Emotion analysis assistance program, emotion analysis assistance device, emotion analysis assistance method, and recording medium

Abstract

Provided is an emotion analysis assistance program that is capable of performing emotion analysis while taking into consideration individual differences. An emotion analysis assistance program according to the present disclosure comprises a setting step, a determination step, and an output step. In the setting step, reference emotion score information that indicates emotion score information serving as a reference for a subject is set on the basis of an emotion score information group pertaining to the subject. In the determination step, correction information for correcting emotion score information pertaining to the subject is determined on the basis of the reference emotion score information and determination reference information, which is used in emotion determination based on emotion score information. In the output step, the correction information is output.

Description

Emotion analysis support program, emotion analysis support device, emotion analysis support method, and recording medium

[0001] The present disclosure relates to an emotion analysis support program, an emotion analysis support device, an emotion analysis support method, and a recording medium.

[0002] When communicating face-to-face, subtle differences in facial expressions and gestures can tell if the other person's behavior is different from usual, but it is difficult to grasp the subtleties of the other person's facial expressions and emotions when communicating remotely via a camera, etc. Therefore, an emotion estimation device is described (Patent Document 1) that includes a first estimation unit that estimates multiple emotion candidates based on input data, an emotion expression model that indicates each of different emotions with an expression value, an identification unit that identifies estimated expression values ​​corresponding to the multiple emotion candidates estimated by the first estimation unit based on the emotion expression model, and a second estimation unit that estimates an emotion by integrating the multiple emotion candidates based on the estimated expression values ​​identified by the identification unit and the expression values ​​of the emotion expression model.

[0003] Japanese Patent Application Laid-Open No. 2019-133447

[0004] According to the invention of Patent Document 1, it is possible to estimate the emotional movements of a subject. However, there is a problem in that even if the emotional value estimated by the device is the same, there may be a discrepancy between the actual emotion felt by the individual.

[0005] Therefore, an object of the present disclosure is to provide an emotion analysis support program, an emotion analysis support device, an emotion analysis support method, and a recording medium that are capable of emotion analysis that takes individual differences into consideration.

[0006] In order to achieve the above-mentioned object, the emotion analysis support program of the present disclosure includes a setting procedure, a determination procedure, and an output procedure, wherein the setting procedure sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject; the determination procedure determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for determining emotions based on the emotion score information and the reference emotion score information; and the output procedure outputs the correction information. This emotion analysis support program causes a computer to execute each of the above procedures.

[0007] The emotion analysis support device of the present disclosure includes a setting unit, a determination unit, and an output unit, wherein the setting unit sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject; the determination unit determines correction information for correcting the emotion score information of the subject, based on determination criteria information used for determining an emotion based on the emotion score information and the reference emotion score information; and the output unit outputs the correction information.

[0008] The emotion analysis support method disclosed herein includes a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject; the determination step determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for determining emotions based on the emotion score information and the reference emotion score information; and the output step outputs the correction information, wherein each of the steps is executed by a computer.

[0009] The recording medium of the present disclosure is a computer-readable recording medium having recorded thereon an emotion analysis support program for causing a computer to execute each of the above steps, the recording medium including: a setting procedure, a determination procedure, and an output procedure; the setting procedure setting reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject; the determination procedure determining correction information for correcting the emotion score information of the subject, based on judgment criteria information used for determining emotions based on the emotion score information and the reference emotion score information; and the output procedure outputting the correction information.

[0010] According to the present disclosure, emotion analysis can be performed taking into account individual differences.

[0011] FIG. 1 is a block diagram showing a configuration of an example of an emotion analysis support device disclosed herein. FIG. 2 is a block diagram showing an example of a hardware configuration of the emotion analysis support device disclosed herein. FIG. 3 is a flowchart showing an example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 4 is a block diagram showing a configuration of an example of an emotion analysis support device disclosed herein. FIG. 5 is a flowchart showing an example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 6 is a block diagram showing a configuration of another example of an emotion analysis support device disclosed herein. FIG. 7 is a flowchart showing another example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 8 is a block diagram showing a configuration of another example of an emotion analysis support device disclosed herein. FIG. 9 is a flowchart showing another example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 10 is a flowchart showing another example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 11 is a block diagram showing a configuration of another example of an emotion analysis support device disclosed herein. FIG. 12 is a flowchart showing another example of a procedure performed by the emotion analysis support program disclosed herein. FIG. 13 is a flowchart showing another example of a procedure performed by the emotion analysis support program disclosed herein.

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The present disclosure is not limited to the following embodiments. In the following drawings, identical parts are designated by the same reference numerals. Furthermore, the descriptions of the embodiments can be mutually incorporated unless otherwise specified, and the configurations of the embodiments can be combined unless otherwise specified. In the present disclosure, each drawing may apply to one or more embodiments.

[0013] [Embodiment 1] The emotion analysis support program of the present disclosure is a program for causing a computer to execute a setting procedure, a determination procedure, and an output procedure. The emotion analysis support program of the present disclosure can also be said to be a program for causing a computer to function as the setting procedure, the determination procedure, and the output procedure. Furthermore, the emotion analysis support program of the present disclosure can also be said to be a program for causing a computer to execute, for example, each step of an emotion analysis support method described below.

[0014] The setting step sets reference emotion score information indicating the emotion score information serving as a standard for the subject, based on a group of emotion score information of the subject; the determination step determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for determining an emotion based on the emotion score information and the reference emotion score information; and the output step outputs the correction information.

[0015] For each of the steps, for example, "step" can be read as "processing." The emotion analysis support program of the present disclosure may be recorded on, for example, a computer-readable recording medium. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples thereof include random access memory (RAM), read-only memory (ROM), hard disk (HD), flash memory (e.g., SSD (Solid State Drive), USB flash memory, SD / SDHC card, etc.), optical disk (e.g., CD-R / CD-RW, DVD-R / DVD-RW, BD-R / BD-RE, etc.), magneto-optical disk (MO), floppy disk (FD), etc. The emotion analysis support program of the present disclosure (also referred to as, for example, a programming product or program product) may be distributed from an external computer, for example. The "distribution" may be, for example, distribution via a communication network or distribution via a device connected via a wire. The emotion analysis support program of the present disclosure may be installed and executed on the device to which it is distributed, or may be executed without being installed. An information processing device capable of executing the emotion analysis support program of the present disclosure can be referred to as, for example, the emotion analysis support device of the present disclosure.

[0016] Next, the configuration of an example of an emotion analysis support device according to the present disclosure will be described with reference to FIG. 1 . FIG. 1 is a block diagram showing an example of the configuration of an emotion analysis support device 10 according to the present disclosure (hereinafter also referred to as the present device 10). As shown in FIG. 1 , the present device 10 includes a setting unit 11, a determination unit 12, and an output unit 13. Although not shown, the present device 10 may also include, for example, an input unit, an output unit, a display unit, and / or a storage unit. The setting unit 11, the determination unit 12, and the output unit 13 are capable of executing, for example, a setting procedure, a determination procedure, and an output procedure in the emotion analysis support program according to the present disclosure, respectively.

[0017] The device 10 may be, for example, a single device including the above-mentioned components, or a device in which the components can be connected via a communication network. The device 10 can also be connected to an external device (described later) via the communication network. The communication network is not particularly limited and any known network can be used, and may be wired or wireless. Examples of the communication network include the Internet, the World Wide Web (WWW), a telephone line, a Local Area Network (LAN), a Storage Area Network (SAN), a Delay Tolerant Networking (DTN), a Low Power Wide Area Network (LPWA), and a Local 5G (L5G). Examples of wireless communication networks include Wi-Fi (registered trademark), Bluetooth (registered trademark), a Local 5G, and a LPWA. The wireless communication may be a form in which each device communicates directly (ad hoc communication), infrastructure communication, indirect communication via an access point, or the like. The device 10 may be incorporated into a server as a system, for example. The device 10 may also be a personal computer (e.g., desktop or laptop PC), a smartphone, a tablet terminal, or the like, on which the program of the present disclosure is installed. The device 10 may also be in the form of cloud computing or edge computing, for example, in which at least one of the units is located on a server and the other units are located on a terminal.

