearly identified, thereby enabling the acquisition of higher-quality anxiety characteristic indicators.

[0118] In some examples, as illustrated in FIG. 5, certain other data based on behavioral data can be generated and used to generate anxiety characteristic indicators.

[0119] Referring to FIG. 5, the virtual reality providing system (100) can generate at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data based on the subject’s behavior data (e.g., S3031). For example, at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data can be generated based on coordinate data of the subject’s body (or face) parts points acquired continuously over time (e.g., in predetermined time units) in a predetermined time interval.

[0120] As previously mentioned, virtual reality content may include missions that require a specific action from the subject, and the virtual reality content may include a mission waiting section, a mission performance section, and a mission completion section. Based on the subject's behavioral data in the virtual reality content, for example, the subject's behavioral data in each section of the virtual reality content, behavioral intensity data, conscientiousness data, compliance data, and proactiveness data of the subject may be generated.

[0121] Behavioral intensity data may include data that quantifies a specific action (e.g., a movement) based on speed, size, etc., when the subject performs a specific action in accordance with the requirements of the virtual reality content. For example, behavioral intensity data may include data that quantifies the rate of change and amount of change of the subject's behavioral data during the time interval in which the subject performs a specific action. For example, behavioral intensity data may include data that quantifies the rate of change and amount of change of coordinate data of specific body (or face) points of the subject during the time interval in which the subject performs a specific action.

[0122] In some examples, behavior intensity data may be generated based on the subject's behavior data during the mission completion phase. The behavior intensity data may include data quantified based on speed, size, etc. of the subject's behavior during the mission completion phase. For example, if the virtual reality providing system (100) is equipped with a motion recognition-based input function, the subject may perform actions (e.g., gestures using hands, arms, head, etc.) to input answers to the survey during the mission completion phase, and data quantified based on speed, size, etc. of such actions may be used as behavior intensity data.

[0123] Conscientiousness data may include data that quantifies an action (e.g., a specific posture, movement, etc.) based on time, frequency, etc., when a subject performs a specific action in accordance with the requirements of virtual reality content. For example, conscientiousness data may include data that quantifies the time taken and the number of attempts made by the subject to perform a specific action. For example, conscientiousness data may include data that quantifies the total time taken from the start to the end of a specific action by the subject, the number of attempts made to perform the specific action, etc.

[0124] In some examples, conscientiousness data may be generated based on the subject's behavioral data during the mission execution phase. Conscientiousness data may include data that quantifies the subject's behavior during the mission execution phase based on criteria such as time or frequency. For example, the subject may take actions to perform the mission, and data quantifying such actions based on time, frequency, etc., can be used as conscientiousness data.

[0125] Compliance data may include data that quantifies the degree of congruence between the action required by the virtual reality content (e.g., a specific posture, movement, etc.) and the action performed by the subject in accordance with the requirements of the virtual reality content, and the degree of similarity between the action required by the virtual reality content and the action performed by the subject in accordance with the requirements of the virtual reality content, when the subject takes a specific action in accordance with the requirements of the virtual reality content.

[0126] For example, the degree of agreement can be a value that quantifies the extent to which two actions correspond according to a preset standard. For instance, when the action required by virtual reality content and the action taken by the subject are both postures of lifting the neck, the neck angle can be the preset standard, and the degree of agreement between the two actions can be calculated based on the neck angle.

[0127] For example, similarity may include distance-based similarity. For instance, when the action required by virtual reality content and the action taken by the subject are both postures of raising the neck, the similarity can be calculated between the set of coordinates of body part points corresponding to that posture (i.e., stored reference values) and the set of coordinates of body part points extracted from the subject's posture. Since the concept of similarity is already known, a detailed explanation is omitted.

[0128] In some examples, compliance data may be generated based on the subject's behavioral data during the mission execution phase. For instance, compliance data may include quantified data regarding the consistency and similarity between the behavior required by the mission and the behavior taken by the subject in response to the requirement. For instance, the subject may take actions to perform the mission, and the consistency and similarity between the behavior required by the mission and the subject's behavior can be quantified and used as compliance data.

[0129] Activeness data may include data quantifying the subject's behavior during the execution of virtual reality content based on criteria such as time, speed, frequency, and magnitude. Since each criterion is as previously described, a detailed explanation is omitted.

[0130] In some examples, proactiveness data may be generated based on the subject's behavioral data during periods without missions, that is, periods when there is no need to take specific actions. The proactiveness data may include data quantifying the subject's behavior during periods without missions based on criteria such as time, speed, frequency, and magnitude.

