Human-computer interaction method based on image recognition and air blowing equipment

Abstract

The invention provides a man-machine interaction method based on image recognition and air blowing equipment, and the method comprises the steps: determining a current working mode of the air blowing equipment under the control of a starting instruction for starting the air blowing equipment; if the current working mode of the air blowing equipment is an intelligent recognition mode, image information is obtained, and the type of a target acted by the air blowing equipment is confirmed based on the image information; and adjusting the blowing mode of the blowing equipment according to the target type. The target type can be recognized, the blowing mode can be debugged according to the target type, and convenience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hair dryer equipment, and in particular to a human-computer interaction method based on image recognition and a hair dryer equipment. Background Art

[0002] With the development of hair dryer technology, hair dryers are becoming more and more intelligent. Most smart hair dryers can adjust the wind speed and temperature according to the distance between the hair dryer's air outlet and the hair, or automatically adjust the wind speed and temperature according to the usage scenario. However, most users currently use hair dryers for other purposes besides drying their hair, such as drying clothes or drying pet hair. However, there is currently no hair dryer that can identify the type of hair dryer it is used for, resulting in low convenience. Summary of the invention

[0003] The present invention provides a human-computer interaction method and a hair dryer based on image recognition, aiming to solve the problem of low convenience caused by the inability of the current hair dryer to identify the target type it acts on.

[0004] In a first aspect, the present invention provides a human-computer interaction method based on image recognition, the method comprising:

[0005] Controlled by a start-up instruction for starting the hair-drying device, confirming a current working mode of the hair-drying device;

[0006] If the current working mode of the blowing device is the intelligent recognition mode, image information is acquired, and the type of target acted by the blowing device is confirmed based on the image information;

[0007] The blowing mode of the blowing device is adjusted according to the target type.

[0008] In a second aspect, the present invention provides a hair dryer, wherein the hair dryer includes any one of the above-mentioned human-computer interaction methods based on image recognition.

[0009] The present invention discloses a human-computer interaction method and a hair dryer based on image recognition, wherein the human-computer interaction method includes being controlled by a start-up instruction for starting the hair dryer, confirming the current working mode of the hair dryer; if the current working mode of the hair dryer is an intelligent recognition mode, acquiring image information, and confirming the target type acted upon by the hair dryer based on the image information; and adjusting the hair dryer mode according to the target type. The embodiment of the present invention can acquire image information, identify the target type acted upon according to the image information, and then adjust the hair dryer mode based on the target type, thereby adapting different wind speeds and wind temperatures according to different types, thereby improving convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0011] Figure 1 is a flow chart of a human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0012] Figure 2 is a first sub-flow chart of a human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0013] Figure 3 is a second sub-flow chart of the human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0014] Figure 4 is a third sub-flow chart of a human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0015] Figure 5 is a fourth sub-flow chart of a human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0016] Figure 6 is a fifth sub-flow chart of a human-computer interaction method based on image recognition provided by an embodiment of the present invention;

[0017] Figure 7 This is the sixth sub-flowchart of the human-computer interaction method based on image recognition provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, operations, elements, components and / or groups thereof.

[0020] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, the singular forms of "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0021] In addition, the directional terms mentioned in the present invention, such as "upper", "lower", "front", "back", "left", "right", "inner", "outer", "side", etc., are only for reference to the directions of the attached drawings and the use status of the product. Therefore, the directional terms used are used to illustrate and understand the present invention, but not to limit the present invention. In addition, in the drawings, structures with similar or identical structures are represented by the same reference numerals.

[0022] See also Figure 1 The present invention provides a human-computer interaction method based on image recognition, which can be applied to a hair dryer to adjust a hair dryer mode according to a target type. The human-computer interaction method based on image recognition includes S110-S130.

[0023] S110, under the control of a start-up instruction for starting the hair-drying device, confirming the current working mode of the hair-drying device.

[0024] In an embodiment of the present invention, the working mode may include three working modes. The first working mode is a traditional mode, the second working mode is an intelligent working mode, and the third working mode is an emotion recognition mode. The user can manually switch the working mode through a button switch set on the hair dryer.

