Cleaner head, vacuum cleaner, learning device, and inference device

Abstract

To provide a vacuum cleaner capable of facilitating disposal work of captured garbage in order to solve a problem that, depending on a residence area of a user, a disposal method of plastic may be different from a disposal method of dust, and in such a case, the user needs to manually separate plastic or the like from garbage captured by a vacuum cleaner, which causes an anxiety of sanitation since the hand of the user may get dirty and causes a problem of securement of convenience.SOLUTION: A cleaner head according to the present disclosure includes: a housing having a suction port facing a surface to be cleaned; a rotary brush provided in the housing; an acquisition part for acquiring garbage information including a feature of garbage sucked by the suction port; and a discrimination part for discriminating a type of garbage on the basis of the garbage information acquired by the acquisition part.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to vacuum cleaners. [Background technology]

[0002] Patent Document 1 discloses a vacuum cleaner that can reduce power consumption. The vacuum cleaner described in Patent Document 1 determines the type of surface to be cleaned based on images or video taken by a camera or the like that is installed to capture the surface to be cleaned, detects the amount of dust using a dust detection sensor, and changes the suction power of the vacuum cleaner or the rotation speed of the rotating brush based on the type of surface to be cleaned and the amount of dust. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2021-183054 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the device described in Patent Document 1, information on the type of surface to be cleaned is acquired using a camera, and the amount of dust is acquired using a dust detection sensor, but information on the type of dust cannot be acquired. The dust may contain foreign matter such as plastic in addition to dust. Depending on the user's area of ​​residence, plastic may be disposed of in a different way than dust and dirt. In this case, the user must manually separate plastic and other materials from the dust captured by the vacuum cleaner, which raises hygiene concerns such as dirtying the user's hands, and also raises issues regarding convenience.

[0005] The present disclosure has been made to solve the above-mentioned problems, and provides a vacuum cleaner that can facilitate the disposal of captured dust. [Means for solving the problem]

[0006] The vacuum cleaner head according to the present disclosure comprises a housing having a suction port facing the surface to be cleaned, a rotating brush provided in the housing, an acquisition unit that acquires dust information including characteristics of the dust sucked into the suction port, and a discrimination unit that discriminates the type of dust based on the dust information acquired by the acquisition unit. [Effects of the Invention]

[0007] According to the present disclosure, the disposal of captured garbage can be facilitated. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is an external view showing an electric vacuum cleaner according to each embodiment. FIG. [Figure 2] 1 is a cross-sectional view showing a cleaner head and an extension tube according to a first embodiment. [Figure 3] 4 is a cross-sectional view of the dust collecting unit according to the first embodiment, showing a state in which the opening / closing unit closes the first collecting unit. FIG. [Figure 4] 4 is a cross-sectional view of the dust collecting section according to the first embodiment, showing a state in which the opening / closing section closes the second collecting section. FIG. [Figure 5] 4 is a cross-sectional view of an opening / closing section according to each embodiment. FIG. [Figure 6] 1 is a functional block diagram showing a vacuum cleaner and a control device according to a first embodiment. [Figure 7] FIG. 2 is a functional block diagram showing a processor and a memory according to each embodiment. [Figure 8] FIG. 2 is a functional block diagram illustrating a processing circuit according to each embodiment. [Figure 9] 4 is a flowchart showing the operation of the electric vacuum cleaner according to the first embodiment. [Figure 10] FIG. 10 is a cross-sectional view showing a cleaner head and an extension tube according to a second embodiment. [Figure 11] FIG. 10 is a functional block diagram showing an electric vacuum cleaner and a control device according to a second embodiment. [Figure 12] 10 is a flowchart showing the operation of the electric vacuum cleaner according to the second embodiment. [Figure 13] FIG. 11 is a functional block diagram showing a learning device according to a third embodiment. [Figure 14] FIG. 10 is a diagram illustrating an example of a neural network according to a third embodiment. [Figure 15] 11 is a flowchart showing a learning process of the learning device according to the third embodiment. [Figure 16] FIG. 10 is a functional block diagram showing an inference device according to a third embodiment. [Figure 17] 11 is a flowchart showing an inference process of the inference device according to the third embodiment. [Figure 18] FIG. 10 is a functional block diagram showing a vacuum cleaner and a control device according to a fourth embodiment. [Figure 19] 10 is a flowchart showing the operation of the electric vacuum cleaner according to the fourth embodiment. [Figure 20] 10 is a cross-sectional view of a suction pipe according to Modification 1, showing a state in which an opening / closing section closes a first collection section. FIG. [Figure 21] 10 is a cross-sectional view of a suction pipe according to Modification 1, showing a state in which an opening / closing section closes a second collection section. FIG. [Figure 22] 10 is a cross-sectional view of an extension tube according to Modification 2, showing a state in which the opening / closing section closes the first collection section. FIG. [Figure 23] 10 is a cross-sectional view of an extension tube according to Modification 2, showing a state in which the opening / closing section closes the second collection section. FIG. [Figure 24] FIG. 11 is a cross-sectional view showing a cleaner head and an extension tube according to a third modification. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following drawings, the same or corresponding parts are designated by the same reference numerals, and descriptions thereof will not be repeated.