[0131] In some examples, activeness data may be generated based on the subject's behavioral data during the mission waiting period. The activeness data may include data quantifying the subject's behavior during the mission waiting period based on time, speed, frequency, size, etc.

[0132] A virtual reality providing system (100) can generate an anxiety characteristic index of a subject based on at least one of the subject's behavioral intensity data, conscientiousness data, compliance data, and activeness data, as well as anxiety score data and biosignal data (e.g., S3032). For example, an anxiety characteristic index can be generated by fusing at least one of the behavioral intensity data, conscientiousness data, compliance data, and activeness data; anxiety score data; and biosignal data.

[0133] According to some embodiments of the present invention, behavior intensity data, conscientiousness data, compliance data, and activeness data (hereinafter abbreviated as behavior intensity data, etc.) of a subject are generated based on the subject's behavior data, and when the behavior intensity data, etc. is used together with the subject's anxiety score data and biosignal data, the performance of predicting anxiety-related indicators can be improved. For example, anxiety score data sufficiently reflects the subject's psychological state, but subjective elements may be reflected excessively. Biosignal data is an objective element, but the subject's anxiety behavior is not directly reflected. Behavioral intensity data, etc., may directly reflect the subject's anxiety behavior, but there is also a possibility that it may be altered by the subject's subjective elements. However, according to some embodiments of the present invention, when anxiety score data and biosignal data, such as behavior intensity data, are used together, they complement each other, and high-quality anxiety characteristic indicators that can be used to predict anxiety-related indicators can be generated.

[0134] According to some of the examples described above, an anxiety characteristic index of a subject can be generated based on the subject's behavioral data, anxiety score data, and biosignal data. However, according to some other examples, an anxiety characteristic index may be generated based on behavioral data and anxiety score data, or based on behavioral data and biosignal data. That is, an anxiety characteristic index can be generated based on at least one of behavioral data, anxiety score data, and biosignal data.

[0135] The virtual reality providing system (100) can predict the subject's anxiety-related indicators based on the subject's anxiety characteristic indicators (e.g., S304).

[0136] In some examples, anxiety-related indicators may include the severity of anxiety disorder (hereinafter abbreviated as severity), the risk of anxiety disorder (hereinafter abbreviated as risk), the response to treatment of anxiety disorder at a predetermined point in time (hereinafter abbreviated as treatment response), the expected duration of treatment for anxiety disorder (hereinafter abbreviated as expected duration of treatment), etc.

[0137] For example, severity and risk may refer to scores or grades based on traditional anxiety assessment scales.

[0138] For example, treatment response may refer to the degree of improvement in the subject's anxiety disorder at a point in time when a predetermined period (e.g., 1 month, 2 months, 3 months, 6 months, etc.) has elapsed from the reference point, provided that the subject maintains the anxiety disorder treatment method being pursued at the time when the anxiety assessment process is provided (hereinafter referred to as the reference point). For example, treatment response may refer to the quantification or categorization of the degree of improvement in the anxiety disorder. For example, categories may be classified into positive response and negative response, early response and delayed response, etc. For example, the degree of improvement in the anxiety disorder may refer to the degree of change in scores or grades according to traditional anxiety assessment scales.

[0139] For example, the expected treatment period may refer to the time required for the anxiety disorder to improve to a predetermined standard from a baseline point. For instance, the predetermined standard may be established by being determined based on scores or grades according to traditional anxiety assessment scales.

[0140] In some examples, as illustrated in FIG. 6, a prediction model (2000) that outputs an anxiety-related indicator (3000) when an anxiety characteristic indicator (1000) is input may be used.

[0141] The prediction model (2000) may include at least one of a rule-based model and a trained artificial intelligence model (hereinafter referred to as an anxiety-related indicator prediction model).

[0142] For example, rule-based models can be pre-configured. For example, an anxiety-related indicator prediction model may include an artificial intelligence model trained using anxiety characteristic indicators labeled with anxiety-related indicators as a dataset. For example, depending on the nature of the anxiety-related indicator, the anxiety-related indicator prediction model may include a regression model or a classification model.

[0143] In some examples, multiple prediction models (2100, 2200, 2300) may be used in combination to predict anxiety-related indicators.

