JP6891732B2 - Information processing equipment, information processing methods, and programs - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and a program.

In recent years, in order to prevent mental health problems of workers, business operators are required to inspect individual workers for the state of stress (stress check).

In addition, a technique for facilitating the input of such a stress check has also been proposed. For example, Patent Document 1 below describes a technique that enables a stress check question to be input at the same time as the time stamped for commuting time and leaving time.

Japanese Unexamined Patent Publication No. 2017-21660

However, in the technique described in Patent Document 1, the stress check is performed regardless of the presence or absence of the stress sign of the user. Therefore, for example, the stress check is performed even when the user does not feel any stress.

Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to adaptively ask a question for determining the degree of stress of a user depending on the presence or absence of signs of stress of the user. It is an object of the present invention to provide new and improved information processing devices, information processing methods, and programs capable of the above.

In order to solve the above problems, according to a certain viewpoint of the present invention, an acquisition unit for acquiring the sensing result of the user's state and a plurality of question items stored in the storage unit for determining the degree of stress. The presence or absence of stress signs of the user and the work of the user, in which the question voice data corresponding to each of the one or more first question items selected from the above is determined based on the sensing result of the state of the user. Information indicating the degree of stress of the user calculated based on the answer of the user to the individual question voice data output by the voice output unit and the voice instruction unit to be output to the voice output unit based on the state. An output control unit that controls the output and an environment information acquisition unit that acquires environmental information indicating the weather or temperature in the environment in which the user is located are provided, and it is determined that the stress sign is present, and the user's work. When it is determined that the degree of drowsiness included in the state is equal to or higher than a predetermined threshold value, the voice instruction unit further outputs sympathy transmission voice data corresponding to the environmental information to the voice output unit. Equipment is provided.

The sensing result of the user's state may include the sensing data of the user's eyes.

The working state of the user may include the degree of drowsiness of the user.

When it is determined that there is the stress sign and the degree of drowsiness is determined to be equal to or higher than a predetermined threshold value, the voice instruction unit asks a question corresponding to each of the one or more first question items. When the voice data for use is output to the voice output unit and it is determined that there is no stress sign, and when it is determined that the degree of drowsiness is less than the predetermined threshold value, the voice instruction unit receives the voice instruction unit. It is not necessary to output the question voice data corresponding to each of the one or more first question items to the voice output unit.

When it is newly determined that the degree of drowsiness is equal to or higher than the predetermined threshold value after the output of the question voice data corresponding to each of the one or more first question items and after the elapse of a predetermined period. , One or more second question items are selected from the plurality of question items excluding the one or more first question items, and the voice instruction unit uses the one or more second question items. The question voice data corresponding to each of the above may be output to the voice output unit.

For each of the one or more first question items, the voice instruction unit is used every time the question voice data corresponding to the question item is output and the user's answer to the question voice data is acquired. May further output the acquired voice data for empathy transmission corresponding to the user's answer to the voice output unit.

With respect to each of the one or more first question items, the voice instruction unit outputs the first question voice data corresponding to the first question of the question item to the presence or absence of stress signs of the user or the user's voice instruction unit. When the voice output unit is made to output based on the degree of drowsiness, and after the output of the first question voice data and the utterance of the user with respect to the first question voice data is detected. , The voice data for the second question corresponding to the second question of the question item may be output to the voice output unit.

The first question may be a question confirming the question itself, and the second question may be a question confirming the degree of the question to be asked.

An eye movement detection unit that detects the pupil diameter and the eyelid opening / closing interval based on the recognition of the user's eye sensing data is further provided, and the presence or absence of the stress sign or the working state is determined by the detection result by the eye movement detection unit. It may be judged based on.

The work state is determined based on the stress sign determination unit that determines the presence or absence of the stress sign based on the pupil diameter detected by the eye movement detection unit and the eyelid opening / closing interval detected by the eye movement detection unit. A work state determination unit may be further provided.

The storage unit further includes the question item, the first question voice data corresponding to the first question of the question item, and the question item, for each of the plurality of question items. The voice data for the second question corresponding to the second question may be associated and stored.

The voice output unit and a voice input unit that picks up the utterance of the user may be further provided.

The output control unit calculates the stress degree of the user based on the user's answer to the individual question voice data output by the voice output unit, and the calculated information indicating the stress degree of the user. You may control the output of.

Further, in order to solve the above problems, according to another viewpoint of the present invention, a step of acquiring a sensing result of a user's state and a step of acquiring environmental information indicating the weather or temperature in the environment in which the user is located. And, the question voice data corresponding to each of one or more first question items selected from a plurality of question items for determining the degree of stress stored in the storage unit is stored in the state of the user. The step of outputting to the voice output unit based on the presence or absence of the stress sign of the user and the working state of the user, which is determined based on the sensing result of the above, and the individual voice data for the question output by the voice output unit. A step of controlling the output of information indicating the degree of stress of the user calculated based on the answer of the user to the above, and a step of outputting the information to the audio output unit are determined to have the stress sign, and the step is determined to have the stress sign. When it is determined that the degree of drowsiness included in the working state of the user is equal to or higher than a predetermined threshold value, an information processing method for further outputting sympathy transmission voice data corresponding to the environmental information to the voice output unit. Is provided.