[0025] When the hair dryer is started for the first time, it enters the traditional mode by default. In the traditional mode, the hair dryer has multiple preset gears, and different gears correspond to different wind speeds and wind temperatures. For example, the first gear can be low speed and low temperature, the second gear can be medium speed and medium temperature, and the third gear can be high speed and high temperature. The specific setting method of the gear is not limited to the above three cases and can be set according to actual conditions. After starting the hair dryer for the first time, the user can adjust the working mode through the buttons on the hair dryer. For example, there are a first button, a second button and a third button. The first button corresponds to the traditional mode, the second button corresponds to the smart recognition mode, and the third button corresponds to the emotion recognition mode. When the user presses the second button, the hair dryer switches to the smart recognition mode and remains in this mode. When the user starts it next time, the hair dryer can still be in the smart recognition mode. In addition, it can also be set so that when the user turns off the hair dryer, the hair dryer automatically returns to the traditional mode.

[0026] S120: If the current working mode of the hair dryer is the intelligent recognition mode, image information is acquired, and the target type acted upon by the hair dryer is confirmed based on the image information.

[0027] In the embodiment of the present invention, in the traditional mode, the gear is manually adjusted by the user, and the user can select the corresponding gear according to actual needs. In the intelligent recognition mode and the emotion recognition mode, the hair dryer intelligently adjusts the wind speed and temperature.

[0028] When it is detected that the hair dryer is in the intelligent recognition mode, the image information is obtained. The hair dryer may be preset with a camera module, and the camera module may be used to capture an image of the area toward which the hair dryer is facing to obtain the image information. After the image information is obtained, the image information may be analyzed to identify the category of information contained in the image information, that is, the target category.

[0029] The target category can be divided into three categories, the first category is people, the second category is animals, and the third category is objects. The above three categories can be confirmed by image recognition of image information. For example, the storage module of the hair dryer can pre-store multiple object models, and the multiple object models include models of people, animals, and objects. After obtaining the image information, the information in the image information is compared with the object model to confirm whether the category of the image information is specifically the first category, the second category, or the third category. It can be understood that after being identified as the first category, the second category, or the third category, the subcategory of the category can be further confirmed. For the first category, after being identified as a person, the gender and age of the person can be further identified. The gender can include male and female, and the age can include multiple intervals. Different intervals are used to correspond to different age groups of people, for example, children, teenagers, young people, middle-aged people, and the elderly. For the second category, which is mainly pets, the types of pets and the types of hair can be further identified. The types of pets can include common pets such as dogs and cats, and the types of hair can include long hair, short hair, curly hair, and other categories. For the third category, which mainly includes clothing and daily necessities, they can be distinguished according to the types of clothing, for example, sweaters and shirts.

[0030] S130, adjusting a blowing mode of the blowing device according to the target type.

[0031] In the embodiment of the present invention, after the specific type of the target type is confirmed, the blowing mode of the blowing device can be adjusted according to the target type, so that the wind speed and wind temperature of the blowing device can be adapted to the target type.

[0032] See also Figure 2 In some embodiments, such as in the present embodiment, the step S130 may include steps S131-S132.

[0033] S131, if the target type is the first type, confirming the degree of hair thinning, degree of hair damage, and age according to the image information, wherein the first type is a person;

[0034] S132, adjusting the wind speed of the hair-drying device according to the degree of hair thinning and the age, and adjusting the wind temperature of the hair-drying device according to the degree of hair damage and the age.

[0035] In the embodiment of the present invention, when the target type is the first type, that is, the target of the hair-drying device is a person, the degree of hair thinning, degree of hair damage and age can be confirmed based on the image information. The degree of hair thinning can be divided into several levels, such as severe, moderate, slight and healthy, and then each level can be quantified. For example, healthy can be quantified as 1, slight can be quantified as 2, moderate can be quantified as 3, and severe can be quantified as 4. When identifying the image information, a plurality of photos of hair with different degrees of thinning can be stored in the hair-drying device, and then the degree of hair thinning in the image information can be determined by comparing the image information with the pre-stored photos.