[0144] For example, as illustrated in FIG. 7, a virtual reality providing system (100) can predict a first anxiety-related indicator (3100) based on an anxiety characteristic indicator (1000) using a first prediction model (2100). A virtual reality providing system (100) can predict a second anxiety-related indicator (3200) based on an anxiety characteristic indicator (1000) using a second prediction model (2200). A virtual reality providing system (100) can predict a third anxiety-related indicator (3300) based on the first anxiety-related indicator (3100) and the second anxiety-related indicator (3200) using a third prediction model (2300).

[0145] In some examples, the virtual reality providing system (100) may further obtain anxiety-related information data of a subject from a third computing device (not shown), etc., including at least one of the subject's age of first onset of anxiety disorder, current age, duration of anxiety symptoms (e.g., may be calculated by counting backward from a reference point), history of past treatment for anxiety disorder (e.g., whether treatment has been received, response to treatment, whether treatment has been completed, whether treatment has been discontinued, etc.), stress level (e.g., may be obtained through a stress-related questionnaire, etc.), and a score or grade according to a traditional anxiety assessment scale. The virtual reality providing system (100) may predict a third anxiety-related indicator (3300) based on the first anxiety-related indicator, the second anxiety-related indicator, and the anxiety-related information data using a third prediction model (2300).

[0146] In some examples, the first anxiety-related indicator (3100) may be a treatment response, and the second anxiety-related indicator (3200) may be severity, risk, or expected duration of treatment. In other examples, the first anxiety-related indicator (3100) may be an expected duration of treatment, and the second anxiety-related indicator (3200) may be severity, risk, or treatment response. The third anxiety-related indicator (3300) may be an indicator of the appropriateness of the treatment method (hereinafter abbreviated as appropriateness indicator).

[0147] For example, the appropriateness indicator may be a quantification or categorization of the appropriateness of the anxiety disorder treatment method being pursued by the subject at a reference point. For example, the appropriateness indicator may be appropriate or inappropriate, a predetermined grade, or a score. For example, the appropriateness indicator may be established based on criteria and judgment results set by experts based on predetermined data (e.g., treatment response, expected duration of treatment, anxiety-related information data, etc.). A third prediction model (2300) may be constructed using the appropriateness indicator established by experts.

[0148] In this specification, the designation of 'one embodiment' of the principles of the present invention and various variations of such expression means that specific features, structures, characteristics, etc., associated with this embodiment are included in at least one embodiment of the principles of the present invention. Accordingly, the expression 'in one embodiment' and any other variations disclosed throughout this specification do not necessarily refer to the same embodiment.

[0149] The implementation of the device and system according to the various embodiments of the present invention described above may be realized with digital electronic circuits, integrated circuits, ASICs (application specific integrated circuits), hardware, firmware, software, or a combination thereof.

[0150] The method according to the various embodiments of the present invention described above may be implemented as a computer program or mobile application and stored on a medium so as to be executed in combination with hardware. The steps of the method or algorithm described in relation to the embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM, ROM, EPROM, EEPROM, flash memory, hard disk, removable disk, CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs. Additionally, the algorithm may be produced in the form of an installation file and provided in the form of an online download, and for this purpose, may be stored on a server accessible through an online software market.

[0151] All embodiments and conditional examples disclosed herein are intended to help those skilled in the art to understand the principles and concepts of the invention. Those skilled in the art will understand that the invention may be implemented in modified forms without departing from the essential nature of the invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a limiting sense. The scope of the invention is defined by the claims, not by the foregoing description, and all variations within the scope of the claims should be interpreted as being included in the invention.

Claims

1. A method executed by at least one processor, (S1) A step of obtaining behavioral data and anxiety score data of the subject, which are obtained while the subject performs an anxiety assessment process including virtual reality content; and (S2) A step of generating an anxiety characteristic index of the subject based on the subject's behavior data and anxiety score data; comprising A method for predicting anxiety-related indicators.

2. In Claim 1, The above behavioral data includes at least one of skeletal data and facial expression data, A method for predicting anxiety-related indicators.

3. In Claim 1, (S1) Step further includes acquiring the subject's biosignal data acquired while the subject performs the anxiety assessment process, and (S2) Step includes generating an anxiety characteristic indicator of the subject based on the subject's behavior data, anxiety score data, and biosignal data. A method for predicting anxiety-related indicators.