Further, in order to solve the above-mentioned problems, according to another viewpoint of the present invention, the computer is used to determine the degree of stress stored in the storage unit and the acquisition unit that acquires the sensing result of the user's state. The question voice data corresponding to each of the one or more first question items selected from the plurality of question items of the above is determined based on the sensing result of the state of the user, and the stress sign of the user. A voice instruction unit to be output to the voice output unit based on the presence / absence and the working state of the user, and the user's answer calculated based on the user's answer to the individual question voice data output by the voice output unit. It functions as an output control unit that controls the output of information indicating the degree of stress and an environmental information acquisition unit that acquires environmental information indicating the weather or temperature in the environment in which the user is located, and determines that the stress sign is present. When it is determined that the degree of drowsiness included in the working state of the user is equal to or higher than a predetermined threshold value, the voice instruction unit outputs the sympathy transmission voice data corresponding to the environmental information. A program is provided that causes the unit to output more.

As described above, according to the present invention, the question for determining the degree of stress of the user can be adaptively asked depending on the presence or absence of the stress sign of the user.

It is a functional block diagram which showed the structural example of the stress measuring apparatus 10-1 which concerns on 1st Embodiment of this invention. It is a figure which showed an example of the voice data for question corresponding to the question item for stress check which concerns on 1st Embodiment. It is a flowchart which showed a part of the process flow which concerns on 1st Embodiment. It is a flowchart which showed a part of the process flow which concerns on 1st Embodiment. It is a functional block diagram which showed the structural example of the stress measuring apparatus 10-2 which concerns on 2nd Embodiment of this invention. It is a figure which showed an example of the voice data for empathy transmission which concerns on 2nd Embodiment. It is a flowchart which showed a part of the process flow which concerns on 2nd Embodiment. It is a flowchart which showed a part of the process flow which concerns on 2nd Embodiment. It is a flowchart which showed a part of the process flow which concerns on 2nd Embodiment. It is a figure which showed the hardware configuration example of the stress measuring apparatus 10 common to each embodiment.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals, so that duplicate description will be omitted.

In addition, the "mode for carrying out the invention" will be described in accordance with the order of items shown below.
1. 1. Background 2. First Embodiment 3. Second embodiment 4. Hardware configuration 5. Modification example

In the following, the stress measuring device 10-1 according to the first embodiment of the present invention and the stress measuring device 10-2 according to the second embodiment of the present invention are collectively referred to as the stress measuring device 10. Sometimes referred to.

<< 1. Background >>
First, the background leading to the creation of the present invention will be described. Conventionally, stress checks have been performed in companies and the like for the purpose of identifying people with high stress. However, in known techniques, the stress check is performed at a fixed time or at any time. Therefore, with known technology, there is a risk that the stress check will be performed on the user even when the stress level of the user is low. Therefore, there is a problem in terms of effectiveness.

Further, in a known technique, a GUI (Graphical User Interface), a questionnaire, or the like is often used to make a user answer all the question items for stress check at once. However, such an answer method imposes a heavy load on the user.

Therefore, with the above circumstances as the first point of view, the stress measuring device 10 according to each embodiment of the present invention has been created. The stress measuring device 10 uses voice data for questions corresponding to each of one or more question items selected from a plurality of question items for determining the degree of stress, showing the presence or absence of stress signs of the user and the presence or absence of stress signs of the user. The voice output unit 126 is made to output based on the working state, and the output of information indicating the degree of stress of the user calculated based on the answer of the user to the individual question voice data is controlled. Therefore, the stress check can be adaptively performed according to the presence or absence of stress signs of the user and the working state of the user.

Here, the stress measuring device 10 is an example of an information processing device according to the present invention. The stress measuring device 10 can be, for example, an interactive device (office device or the like) that provides business support. For example, the stress measuring device 10 may be a telephone (for example, a mobile phone such as a smartphone or a stationary telephone), a copier, a general-purpose PC (Personal Computer), a tablet terminal, or the like. Alternatively, the stress measuring device 10 may be a device for a telephone conference system. Hereinafter, the contents of each embodiment will be described in detail in order.

<< 2. First Embodiment >>
<2-1. Configuration>
First, the first embodiment will be described. FIG. 1 is a functional block diagram showing a configuration example of the stress measuring device 10-1 according to the first embodiment. As shown in FIG. 1, the stress measuring device 10-1 includes a control unit 100, a communication unit 120, a sensor unit 122, a voice input unit 124, a voice output unit 126, and a storage unit 128.

{2-1-1. Control unit 100}
The control unit 100 generally controls the operation of the stress measuring device 10-1 by using hardware such as a CPU (Central Processing Unit) 150 described later and a RAM (Random Access Memory) 154 described later. Further, as shown in FIG. 1, the control unit 100 includes a sensing result acquisition unit 102, an eye movement detection unit 104, a stress sign determination unit 106, a work state determination unit 108, a question instruction unit 110, and an output control unit 112. Has. Further, the output control unit 112 includes a stress degree calculation unit 114.

{2-1-2. Sensing result acquisition unit 102}
The sensing result acquisition unit 102 is an example of the acquisition unit according to the present invention. The sensing result acquisition unit 102 acquires the sensing result regarding the user's state by the sensor unit 122 or the like described later. For example, the sensing result acquisition unit 102 acquires the sensing result of the user's eye. As an example, the sensing result acquisition unit 102 receives the captured image of the user's eye captured by the camera directed at the user's eye from the camera, so that the captured image is obtained as the sensing result of the user's eye. May be obtained as. The camera may be included in the sensor unit 122, which will be described later. Alternatively, the camera may be installed outside the stress measuring device 10-1 and may be configured to be communicable with the stress measuring device 10-1.

