JP7255437B2 - Diffusion object control method, diffusion object control program, and diffusion object control device - Google Patents

Description

The embodiments of the present invention relate to a diffusion object control method, a diffusion object control program, and a diffusion object control device.

Conventionally, a diffusion object such as a scent has the effect of reducing stress and improving tension and performance, and is sometimes used to improve the atmosphere of workshops, meetings, and the like. However, since there are individual differences in the perception of scents, etc., it is important to adjust the intensity appropriately according to the comfort and discomfort of the person and present the diffusion target.

Conventional techniques for judging human comfort/discomfort include speech parameters of speech uttered by a subject before a desired stimulus is provided, and speech parameters of speech uttered by a subject when a desired stimulus is provided. are compared, and whether or not the subject's feeling is pleasant is determined based on the comparison result.

JP 2009-042671 A

However, in the conventional technology described above, since diffusion objects are presented to individuals according to their comfort and discomfort, there is a problem that it is difficult to provide a place where many people can spend time comfortably. For example, if there are many people who are relatively close to the emission position of the diffusion target, the scent may be too strong and the person may feel uncomfortable just by averaging the sum of pleasantness and discomfort of each person. may increase.

An object of one aspect is to provide a diffusion object control method, a diffusion object control program, and a diffusion object control device that can support provision of a place where many people can spend comfortably.

In the first scheme, the diffusion target control method causes a computer to execute a detection process, an emotion determination process, a calculation process, a state determination process, and an adjustment process. The detecting process detects the position of each user existing in the field from which the diffuse object is emitted. In the emotion determination process, the user's emotion is determined for each user based on at least one feature amount of each user's video and audio. In the calculation process, the distance to the emission position of the diffusion target is calculated for each user based on the detected position of the user. In the process of determining the state, the state of the field is determined based on the emotion determined for each user and the calculated distance. The adjusting process adjusts the intensity of emitting the diffuse object according to the determined field state.

According to one embodiment of the present invention, it is possible to support provision of a place where many people can spend time comfortably.

FIG. 1 is a block diagram illustrating a functional configuration example of a diffusion target control device according to a first embodiment; FIG. 2 is a flowchart illustrating an operation example of the diffusion target control device according to the first embodiment; FIG. 3 is a flowchart illustrating an example of the perceptual state determination process. FIG. 4 is a flow chart showing an example of the field state determination processing. FIG. 5 is a flow chart showing an example of the scent presentation control process. FIG. 6 is a block diagram illustrating a functional configuration example of a diffusion target control device according to a second embodiment; FIG. 7 is a flowchart illustrating an operation example of the diffusion target control device according to the second embodiment. FIG. 8 is a flow chart showing an example of the field state determination processing. FIG. 9 is an explanatory diagram for explaining the distance feature amount. FIG. 10 is a block diagram showing an example of a computer that executes programs.

A diffusion object control method, a diffusion object control program, and a diffusion object control device according to embodiments will be described below with reference to the drawings. Configurations having the same functions in the embodiments are denoted by the same reference numerals, and overlapping descriptions are omitted. The diffusion object control method, the diffusion object control program, and the diffusion object control device described in the following embodiments are merely examples, and do not limit the embodiments. Moreover, each of the following embodiments may be appropriately combined within a non-contradictory range.

(First embodiment)
FIG. 1 is a block diagram illustrating a functional configuration example of a diffusion target control device according to a first embodiment; As shown in FIG. 1, a diffusion object control apparatus 1 controls a diffusion object presentation unit 2 installed in a place (for example, a conference room) where a plurality of users (persons H1, H2, H3, . . . ) gather. It is a device that controls the diffusion target such as the aromatic substance released by 2 so that most of the people H1, H2, H3, . . . feel comfortable. As a result, the diffusion target control device 1 assists in providing a comfortable place for many people (people H1, H2, H3, . . . ).

In the present embodiment, the diffusion object presenting unit 2 is a scent releasing device that releases a predetermined aromatic substance in the form of a mist or vaporized, and exemplifies a configuration for presenting the scent to the place. However, the diffusion target is not limited to aromatic substances, and any substance may be used as long as it is perceived by persons H1, H2, and H3 and helps reduce stress, improve tension, and improve performance.

For example, the diffused object presenting unit 2 may be an acoustic device that emits sounds such as BGM, or an air conditioner that emits air after air conditioning with adjusted temperature, humidity, ion concentration, and the like. That is, in addition to the aromatic substance, the diffusion target may be sound such as BGM, or air after air conditioning in which the temperature, humidity, ion concentration, etc. are adjusted. It may be at least one such as Also, the diffusion target may be a combination of an aromatic substance and sound, or an aromatic substance and air after air conditioning.

The diffusion target control device 1 includes a first position acquisition unit 10, a second position acquisition unit 11, a facial expression feature amount extraction unit 12, a voice feature amount extraction unit 13, a perception state determination unit 14, and a field sensor. It has a state determination unit 15 and a diffusion target presentation control unit 16 .

The first position acquisition unit 10 is a processing unit that acquires position information of the diffusion target presentation unit 2 . Specifically, the first position acquisition unit 10 refers to a GPS (Global Positioning System), setting information preset in a memory or the like in advance to determine the installation position of the diffusion target presentation unit 2, that is, the diffusion target. Get the position information indicating the emission position of the . The first position acquisition unit 10 outputs the acquired position information of the diffusion target presentation unit 2 to the field state determination unit 15 .