[0018] 2 is a block diagram illustrating an example of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, a storage device 104, an input device 105, an output device 106, and a communication device 107. The components of the device 10 are connected to each other via the bus 103 and their respective interfaces (I / F).

[0019] The central processing unit 101 cooperates with other components via a controller (such as a system controller or an I / O controller) and controls the entire device 10. In the device 10, the central processing unit 101 executes, for example, the program disclosed herein (emotion analysis support program) and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as a setting unit 11, a determination unit 12, and an output unit 13. The device 10 may include, as a computing device, other computing devices such as a CPU, a GPU (Graphics Processing Unit), an APU (Accelerated Processing Unit), or a combination thereof.

[0020] The bus 103 can also be connected to, for example, external devices. Examples of the external devices include an external storage device (such as an external database), a printer, an external input device, an external display device, and an external imaging device. The device 10 can be connected to an external network (the communication line network) by, for example, a communication device 107 connected to the bus 103, and can also be connected to other devices via the external network.

[0021] The memory 102 may be, for example, a main memory (primary storage device). When the central processing unit 101 performs processing, the memory 102 reads various operating programs, such as the program of the present disclosure, stored in the storage device 104 (described later), and the central processing unit 101 receives data from the memory 102 and executes the programs. The main memory may be, for example, a RAM (random access memory). Alternatively, the memory 102 may be, for example, a ROM (read only memory).

[0022] The storage device 104 is also referred to as an auxiliary storage device, for example, in contrast to the main memory (primary storage device). As described above, the storage device 104 stores an operating program including the program of the present disclosure. The storage device 104 may be, for example, a combination of a recording medium and a drive that reads and writes from and to the recording medium. The recording medium is not particularly limited and may be, for example, an internal or external type, such as a hard disk drive (HDD), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, or memory card. The storage device 104 may be, for example, a hard disk drive (HDD) or a solid-state drive (SSD) that integrates a recording medium and a drive. When the device 10 includes the storage unit, for example, the storage device 104 functions as the storage unit. The storage unit can record, for example, emotion score information, reference emotion score information, judgment criterion information, correction information, corrected emotion score information, emotion, type of situation, reference emotion score information by situation, correction information by situation, normal situation, reference emotion score information in normal situations, correction information in normal situations, appropriate emotion, inappropriate emotion, warning information, warning release information, etc., which will be described later.

[0023] In the present device 10, the memory 102 and the storage device 104 can also store various information such as log information, information acquired from an external database (not shown) or an external device, information generated by the present device 10, and information used when the present device 10 executes processing. In this case, the memory 102 and the storage device 104 may store, for example, the above-mentioned information on the user of the present device. Note that at least a portion of the information may be stored, for example, in an external server other than the memory 102 and the storage device 104, or may be stored in a distributed manner across multiple terminals using blockchain technology or the like.

[0024] The device 10 further includes, for example, an input device 105 and an output device 106. Examples of the input device 105 include pointing devices such as a touch panel, track pad, and mouse; a keyboard; imaging means such as a camera and scanner; card readers such as an IC card reader and a magnetic card reader; and audio input means such as a microphone. Examples of the output device 106 include display devices such as an LED display and a liquid crystal display; audio output devices such as a speaker; a printer; and the like. In the first embodiment, the input device 105 and the output device 106 are configured separately, but the input device 105 and the output device 106 may be configured as an integrated device, such as a touch panel display.

[0025] An example of processing by the emotion analysis support program of the present disclosure will be described in more detail with reference to Fig. 3. Fig. 3 is a flowchart showing an example of each procedure of the emotion analysis support program of the present disclosure.

[0026] The setting unit 11 sets reference emotion score information indicating the emotion score information that serves as a reference for the subject, based on a group of emotion score information of the subject (S1, setting step).

[0027] The emotion score information is, for example, information that scores the subject's basic emotion based on the subject's biometric information. The basic emotion is, for example, a fundamental element of emotion, as described below. When the emotion is determined based on Russell's circumplex model, for example, the basic emotion may be, for example, valence (VALENCE) indicating "pleasant-unpleasant" or arousal (AROUSAL) indicating "awake-sleepy." The biometric information is, for example, information about a living organism, such as information about facial expressions, information about voice, or information about physiological indices. The biometric information may be, for example, feature quantities (e.g., mean, standard deviation, coefficient of variation, root-mean-square, frequency components, etc.) calculated using a known method based on the above-described biometric information. The physiological indices include, for example, brain waves, heart rate, pulse, blood pressure, electrocardiogram, electromyogram, sweating, body temperature, skin temperature, and combinations thereof. The information on the physiological index may be, for example, the physiological index itself (e.g., the value of the physiological index, the ratio of the physiological index, etc.), or a feature calculated from the physiological index using a known method. For example, if the physiological index is a pulse rate, the information on the physiological index may be PPI (pulse peak interval). The medium for acquiring the biological information may be, for example, a medical device or a wearable device. The medical device may be, for example, a device having a function for measuring the biological information. Examples of the medical device include an electroencephalograph, a heart rate monitor, a pulse rate monitor, a blood pressure monitor, an electrocardiograph, an electromyograph, a sweat meter (a skin potential meter), a thermometer, and a skin thermometer. The wearable device may be, for example, a device having a function for measuring the biological information. Examples of the wearable device include a wristband type, a watch type, a clip type, a ring type, an earphone type, a glasses type, a contact lens type, a patch type, and a clothing type. The biometric information may be acquired by, for example, associating terminal identification information (such as an identification number) that can identify a medium from which the biometric information is acquired with the biometric information and acquiring the information.Furthermore, for example, if the biometric information acquisition medium includes user identification information (e.g., an identification number) capable of identifying the subject, the biometric information may be acquired by linking at least one of the terminal identification information and the user identification information to the biometric information. The biometric information acquisition medium may be, for example, the device disclosed herein itself, or a device other than the device disclosed herein. The biometric information may be stored in a storage unit, such as the memory 102 or storage device 104 of the device disclosed herein, or in a storage unit of a device other than the device disclosed herein. The storage unit may, for example, store the terminal identification information and the user identification information in a linked manner. In this case, the storage unit may, for example, be capable of identifying the user identification information linked to the terminal identification information. The storage unit may, for example, be a database, and the type of the database may, for example, be a hierarchical type, a network type, or a relational type.

[0028] The emotion score information may be obtained, for example, by an emotion score information output model that outputs the emotion score information of the subject when the biometric information of the subject is input. The emotion score information output model may be, for example, a publicly known model, such as the emotion analysis engine included in the "NEC Emotion Analysis Solution." The emotion score information output model may be, for example, stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein. The emotion score information may be, for example, one-dimensional data or multidimensional data. If the emotion score information is multidimensional data, the emotion score information may be coordinate information in a multidimensional Cartesian coordinate system or a multidimensional polar coordinate system based on a publicly known emotion model. In this case, the emotion determination described below may be performed based on, for example, a publicly known emotion model. The emotion model may be, for example, the Russell Circumplex model described below. The emotion score information may be, for example, stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0029] The Russell circumplex model is a model that proposes that all emotions are arranged as coordinate information in a two-dimensional Cartesian coordinate system or a two-dimensional polar coordinate system consisting of a coordinate axis indicating "pleasant-unpleasant" (AROUSAL axis) and a coordinate axis indicating "alertness-sleepiness" (VALENCE axis). The two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system based on the Russell circumplex model classifies, for example, of the four quadrants of the two-dimensional Cartesian coordinate system or the two-dimensional polar coordinate system, the first quadrant is "HAPPY," the second quadrant is "ANGRY," the third quadrant is "SAD," and the fourth quadrant is "RELAXED." Therefore, emotion determination based on the Russell circumplex model can determine the emotion based on, for example, the quadrant in which the coordinate information indicated by the emotion score information is located. Furthermore, the two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system based on the Russell torus model classifies the type of emotion using, for example, a vector whose starting point is coordinate information related to the origin of the two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system and whose ending point is coordinate information related to the emotion score information. Specifically, the two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system based on the Russell torus model classifies the type of emotion in the two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system based on, for example, the angle between the vector and the coordinate axis and the length of the vector. Therefore, emotion determination based on the Russell torus model can determine the emotion based on, for example, coordinate information related to the origin of the two-dimensional Cartesian coordinate system or two-dimensional polar coordinate system and coordinate information related to the emotion score information. In this case, emotions determined based on the Russell circumplex model include, for example, emotions included in the "ANGRY" quadrant such as "tense," "nervous," "stressed," and "upset," emotions included in the "SAD" quadrant such as "sad," "depressed," and "bored," emotions included in the "RELAXED" quadrant such as "calm," "relaxed," "serene," and "content," and emotions included in the "HAPPY" quadrant such as "happy," "elated," "excited," and "alert."