Alternatively, the sensing result acquisition unit 102 may acquire the sensing result of the potential from the contacted skin by the electro-oculography sensor built in the eyeglass-type device worn by the user as the sensing result of the user's eye. Good. The stress measuring device 10-1 may be configured to be communicable with the spectacle-type device, or the stress measuring device 10-1 and the spectacle-type device may be integrally configured. ..

Further, the sensing result acquisition unit 102 may acquire the sensing result (for example, the pitch of the voice) of the movement of the user's head and the state of the user's utterance from, for example, the sensor unit 122.

{2-1-3. Eye movement detection unit 104}
The eye movement detection unit 104 detects the eye movement of the user (for example, pupil diameter, eyelid opening / closing interval, etc.) based on the sensing result acquired by the sensing result acquisition unit 102. For example, the eye movement detection unit 104 may detect the eye movement of the user by performing image recognition on the acquired image of the user's eye. Alternatively, the eye movement detection unit 104 may detect the eye movement of the user based on the change in voltage measured by the electro-oculography sensor (of the spectacle-type device worn by the user).

{2-1-4. Stress sign determination unit 106}
The stress sign determination unit 106 determines the presence or absence of the stress sign of the user based on the detection result by the eye movement detection unit 104. For example, the stress sign determination unit 106 determines the presence or absence of a stress sign of the user based on the detection result of the ratio of the pupil diameter of the user by the eye movement detection unit 104. Here, the stress sign may mean a sign that the user is feeling stress above a certain level. The stress sign determination unit 106 may determine the presence or absence of stress signs of the user, for example, based on the number of times the ratio of the pupil diameter exceeds a predetermined value.

{2-1-5. Work status determination unit 108}
The work state determination unit 108 determines the user's work state based on the sensing result acquired by the sensing result acquisition unit 102. Here, the working state of the user includes, for example, the degree of drowsiness of the user and the degree of concentration of the user. For example, the work state determination unit 108 determines the work state of the user based on the detection result by the eye movement detection unit 104. As an example, the working state determination unit 108 determines the degree of drowsiness of the user based on the detection result of the eyelid opening / closing interval of the user by the eye movement detection unit 104. The work state determination unit 108 may determine the degree of drowsiness of the user, for example, based on the number of times the eyelid opening / closing interval exceeds a predetermined value.

Alternatively, the work state determination unit 108 may perform a head movement sensing result (for example, movement speed or movement pattern) acquired by the sensing result acquisition unit 102, a detection result of whether or not the user is yawning, or the like. The degree of drowsiness of the user may be determined based on the above.

{2-1-6. Question indicator 110}
The question instruction unit 110 is an example of the voice instruction unit according to the present invention. The question instruction unit 110 is one or more questions selected from a plurality of question items for determining the degree of stress (hereinafter, referred to as a plurality of question items for stress check) stored in the storage unit 128. The question voice data corresponding to each of the items is output as voice based on the presence or absence of the stress sign of the user determined by the stress sign determination unit 106 and the work state of the user determined by the work state determination unit 108. Output to unit 126. For example, when it is determined that there is no sign of stress of the user, and when it is determined that the degree of drowsiness of the user is less than a predetermined threshold value, the question instruction unit 110 determines that one or more question items. The question voice data corresponding to each is not output to the voice output unit 126. Even when it is determined that the degree of concentration of the user is equal to or higher than a predetermined threshold value, the question instruction unit 110 does not have to output the question voice data to the voice output unit 126.

Further, when it is determined that there is a stress sign of the user and the degree of drowsiness of the user is determined to be equal to or higher than the predetermined threshold value, the question instruction unit 110 displays each of the one or more question items. The question voice data corresponding to is output to the voice output unit 126. Even when it is determined that there is a stress sign of the user and the degree of concentration of the user is less than a predetermined threshold value, the question instruction unit 110 asks each of the one or more question items. The corresponding question voice data may be output to the voice output unit 126.

For example, the question instruction unit 110 selects a predetermined number of question items (first question item) as a question target at the current question timing from the plurality of question items, and then asks the predetermined number of questions. The voice output unit 126 is made to output the question voice data corresponding to each of the items. Then, after the lapse of a predetermined time and when it is newly determined that the degree of drowsiness of the user is equal to or higher than the predetermined threshold value, the question instruction unit 110 performs the previous time among the plurality of question items. From the question items other than all the question items selected as the question target by the question timing of, a predetermined number of question items (second question item) are newly selected as the question target at this question timing. Then, the voice output unit 126 is made to output the question voice data corresponding to each of the selected predetermined number of question items.

Hereinafter, the above functions will be described in more detail. For example, the question instruction unit 110 is first asked from a plurality of stress check question items stored in the storage unit 128 by the previous question timing at each question timing (for the same user). From one or more question items that have not been asked, a predetermined number of question items are randomly selected, for example, as question items at the question timing. (That is, the question items at each question timing do not overlap.) Then, the question instruction unit 110 asks the first question corresponding to the first question of the question item for each of the predetermined number of selected question items. The voice data for the second question and the voice data for the second question corresponding to the second question of the question item are output to the voice output unit 126. For example, the question instruction unit 110 first causes the voice output unit 126 to output the first question voice data corresponding to the first question of the question item for each of the predetermined number of question items. Next, when the utterance of the user's answer to the first question voice data is detected, the question instruction unit 110 receives the second question voice data corresponding to the second question of the question item. Is output to the audio output unit 126. Then, when the utterance of the answer of the user to the second question voice data is detected, the question instruction unit 110 performs the same with respect to the question items in the next order among the predetermined number of question items. The process is repeated (that is, the output control of the above-mentioned first question voice data and the second question voice data is performed). Here, the first question of the question item may be a question confirming the question itself. In addition, the second question of the question item may be a question confirming the degree of the matter to be asked. By asking the two types of questions in this way, it becomes easier for the user to understand each question, and it is possible to realize a natural dialogue with the user.