[0036] After obtaining the degree of hair thinning, the age can be identified. For example, the user's age can be identified through an AI model. The user's age can be identified by capturing the user's facial information, or the user can actively input age information. In addition, multiple age groups can be pre-set, such as teenagers (10-18 years old), adults (19-45 years old), middle-aged and elderly people (46-65 years old) and elderly people (65 years old and above). After obtaining the user's age, the users are grouped according to their specific age. For example, if the user is 20 years old, the user can be divided into adults. Different age groups correspond to different constants. For example, adults can correspond to 12. Finally, the wind speed is calculated according to the formula y1=k1 / x1, where y1 is the wind speed, k1 is the constant corresponding to the age group and k1>0, and x1 is the degree of hair thinning and x1>0. For example, if a user is 20 years old and his hair is slightly sparse, then y1=12 / 2=6. The calculated 6 is related to the wind speed. Multiple gears can be preset in the hair dryer to match different wind speeds. For example, the MOS tube PWM of the hair dryer can be driven to control the duty cycle. The wind speed gear can be adjusted by adjusting different duty cycles 0-100%. If the adjustable gear is 50 gears, then the 1st gear corresponds to a duty cycle of 2%, the 2nd gear corresponds to a duty cycle of 4%, the 3rd gear corresponds to a duty cycle of 6%, the 4th gear corresponds to a duty cycle of 8%... The 50th gear corresponds to a duty cycle of 100%. It can be seen from the above formula that the greater the hair thinning, the lower the wind speed, that is, the wind speed is inversely proportional to the hair thinning degree.

[0037] The degree of hair damage can refer to the degree of hair thinning. The degree of hair damage can also be divided into several levels, such as severe, moderate, mild, and healthy, and each level is quantified. Then the wind temperature is calculated according to the formula y2=k2 / x2, where y2 is the wind temperature, k2 is the constant corresponding to the age group and k2>0, and x2 is the degree of hair damage and x2>0. From the above formula, it can be seen that the degree of hair damage is inversely proportional to the wind temperature. The greater the degree of hair damage, the lower the temperature.

[0038] The wind speed and wind temperature can be determined respectively by the above two formulas, thereby realizing intelligent control of the wind speed and wind temperature.

[0039] See also Figure 3 In some embodiments, such as in the present embodiment, the step S130 may include steps S133-S134.

[0040] S133, if the target type is the second type, confirming the hair category according to the image information, wherein the second type is animals;

[0041] S134, adjusting the wind speed and wind temperature of the hair-drying device according to the hair category.

[0042] In an embodiment of the present invention, for the second type, the target of the hair drying device is an animal. In a household environment, common animals are pets, such as cats and dogs. The hair categories can be divided into long hair, curly hair, short hair and other categories. For example, for short-haired pets, the wind speed and temperature can be adjusted to high wind and high speed. For long-haired pets, the wind speed and temperature can be adjusted to medium speed and medium temperature. For curly-haired pets, the wind speed and temperature can be adjusted to low speed and low temperature.

[0043] See also Figure 4 In some embodiments, such as in the present embodiment, the step S130 may include steps S135-S136.

[0044] S135, if the target type is the third type, confirming the category of the object according to the image information, wherein the third type is an object;

[0045] S136, adjusting the wind speed and wind temperature of the blowing device according to the category of the items.

[0046] In an embodiment of the present invention, the third type is objects, for example, clothes, tables, stools and other furniture, and the wind speed and temperature can be adjusted according to the category of the objects. For example, medium speed and medium temperature can be used for clothes, and high speed and high temperature can be used for furniture items.

[0047] See also Figure 5 In some embodiments, such as in the present embodiment, the method may include steps S140-S150.

[0048] S140, if the current working mode of the hair dryer is the emotion recognition mode, obtaining the user's facial information or voice information;

[0049] S150: Adjust a blowing mode of the blowing device according to the facial information or the sound information.

[0050] In the embodiment of the present invention, the emotion recognition mode is mainly used to identify the current emotional state of the user based on facial information or sound information, and adjust the blowing mode of the hair dryer according to the emotional state. In addition, the auxiliary mode can also be started at the same time. For example, a player can be provided in the hair dryer to play different songs according to the emotional state of the user. The emotional state can be divided into happy, normal and depressed. Then three groups of songs can be preset in advance. The first group of songs corresponds to happy, the second group of songs corresponds to normal, and the third group of songs corresponds to depressed. Songs in different groups are played according to the emotional state of the user.

[0051] See also Figure 6 In some embodiments, such as in this embodiment, step S150 may include steps S151-S152.

[0052] S151, confirming the current emotional state of the user according to the facial information;

[0053] S152, adjusting the blowing mode of the blowing device according to the emotional state.

[0054] In the embodiment of the present invention, when the user's facial information can be obtained, the user's emotional state can be identified through the facial information, that is, the user's emotional state can be confirmed through the user's facial expression. When the user's facial information cannot be obtained, the user's voice information can be obtained, so as to confirm the user's emotional state based on the user's tone of voice.