[0030] The reference emotion score information is, for example, information indicating the emotion score information serving as a standard for the subject, set based on a group of the emotion score information of the subject. The group of emotion score information is, for example, a collection of emotion score information acquired from the same subject. The group of emotion score information may be, for example, a collection of two or more pieces of emotion score information, and the number of pieces of emotion score information included in the group is not particularly limited. The group of emotion score information may be, for example, two or more pieces of emotion score information acquired over a predetermined period. The unit of the predetermined period may be, for example, years, months, weeks, days, hours, or seconds. The reference emotion score information may be, for example, different between subjects or may be the same. The reference emotion score information may be, for example, information indicating the emotion score information that is standard for the subject, set based on a group of the emotion score information of the subject. In this case, the reference emotion score information may also be referred to as, for example, standard emotion score information. The reference emotion score information may be, for example, a representative value (e.g., average value, median, mode, etc.) for the group of emotion score information. The representative value may be calculated, for example, by a known method. For example, if the emotion score information is coordinate information, the reference emotion score information may be, for example, a barycentric coordinate for the group of emotion score information. The barycentric coordinate may be calculated, for example, by a known method. For example, if the emotion score information is coordinate information, the reference emotion score information may be, for example, a mean vector for the group of emotion score information. The mean vector may be calculated, for example, by a known method. The reference emotion score information may be, for example, stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0031] The determination unit 12 determines correction information for correcting the emotion score information of the subject based on the determination criteria information used to determine the emotion based on the emotion score information and the reference emotion score information (S2, determination step).

[0032] The determination criterion information is, for example, information used to determine the emotion based on the emotion score information. The determination criterion information may be, for example, a threshold value that is a boundary value distinguishing one emotion from another emotion. If the emotion score information is coordinate information, the determination criterion information may be, for example, coordinate information related to the origin, which is the intersection of each coordinate axis in a Cartesian coordinate system or a polar coordinate system. The determination criterion information may be, for example, stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0033] The correction information is, for example, information for correcting the emotion score information of the subject, determined based on the judgment criterion information and the reference emotion score information. For example, if the judgment criterion information is a threshold, the correction information may be the difference between the value of the reference emotion score information and the threshold value indicated by the judgment criterion information. In this case, determining the correction information involves, for example, calculating the difference between the value of the reference emotion score information and the threshold value indicated by the judgment criterion information. For example, if the judgment criterion information is the origin of a Cartesian coordinate system or a polar coordinate system, the correction information may be the difference between coordinate information indicated by the reference emotion score information and coordinate information relating to the origin in the Cartesian coordinate system or the polar coordinate system indicated by the judgment criterion information. In this case, determining the correction information involves, for example, calculating the difference between coordinate information indicated by the reference emotion score information and coordinate information relating to the origin in the Cartesian coordinate system or the polar coordinate system indicated by the judgment criterion information. The correction information may be, for example, the reference emotion score information minus the judgment criterion information, or the reference emotion score information minus the judgment criterion information. The correction information may be, for example, information including a positive or negative sign (e.g., a positive number, a negative number, etc.), or information excluding a positive or negative sign (e.g., an absolute value, etc.). The correction information may be stored in a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0034] The output unit 13 outputs the correction information (S3, output step). The correction information may include, for example, situation-specific correction information (to be described later) and normal correction information (to be described later).

[0035] The output unit 13 may output the correction information in at least one of a text format, an image format, and a format that combines these, for example.

[0036] The output unit 13 may output the correction information to a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or to a storage unit of a device other than the device disclosed herein. The output unit 13 may store the output correction information in the storage unit, for example.

[0037] The distribution of the emotion score information group often differs for each subject, for example, and as a result, the reference emotion score information often differs for each subject. Therefore, when the same determination criterion information is used, the emotion determined based on the emotion score information is affected by the difference in the reference emotion score information for each subject. According to the present disclosure, it is possible to provide the correction information that can reduce the influence of the difference in the reference emotion score information for each subject, for example.

[0038] The emotion analysis support method (hereinafter also referred to as the method of the present disclosure) of the present disclosure is a method implemented, for example, by replacing the "procedures" in the program of the present disclosure with "processes." Specifically, the method of the present disclosure includes a setting process, a determination process, and an output process. The setting process sets reference emotion score information indicating the emotion score information serving as a reference for the subject based on a group of emotion score information of the subject. The determination process determines correction information for correcting the emotion score information of the subject based on the reference emotion score information and judgment criteria information used to determine emotions based on the emotion score information. The output process outputs the correction information. The method of the present disclosure can be implemented, for example, using the device 10 of the present disclosure shown in FIG. 1 or FIG. 2. Note that the method of the present disclosure is not limited to a method using the device 10 of the present disclosure. For example, the description of the program and the device of the present disclosure can be used for the method of the present disclosure.

[0039] According to the emotion analysis support program of the present disclosure, a setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject based on a group of emotion score information of the subject, a determination step determines correction information for correcting the emotion score information of the subject based on determination criteria information used for determining emotions based on the emotion score information and the reference emotion score information, and an output step outputs the correction information. Thus, according to the present disclosure, emotions can be analyzed while taking individual differences into consideration.

[0040] Second Embodiment Another example of the emotion analysis support program of the present disclosure will be described.

[0041] FIG. 6 is a block diagram showing an example configuration of an emotion analysis support device 10B. As shown in FIG. 6, the emotion analysis support device 10B includes a generation unit 15 and a determination unit 16 in addition to the configuration of the emotion analysis support device 10 of embodiment 1. The hardware configuration of the emotion analysis support device 10B is the same as that of the emotion analysis support device 10 of FIG. 2, except that the central processing unit 101 includes the configuration of the emotion analysis support device 10B of FIG. 6 instead of the configuration of the emotion analysis support device 10 of FIG. 1. The processing of the generation unit 15 and the determination unit 16 will be described below. The processing of the generation unit 15 and the determination unit 16 can be inserted at any position in the flowchart of FIG. 3 described in embodiment 1, for example. However, as shown in FIG. 7, the processing of the generation unit 15 and the determination unit 16 is preferably inserted after S3, for example.

[0042] The generation unit 15 generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, for example (S5, generation step).

[0043] The corrected emotion score information is, for example, information obtained by correcting the emotion score information of the subject, generated based on the correction information of the subject. For example, if the correction information is obtained by subtracting the judgment criterion information from the reference emotion score information, the corrected emotion score information is generated by subtracting the correction information from the emotion score information of the subject. For example, if the correction information is obtained by subtracting the reference emotion score information from the judgment criterion information, the corrected emotion score information is generated by adding the correction information to the emotion score information of the subject. The emotion score information to be corrected may be, for example, different from the emotion score information used to set the reference emotion score information, or may be the same information. In the former case, the corrected emotion score information is, for example, obtained by correcting the emotion score information acquired within a second predetermined period using the correction information determined based on a group of the emotion score information of the subject acquired within a first predetermined period. In the latter case, the corrected emotion score information is, for example, emotion score information acquired within a predetermined period corrected by the correction information determined based on a group of emotion score information of the subject acquired within the predetermined period. The first predetermined period is preferably, for example, a period in which the subject is in a normal state of mind, as described below. The first predetermined period is preferably, for example, a period longer than the second predetermined period. The second predetermined period is, for example, a period for analyzing the emotion of the subject. The second predetermined period is preferably, for example, a period shorter than the first predetermined period. The corrected emotion score information may be stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0044] The determination unit 16 determines the emotion of the subject based on, for example, the determination criterion information and the corrected emotion score information (S6, determination step).