The above-mentioned predetermined number (that is, the number of question items selected for each question timing) can be arbitrarily changed. In addition, the above-mentioned predetermined numbers may be the same number or different for each question timing.

(2-1-6-1. Question data for stress check)
FIG. 2 is a diagram showing an example of question voice data (stress check question data 20) corresponding to the plurality of question items for stress check. As shown in FIG. 2, in the stress check question data 20, for example, No. 200, the question item 202, the first question voice data 204, and the second question voice data 206 are associated with each other. For example, in the data of the first record shown in FIG. 2, the question item is "must do a lot of work", and the first question voice data corresponding to the question item is "recently work". An example in which the voice data is "Are there many?" And the voice data for the second question corresponding to the question item is "How much? Very? Quite? Somewhat? At all?" Is shown.

The plurality of question items for the stress check may be the same as, for example, a plurality of question items (for example, 23 question items) defined by a public institution (Ministry of Health, Labor and Welfare, etc.), or other questions. It may be determined by a person (for example, the manager of the stress measuring device 10-1). Further, the stress check question data 20 is stored in, for example, the storage unit 128.

{2-1-7. Stress degree calculation unit 114}
The stress degree calculation unit 114 calculates the stress degree of the user based on the user's answer to the question voice data corresponding to each of the plurality of question items for the stress check. For example, the stress degree calculation unit 114 first converts the voice recognition result (wording) of the utterance of the user's answer to the second question voice data corresponding to the question item into a numerical value for each of the plurality of question items. Convert. Then, the stress degree calculation unit 114 calculates the stress degree of the user based on the converted numerical value for each of the plurality of question items and a predetermined calculation formula (for example, a calculation formula determined by a public institution). ..

Here, a specific example of converting the above user's answer into a numerical value will be described. For example, in the stress degree calculation unit 114, for each of the plurality of question items, the greater the degree (degree) indicated by the voice recognition result of the user's answer to the second question voice data of the question item, the more after conversion. The answer may be converted to a numerical value so that the numerical value of is larger (or smaller). In the example shown in FIG. 2, the stress degree calculation unit 114 performs the second question voice data corresponding to the question item of "No. 1" (that is, "how much? Very? Quite? Somewhat? At all?" "4" to indicate that the user's answer to "?") Is "very many", "3" to indicate "quite many", and "2" to indicate "somewhat many". , If it indicates "not at all", the answer may be converted to "1".

{2-1-8. Output control unit 112}
The output control unit 112 controls the output of information indicating the stress degree of the user calculated by the stress degree calculation unit 114. For example, when the stress measuring device 10-1 has a display (display unit), the output control unit 112 may display a character string or an image indicating the degree of stress of the user on the display, or output control. The unit 112 may be displayed on an external device (not shown) capable of communicating with the stress measuring device 10-1 via a communication network such as the Internet. Alternatively, the output control unit 112 may output the feedback voice (“the stress degree seems to be high” or the like) corresponding to the stress degree of the user to the voice output unit 126. Alternatively, the output control unit 112 may cause the communication unit 120 to send an e-mail containing information indicating the degree of stress of the user to a specific person such as a doctor.

{2-1-9. Communication unit 120}
The communication unit 120 transmits / receives information to / from other devices via a communication network such as the Internet. For example, the communication unit 120 receives a sensing result (for example, an image captured by the user's eye) by an external sensor (not shown) from the external sensor.

{2-1-10. Sensor unit 122}
The sensor unit 122 senses the state of the user (for example, the state of the user's eyes). The sensor unit 122 includes, for example, a camera (image sensor), an electro-oculography sensor, a biosensor (pulse sensor, etc.), and / or a temperature sensor.

{2-1-11. Voice input unit 124}
The voice input unit 124 collects (inputs) the user's voice. The voice input unit 124 may be configured to include a microphone.

{2-1-12. Audio output unit 126}
The audio output unit 126 outputs audio according to the control of the control unit 100. For example, the audio output unit 126 includes a speaker, earphones, headphones, and the like.

{2-1-13. Storage 128}
The storage unit 128 stores various data and various software. For example, the storage unit 128 stores the stress check question data 20 shown in FIG. In addition, the storage unit 128 stores the data of the user's answer to each of the plurality of question items for stress check (for example, the recorded data of the answer or the voice recognition result of the answer) for each user.

<2-2. Process flow>
The configuration of the first embodiment has been described above. Next, the flow of processing according to the first embodiment will be described with reference to FIGS. 3 and 4. 3 and 4 are flowcharts showing the flow of processing according to the first embodiment.

As shown in FIG. 3, first, the sensing result acquisition unit 102 of the stress measuring device 10-1 constantly acquires the sensing result of the user's eye by the sensor unit 122 or the like. Then, the eye movement detection unit 104 constantly detects the eye movement of the user based on the acquired sensing result (S101).

Subsequently, the stress sign determination unit 106 determines the presence or absence of the stress sign of the user based on the detection result of the eye movement in S101 (S103).

Subsequently, the work state determination unit 108 determines the degree of drowsiness of the user based on the detection result of the eye movement in S101 (S105).