The second position acquisition unit 11 is a processing unit that acquires position information of each of the people H1, H2, H3, . That is, the second position acquisition unit 11 is an example of a detection unit that detects the positions of the persons H1, H2, H3, . . .

Specifically, the second position acquisition unit 11 uses a known image recognition technology from the image of the camera 4 installed in the place where the diffusion target presentation unit 2 is emitted, to identify each of the persons H1, H2, H3, . Identify. The diffusion target control device 1 individually manages the information of the persons H1, H2, H3, . Next, the second position acquisition unit 11 acquires the position information of each of the identified persons H1, H2, H3, . . . . It should be noted that the second position acquisition unit 11 may acquire position information from the GPS devices of the persons H1, H2, H3, and so on. The second position acquisition unit 11 outputs the acquired position information of each of the persons H1, H2, H3, . . .

The facial expression feature amount extraction unit 12 is a processing unit that extracts the facial expression feature amount of each of the persons H1, H2, H3, . Specifically, the facial expression feature quantity extraction unit 12 uses the features of the facial regions (for example, around the nose) of each of the persons H1, H2, H3, . . . Extract. The facial expression feature amount extraction unit 12 outputs the acquired facial expression feature amounts of each of the persons H1, H2, H3, . . .

The speech feature quantity extraction unit 13 extracts the speech feature quantity of each of the persons H1, H2, H3, . Department.

Specifically, the sound feature amount extraction unit 13 identifies the position of the sound source of the sound obtained by the plurality of microphones 3 based on the time difference between the sounds obtained from each microphone 3 . Next, the speech feature extraction unit 13 identifies which of the persons H1, H2, H3, . Next, the speech feature extraction unit 13 extracts speech features from the specified sound sources (people H1, H2, H3, . . . ) using a known speech recognition technology. Next, the audio feature amount extraction unit 13 outputs the extracted audio feature amount to the perceptual state determination unit 14 .

Note that the speech feature quantity acquired by the speech feature quantity extraction unit 13 includes a linguistic feature quantity and a non-linguistic feature quantity. For example, the linguistic feature amount indicates the language uttered by persons H1, H2, H3, . The non-linguistic features are sounds generated by the actions of the persons H1, H2, H3, .

The perceptual state determination unit 14 is a processing unit that determines the emotion (the perceptual state of the diffusion target) for each of the identified persons H1, H2, H3, . . That is, the perceptual state determination unit 14 is an example of an emotion determination unit that determines the emotion of each person H1, H2, H3, . be.

Specifically, the perceptual state determination unit 14 uses a known emotion determination technique disclosed in Japanese Unexamined Patent Application Publication No. 2009-042671 or the like to determine whether or not each of the identified persons H1, H2, H3, . . . is determined, for example, as a numerical value ranging from unpleasant: -3 to pleasant: +3. The perceptual state determination unit 14 outputs determination results of emotions of each of the identified persons H1, H2, H3, . . .

Emotion determination in the perceptual state determination unit 14 may be performed using a learning model that has been learned to determine emotion from facial expression feature amounts and voice feature amounts by supervised machine learning. Emotion determination in the perceptual state determination unit 14 is performed based on at least one feature amount of video and audio (one of facial expression feature amount, language feature amount, and non-language feature amount) or a combination of a plurality of feature amounts. may

For each identified person H1, H2, H3, . Calculate the distance of That is, the field state determination unit 15 is an example of a position calculation unit.

Further, the field state determination unit 15 determines the emotion determined by the perception state determination unit 14 for each of the identified persons H1, H2, H3, . . . is a processing unit that determines the state of the field with respect to the diffuse object based on . That is, the field state determination unit 15 is an example of a state determination unit.

Specifically, the field state determination unit 15 selects one of a plurality of categories indicating the state of the field related to the diffusion target based on the emotion and distance of each of the identified persons H1, H2, H3, . . . Determine if it can be classified into categories. For example, the classification is as follows: "strong scent" with a strong diffusion target, "weak scent" with a weak diffusion target, "poor scent" with a poor diffusion target type, and "appropriate scent" with an appropriate diffusion target. There is. Next, the field state determination unit 15 outputs information indicating the determined field state (field state classification) to the diffusion target presentation control unit 16 .

The diffusion target presentation control unit 16 is a processing unit that controls the emission of the diffusion target according to the field state (field state classification) regarding the diffusion target determined by the field state determination unit 15 . That is, the diffusion target presentation control unit 16 is an example of a control unit.

Specifically, when the field state determined by the field state determination section 15 is “strongly fragrant,” the diffusion target presentation control section 16 reduces the intensity at which the diffusion target presentation section 2 emits the diffusion target. Further, when the field state determined by the field state determination section 15 is "weak scent", the diffusion target presentation control section 16 increases the intensity of emitting the diffusion target from the diffusion target presentation section 2 . Further, the diffusion target presentation control unit 16 causes the diffusion target presentation unit 2 to change the type of the diffusion target when the field state determined by the field state determination unit 15 is “bad”. For example, the diffusion target presentation control unit 16 switches the fragrance that the diffusion target presentation unit 2 is currently emitting to a different aromatic substance. Further, when the field state determined by the field state determination section 15 is "scent appropriate", the diffusion target presentation control section 16 causes the diffusion target presentation section 2 to maintain the intensity of releasing the diffusion target.