[0045] The emotion determination is performed, for example, based on the determination criterion information and the corrected emotion score information. If the determination criterion information is a threshold, the emotion determination may be performed by determining whether the corrected emotion score information exceeds the threshold (or is equal to or greater than the threshold), or whether it is less than the threshold (or is equal to or less than the threshold).

[0046] For example, when the determination criterion information is the origin of a Cartesian coordinate system or a polar coordinate system, the emotion determination may be performed based on the known emotion model described above. Examples of the emotion model include the Russell Circumplex model described above. The emotion determination based on the Russell Circumplex model can be implemented by, for example, replacing emotion score information with corrected emotion score information. For example, when the determination criterion information is the origin of a Cartesian coordinate system or a polar coordinate system, the emotion determination may be performed based on the quadrant in which coordinate information related to the corrected emotion score information is located. Furthermore, when the determination criterion information is the origin of a Cartesian coordinate system or a polar coordinate system, the emotion determination may be performed based on coordinate information related to the origin and coordinate information related to the corrected emotion score information. The emotion may be stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or in a storage unit of a device other than the device disclosed herein.

[0047] The output unit 13 may, for example, output the determined emotion. The output unit 13 may, for example, output the emotion in at least one format of a character format, an image format, or a format combining these. The output unit 13 may, for example, output the emotion to a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or may output the emotion to a storage unit of a device other than the device disclosed herein. The output unit 13 may, for example, store the output emotion in the storage unit.

[0048] Third Embodiment Another example of the emotion analysis support program of the present disclosure will be described.

[0049] FIG. 4 is a block diagram showing an example configuration of an emotion analysis support device 10A. As shown in FIG. 4, the emotion analysis support device 10A includes a situation identification unit 14 in addition to the configuration of the emotion analysis support device 10 of embodiment 1. The hardware configuration of the emotion analysis support device 10A is the same as that of the emotion analysis support device 10 of FIG. 2, except that the central processing unit 101 includes the configuration of the emotion analysis support device 10A of FIG. 4 instead of the configuration of the emotion analysis support device 10 of FIG. 1. The processing of the situation identification unit 14 will be described below. The processing of the situation identification unit 14 can be inserted, for example, at any position in the flowchart of FIG. 3 described in embodiment 1, but as shown in FIG. 5, the processing of the situation identification unit 14 is preferably inserted, for example, before S1A.

[0050] The situation identification unit 14 identifies the type of situation in which the subject is placed (S4, situation identification step).

[0051] The type of situation is, for example, a type of work performed at the location where the subject is located. The location is, for example, the place where the subject performs the work, and examples thereof include factories (e.g., factories related to basic materials industries, factories related to processing and assembly industries, factories related to lifestyle-related industries, etc.), construction sites (e.g., civil engineering sites, architectural sites, electrical work sites, demolition sites, etc.), warehouses (e.g., standard warehouses, refrigerated warehouses, water-surface warehouses, etc.), cars (e.g., standard automobiles, compact automobiles, light automobiles, large special-purpose automobiles, compact special-purpose automobiles, etc.), social welfare facilities (e.g., nursing homes, disability support facilities, elderly welfare facilities, child welfare facilities, etc.), hospitals (e.g., treatment rooms, operating rooms, etc.), and offices (e.g., work desks, conference rooms, etc.). The work includes, for example, any behavior performed by the subject at the location. If the location is a factory, examples of the work include manufacturing, assembly, processing, painting, inspection, quality testing, joining, packaging, sorting, transportation, cleaning, and maintenance and inspection. For example, if the location is the construction site, the work may include excavation, compaction, leveling, concrete leveling, concrete pouring, cart transport, rebar assembly, etc. For example, if the location is the vehicle, the work may include driving the vehicle, etc. The type of situation may be stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0052] The type of situation may be identified based on image information acquired by a photographing device (e.g., a camera, etc.). The photographing device may be, for example, equipped by the subject or installed at the location where the subject is located. In the former case, examples of the photographing device include a wearable camera and an action camera. In the latter case, examples of the photographing device include a surveillance camera and a camera mounted on a personal computer. The image information includes, for example, photographed person information about the subject photographed by the photographing device (e.g., information about the subject's posture, etc.), tool information about the tool used by the subject (e.g., information about the type of tool, etc.), and environmental information about the subject's surrounding environment (e.g., information about the subject's hands or feet, etc.). The format of the image information may be, for example, an image format or a video format.

[0053] The situation type may be identified based on, for example, at least one of the subject information, the tool information, and the environmental information included in the image information. The situation type may be identified, for example, using a situation type identification model. The situation type identification model is a model that identifies the situation type when, for example, at least one of the subject information, the tool information, and the environmental information is input. The situation type identification model may be, for example, a publicly known model, such as the "NEC Digital Twin Solution Site Visualization and Analysis Service." The situation type identification model may be, for example, stored in a storage unit such as the memory 102 or storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0054] The identification of the type of situation may involve, for example, performing person matching of the photographed person simultaneously with or in addition to the identification of the type of situation. The person matching may be, for example, matching based on physical features or matching based on a person matching model that applies machine learning or the like. The person matching function may be provided, for example, by the device of the present disclosure, or by a device other than the device of the present disclosure (e.g., the photographing means, etc.). The person matching based on physical features may, for example, be performed by comparing the physical features of the photographed person's body image acquired by the photographing means with the physical features of the body images of each of the subjects that have been generated in advance. In this case, the person matching based on the physical features may, for example, match the subject whose matching score, indicating the degree to which the physical features match, exceeds a predetermined threshold as the photographed person. The person matching based on the person matching model may, for example, perform person matching based on the person matching model that matches the subject whose matching score exceeds a predetermined threshold as the photographed person when the physical features of the photographed person's body image acquired by the photographing means are input. Furthermore, person matching based on the person matching model may, for example, be performed by inputting a body image of the subject acquired by the imaging means and outputting body feature values ​​related to the body image. In this case, person matching based on the person matching model may, for example, be performed based on the body feature values ​​output by the person matching model. The body image may, for example, include a body part image (e.g., a face image, an image of the back of the head, etc.) including a body part of the subject, or a whole body image (e.g., a forward-facing image, a rear-facing image, a side-facing image, an oblique-facing image, etc.) including the subject's entire body. The body image may, for example, be in the form of an image or a video. The person matching model may, for example, be stored in a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or in a storage unit of a device other than the device disclosed herein.

[0055] The setting unit 11 executes S1 in the same manner as S1 in the embodiment 1. In the case of the present disclosure, the setting unit 11 sets, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a reference for each situation of the subject, based on a group of emotion score information for each situation of the subject (S1A, setting procedure).

[0056] The situation-specific reference emotion score information is, for example, information indicating the emotion score information that serves as a standard for each of the situations of the subject, which is set based on a group of the emotion score information for each of the situations of the subject. For the situation-specific reference emotion score information, for example, the above-mentioned description of the reference emotion score information can be used by replacing the reference emotion score information with situation-specific reference emotion score information.

[0057] The determination unit 12 executes S2 in the same manner as S2 in Embodiment 1. In the case of the present disclosure, the determination unit 12 determines, for each situation, situation-specific correction information for correcting the emotion score information of the subject in each situation, based on the judgment criterion information and the situation-specific reference emotion score information (S2A, determination procedure).

[0058] The situation-specific correction information is, for example, information for correcting the emotion score information for each situation of the subject, which is determined based on the judgment criterion information and the situation-specific reference emotion score information. For example, the situation-specific correction information can be used in the above-mentioned description of the correction information by replacing the correction information with situation-specific correction status.

[0059] The output unit 13 executes S3 in the same manner as S3 in the embodiment 1. In this case, the output unit 13 outputs, for example, the situation-specific correction information for each situation (S3A, output procedure).