Then, when it is determined in S103 that there is no sign of stress (S107: No), the stress measuring device 10-1 performs the processing after S103 again.

On the other hand, when it is determined that there is a stress sign in S103 and the degree of drowsiness determined in S105 is less than a predetermined threshold value (S107: Yes, S109: No), the stress measuring device 10-1 is again used. The processing after S105 is performed.

On the other hand, when it is determined that there is a stress sign in S103 and the degree of drowsiness determined in S105 is equal to or higher than the predetermined threshold value (S107: Yes, S109: Yes), the voice output unit 126 asks a question. According to the control of the unit 110, the voice data for calling the user (voice data for the intro) is output as voice (S111).

After that, the question instruction unit 110 waits until the utterance of the response of the user is detected (S113). Then, when the utterance of the response of the user is detected (S113: Yes), the question indicating unit 110 asks this question from among the plurality of question items for stress check stored in the storage unit 128. A predetermined number of question items are selected as targets (S115).

Here, the flow of processing after S115 will be described with reference to FIG. As shown in FIG. 4, after S115, the question instruction unit 110 first extracts one question item that has not yet been asked from the predetermined number of question items selected in S115. Then, the voice output unit 126 outputs the first question voice data corresponding to the extracted question item by voice according to the control of the question instruction unit 110 (S121).

After that, the question instruction unit 110 waits until the utterance of the response of the user is detected (S123). Then, when the utterance of the response of the user is detected (S123: Yes), the voice output unit 126 voices the second question voice data corresponding to the question item under the control of the question instruction unit 110. Output (S125).

After that, the control unit 100 waits until the utterance of the user's answer to the second question voice data is detected (S127). Then, when the utterance of the answer of the user is detected (S127: Yes), the control unit 100 stores the answer data of the user in the storage unit 128 (S129).

After that, if there is a question item that has not yet been asked among the predetermined number of question items selected in S115 (S131: No), the question instruction unit 110 performs the processing after S121 again.

On the other hand, when the questions regarding all of the predetermined number of question items selected in S115 are completed (S131: Yes), the control unit 100 then asks the user about all the question items for stress check. It is determined whether or not the question has been completed (S133).

If there is a question item that has not yet been asked to the user among all the question items for the stress check (S133: No), the stress measuring device 10-1 again performs the processing after S105. Do.

On the other hand, when the questions regarding all the question items for the stress check to the user are completed (S133: Yes), the stress degree calculation unit 114 is stored in the storage unit 128, for example, for the stress check. The degree of stress of the user is calculated based on the answer data of the user for each of all the question items (S135).

After that, the output control unit 112 controls the output of information indicating the degree of stress of the user calculated in S135. For example, the output control unit 112 causes an external device to transmit information indicating the stress degree of the user to the communication unit 120, or causes the voice output unit 126 to output a feedback voice corresponding to the stress degree of the user ( S137).

<2-3. Effect>
{2-3-1. Effect 1}
As described above, the stress measuring device 10-1 according to the first embodiment acquires the sensing result of the user's state, and one or more question items selected from a plurality of question items for stress check. The question voice data corresponding to each of the above is output to the voice output unit 126 based on the presence or absence of stress signs of the user and the working state of the user, and based on the user's answer to the individual question voice data. To calculate the degree of stress of the user. Therefore, the stress check can be adaptively performed according to the presence or absence of a stress sign of the user and the working state of the user.

For example, when it is determined that there is a sign of stress of the user and the degree of drowsiness of the user is determined to be equal to or higher than a predetermined threshold value, the stress measuring device 10-1 asks each of the one or more question items. The corresponding question voice data is output to the voice output unit 126. Therefore, the stress check can be performed on the user at the timing when the stress degree of the user is high, so that the stress check can be performed more effectively.

Further, since the stress measuring device 10-1 uses both the stress estimation based on the detection of the eye movement and the stress check in the form of a question, the stress degree of the user can be estimated with high accuracy.

{2-3-2. Effect 2}
Further, the stress measuring device 10-1 performs a stress check only when, for example, it is determined that the degree of drowsiness of the user is equal to or higher than a predetermined threshold value. Therefore, the risk of interfering with the user's work is low, and the effect of awakening the user's drowsiness can be expected.

{2-3-3. Effect 3}
Further, the stress measuring device 10-1 selects only a few question items from a plurality of question items for stress check at each question timing, and checks the several question items in a simple interactive format. Can be done by Therefore, there is an advantage that the load of the user's answer is reduced as compared with the method of checking all the items for the stress check collectively using, for example, a GUI or a questionnaire.

<2-4. Modification example>
The first embodiment is not limited to the above-mentioned example. For example, when the stress degree of the user is equal to or more than a predetermined value calculated by the stress degree calculation unit 114, the stress measuring device 10-1 calls between the user and a predetermined person (such as a doctor). You may make a call by connecting.

<< 3. Second embodiment >>
The first embodiment has been described above. By the way, in general, when the system outputs a voice to the user that shares the user's feelings (for example, feelings about the environment such as weather, feelings about the user's condition, etc.), the user causes the system. It is known that they tend to talk more actively with.

Next, the second embodiment will be described. As will be described later, according to the second embodiment, for example, the user can be made to output the current environmental information and the voice data for empathy transmission corresponding to the user's answer to each question for stress check. it can. Here, the voice data for empathy transmission may be, for example, voice data having contents indicating sympathy for the user's emotions (senses) assumed from the current environmental information and the contents of the user's response.