FIG. 2 is a flowchart showing an operation example of 01 according to the first embodiment.

As shown in FIG. 2, prior to processing, the second position acquisition unit 11 acquires person position information 30 for each person H1, H2, H3, . Also, from the image 20 of the camera 4, the facial expression feature quantity extraction unit 12 acquires the facial expression feature quantity 31 of each of the persons H1, H2, H3, . Also, from the voice 21 of the microphone 3, the voice feature quantity extraction unit 13 acquires the linguistic feature quantity 32 and the non-linguistic feature quantity 33 uttered by each of the persons H1, H2, H3, . . . Also, the first position acquisition unit 10 acquires the position information 34 of the diffusion target presentation unit 2 .

When the process is started, the perceptual state determination unit 14 performs the perceptual state determination process for each of the persons H1, H2, H3, . (S1).

FIG. 3 is a flowchart illustrating an example of the perceptual state determination process. As shown in FIG. 3, the perceptual state determination unit 14 inputs the acquired facial expression feature quantity 31, verbal feature quantity 32, and non-verbal feature quantity 33 for each of the persons H1, H2, H3, . . . into the perceptual state determination engine. This perceptual state determination engine uses a known emotion determination technique disclosed in Japanese Unexamined Patent Application Publication No. 2009-042671 or a learning model learned by supervised machine learning. The perceptual state determination engine determines the emotion (perceptual state) of each person based on the input of the facial expression feature amount 31, the verbal feature amount 32, and the non-verbal feature amount 33, for example, from unpleasant: -3 to pleasant: +3. Output as a numerical value (comfort level).

Returning to FIG. 2, following S1, the field state determination unit 15 determines the comfort level determined by the perception state determination unit 14 for each of the persons H1, H2, H3, . Field state determination processing is performed based on the distance to the release position (S2).

FIG. 4 is a flow chart showing an example of the field state determination processing. As shown in FIG. 4, when the process is started, the field state determination unit 15 determines the position information (Pn (x, y, z)) of each person H1, H2, H3, and the degree of comfort (Vn). And the position information (S(x, y, z)) of the diffusion target presentation control unit 16 is acquired (S20).

Next, the field state determination unit 15 determines the number of unpleasantness determinations (CntNN) that are determined to be unpleasant for people near the emission position of the diffusion target, The number of discomfort determinations (CntNF) and the comfort level (Vf) of the place are initialized (set to 0) (S21).

Next, the field state determination unit 15 sets the number of persons H1, H2, and H3 identified from the image 20 of the camera 4 (the number of participants) to N, and performs loop processing (n=0, n<N) for each person. (S22-S29).

Specifically, the place state determination unit 15 adds the value of the comfort level (Vn) of each person to the comfort level (Vf) of the place, and calculates the sum of the comfort levels (the number of comfortable people may be used). (S23).

Next, the field state determination unit 15 sets the distance (|Ln|) between each person and the diffusion object presentation unit 2 as |Ln|=|Pn(x, y, z)−S(x, y, z)| (S24).

Next, the field state determination unit 15 determines whether or not each person's degree of comfort (Vn) is a value indicating discomfort (Vn<0) (S25). If the value does not indicate discomfort (S25: No), the field state determination unit 15 advances the process to S29, increments the value of n, and continues the loop process.

If the value indicates discomfort (S25: Yes), the field state determination unit 15 determines whether or not the distance |Ln| to the diffusion object presentation unit 2 is less than a predetermined threshold (ThL) (S26) . Note that the threshold (ThL) is a preset value for determining whether the distance |Ln| to the diffusion target presentation unit 2 is close or far. For example, a value such as 1/4 of the maximum room length of a conference room is set.

When the distance |Ln| is not less than the predetermined threshold value (ThL) (S26: No), the field state determination unit 15 increments the number of unpleasantness determinations (CntNF) of people at a distance determined to be unpleasant (S27). . When the distance |Ln| is less than the predetermined threshold value (ThL) (S26: Yes), the field state determination unit 15 increments the discomfort determination number (CntNN) determined to be unpleasant by a person at a short distance. (S28). Next, the field state determination unit 15 increments the value of n and continues the loop processing (S29).

Following the loop processing of S22 to S29, the field state determination unit 15 determines whether or not the discomfort determination number (CntNN) of people in the short distance determined to be unpleasant exceeds a predetermined threshold (ThNN) (S30). ). Note that the threshold value (ThNN) is a value set in advance to determine the number of people who are uncomfortable at a short distance from the diffusion target presentation unit 2, such as 1/4 of the number of participants (N). value is set.

When the discomfort determination number (CntNN) determined to be unpleasant among people in the short distance does not exceed the predetermined threshold (ThNN) (S30: No), the field state determination unit 15 determines that the sum of the comfort levels (Vf) is a predetermined value. (S31). Note that the threshold value (ThV) is a preset value for determining the comfort level of a place based on the total comfort level or the number of comfortable people. For example, when determining the comfort level of a place from the sum of the comfort levels, a value obtained by +3 (maximum comfort level)*number of participants (N)*3/4 is set as the threshold value (ThV). Further, when determining the comfort level of the place from the number of comfortable people, a value obtained by multiplying the number of participants (N)×3/4 is set as the threshold value (ThV).