[0060] The distribution of the emotion score information group often differs depending on the type of situation, for example. As a result, the situation-specific reference emotion score information often differs for each situation, for example. For this reason, when the same judgment criteria are used, the emotion determined based on the emotion score information is affected by the difference in the situation-specific reference emotion score information for each situation. According to the present disclosure, it is possible to provide the situation-specific correction information that can reduce the influence of the difference in the situation-specific reference emotion score information for each situation.

[0061] Furthermore, the emotion analysis support device 10C may include a generation unit 15 and a determination unit 16 in addition to the configuration of the emotion analysis support device 10A of embodiment 3. FIG. 8 is a block diagram showing an example configuration of the emotion analysis support device 10C. As shown in FIG. 8, the emotion analysis support device 10C includes a generation unit 15 and a determination unit 16 in addition to the configuration of the emotion analysis support device 10A of embodiment 3. The hardware configuration of the emotion analysis support device 10C is the same as that of the emotion analysis support device 10 of FIG. 2, except that the central processing unit 101 includes the configuration of the emotion analysis support device 10A of FIG. 4, the generation unit 15, and the determination unit 16 instead of the configuration of the emotion analysis support device 10 of FIG. 1. The processing of the present disclosure will be described below. The processing of the generation unit 15 and the determination unit 16 can be inserted at any position in the flowchart of FIG. 5 described in embodiment 3, for example. However, as shown in FIGS. 9 and 10, the processing of the generation unit 15 and the determination unit 16 is preferably inserted after S3A, for example.

[0062] The generation unit 15 may, for example, generate corrected emotion score information by correcting the emotion score information of the subject for each of the situations based on the situation-specific correction information of the subject (S5A, generation step).

[0063] In this case, the corrected emotion score information is, for example, information obtained by correcting the emotion score information of the subject, which is generated based on the situation-specific correction information of the subject. For example, the above-mentioned description can be used for the corrected emotion score information.

[0064] The determination unit 16 may determine the subject's emotion for each of the situations based on the determination criterion information and the corrected emotion score information, for example (S6A, determination step).

[0065] In this case, the emotion determination is performed for each of the situations based on, for example, the determination criterion information and the corrected emotion score information. For example, the above description can be used for the emotion determination.

[0066] Furthermore, for example, when the situation indicates a normal situation in which the subject is calm, the setting unit 11 may set normal reference emotion score information indicating the emotion score information that serves as a reference in the normal situation of the subject, based on a group of emotion score information in the normal situation of the subject (S1B, setting procedure).

[0067] The normal situation is, for example, the situation in which the subject is calm. The calm state indicates, for example, the subject's usual emotional state. The emotion corresponding to the calm state does not indicate a specific emotion (e.g., "RELAXED" in the fourth quadrant) in a two-dimensional Cartesian coordinate system or a two-dimensional polar coordinate system based on Russell's circumplex model. The emotion corresponding to the calm state may differ for each subject, for example, one subject may feel "HAPPY" in the first quadrant, while another subject may feel "SAD" in the third quadrant.

[0068] The normal state reference emotion score information is, for example, information indicating the emotion score information that serves as a reference in the normal state of the subject, which is set based on a group of the emotion score information in the normal state of the subject. For the normal state reference emotion score information, for example, the above-mentioned description regarding the reference emotion score information can be used by replacing reference emotion score information with normal state reference emotion score information.

[0069] The determination unit 12 may determine, for example, normal state correction information for correcting the emotion score information of the subject in the normal situation based on the judgment criteria information and the normal state reference emotion score information (S2B, determination procedure).

[0070] The normal state correction information is, for example, information for correcting the emotion score information of the subject, which is determined based on the judgment criterion information and the normal state reference emotion score information. For example, the normal state correction information can be used in the above-mentioned description of the correction information by replacing the correction information with normal state correction status.

[0071] The output unit 13 executes S3 in the same manner as S3 in the embodiment 1. In this case, the output unit 13 outputs, for example, the normal state correction information (S3B, output step).

[0072] The distribution of the emotion score information group in the normal situation often differs for each subject, for example, and as a result, the normal reference emotion score information often differs for each subject, for example. Therefore, when the same judgment criteria are used, the emotion determined based on the emotion score information is affected by the difference in the normal reference emotion score information for each subject. According to the present disclosure, it is possible to provide the normal correction information that can reduce the influence of the difference in the normal reference emotion score information for each subject, for example.

[0073] Furthermore, the generation unit 15 may generate corrected emotion score information by correcting the emotion score information of the subject for each of the situations based on the normal state correction information of the subject (S5B, generation procedure).

[0074] In this case, the corrected emotion score information is, for example, information obtained by correcting the emotion score information of the subject, which is generated based on the normal state correction information of the subject. For example, the above-mentioned description can be used for the corrected emotion score information.

[0075] The determination unit 16 may determine the subject's emotion for each of the situations based on the determination criterion information and the corrected emotion score information, for example (S6A, determination step).

[0076] In this case, the emotion determination is performed for each of the situations based on, for example, the determination criterion information and the corrected emotion score information. For example, the above description can be used for the emotion determination.

[0077] Furthermore, the emotion analysis support device 10D may include, for example, a warning unit 17 in addition to the configuration of the emotion analysis support device 10A of embodiment 3, the generation unit 15, and the determination unit 16. FIG. 11 is a block diagram showing an example configuration of the emotion analysis support device 10D. As shown in FIG. 11, the emotion analysis support device 10D includes, in addition to the configuration of the emotion analysis support device 10A of embodiment 3, a generation unit 15, a determination unit 16, and a warning unit 17. The hardware configuration of the emotion analysis support device 10D is similar to, for example, the hardware configuration of the emotion analysis support device 10 of FIG. 2, except that the central processing unit 101 includes the configuration of the warning unit 17 in addition to the situation identification unit 14, the generation unit 15, and the determination unit 16. The processing of the warning unit 17 will be described below. The processing of the warning unit 17 can be inserted, for example, at any position in the flowcharts of FIGS. 9 and 10 described in embodiment 3. However, as shown in FIGS. 12 and 13, the processing of the warning unit 17 is preferably inserted, for example, after the determination procedure.

[0078] For example, the warning unit 17 determines whether the emotion of the subject placed in a specific situation is appropriate for the specific situation, and if it is determined that the emotion is not appropriate for the specific situation, outputs warning information informing the subject that the emotion is not appropriate (S7, warning procedure).

[0079] The determination of whether the emotion is appropriate in the specific situation may be performed, for example, by determining whether the emotion of the subject in the specific situation determined by the determination procedure matches an appropriate emotion previously set as appropriate for the specific situation. In this case, the emotion in the specific situation is determined to be appropriate in the specific situation, for example, if the emotion in the specific situation matches the appropriate emotion. In other words, the emotion in the specific situation is determined to be inappropriate in the specific situation, for example, if the emotion in the specific situation does not match the appropriate emotion. The determination of whether the emotion is appropriate in the specific situation may be performed, for example, by determining whether the emotion of the subject in the specific situation determined by the determination procedure matches an inappropriate emotion previously set as inappropriate for each situation. In this case, the emotion in the specific situation is determined to be appropriate in the specific situation, for example, if the emotion in the specific situation does not match the inappropriate emotion. In other words, the emotion in the specific situation is determined to be inappropriate in the specific situation, for example, if the emotion in the specific situation matches the inappropriate emotion.