[0055] After the emotional state is confirmed, the blowing mode of the hair dryer is adjusted according to the emotional state, that is, the wind speed and wind temperature of the hair dryer and the type of music played by the player are adjusted.

[0056] See also Figure 7 In some embodiments, such as in the present embodiment, the step S151 may include steps S1511-S1514.

[0057] S1511, confirming the initial relative position between the eyebrow and the eyebrow tip of the user according to preset input information to obtain a first position;

[0058] S1512, confirming the initial relative position between the eyebrows of the user according to the preset input information to obtain a second position;

[0059] S1513. Confirm the initial relative position between the user's upper lip and lower lip according to the preset input information to obtain a third position.

[0060] S1514. Confirm the real-time first position, real-time second position, and real-time third position respectively according to the facial information, and confirm the emotional state according to the real-time first position, the real-time second position, and the real-time third position.

[0061] In the embodiment of the present invention, when the user uses it for the first time, the user needs to first input a face, confirm the initial relative position a between the eyebrows and the nose tip, that is, the first position; confirm the initial relative position b between the two eyebrows, that is, the second position; confirm the initial relative position c between the upper and lower lips of the mouth, that is, the third position; the camera captures the changes of these three positions in real time as A, B, and C respectively. When A > a + 2 mm (indicating that the eyebrows are raised) or C > c + 2 mm (indicating that the mouth is open), it is determined at this time that the user's emotion is happy, and the working mode of the hair dryer is adjusted to high wind and high temperature, and the music playback and voice playback adopt the content of the preset happy group; when B < b - 2 mm (indicating frowning), it is determined at this time that the user's emotion is frustrated, and the working mode of the hair dryer is adjusted to low wind and low temperature, and the music playback and voice playback adopt the content of the preset frustrated group; when a face is captured, but the first two situations are not met, it is determined at this time that the user's emotion is normal, and the working mode of the hair dryer is adjusted to medium wind and medium temperature, and the music playback and voice playback adopt the content of the preset normal group.

[0062] In some embodiments, for example, in this embodiment, the step S1514 may include the following steps:

[0063] If the difference between the real-time first position and the first position is greater than a first preset threshold, or if the difference between the real-time third position and the third position is greater than a third threshold, then confirm that the emotional state is happy;

[0064] If the difference between the real-time second position and the second position is less than a second preset threshold, then confirm that the emotional state is frustrated.

[0065] In an embodiment of the present invention, taking the previous example as an example, when A > a + 2 mm (indicating that the eyebrows are raised) or C > c + 2 mm (indicating that the mouth is open), that is, the difference between the real-time first position and the first position is greater than the first preset threshold, or the difference between the real-time third position and the third position is greater than the third threshold, at this time, it is determined that the user's emotion is happy, the working mode of the hair dryer is adjusted to high wind and high temperature, and the music playback and voice playback adopt the content of the preset happy group; when B < b - 2 mm (indicating frowning), that is, the difference between the real-time second position and the second position is less than the second preset threshold, at this time, it is determined that the user's emotion is frustrated, the working mode of the hair dryer is adjusted to low wind and low temperature, and the music playback and voice playback adopt the content of the preset frustrated group; when a human face is captured but the previous two situations are not met, at this time, it is determined that the user's emotion is normal, the working mode of the hair dryer is adjusted to medium wind and medium temperature, and the music playback and voice playback adopt the content of the preset normal group.

[0066] In some embodiments, for example, in this embodiment, step S152 may include the following steps:

[0067] If the emotional state is happy, adjust the blowing mode to the high-speed and high-temperature mode;

[0068] If the emotional state is normal, adjust the blowing mode to the medium-speed and medium-temperature mode;

[0069] If the emotional state is frustrated, adjust the blowing mode to the low-speed and low-temperature mode.

[0070] In an embodiment of the present invention, the emotional states include happy, normal, and frustrated, which respectively correspond to the high-speed and high-temperature mode, the medium-speed and medium-temperature mode, and the low-speed and low-temperature mode. At the same time, songs within the corresponding group can also be played according to different emotional states.