When the discomfort determination number (CntNN) determined to be unpleasant by a person at a short distance exceeds a predetermined threshold value (ThNN) (S30: Yes), the field state determination unit 15 determines that a person at a distance is unpleasant. It is determined whether or not the discomfort determination number (CntNF) exceeds a predetermined threshold (ThNF) (S32). Note that the threshold value (ThNF) is a value set in advance to determine the number of people who are uncomfortable at a distance from the diffusion target presentation unit 2, and is, for example, 1/4 of the number of participants (N). value is set.

When the number of unpleasant judgments (CntNN) judged to be unpleasant among people in a short distance does not exceed a predetermined threshold (ThNN) and the sum of comfort levels (Vf) exceeds a predetermined threshold (ThV) (S31: Yes), The field state determination unit 15 determines that the field state regarding the diffusion target is "appropriate scent", which means that the diffusion target is appropriate (S33).

In addition, when the number of discomfort judgments (CntNN) judged to be unpleasant among people at a short distance does not exceed a predetermined threshold value (ThNN) and the sum of comfort levels (Vf) does not exceed a predetermined threshold value (ThV) (S31: No), the field state determination unit 15 determines that the field state of the diffusion target is "weak scent", which means that the diffusion target has a weak intensity (S34).

In addition, the number of discomfort determinations (CntNN) determined as unpleasant for people in a short distance exceeds a predetermined threshold (ThNN), and the number of discomfort determinations (CntNF) for people in a long distance is determined to be unpleasant, and the number of discomfort determinations (CntNF) exceeds a predetermined threshold (ThNF). ) (S32: Yes), the field state determination unit 15 determines that the type of the diffusion target is "bad" for the state of the field regarding the diffusion target (S35).

In addition, the number of discomfort determinations (CntNN) determined as unpleasant for people in a short distance exceeds a predetermined threshold (ThNN), and the number of discomfort determinations (CntNF) for people in a long distance is determined to be unpleasant, and the number of discomfort determinations (CntNF) exceeds a predetermined threshold (ThNF). ) (S32: No), the field state determination unit 15 determines that the field state regarding the diffusion target is “strong fragrance” in which the strength of the diffusion target is high (S36).

Next, the field state determination unit 15 outputs information indicating the determined field state (field state classification) to the diffusion target presentation control unit 16 (S37).

Returning to FIG. 2, subsequent to S2, the diffusion target presentation control unit 16 performs diffusion target presentation control processing based on the information indicating the state of the field determined by the field state determination unit 15 (classification of the state of the field). (Scent presentation control process) is performed (S3).

FIG. 5 is a flow chart showing an example of the scent presentation control process. As shown in FIG. 5, when the process is started, the diffusion target presentation control unit 16 determines the classification result of the field state in the field state determination unit 15 (S40).

If the classification result is "appropriate fragrance", the diffusion object presentation control unit 16 leaves the fragrance output (intensity of emitting the diffusion object) in the diffusion object presentation unit 2 unchanged (S41), and ends the process.

When the classification result is "weak fragrance", the diffusion object presentation control unit 16 increases the fragrance output (the intensity of emitting the diffusion object) in the diffusion object presentation unit 2 (S42), and ends the process.

When the classification result is "strong fragrance", the diffusion object presentation control unit 16 reduces the fragrance output (intensity of releasing the diffusion object) in the diffusion object presentation unit 2 (S43), and ends the process.

When the classification result is "bad fragrance", the diffusion target presentation control unit 16 changes the type of fragrance in the diffusion target presentation unit 2 (S44), and ends the process.

(Second embodiment)
FIG. 6 is a block diagram illustrating a functional configuration example of a diffusion target control device according to a second embodiment; As shown in FIG. 1, the diffusion object control device 1a includes an airflow sensor 5 for detecting the airflow from which the diffusion object presenting unit 2 emits the diffusion object, and an airflow determination unit for determining the direction and strength of the detected airflow. 17 is different from the diffusion target control device 1 .

FIG. 7 is a flow chart showing an operation example of the diffusion target control device 1a according to the second embodiment. As shown in FIG. 7, the airflow sensor 5 of the diffusion object control device 1a detects the airflow at which the diffusion object presenting unit 2 emits the diffusion object using an anemometer, anemoscope, or the like (S4). Next, the airflow determination unit 17 of the diffusion target control device 1a determines the direction and strength of the airflow based on the detection result of the airflow sensor 5 (S5). Next, the field state determination unit 15 performs a field state determination process based on the direction and strength of the airflow determined by the airflow determination unit 17 (S2a).

FIG. 8 is a flowchart showing an example of the field state determination process, and more specifically, a diagram for explaining the details of the field state determination process (S2a). As shown in FIG. 8, in the field state determination process (S2a), the processes of S20a, S24a, S25a, and S26a are different from the field state determination process (S2) in the first embodiment.

Specifically, in S20a, the field state determination unit 15 determines the location information (Pn (x, y, z)) of each of the persons H1, H2, H3, . In addition to 16 positional information (S(x,y,z)), an airflow vector (A(x,y,z)) indicating the direction and strength of the airflow is obtained.