[0080] The appropriate emotion is, for example, the emotion that encourages the subject to perform the work. Conversely, the inappropriate emotion is, for example, the emotion that hinders the subject from performing the work. The inappropriate emotion may be, for example, the emotion that puts the subject at risk during the work. For example, when the situation is performing the inspection in the factory, the appropriate emotion may be, for example, "alert" or "excited," which indicates a high level of arousal, or "happy" or "elated," which indicates a high level of sensory valence. Conversely, when the situation is performing the inspection in the factory, the inappropriate emotion may be, for example, "calm" or "relaxed," which indicates a low level of arousal, or "upset" or "stressed," which indicates a low level of sensory valence. The appropriate emotion or the inappropriate emotion may be, for example, arbitrarily set in advance by the subject or by a supervisor of the work. The appropriate emotion or the inappropriate emotion may be preset based on, for example, the results of emotion analysis of accidents that have occurred in the past in the specific situation. For example, the appropriate emotion or the inappropriate emotion may be preset as one emotion for the specific situation, or as two or more emotions for the specific situation. The appropriate emotion and the inappropriate emotion may be stored in a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0081] The warning information may be, for example, information that notifies the subject that the emotion is inappropriate if the emotion is determined to be inappropriate in the specific situation. The warning information may be, for example, information that prompts the subject to leave the specific situation. The output format of the warning information may be, for example, at least one of a text format, an image format, an audio format, or a combination thereof. The warning information may be, for example, stored in a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0082] Furthermore, for example, after outputting the warning information, the warning unit 17 may determine whether the emotion of the subject placed in the specific situation is appropriate for the specific situation, and if it is determined that the emotion is appropriate for the specific situation, output warning cancellation information informing the subject that the emotion is appropriate. For example, the above description can be used to determine whether the emotion is appropriate for the specific situation.

[0083] The warning cancellation information may be, for example, information that informs the subject that the emotion is appropriate if the emotion is determined to be appropriate in the specific situation. The warning cancellation information may be, for example, information that prompts the subject to return to the specific situation. The warning cancellation information may be, for example, information that cancels the output of the warning information, or may be information separate from the output of the warning information. The output format of the warning cancellation information may be, for example, at least one of a text format, an image format, an audio format, or a combination thereof. The warning cancellation information may be, for example, stored in a storage unit such as the memory 102 or the storage device 104 of the device disclosed herein, or may be stored in a storage unit of a device other than the device disclosed herein.

[0084] According to the emotion analysis support program of the present disclosure, a situation identification step identifies the type of situation in which the subject is placed, a setting step sets situation-specific reference emotion score information indicating the emotion score information serving as a reference for each situation of the subject based on a group of emotion score information for each situation of the subject, and a determination step determines situation-specific correction information for each situation for correcting the emotion score information for each situation of the subject based on the judgment criteria information and the situation-specific reference emotion score information. Thus, according to the present disclosure, emotions can be analyzed taking into account individual differences. Furthermore, according to the present disclosure, emotions can be analyzed taking into account, for example, differences in the type of situation.

[0085] [Embodiment 4] An example of a usage form of the device of the present disclosure will be described below. In the following description, an example of inspecting products in a factory will be described, but the present disclosure is not limited to the following description.

[0086] First, the situation-specific correction information for when worker A performs inspection is determined. Specifically, worker A, for example, wears a wristband-type wearable device equipped with a pulse monitor function and performs inspection work for a first predetermined period. During the inspection, the wearable device, for example, associates acquired biometric information (pulse rate) with the wearable device's device identification information and transmits it to the device disclosed herein. The device disclosed herein, for example, inputs the acquired pulse rate of worker A into an emotion score information output model and obtains the output emotion score information of worker A. In the present disclosure, the emotion score information is, for example, a point (coordinate information) in a two-dimensional Cartesian coordinate system based on Russell's circular ring model consisting of an AROUSAL axis and a VALENCE axis. In this case, the pair of numbers (x, y) specifying the position of the point indicates, for example, x as the position on the VALENCE axis and y as the position on the AROUSAL axis. The device disclosed herein, for example, identifies the user identification information of the worker A linked to the acquired terminal identification information in a database stored in a storage unit, and stores the emotion score information of the worker A in a corresponding field, linking it to the user identification information of the worker A. After the first predetermined period has elapsed, for example, a group of the emotion score information of the worker A is stored in the database. For example, the device disclosed herein sets the barycentric coordinates (-2, 3) as the situation-specific reference emotion score information of the worker A based on the group of the emotion score information of the worker A. In this case, the situation-specific reference emotion score information of the worker A is located, for example, to the upper left of the origin of the two-dimensional Cartesian coordinate system. Therefore, when the worker A is performing an inspection, for example, the worker A can understand that feeling stress is a normal state. The device disclosed herein, for example, subtracts coordinate information (-2, 3) related to the situation-specific reference emotion score information from the origin (0, 0) of the two-dimensional Cartesian coordinate system, which is the determination criterion information, and determines (2, -3), which is the difference between the determination criterion information and the situation-specific reference emotion score information, as situation-specific correction information. The device disclosed herein, for example, associates the situation-specific correction information with the user identification information of the worker A and stores it in the corresponding feed in the database.In this case, the device of the present disclosure may, for example, associate the situation-specific reference emotion score information with the user identification information of the worker A and store it in the corresponding feed.

[0087] Next, the emotion of the worker A when performing inspection is determined based on the situation-specific correction information. Specifically, the worker A, for example, wears the wearable device and performs inspection work for a second predetermined period. During the work, the wearable device, for example, as described above, associates the acquired pulse rate with the device identification information of the wearable device and transmits it to the device of the present disclosure. For example, as described above, the device of the present disclosure inputs the acquired pulse rate of the worker A into an emotion score information output model and obtains the output emotion score information of the worker A, (-10, 1). For example, the device of the present disclosure generates corrected emotion score information, (-8, -2), by adding the situation-specific correction information, (2, -3), to the acquired emotion score information of the worker A, (-10, 1). The device disclosed herein, for example, determines that worker A's emotion is "SAD" because the corrected emotion score information is located in the third quadrant of the two-dimensional orthogonal coordinate system based on the positional relationship between the origin (0, 0) of the judgment criterion information and the corrected emotion score information (-8, -2). The device disclosed herein also determines worker A's emotion using a vector whose starting point is the origin (0, 0) of the judgment criterion information and whose ending point is the corrected emotion score information (-8, -2). In this case, the device disclosed herein determines that worker A's emotion is "depressed" based on, for example, the angle between the vector and the VALENCE axis or the AROUSAL axis and the length of the vector. The device disclosed herein, for example, identifies the user identification information of the worker A linked to the terminal identification information in the database, and stores the emotion of the worker A in a corresponding field by linking it to the user identification information of the worker A. In this case, the device disclosed herein may, for example, store the corrected emotion score information in a corresponding field in the database by linking it to the user identification information of the worker A. After the second predetermined period has elapsed, for example, the group of emotions of the worker A corrected as described above is stored in the database.

[0088] Furthermore, if the worker A feels unwell while performing an inspection, the wearable device outputs an alarm to encourage the worker to leave the task. Specifically, during an inspection, if the worker's emotion is, for example, "depressed," the worker is more likely to make mistakes, such as overlooking damaged items, which hinders the worker's inspection. For this reason, an inspection supervisor, for example, pre-sets "depressed" as an inappropriate emotion for performing inspection work in the device disclosed herein. For example, while the worker A is performing an inspection, the device disclosed herein determines whether the emotion of the worker A determined as described above matches the inappropriate emotion. For example, if the emotion of the worker A matches the inappropriate emotion, the device disclosed herein determines that the emotion of the worker A is inappropriate for performing an inspection. In this case, the device disclosed herein, for example, outputs warning information to the wearable device worn by the worker A, and the wearable device that has received the warning information emits an alarm sound to prompt the worker A to leave the inspection work. The worker A leaves the inspection work and takes a break in response to the alarm sound. The device disclosed herein, for example, determines whether the emotion of the worker A determined as described above matches the inappropriate emotion while the worker A is taking the break. For example, if the emotion of the worker A does not match the inappropriate emotion, the device disclosed herein determines that the emotion of the worker A is appropriate for performing inspection. In this case, the device disclosed herein, for example, outputs warning cancellation information to the wearable device worn by the worker A, and the wearable device that has received the warning cancellation information cancels the alarm sound to notify the worker A that he or she can return to the inspection work.

[0089] According to the present disclosure, emotions can be analyzed while taking into consideration individual differences. Also, according to the present disclosure, emotions can be analyzed while taking into consideration, for example, differences in the types of situations.