4. In Claim 3, The above biosignal data includes brainwave data, A method for predicting anxiety-related indicators.

5. In Claim 1, (S2) step includes: a step of extracting behavioral characteristic information of the subject based on the behavioral data of the subject using a trained artificial intelligence model; and a step of generating an anxiety characteristic index of the subject based on the behavioral characteristic information and anxiety score data of the subject. The above-mentioned trained artificial intelligence model is one in which representation learning is performed using a contrastive learning method with a behavioral data set obtained from the above-mentioned virtual reality content, A method for predicting anxiety-related indicators.

6. In Claim 5, The above virtual reality content includes a mission that requires a specific action from the subject, and The above virtual reality content includes a mission waiting section, a mission execution section, and a mission completion section, and The above-mentioned trained artificial intelligence model is one in which representation learning is performed using a contrastive learning method with behavioral data sets acquired from each segment of the above-mentioned virtual reality content, A method for predicting anxiety-related indicators.

7. In Claim 1, The virtual reality content includes requiring at least one action from the subject, and the action data includes action data acquired at multiple points in time while the virtual reality content is being performed. (S2) The step comprises: generating at least one of the subject’s behavioral intensity data, conscientiousness data, compliance data, and activeness data for the virtual reality content based on the subject’s behavioral data; and generating the subject’s anxiety characteristic index based on at least one of the subject’s behavioral intensity data, conscientiousness data, compliance data, and activeness data and anxiety score data. A method for predicting anxiety-related indicators.

8. In Claim 7, The above behavior intensity data includes data that quantifies the behavior of the subject performed according to the requirements of the virtual reality content based on speed or magnitude, and The above-mentioned sincerity data includes data that quantifies the actions of the subject performed in accordance with the requirements of the above-mentioned virtual reality content based on time or frequency, and The above compliance data includes data quantifying the degree of agreement between the behavior required by the virtual reality content and the behavior of the subject performed according to the requirement; or the degree of similarity between the behavior required by the virtual reality content and the behavior of the subject performed according to the requirement. The above activeness data includes data that quantifies the behavior of the subject based on time, speed, frequency, or magnitude while the virtual reality content is being performed. A method for predicting anxiety-related indicators.

9. In Claim 1, The virtual reality content includes a mission that requires a specific action from the subject, and the virtual reality content includes a mission waiting section, a mission execution section, and a mission completion section, and the action data includes at least one action data obtained in each section of the virtual reality content. (S2) The step comprises: generating at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data for the virtual reality content based on the subject’s behavior data; and generating an anxiety characteristic index of the subject based on at least one of the subject’s behavior intensity data, conscientiousness data, compliance data, and activeness data and anxiety score data. The above behavioral intensity data includes data that quantifies the behavior of the subject in the mission completion section based on speed or magnitude, and The above conscientiousness data includes data that quantifies the subject's actions for performing the actions required by the mission during the mission execution section, based on time or frequency. The above compliance data includes data that quantifies the degree of agreement between the behavior required by the mission and the behavior of the subject in the mission performance section; or the degree of similarity between the behavior required by the mission and the behavior of the subject. The above-mentioned activeness data includes data that quantifies the behavior of the subject during the mission waiting period based on time, speed, frequency, or magnitude. A method for predicting anxiety-related indicators.

10. In Claim 1, (S2) Step includes fusing the subject’s behavior data and anxiety score data to generate an anxiety characteristic index of the subject, and The above fusion includes concatenation, A method for predicting anxiety-related indicators.

11. In Claim 1, The method further comprises the step of predicting the subject's anxiety-related indicators based on the subject's anxiety characteristic indicators using a preset rule-based model or a trained artificial intelligence model. A method for predicting anxiety-related indicators.

12. In Claim 11, The above anxiety-related indicators include at least one of severity, risk, treatment response at a given point in time, and expected duration of treatment. A method for predicting anxiety-related indicators.

13. A method executed by at least one processor, A step of providing the subject with an anxiety assessment process including virtual reality content; A step of acquiring behavioral data and anxiety score data of the subject while the subject performs the anxiety assessment process; and A step comprising generating an anxiety characteristic index of the subject based on the subject's behavioral data and anxiety score data; A method for predicting anxiety-related indicators.

14. At least one memory; and It includes at least one processor that executes instructions stored in at least one memory; and The above-mentioned at least one processor is, Obtaining behavioral data and anxiety score data of the subject obtained while the subject performs an anxiety assessment process including virtual reality content, and Controlling to generate an anxiety characteristic indicator of the subject based on the subject's behavior data and anxiety score data, A device for predicting anxiety-related indicators.

15. An application program stored on a recording medium to execute the method according to claim 1 when operated by at least one processor.

Images