In addition, in S24a, the field state determination unit 15 calculates the vector (Ln(x, y, z)) between each person and the diffused object presentation unit 2 as Ln(x, y, z)=Pn(x, y, z)-S(x, y, z).

Further, in S25a, the field state determination unit 15 obtains a distance feature amount (Ln') using the vector inner product and the distance as Ln'=|Ln|×(A, Ln).

FIG. 9 is an explanatory diagram for explaining the distance feature amount. As shown in FIG. 9, the distance feature amount is obtained by multiplying the inner product of the airflow vector (A (x, y, z)) and the position vectors (L1, L2, . . . ) of the persons H1, H2, . is. Note that the inner product (A, Ln) of the airflow vector and the position vector is (A, Ln)=|A|×|L|×cos θ.

In the illustrated example, the distance feature amount indicates a positive value for the person H1. This means that the diffusion object reaches far, and is synonymous with near (approaching the diffusion object presentation unit 2) from the viewpoint of concentration. Also, for the person H2, the distance feature amount indicates a negative value. This means that the diffused object does not reach far, and is synonymous with far (far from the diffused object presenting unit 2) in terms of density.

In S26a, the field state determination unit 15 determines whether or not the value of the distance to the diffusion object presentation unit 2 converted into the distance feature amount Ln is less than a predetermined threshold (ThL).

In this manner, the field state determination unit 15 may determine the field state by considering the degree of influence of the diffusion target by the airflow.

As described above, the diffusion object control device 1 includes the second position acquisition unit 11 , the perception state determination unit 14 , the field state determination unit 15 , and the diffusion object presentation control unit 16 . The second position acquisition unit 11 detects the position of each user (people H1, H2, H3, . . . ) present in the field emitted by the diffusion target. The perceptual state determination unit 14 determines the user's emotion based on at least one feature amount of video and audio of each user. The field state determination unit 15 calculates, for each user, the distance to the diffusion target emission position by the diffusion target presentation unit 2 based on the detected position of the user. Further, the field state determination unit 15 determines the state of the field based on the emotion determined for each user and the calculated distance. The diffusion object presentation control unit 16 adjusts the intensity with which the diffusion object presentation unit 2 emits the diffusion object according to the determined state of the field. In this way, the diffusion object control device 1 adjusts the intensity of emitting the diffusion object according to the state of the field based on the distance to the emission position of the emission object and the emotion of a plurality of users. Diffusion objects can be emitted without making people uncomfortable, and it is possible to support the provision of a place where many people can spend comfortably.

Also, the diffusion target is at least one of an aromatic substance, sound, and air after air conditioning. For this reason, the diffusion target control device 1 can adjust the intensity of emitting at least one of the aromatic substance, the sound, and the air after air conditioning, and support the provision of a place where many people can spend comfortably.

The diffusion object control device 1 further has an airflow sensor 5 for detecting an airflow related to the emission of the diffusion object, and the field state determination unit 15 determines the state of the field based on the direction and strength of the detected airflow. do. Therefore, the diffusion object control device 1 can determine the state of the field in consideration of the degree of influence of the airflow on the diffusion object, and can obtain the state of the field with higher accuracy.

In addition, the diffusion target presentation control unit 16 adjusts the type of diffusion target according to the determined state of the field. As a result, the diffusion target control device 1 can adjust the types of diffusion targets and support the provision of a place where a large number of people can spend time comfortably.

In addition, the field state determination unit 15 determines the number of first users whose calculated distance is shorter than the predetermined distance and the number of second users whose calculated distance is longer than the predetermined distance for the users whose emotions are determined to be unpleasant. Ask for Next, the field state determination unit 15 determines the state of the field according to the obtained numbers of the first and second users. As a result, the diffusion target control device 1 can determine the state of the field according to the number of users who feel uncomfortable near the emission position of the diffusion target and the number of users who feel uncomfortable far from the emission position of the diffusion target. You can adjust the intensity of emitting the diffuse object so that the person can spend comfortably.

Further, when the number of first users is larger than a predetermined number and the number of second users is smaller than a predetermined number, the field state determination unit 15 determines that the intensity of the diffusion target is high (for example, S36). The diffusion object presentation control unit 16 reduces the intensity of emitting the diffusion object when the intensity of the diffusion object is high (for example, S43). For example, many users who are close to the diffusion target are uncomfortable, and users who are far from the diffusion target are not so uncomfortable. is strong, it can be estimated that the user near the release position feels uncomfortable. Therefore, in such a field situation, the diffusion object control device 1 can reduce the intensity of emitting the diffusion object, thereby improving the comfort level of the user near the emission object.

Further, when the number of first users is greater than a predetermined number and the number of second users is greater than a predetermined number, the field state determination unit 15 determines that the diffusion target is in a bad state (for example, S35). . If the diffusion target is in a bad state, the diffusion target presentation control unit 16 changes the type of the diffusion target (for example, S44). For example, many users who are close to the diffusion target and users who are far from the diffusion target are uncomfortable, because the type of diffusion target is not suitable for many users. , it can be estimated that both users feel uncomfortable. Therefore, the diffusion target control device 1 can improve the comfort level of both users by changing the type of the diffusion target in such a field situation.