[0090] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0091] This application claims priority based on Japanese Patent Application No. 2024-054998, filed March 28, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0092] <Supplementary Notes> Some or all of the above embodiments can be described as in the following supplementary notes, but are not limited to the following. (Supplementary Note 1) An emotion analysis support program for causing a computer to execute each of the above steps, including a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject, the determination step determines correction information for correcting the emotion score information of the subject, based on judgment criterion information used for determining an emotion based on the emotion score information and the reference emotion score information, and the output step outputs the correction information. (Supplementary Note 2) The emotion analysis support program according to Supplementary Note 1, further including a generation step and a judgment step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject, based on the correction information of the subject, and the judgment step judges the emotion of the subject based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 3) The emotion analysis support program according to Supplementary Note 1, further comprising a situation identification step, wherein the situation identification step identifies a type of situation in which the subject is placed, the setting step sets, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a reference for each of the situations of the subject, based on a group of emotion score information of the subject for each of the situations, and the determination step determines, for each situation, situation-specific correction information for correcting the emotion score information of the subject for each of the situations, based on the judgment criterion information and the situation-specific reference emotion score information. (Supplementary Note 4) The emotion analysis support program according to Supplementary Note 3, further comprising a generation step and a judgment step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject for each of the situations, based on the situation-specific correction information of the subject, and the judgment step judges the emotion of the subject for each of the situations, based on the judgment criterion information and the corrected emotion score information.(Supplementary Note 5) The emotion analysis support program according to Supplementary Note 3, wherein the setting step, when the situation indicates a normal situation in which the subject is calm, sets normal state reference emotion score information indicating the emotion score information that serves as a reference for the subject's normal situation, based on a group of emotion score information for the subject's normal situation, and the determination step, determines normal state correction information for correcting the emotion score information for the subject's normal situation, based on the judgment criterion information and the normal state reference emotion score information. (Supplementary Note 6) The emotion analysis support program according to Supplementary Note 5, further comprising a generation step and a judgment step, wherein the generation step generates corrected emotion score information by correcting the emotion score information for each situation of the subject, based on the subject's normal state correction information, and the judgment step judges the emotion of the subject in each situation, based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 7) The emotion analysis support program according to Supplementary Note 4 or 6, further comprising a warning step of determining whether the emotion of the subject placed in a specific situation is appropriate for the specific situation, and if the emotion is determined to be inappropriate for the specific situation, outputting warning information informing the subject that the emotion is inappropriate. (Supplementary Note 8) An emotion analysis support device comprising a setting unit, a determination unit, and an output unit, wherein the setting unit sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject, the determination unit determines correction information for correcting the emotion score information of the subject, based on the reference emotion score information and determination criteria information used for determining an emotion based on the emotion score information, and the output unit outputs the correction information. (Supplementary Note 9) The emotion analysis support device according to Supplementary Note 8, further comprising a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, and the determination unit determines the emotion of the subject based on the determination criterion information and the corrected emotion score information.(Supplementary Note 10) The emotion analysis support device according to Supplementary Note 8, further including a situation identification unit, wherein the situation identification unit identifies a type of situation in which the subject is placed, the setting unit sets, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a reference for each of the situations of the subject, based on a group of emotion score information of the subject for each of the situations, and the determination unit determines, for each situation, situation-specific correction information for correcting the emotion score information of the subject for each of the situations, based on the judgment criterion information and the situation-specific reference emotion score information. (Supplementary Note 11) The emotion analysis support device according to Supplementary Note 10, further including a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information of the subject for each of the situations, based on the situation-specific correction information of the subject, and the determination unit determines the emotion of the subject for each of the situations, based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 12) The emotion analysis support device according to Supplementary Note 10, wherein when the situation indicates a normal situation in which the subject is calm, the setting unit sets normal state reference emotion score information indicating the emotion score information that serves as a reference for the subject's normal situation, based on a group of emotion score information for the subject's normal situation, and the determination unit determines normal state correction information for correcting the emotion score information for the subject's normal situation, based on the judgment criterion information and the normal state reference emotion score information. (Supplementary Note 13) The emotion analysis support device according to Supplementary Note 12, further comprising a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information for each situation of the subject, based on the normal state correction information of the subject, and the determination unit determines the emotion of the subject in each situation, based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 14) The emotion analysis support device according to Supplementary Note 11 or 13, further comprising a warning unit that determines whether the emotion of the subject placed in a specific situation is appropriate for the specific situation, and when it is determined that the emotion is not appropriate for the specific situation, outputs warning information that notifies the subject that the emotion is not appropriate.(Supplementary Note 15) An emotion analysis support method according to Supplementary Note 15, comprising: a setting step, a determining step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject, the determining step determines correction information for correcting the emotion score information of the subject, based on judgment criterion information used for judging an emotion based on the emotion score information and the reference emotion score information, and the output step outputs the correction information, wherein each of the steps is carried out by a computer. (Supplementary Note 16) The emotion analysis support method according to Supplementary Note 15, further comprising: a generating step and a judging step, wherein the generating step generates corrected emotion score information by correcting the emotion score information of the subject, based on the correction information of the subject, and the judging step judges the emotion of the subject based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 17) The emotion analysis support method according to Supplementary Note 15, further comprising a situation specifying step of specifying a type of situation in which the subject is placed, the setting step of setting, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a reference for each of the situations of the subject, based on a group of emotion score information of the subject for each of the situations, and the determining step of determining, for each situation, situation-specific correction information for correcting the emotion score information of the subject for each of the situations, based on the judgment criterion information and the situation-specific reference emotion score information. (Supplementary Note 18) The emotion analysis support method according to Supplementary Note 17, further comprising a generating step and a determining step, the generating step of generating corrected emotion score information by correcting the emotion score information of the subject for each of the situations, based on the situation-specific correction information of the subject, and the determining step of determining the emotion of the subject for each of the situations, based on the judgment criterion information and the corrected emotion score information.(Supplementary Note 19) The emotion analysis support method according to Supplementary Note 17, wherein the setting step, when the situation indicates a normal situation in which the subject is calm, sets normal state reference emotion score information indicating the emotion score information that serves as a reference for the subject's normal situation, based on a group of emotion score information for the subject's normal situation, and the determining step determines normal state correction information for correcting the emotion score information for the subject's normal situation, based on the judgment criterion information and the normal state reference emotion score information. (Supplementary Note 20) The emotion analysis support method according to Supplementary Note 19, further comprising a generating step and a judging step, wherein the generating step generates corrected emotion score information by correcting the emotion score information for the subject in each situation, based on the subject's normal state correction information, and the judging step judges the emotion of the subject in each situation, based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 21) The emotion analysis support method according to Supplementary Note 18 or 20, further comprising a warning step of determining whether the emotion of the subject placed in a specific situation is appropriate for the specific situation, and outputting warning information informing the subject that the emotion is inappropriate if it is determined that the emotion is inappropriate for the specific situation. (Supplementary Note 22) A computer-readable recording medium having recorded thereon an emotion analysis support program for causing a computer to execute each of the steps, comprising a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject, the determination step determines correction information for correcting the emotion score information of the subject, based on the reference emotion score information and determination criteria information used for determining an emotion based on the emotion score information, and the output step outputs the correction information. (Supplementary Note 23) The recording medium according to Supplementary Note 22, further comprising a generating step and a determining step, wherein the generating step generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, and the determining step determines the emotion of the subject based on the determination criterion information and the corrected emotion score information.(Supplementary Note 24) The recording medium of Supplementary Note 22, further comprising a situation identification step, wherein the situation identification step identifies a type of situation in which the subject is placed, the setting step sets, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a reference for each of the situations of the subject, based on a group of emotion score information of the subject for each of the situations, and the determination step determines, for each situation, situation-specific correction information for correcting the emotion score information of the subject for each of the situations, based on the judgment criterion information and the situation-specific reference emotion score information. (Supplementary Note 25) The recording medium of Supplementary Note 24, further comprising a generation step and a judgment step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject for each of the situations, based on the situation-specific correction information of the subject, and the judgment step judges the emotion of the subject for each of the situations, based on the judgment criterion information and the corrected emotion score information. (Supplementary Note 26) The recording medium according to Supplementary Note 24, wherein the setting step, when the situation indicates a normal situation in which the subject is calm, sets normal state reference emotion score information indicating the emotion score information serving as a reference in the normal situation of the subject, based on a group of emotion score information in the normal situation of the subject, and the determination step, determines normal state correction information for correcting the emotion score information in the normal situation of the subject, based on the judgment criterion information and the normal state reference emotion score information. (Supplementary Note 27) The recording medium according to Supplementary Note 26, further comprising a generation step and a judgment step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject in each of the situations, based on the normal state correction information of the subject, and the judgment step judges the emotion of the subject in each of the situations, based on the judgment criterion information and the corrected emotion score information. (Appendix 28) The recording medium according to Appendix 25 or 27, further comprising a warning step of determining whether the emotion of the subject placed in a specific situation is appropriate in the specific situation, and outputting warning information informing the subject that the emotion is inappropriate if the emotion is determined to be inappropriate in the specific situation.