<3-1. Configuration>
First, the configuration according to the second embodiment will be described. FIG. 5 is a functional block diagram showing a configuration example of the stress measuring device 10-2 according to the second embodiment. As shown in FIG. 5, the stress measuring device 10-2 further has an environmental information acquisition unit 116 and an empathy transmission instruction unit 118 as compared with the stress measuring device 10-1 shown in FIG. In the following, only the components having the functions different from those of the first embodiment will be described, and the description of the same contents will be omitted.

{3-1-1. Environmental information acquisition unit 116}
The environmental information acquisition unit 116 acquires environmental information in the environment in which the user (target of stress check) is located. Here, the environmental information can be data indicating the weather and temperature in the environment (for example, the temperature in the room when the user is in the room). For example, the environmental information acquisition unit 116 may acquire the temperature sensed by the sensor unit 122 as a part of the environmental information. Further, the environmental information acquisition unit 116 may acquire the weather and temperature information of the user's current location received from an external site via the communication network as a part of the environmental information.

{3-1-2. Empathy transmission instruction unit 118}
The sympathy transmission instruction unit 118 is an example of the voice instruction unit according to the present invention. The empathy transmission instruction unit 118 uses the voice data for empathy transmission corresponding to the environmental information acquired by the environmental information acquisition unit 116 to determine the presence or absence of stress signs of the user and the work state determination as determined by the stress sign determination unit 106. The voice output unit 126 is made to output based on the working state of the user determined by the unit 108. For example, at each question timing, immediately before the output of the first question voice data at the question timing, the sympathy transmission instruction unit 118 causes the voice output unit 126 to output the sympathy transmission voice data corresponding to the environmental information.

Further, the empathy transmission instruction unit 118 voices the empathy transmission voice data corresponding to the user's answer based on the detection of the user's answer to the question voice data corresponding to each of the plurality of stress check question items. The output unit 126 is made to output. For example, for each question item, each time the second question voice data corresponding to the question item is output and the user's answer to the second question voice data is acquired, the empathy transmission instruction unit 118 Causes the voice output unit 126 to output sympathy transmission voice data corresponding to the user's answer.

(3-1-2-1. Voice data for empathy transmission)
FIG. 6 is a diagram showing an example of sympathy transmission voice data (sympathy transmission voice data 30). As shown in FIG. 6, in the sympathy transmission voice data 30, for example, the type 300, the variable 302, the value 304, and the voice data 306 are associated with each other. The sympathy transmission voice data 30 is stored in, for example, a storage unit 128.

In the example shown in FIG. 6, when the environmental information acquired by the environmental information acquisition unit 116 indicates "weather: sunny", the sympathy transmission instruction unit 118 uses the sympathy transmission instruction unit 118 as voice data for sympathy transmission corresponding to the environmental information. The voice data "It's a nice weather today" can be acquired, and the voice data can be output to the voice output unit 126. In addition, when the user's answer indicating "very many" is detected after the output of the second question voice data corresponding to "question item 1 (for stress check)", the empathy transmission instruction unit 118 Can acquire the voice data "It is hard to have a lot of work" as the voice data for empathy transmission corresponding to the answer of the user, and output the voice data to the voice output unit 126.

Note that FIG. 6 shows an example in which one voice data 306 is registered for each combination of the type 300, the variable 302, and the value 304, but the present invention is not limited to this example. On the other hand, a plurality of types of voice data 306 may be registered. In this case, the empathy transmission instruction unit 118 may randomly select any one of the plurality of types of voice data each time.

<3-2. Process flow>
The configuration of the second embodiment has been described above. Next, the flow of processing according to the second embodiment will be described with reference to FIGS. 7 to 9. 7 to 9 are flowcharts showing the flow of processing according to the second embodiment. The processing of S101 to S109 shown in FIG. 7 is the same as that of S101 to S109 according to the first embodiment.

In S109, when the determined degree of drowsiness is equal to or greater than a predetermined threshold value (S109: Yes), the environmental information acquisition unit 116 acquires environmental information in the environment in which the user is located (S201).

The processing of S111 to S113 shown in FIG. 7 is the same as that of S111 to S113 according to the first embodiment.

Here, with reference to FIG. 8, the processing flow in the case where the utterance of the response of the user is detected in S113 (S113: Yes) will be described. As shown in FIG. 8, in this case, first, the empathy transmission instruction unit 118 extracts the empathy transmission voice data associated with the environmental information acquired in S201 from the storage unit 128. Then, the voice output unit 126 outputs the extracted sympathy transmission voice data by voice according to the control of the sympathy transmission instruction unit 118 (S203).

The processing of S115 to S127 shown in FIG. 8 is the same as that of S115 to S127 according to the first embodiment.

When the utterance of the user's answer is detected in S127 (S127: Yes), the empathy transmission instruction unit 118 uses the second question voice data output in S125 and the user's voice data acquired in S127. The sympathy transmission voice data associated with the answer (for example, voice recognition result) is extracted from the storage unit 128. Then, the voice output unit 126 outputs the extracted sympathy transmission voice data by voice according to the control of the sympathy transmission instruction unit 118 (S205).

The processing of S129 to S137 shown in FIGS. 8 and 9 is the same as that of S129 to S137 according to the first embodiment.