Further, when the number of first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is less than a predetermined number, the field state determination unit 15 determines that the intensity of the diffusion target is weak. (eg S34). The diffused object presentation control unit 16 increases the intensity of emitting the diffused object when the intensity of the diffused object is low (for example, S42). For example, many users who are close to the diffusion target are not uncomfortable, and the total number of comfortable users is small. can be estimated. Therefore, the diffusion object control device 1 can improve the comfort level of many users by increasing the intensity of emitting the diffusion object in such a field situation.

Further, when the number of first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is greater than a predetermined number, the field state determination unit 15 determines that the intensity of the diffusion target is in an appropriate state. Determine (for example, S33). When the intensity of the diffusion object is in an appropriate state, the diffusion object presentation control unit 16 maintains the intensity for releasing the diffusion object (for example, S40). Many of the users who are close to the diffusion target are not uncomfortable, and the total number of comfortable users is large. Therefore, in such a field situation, the diffusion object control device 1 maintains the intensity of emitting the diffusion object, thereby providing a place where many users can continue to be comfortable.

Also, each constituent element of each part illustrated does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each part is not limited to the one shown in the figure, and all or part of it can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. can be configured as For example, the first position acquisition unit 10 and the second position acquisition unit 11, the facial expression feature amount extraction unit 12 and the voice feature amount extraction unit 13 may be integrated. Moreover, the illustrated processes are not limited to the order described above, and may be performed simultaneously or in a different order as long as the contents of the processes are not inconsistent.

Furthermore, the various processing functions performed by each device may be executed in whole or in part on a CPU (or a microcomputer such as an MPU or MCU (Micro Controller Unit)). Also, various processing functions may be executed in whole or in part on a program analyzed and executed by a CPU (or a microcomputer such as an MPU or MCU) or on hardware based on wired logic. It goes without saying that it is good.

By the way, the various processes described in each of the above embodiments can be realized by executing a prepared program on a computer. Therefore, an example of a computer that executes a program having functions similar to those of the above-described embodiments will be described below. FIG. 10 is a block diagram showing an example of a computer that executes programs.

As shown in FIG. 10, the computer 100 has a CPU 101 that executes various arithmetic processes, an input device 102 that receives data input, and a monitor 103 . The computer 100 also includes a medium reading device 104 for reading a program or the like from a storage medium, an interface device 105 for connecting with various devices, and a communication device 106 for connecting with other information processing devices or the like by wire or wirelessly. have The computer 100 also has a RAM 107 that temporarily stores various information, and a hard disk device 108 . Each device 101 to 108 is also connected to a bus 109 .

The hard disk device 108 includes the first position acquisition unit 10, the second position acquisition unit 11, the facial expression feature amount extraction unit 12, the voice feature amount extraction unit 13, the perception state determination unit 14, and the field state shown in FIG. A program 108A having the same functions as those of the determination unit 15 and diffusion target presentation control unit 16 is stored. The hard disk device 108 includes a first position acquisition unit 10, a second position acquisition unit 11, a facial expression feature amount extraction unit 12, a voice feature amount extraction unit 13, a perceptual state determination unit 14, and a field state determination unit 15. and various data for realizing the diffusion target presentation control unit 16 are stored. The input device 102 receives input of various information such as operation information from the user of the computer 100, for example. The monitor 103 displays various screens such as a display screen to the user of the computer 100, for example. The interface device 105 is connected with, for example, a printing device. The communication device 106 is connected to a network (not shown) and exchanges various information with other information processing devices.

The CPU 101 reads a program 108A stored in the hard disk device 108, develops it in the RAM 107, and executes it to perform various processes. This program also includes the first position acquisition unit 10, the second position acquisition unit 11, the facial expression feature amount extraction unit 12, the voice feature amount extraction unit 13, the perception state determination unit 14, and the computer 100 shown in FIG. It can function as the field state determination unit 15 and the diffusion target presentation control unit 16 .

Note that the program 108A described above does not have to be stored in the hard disk device 108 . For example, the computer 100 may read and execute the program 108A stored in a storage medium readable by the computer 100 . Examples of storage media readable by the computer 100 include portable recording media such as CD-ROMs, DVDs (Digital Versatile Discs), and USB (Universal Serial Bus) memories, semiconductor memories such as flash memories, and hard disk drives. . Alternatively, the program 108A may be stored in a device connected to a public line, the Internet, a LAN, etc., and the computer 100 may read and execute the program 108A from these devices.

Further, the following additional remarks are disclosed with respect to the above embodiment.

(Appendix 1) Detecting the position of each user existing in the field where the diffusion target is emitted,
determining the user's emotion based on at least one feature quantity of video and audio of each of the users;
calculating, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
determining the state of the field based on the emotion determined for each user and the calculated distance;
Adjusting the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion object control method characterized in that the processing is executed by a computer.