[0093] According to the present disclosure, emotions can be analyzed while taking individual differences into consideration. Therefore, the present disclosure can be widely and usefully used in fields such as psychology.

[0094] 10, 10A, 10B, 10C, 10D Emotion analysis support device 11 Setting unit 12 Determination unit 13 Output unit 14 Situation identification unit 15 Generation unit 16 Determination unit 17 Warning unit 101 Central processing unit 102 Memory 103 Bus 104 Storage device 105 Input device 106 Output device 107 Communication device

Claims

1. An emotion analysis support program for causing a computer to execute each of the steps, the program comprising: a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject, based on a group of emotion score information of the subject; the determination step determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for judging emotions based on the emotion score information and the reference emotion score information; and the output step outputs the correction information.

2. The emotion analysis support program according to claim 1, further comprising a generation step and a determination step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, and the determination step determines the emotion of the subject based on the determination criterion information and the corrected emotion score information.

3. The emotion analysis support program according to claim 1, further comprising a situation identification step, wherein the situation identification step identifies a type of situation in which the subject is placed; the setting step sets, for each situation, situation-specific reference emotion score information indicating the emotion score information that serves as a standard for each situation of the subject, based on a group of emotion score information for each situation of the subject; and the determination step determines, for each situation, situation-specific correction information for correcting the emotion score information for each situation of the subject, based on the judgment criteria information and the situation-specific reference emotion score information.

4. The emotion analysis support program according to claim 3, further comprising a generation step and a determination step, wherein the generation step generates corrected emotion score information by correcting the emotion score information for each of the situations of the subject based on the situation-specific correction information for the subject, and the determination step determines the emotion of the subject for each of the situations based on the determination criterion information and the corrected emotion score information.

5. The emotion analysis support program of claim 3, wherein the setting step, when the situation indicates a normal situation in which the subject is calm, sets normal reference emotion score information indicating the emotion score information that serves as a reference for the subject in the normal situation based on a group of emotion score information for the subject in the normal situation, and the determination step, based on the judgment criteria information and the normal reference emotion score information, determines normal correction information for correcting the emotion score information for the subject in the normal situation.

6. An emotion analysis support program as claimed in claim 5, further comprising a generation step and a determination step, wherein the generation step generates corrected emotion score information by correcting the emotion score information of the subject in each of the situations based on the normal state correction information of the subject, and the determination step determines the emotion of the subject in each of the situations based on the determination criterion information and the corrected emotion score information.

7. An emotion analysis support program as claimed in claim 4 or 6, further comprising a warning step which determines whether the emotion of the subject placed in a specific situation is appropriate in the specific situation, and if it is determined that the emotion is not appropriate in the specific situation, outputs warning information informing the subject that the emotion is not appropriate.

8. An emotion analysis support device including a setting unit, a determination unit, and an output unit, wherein the setting unit sets reference emotion score information indicating the emotion score information serving as a standard for the subject, based on a group of emotion score information of the subject; the determination unit determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for judging emotions based on the emotion score information and the reference emotion score information; and the output unit outputs the correction information.

9. The emotion analysis support device according to claim 8, further comprising a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, and the determination unit determines the emotion of the subject based on the determination criterion information and the corrected emotion score information.

10. The emotion analysis support device according to claim 8, further comprising a situation identification unit, wherein the situation identification unit identifies the type of situation in which the subject is placed, the setting unit sets situation-specific reference emotion score information indicating the emotion score information that serves as a standard for each of the situations of the subject, based on a group of emotion score information for each of the situations of the subject, and the determination unit determines situation-specific correction information for each of the situations, based on the judgment criteria information and the situation-specific reference emotion score information, to correct the emotion score information for each of the situations of the subject.

11. The emotion analysis support device according to claim 10, further comprising a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information for each of the situations of the subject based on the situation-specific correction information for the subject, and the determination unit determines the emotion of the subject for each of the situations based on the determination criterion information and the corrected emotion score information.

12. The emotion analysis support device described in claim 10, wherein when the situation indicates a normal situation in which the subject is calm, the setting unit sets normal reference emotion score information indicating the emotion score information that serves as a reference for the subject in the normal situation based on a group of emotion score information for the subject in the normal situation, and the determination unit determines normal correction information for correcting the emotion score information for the subject in the normal situation based on the judgment criteria information and the normal reference emotion score information.

13. An emotion analysis support device as described in claim 12, further comprising a generation unit and a determination unit, wherein the generation unit generates corrected emotion score information by correcting the emotion score information of the subject in each of the situations based on the normal state correction information of the subject, and the determination unit determines the emotion of the subject in each of the situations based on the determination criterion information and the corrected emotion score information.

14. An emotion analysis support device as described in claim 11 or 13, further comprising a warning unit that determines whether the emotion of the subject placed in a specific situation is appropriate in the specific situation, and if it is determined that the emotion is not appropriate in the specific situation, outputs warning information informing the subject that the emotion is not appropriate.

15. A method for supporting emotion analysis, comprising a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a standard for the subject, based on a group of emotion score information of the subject; the determination step determines correction information for correcting the emotion score information of the subject, based on judgment criteria information used for judging emotions based on the emotion score information and the reference emotion score information; and the output step outputs the correction information, wherein each of the steps is executed by a computer.

16. The emotion analysis support method according to claim 15, further comprising a generating step and a determining step, wherein the generating step generates corrected emotion score information by correcting the emotion score information of the subject based on the correction information of the subject, and the determining step determines the emotion of the subject based on the determination criterion information and the corrected emotion score information.

17. The emotion analysis support method according to claim 15, further comprising a situation specifying step, wherein the situation specifying step specifies the type of situation in which the subject is placed, the setting step sets situation-specific reference emotion score information indicating the emotion score information serving as a standard for each of the situations of the subject, based on a group of emotion score information for each of the situations of the subject, and the determination step determines situation-specific correction information for each of the situations, based on the judgment criteria information and the situation-specific reference emotion score information, for correcting the emotion score information for each of the situations of the subject.

18. The emotion analysis support method according to claim 17, further comprising a generating step and a determining step, wherein the generating step generates corrected emotion score information by correcting the emotion score information of the subject for each of the situations based on the situation-specific correction information of the subject, and the determining step determines the emotion of the subject for each of the situations based on the determination criterion information and the corrected emotion score information.

19. The emotion analysis support method according to claim 17, wherein the setting step, when the situation indicates a normal situation in which the subject is calm, sets normal-time reference emotion score information indicating the emotion score information that serves as a reference for the subject in the normal situation based on a group of emotion score information for the subject in the normal situation; and the determination step, based on the judgment criteria information and the normal-time reference emotion score information, determines normal-time correction information for correcting the emotion score information for the subject in the normal situation.

20. A computer-readable recording medium having recorded thereon an emotion analysis support program for causing a computer to execute each of the above steps, the computer-readable recording medium comprising a setting step, a determination step, and an output step, wherein the setting step sets reference emotion score information indicating the emotion score information serving as a reference for the subject based on a group of emotion score information of the subject, the determination step determines correction information for correcting the emotion score information of the subject based on judgment criteria information used for judging emotions based on the emotion score information and the reference emotion score information, and the output step outputs the correction information.

Images