<3-3. Effect>
As described above, the stress measuring device 10-2 according to the second embodiment uses the voice data for empathy transmission corresponding to the environmental information in the environment in which the user is located according to the presence or absence of stress signs of the user and the stress sign of the user. The audio output unit 126 is made to output based on the working state. Further, the stress measuring device 10-2 outputs the sympathy transmission voice data corresponding to the user's answer to the voice output unit 126 based on the detection of the user's answer to the question voice data corresponding to each question item. Let me. Therefore, it can be expected that the user will answer more positively when the individual question voice data is output.

For example, when performing a stress check on a user, the stress measuring device 10-2 gives the user a voice having a content that shares the user's feeling for the current environmental information and the user's feeling for the stress state. Can be presented to. As a result, the user can be expected to concentrate more on the interaction with the stress measuring device 10-2. As a result, it can be expected that the performance rate of the stress check will be improved.

<< 4. Hardware configuration >>
Next, the hardware configuration of the stress measuring device 10 according to each embodiment will be described with reference to FIG. As shown in FIG. 10, the stress measuring device 10 includes a CPU 150, a ROM (Read Only Memory) 152, a RAM 154, an internal bus 156, an input / output interface 158, an input device 160, an output device 162, and an HDD (Hard Disk Drive) 164. , And a network interface 166.

The CPU 150 functions as an arithmetic processing device and a control device, and controls the overall operation in the stress measuring device 10 according to various programs. Further, the CPU 150 realizes the function of the control unit 100. The CPU 150 is composed of a processor such as a microprocessor.

The ROM 152 stores programs, calculation parameters, and the like used by the CPU 150.

The RAM 154 temporarily stores a program used in the execution of the CPU 150, parameters that are appropriately changed in the execution, and the like.

The internal bus 156 is composed of a CPU bus and the like. The internal bus 156 connects the CPU 150, the ROM 152, and the RAM 154 to each other.

The input / output interface 158 connects the input device 160, the output device 162, the HDD 164, and the network interface 166 to the internal bus 156.

The input device 160 is an input means for a user to input information such as a touch panel, a button, a switch, a lever, or a microphone, and an input control circuit that generates an input signal based on the input by the user and outputs the input signal to the CPU 150. It is composed of.

The output device 162 includes, for example, a display such as an LCD (Liquid Crystal Display) or an OLED (Organic Light Emitting Diode), or a display device such as a projector. Further, the output device 162 may include an audio output device such as a speaker.

HDD 164 is a device for storing data. The HDD 164 includes, for example, a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, a deleting device for deleting the data recorded on the storage medium, and the like. Further, the HDD 164 stores a program executed by the CPU 150 and various data. The HDD 164 functions as a storage unit 128.

The network interface 166 is a communication interface composed of a communication device for connecting to a communication network such as the Internet. The network interface 166 functions as a communication unit 120. The network interface 166 may be a wireless LAN (Local Area Network) compatible communication device, an LTE (Long Term Evolution) compatible communication device, or a wire communication device that performs wired communication.

<< 5. Modification example >>
Although the preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, the present invention is not limited to such examples. It is clear that a person having ordinary knowledge in the field of technology to which the present invention belongs can come up with various modifications or modifications within the scope of the technical idea described in the claims. , These are also naturally understood to belong to the technical scope of the present invention.

<5-1. Modification 1>
For example, in each of the above-described embodiments, an example of determining the presence or absence of a stress sign of the user based on the sensing result of the user's state has been described, but the present invention is not limited to such an example. For example, the stress measuring device 10 according to each embodiment is connected to a business system (including, for example, an attendance management system), and the stress measuring device 10 is based on information about a user received from the business system. The presence or absence of stress signs of the user may be determined. As an example, when the overtime hours of individual users are received from the business system, the stress measuring device 10 stresses the individual users based on whether the overtime hours of the individual users exceed a predetermined threshold value. The presence or absence of signs may be determined.

<5-2. Modification 2>
Further, any one or more of the sensor unit 122, the audio input unit 124, and the audio output unit 126 is included in the stress measuring device 10, but instead is included in another device (for example, a user) capable of communicating with the stress measuring device 10. May be included in mobile devices, etc.). For example, the mobile terminal may include a voice input unit 124 and a voice output unit 126. In this case, when it is determined that there is a stress sign and the degree of drowsiness of the user is determined to be equal to or higher than a predetermined threshold value, the stress measuring device 10 communicates with the mobile terminal to cause the user. It is possible to perform a stress check on the device.

<5-3. Modification 3>
Further, in each embodiment, an example in which the stress measuring device 10 is an interactive office device has been mainly described, but the present invention is not limited to such an example. For example, when the sensor unit 122, the voice input unit 124, and the voice output unit 126 are included in other devices in the environment in which the user is located, the stress measuring device 10 is a server capable of communicating with the other devices. There may be.

Further, according to each embodiment of the present invention, it is possible to provide a computer program for causing hardware such as the CPU 150, ROM 152, and RAM 154 to exhibit the same functions as the configuration of the stress measuring device 10 according to each embodiment. is there. A storage medium on which the computer program is recorded is also provided.