[0071] In addition, for sound information, the frequency range of human voices (85 Hz - 1100 Hz) is divided into three regions. For example, 85 - 300 Hz is divided into the bass region, 300 - 600 Hz is divided into the midrange region, and 600 - 1100 Hz is divided into the treble region. When the captured pitch is in the treble region, at this time, it is determined that the user's emotion is happy, the working mode of the hair dryer is adjusted to high wind and high temperature, and the music playback and voice playback adopt the content of the preset happy group; when the captured pitch is in the midrange region, at this time, it is determined that the user's emotion is normal, the working mode of the hair dryer is adjusted to medium wind and medium temperature, and the music playback and voice playback adopt the content of the preset normal group; when the captured pitch is in the bass region, at this time, it is determined that the user's emotion is frustrated, the working mode of the hair dryer is adjusted to low wind and low temperature, and the music playback and voice playback adopt the content of the preset frustrated group.

[0072] The present invention also provides a blowing device, and the hair dryer includes the image recognition-based human-computer interaction method according to any one of the above embodiments.

[0073] The human-computer interaction method and hair dryer based on image recognition disclosed in the present invention can obtain image information, and identify the target type according to the image information, and then adjust the blowing mode of the hair dryer based on the target type, so as to adapt different wind speeds and temperatures according to different types, thereby improving convenience.

[0074] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A human-computer interaction method based on image recognition, characterized in that: Applied to a blowing device, the method comprises: Controlled by a start-up instruction for starting the hair-drying device, confirming a current working mode of the hair-drying device; If the current working mode of the blowing device is the intelligent recognition mode, image information is acquired, and the type of target acted by the blowing device is confirmed based on the image information; The blowing mode of the blowing device is adjusted according to the target type.

2. The method according to claim 1, characterized in that The step of adjusting the blowing mode of the blowing device according to the target type comprises: If the target type is the first type, the degree of hair thinning, degree of hair damage and age are respectively determined according to the image information, wherein the first type is a person; The wind speed of the hair-drying device is adjusted according to the degree of hair thinning and the age, and the wind temperature of the hair-drying device is adjusted according to the degree of hair damage and the age.

3. The method according to claim 2, characterized in that The step of adjusting the blowing mode of the blowing device according to the target type further includes: If the target type is the second type, confirming the hair category according to the image information, wherein the second type is animals; The wind speed and wind temperature of the hair-drying device are adjusted according to the hair category.

4. The method according to claim 3, characterized in that The step of adjusting the blowing mode of the blowing device according to the target type further includes: If the target type is the third type, confirming the category of the object according to the image information, wherein the third type is an object; The wind speed and wind temperature of the blowing device are adjusted according to the category of the items.

5. The method according to claim 1, characterized in that The method further comprises: If the current working mode of the hair dryer is the emotion recognition mode, acquiring the user's facial information or voice information; The blowing mode of the blowing device is adjusted according to the facial information or the sound information.

6. The method according to claim 5, characterized in that The step of adjusting the working mode of the hair dryer according to the facial information or the sound information comprises: confirming the user's current emotional state based on the facial information; The blowing mode of the blowing device is adjusted according to the emotional state.

7. The method according to claim 6, characterized in that The step of confirming the user's current emotional state according to the facial information comprises: confirming the initial relative position between the eyebrow and the eyebrow tip of the user according to the preset input information to obtain a first position; confirming the initial relative position between the eyebrows of the user according to the preset input information to obtain a second position; confirming the initial relative position between the upper lip and the lower lip of the user according to the preset input information to obtain a third position; The real-time first position, the real-time second position and the real-time third position are respectively confirmed according to the facial information, and the emotional state is confirmed according to the real-time first position, the real-time second position and the real-time third position.

8. The method according to claim 7, characterized in that The step of confirming the emotional state according to the real-time first position, the real-time second position, and the real-time third position comprises: If the difference between the real-time first position and the first position is greater than a first preset threshold, or if the difference between the real-time third position and the third position is greater than a third threshold, confirming that the emotional state is happy; If the difference between the real-time second position and the second position is smaller than a second preset threshold, the emotional state is confirmed to be depression.

9. The method according to claim 6, characterized in that The step of adjusting the blowing mode of the blowing device according to the emotional state comprises: If the emotional state is happy, the blowing mode is adjusted to a high-speed and high-temperature mode; If the emotional state is normal, the blowing mode is adjusted to a medium-speed medium-temperature mode; If the emotional state is depression, the blowing mode is adjusted to a low-speed and low-temperature mode.

10. A blowing device, characterized in that: It includes a human-computer interaction method based on image recognition as described in any one of claims 1 to 9.

Images