(Appendix 2) The diffusion target is at least one of an aromatic substance, sound, and air after air conditioning.
The diffusion target control method according to Supplementary Note 1, characterized by:

(Appendix 3) The computer further performs a process of detecting airflow related to the release of the diffusion target,
The process of determining the state determines the state of the field based on the direction and strength of the detected airflow.
The diffusion object control method according to appendix 1 or 2, characterized by:

(Appendix 4) The adjusting process adjusts the type of the diffusion target according to the determined state of the field.
The diffusion object control method according to any one of appendices 1 to 3, characterized by:

(Supplementary note 5) The processing for determining the state includes, for users whose emotions are determined to be unpleasant, the number of first users whose calculated distance is shorter than a predetermined distance, and the number of users whose calculated distance is longer than a predetermined distance. The number of users is obtained, and the state of the field is determined according to the obtained numbers of the first and second users;
The diffusion object control method according to any one of appendices 1 to 4, characterized by:

(Appendix 6) In the processing for determining the state, when the number of the first users is greater than a predetermined number and the number of the second users is less than a predetermined number, the intensity of the diffusion target is high. determined to be
The adjusting process reduces the intensity of emitting the diffusion object when the intensity of the diffusion object is high.
The diffusion target control method according to appendix 5, characterized by:

(Supplementary Note 7) In the process of determining the state, when the number of the first users is greater than a predetermined number and the number of the second users is greater than a predetermined number, it is determined that the diffusion target is in a bad state. death,
The adjusting process changes the type of the diffusion target when the diffusion target is in a bad state.
The diffusion target control method according to appendix 5, characterized by:

(Supplementary Note 8) In the process of determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is less than a predetermined number, the intensity of the diffusion target is low. determined to be
The adjusting process increases the intensity of emitting the diffusion target when the intensity of the diffusion target is weak.
The diffusion target control method according to appendix 5, characterized by:

(Supplementary Note 9) In the processing for determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is greater than a predetermined number, the intensity of the diffusion target is appropriate. determined to be in a state of
The adjusting process maintains the intensity of emitting the diffusion object when the intensity of the diffusion object is in an appropriate state.
The diffusion target control method according to appendix 5, characterized by:

(Appendix 10) Detecting the position of each user existing in the field where the diffusion target is emitted,
determining the user's emotion based on at least one feature quantity of video and audio of each of the users;
calculating, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
determining the state of the field based on the emotion determined for each user and the calculated distance;
Adjusting the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion target control program characterized by causing a computer to execute processing.

(Appendix 11) The diffusion target is at least one of an aromatic substance, sound, and air after air conditioning.
The diffusion target control program according to appendix 10, characterized by:

(Appendix 12) Further causing the computer to perform a process of detecting airflow related to the release of the diffusion target,
The process of determining the state determines the state of the field based on the direction and strength of the detected airflow.
The diffusion target control program according to appendix 10 or 11, characterized by:

(Appendix 13) The adjusting process adjusts the type of the diffusion target according to the determined state of the field.
13. The diffusion target control program according to any one of appendices 10 to 12, characterized by:

(Supplementary note 14) The processing for determining the state includes, for users whose emotions are determined to be unpleasant, the number of first users whose calculated distance is shorter than a predetermined distance, and the number of users whose calculated distance is longer than a predetermined distance. The number of users is obtained, and the state of the field is determined according to the obtained numbers of the first and second users;
14. The diffusion target control program according to any one of appendices 10 to 13, characterized by:

(Supplementary Note 15) In the processing for determining the state, when the number of the first users is greater than a predetermined number and the number of the second users is less than a predetermined number, the intensity of the diffusion target is high. determined to be
The adjusting process reduces the intensity of emitting the diffusion object when the intensity of the diffusion object is high.
The diffusion target control program according to appendix 14, characterized by:

(Supplementary Note 16) The processing for determining the state determines that the diffusion target is in a bad state when the number of the first users is greater than a predetermined number and the number of the second users is greater than a predetermined number. death,
The adjusting process changes the type of the diffusion target when the diffusion target is in a bad state.
The diffusion target control program according to appendix 14, characterized by:

(Supplementary Note 17) In the processing for determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is less than a predetermined number, the intensity of the diffusion target is low. determined to be
The adjusting process increases the intensity of emitting the diffusion target when the intensity of the diffusion target is weak.
The diffusion target control program according to appendix 14, characterized by:

(Supplementary Note 18) In the process of determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is greater than a predetermined number, the intensity of the diffusion target is appropriate. determined to be in a state of
The adjusting process maintains the intensity of emitting the diffusion object when the intensity of the diffusion object is in an appropriate state.
The diffusion target control program according to appendix 14, characterized by:

(Appendix 19) A detection unit that detects the position of each user existing in the field where the diffusion target is emitted;
an emotion determination unit that determines the user's emotion based on at least one feature quantity of video and audio of each user;
a position calculation unit that calculates, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
a state determination unit that determines the state of the field based on the emotion determined for each user and the calculated distance;
a control unit that adjusts the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion target control device comprising:

(Appendix 20) The diffusion target is at least one of an aromatic substance, sound, and air after air conditioning.
19. The diffusion target control device according to Supplementary Note 19, characterized by:

(Appendix 21) further comprising an airflow detection unit that detects an airflow related to the release of the diffusion target,
The state determination unit determines the state of the field based on the direction and strength of the detected airflow;
21. The diffusion target control device according to appendix 19 or 20, characterized by:

(Appendix 22) The control unit adjusts the type of the diffusion target according to the determined state of the field.
22. The diffusion target control device according to any one of appendices 19 to 21, characterized by:

(Supplementary note 23) The state determination unit determines the number of first users for whom the calculated distance is shorter than a predetermined distance and the number of second users for whom the calculated distance is longer than the predetermined distance for users whose emotions are determined to be unpleasant. and determining the state of the field according to the number of first and second users obtained;
23. The diffusion target control device according to any one of appendices 19 to 22, characterized by:

(Supplementary Note 24) The state determination unit determines that the intensity of the diffusion target is high when the number of the first users is greater than a predetermined number and the number of the second users is less than a predetermined number. death,
The control unit reduces the intensity of emitting the diffusion target when the intensity of the diffusion target is high.
The diffusion target control device according to appendix 23, characterized by:

(Supplementary Note 25) The state determination unit determines that the diffusion target is in a bad state when the number of the first users is greater than a predetermined number and the number of the second users is greater than a predetermined number,
The control unit changes the type of the diffusion target when the diffusion target is in a bad state.
The diffusion target control device according to appendix 23, characterized by:

(Appendix 26) When the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is less than a predetermined number, the state determination unit determines that the intensity of the diffusion target is weak. determined to be
The control unit increases the intensity of emitting the diffusion target when the intensity of the diffusion target is weak.
The diffusion target control device according to appendix 23, characterized by:

(Supplementary Note 27) When the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is greater than a predetermined number, the state determination unit determine that there is
The control unit maintains the intensity of emitting the diffusion target when the intensity of the diffusion target is in an appropriate state.
The diffusion target control device according to appendix 23, characterized by:

DESCRIPTION OF SYMBOLS 1, 1a...Diffusion object control apparatus 2...Diffusion object presentation part 3...Microphone 4...Camera 5...Airflow sensor 10...First position acquisition part 11...Second position acquisition part 12...Facial feature quantity extraction part 13...Voice Feature amount extraction unit 14 Perceptual state determination unit 15 Field state determination unit 16 Diffusion target presentation control unit 17 Airflow determination unit 20 Image 21 Audio 30 Human position information 31 Expression feature amount 32 Language feature Quantity 33 Non-linguistic feature quantity 34 Positional information 100 Computer 101 CPU
102... Input device 103... Monitor 104... Medium reading device 105... Interface device 106... Communication device 107... RAM
108 Hard disk device 108A Program 109 Bus H1 to H3 People

Claims (11)

Detecting the position of each user existing in the field where the diffuse object is emitted,
determining the user's emotion based on at least one feature quantity of video and audio of each of the users;
calculating, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
determining the state of the field based on the emotion determined for each user and the calculated distance;
Adjusting the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion object control method characterized in that the processing is executed by a computer. The diffusion target is at least one of an aromatic substance, sound, and air after air conditioning.
The diffusion object control method according to claim 1, characterized in that: further computer-executed processing to detect air currents associated with diffuse target emissions;
The process of determining the state determines the state of the field based on the direction and strength of the detected airflow.
3. The diffusion object control method according to claim 1 or 2, characterized in that: The adjusting process adjusts the type of the diffusion target according to the determined state of the field.
The diffusion object control method according to any one of claims 1 to 3, characterized in that: The processing for determining the state includes determining the number of first users for whom the calculated distance is shorter than a predetermined distance and the number of second users for which the calculated distance is longer than the predetermined distance for users whose emotions are determined to be unpleasant. and determine the state of the field according to the number of the first and second users obtained,
The diffusion object control method according to any one of claims 1 to 4, characterized in that: In the processing for determining the state, when the number of the first users is greater than a predetermined number and the number of the second users is less than a predetermined number, it is determined that the intensity of the diffusion target is strong,
The adjusting process reduces the intensity of emitting the diffusion object when the intensity of the diffusion object is high.
The diffusion object control method according to claim 5, characterized in that: The processing for determining the state includes determining that the diffusion target is in a bad state when the number of the first users is greater than a predetermined number and the number of the second users is greater than a predetermined number,
The adjusting process changes the type of the diffusion target when the diffusion target is in a bad state.
The diffusion object control method according to claim 5, characterized in that: In the processing for determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is less than a predetermined number, it is determined that the intensity of the diffusion target is weak. death,
The adjusting process increases the intensity of emitting the diffusion target when the intensity of the diffusion target is weak.
The diffusion object control method according to claim 5, characterized in that: In the processing for determining the state, when the number of the first users is less than a predetermined number and the total number of users whose emotions are determined to be pleasant is greater than a predetermined number, it is determined that the intensity of the diffusion target is in an appropriate state. judge,
The adjusting process maintains the intensity of emitting the diffusion object when the intensity of the diffusion object is in an appropriate state.
The diffusion object control method according to claim 5, characterized in that: Detecting the position of each user existing in the field where the diffuse object is emitted,
determining the user's emotion based on at least one feature quantity of video and audio of each of the users;
calculating, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
determining the state of the field based on the emotion determined for each user and the calculated distance;
Adjusting the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion target control program characterized by causing a computer to execute processing. a detection unit that detects the position of each user existing in the field where the diffusion target is emitted;
an emotion determination unit that determines the user's emotion based on at least one feature quantity of video and audio of each user;
a position calculation unit that calculates, for each user, a distance to the emission position of the diffusion target based on the detected position of the user;
a state determination unit that determines the state of the field based on the emotion determined for each user and the calculated distance;
a control unit that adjusts the intensity of emitting the diffusion target according to the determined state of the field;
A diffusion target control device comprising:

Images