10-1, 10-2 Stress measuring device 100 Control unit 102 Sensing result acquisition unit 104 Eye movement detection unit 106 Stress sign judgment unit 108 Work state judgment unit 110 Question instruction unit 112 Output control unit 114 Stress degree calculation unit 116 Environmental information acquisition Unit 118 Empathy transmission instruction unit 120 Communication unit 122 Sensor unit 124 Voice input unit 126 Voice output unit 128 Storage unit

Claims (15)

An acquisition unit that acquires the sensing result of the user's status,
Sensing the state of the user with question voice data corresponding to each of one or more first question items selected from a plurality of question items for determining the degree of stress stored in the storage unit. A voice instruction unit that outputs to the voice output unit based on the presence or absence of stress signs of the user and the working state of the user, which is determined based on the result,
An output control unit that controls the output of information indicating the degree of stress of the user calculated based on the user's answer to the individual question voice data output by the voice output unit.
It is provided with an environmental information acquisition unit that acquires environmental information indicating the weather or temperature in the environment in which the user is located.
When it is determined that there is the stress sign and the degree of drowsiness included in the working state of the user is determined to be equal to or higher than a predetermined threshold value, the voice instruction unit transmits sympathy corresponding to the environmental information. An information processing device that further outputs voice data for use to the voice output unit. The information processing device according to claim 1, wherein the sensing result of the user's state includes sensing data of the user's eyes. The information processing device according to claim 2, wherein the working state of the user includes the degree of drowsiness of the user. When it is determined that there is the stress sign and the degree of drowsiness is determined to be equal to or higher than a predetermined threshold value, the voice instruction unit asks a question corresponding to each of the one or more first question items. To output the voice data for the voice to the voice output unit,
When it is determined that there is no sign of stress, and when it is determined that the degree of drowsiness is less than the predetermined threshold value, the voice instruction unit asks each of the one or more first question items. The information processing device according to claim 3, wherein the corresponding question voice data is not output to the voice output unit. When it is newly determined that the degree of drowsiness is equal to or higher than the predetermined threshold value after the output of the question voice data corresponding to each of the one or more first question items and after the elapse of a predetermined period. , One or more second question items are selected from the plurality of question items excluding the one or more first question items, and
The information processing device according to claim 4, wherein the voice instruction unit outputs question voice data corresponding to each of the one or more second question items to the voice output unit. For each of the one or more first question items, the voice instruction unit is used every time the question voice data corresponding to the question item is output and the user's answer to the question voice data is acquired. The information processing apparatus according to claim 4 or 5, wherein the voice output unit further outputs the acquired voice data for sympathy transmission corresponding to the user's answer. For each of the one or more first question items, the voice instruction unit outputs the first question voice data corresponding to the first question of the question item to the presence or absence of stress signs of the user or the user's voice data. Output to the audio output unit based on the degree of drowsiness, and
After the output of the first question voice data, and when the user's utterance to the first question voice data is detected, a second question corresponding to the second question of the question item is detected. The information processing apparatus according to any one of claims 4 to 6 , wherein the question voice data is output to the voice output unit. The first question mentioned above is a question that confirms what you want to ask.
The information processing apparatus according to claim 7 , wherein the second question is a question for confirming the degree of the matter to be asked. Further provided with an eye movement detection unit that detects the pupil diameter and the eyelid opening / closing interval based on the recognition of the user's eye sensing data.
The information processing apparatus according to any one of claims 4 to 8 , wherein the presence or absence of the stress sign or the working state is determined based on the detection result by the eye movement detection unit. A stress sign determination unit that determines the presence or absence of the stress sign based on the pupil diameter detected by the eye movement detection unit, and a stress sign determination unit.
The information processing apparatus according to claim 9 , further comprising a work state determination unit that determines the work state based on the eyelid opening / closing interval detected by the eye movement detection unit. The storage unit is further provided.
The storage unit corresponds to the question item, the voice data for the first question corresponding to the first question of the question item, and the second question of the question item for each of the plurality of question items. The information processing device according to claim 9 , which stores the voice data for a second question in association with each other. With the audio output unit
The information processing device according to claim 10 or 11 , further comprising a voice input unit for picking up the user's utterance. The output control unit calculates the degree of stress of the user based on the answer of the user to the individual voice data for questions output by the voice output unit, and also
The information processing device according to claim 12 , which controls the output of the calculated information indicating the degree of stress of the user. Steps to get the sensing result of the user's status,
A step of acquiring environmental information indicating the weather or temperature in the environment in which the user is located, and
Sensing the state of the user with question voice data corresponding to each of one or more first question items selected from a plurality of question items for determining the degree of stress stored in the storage unit. A step of outputting to the voice output unit based on the presence or absence of the stress sign of the user and the working state of the user, which is determined based on the result, and
A step of controlling the output of information indicating the degree of stress of the user calculated based on the answer of the user to the individual voice data for question output by the voice output unit, and a step of controlling the output of the information indicating the degree of stress of the user.
Including
When it is determined that the stress sign is present and the degree of drowsiness included in the working state of the user is determined to be equal to or higher than a predetermined threshold value, the step of outputting to the voice output unit provides the environmental information. An information processing method for further outputting the corresponding voice data for empathy transmission to the voice output unit. Computer,
An acquisition unit that acquires the sensing result of the user's status,
Sensing the state of the user with question voice data corresponding to each of one or more first question items selected from a plurality of question items for determining the degree of stress stored in the storage unit. A voice instruction unit that outputs to the voice output unit based on the presence or absence of stress signs of the user and the working state of the user, which is determined based on the result,
An output control unit that controls the output of information indicating the degree of stress of the user calculated based on the user's answer to the individual question voice data output by the voice output unit .
It functions as an environmental information acquisition unit that acquires environmental information indicating the weather or temperature in the environment in which the user is located.
When it is determined that there is the stress sign and the degree of drowsiness included in the working state of the user is determined to be equal to or higher than a predetermined threshold value, the voice instruction unit transmits sympathy corresponding to the environmental information. A program that further outputs voice data for use to the voice output unit.

Images