[0010] Embodiment 1 <Vacuum cleaner configuration> Fig. 1 is an external view showing a vacuum cleaner 1 according to Embodiment 1. As shown in Fig. 1, the vacuum cleaner 1 has a cleaner head 2, a suction pipe 60, an extension pipe 65, a main body 70, a dust collection unit 100, a handle 102, and a switch 103. Air sucked from the cleaner head 2 by suction wind generated in the main body 70 flows through the extension pipe 65 and the suction pipe 60 into the main body 70, where dust is removed before being discharged to the outside.

[0011] 2 is a cross-sectional view showing the cleaner head 2 and extension tube 65 according to Embodiment 1. As shown in FIG. 2, the cleaner head 2 has a housing 10, a rotating brush 11, a roller 12, and a camera 32.

[0012] The housing 10 has a suction port 20 facing the surface to be cleaned. On the opposite side of the housing 10 from the suction port 20, a communication part 21 connected to an extension pipe 65 is provided.

[0013] The rotating brush 11 is a rotating body for sucking up dirt on the surface to be cleaned. The rotating brush 11 is provided in the housing 10 and has bristles 31. The rotating brush 11 is connected to a first electric motor 30 built into the cleaner head 2. When the first electric motor 30 rotates, the rotational force (torque) of the first electric motor 30 is transmitted to rotate the rotating brush 11, which then scrapes up dirt on the surface to be cleaned.

[0014] Roller 12 is a wheel that is provided at the bottom of housing 10 and comes into contact with the surface to be cleaned. Roller 12 makes rolling contact with the surface to be cleaned, thereby preventing contact between rotating brush 11 and the surface to be cleaned.

[0015] The camera 32 has a lens 40 and an imaging element 41. The imaging element 41 outputs an imaging signal corresponding to an optical image formed by the lens 40. Specifically, the imaging element 41 generates image data.

[0016] The extension pipe 65 is a hollow tubular member. One end of the extension pipe 65 is connected to the communication portion 21 of the housing 10.

[0017] 1, the other end of the extension pipe 65 is connected to the suction pipe 60. The suction pipe 60 is further connected to the main body 70. The main body 70 has a blower 110, a battery 101, and a control device 150. The configuration of the control device 150 will be described later.

[0018] The blower 110 has a second motor (not shown) and blades (not shown) connected to the second motor. When the second motor rotates, the torque of the second motor is transmitted to rotate the blades, generating suction air that flows from the cleaner head 2 through the extension tube 60 to the dust collecting unit 100.

[0019] The battery 101 supplies power to the first electric motor 30, the second electric motor, and the control device 150.

[0020] The grip portion 102 is a handle that is gripped by the user.

[0021] Switch 103 is an operation unit that allows the user to turn on / off vacuum cleaner 1. When switch 103 is turned on, first electric motor 30 and second electric motor start to rotate, thereby starting to rotate rotating brush 11 and blower 110. The form of switch 103 is not limited, and may be, for example, a push button switch, a slide switch, or a touch panel switch.

[0022] The dust collection unit 100 collects dirt and other contaminants from the air drawn into the main body unit 70. The dust collection unit 100 is detachable from the main body unit 70.

[0023] 3-4 are cross-sectional views showing the dust collecting unit 100 according to the first embodiment. FIG. 3 shows a state in which the open-close unit 124 blocks the first collecting unit 120. FIG. 4 shows a state in which the open-close unit 124 blocks the second collecting unit 121. Hereinafter, the state in which the open-close unit 124 blocks the first collecting unit 120 will be referred to as the "first mode," and the state in which the open-close unit 124 blocks the second collecting unit 121 will be referred to as the "second mode." Note that the state in which the open-close unit 124 does not block either the first collecting unit 120 or the second collecting unit 121 will be referred to as the "third mode." The outer shell of the dust collecting unit 100 is formed by a dust collecting container 115. In the dust collecting unit 100, a first collecting unit 120 that collects dust contained in garbage and a second collecting unit 121 that collects garbage other than dust are formed inside the dust collecting container 115. Dust collection unit 100 also has a first opening 122 facing first collection unit 120, and a second opening 123 formed by opening a portion of the side wall of dust collection unit 100. Dust collection unit 100 also has an opening / closing unit 124 that opens and closes either first opening 122 or second opening 123. In other words, opening / closing unit 124 switches between a first mode and a second mode.

[0024] The term "dust" refers to fine particulate matter that easily floats in the air, such as dust, pollen, sand, and ash.

[0025] 5 is a cross-sectional view of the open-close unit 124 according to the first embodiment. The open-close unit 124 is configured in a mesh shape with a plurality of openings 125. By having a plurality of openings 125, it becomes easier for the open-close unit 124 to capture plastics and the like contained in dust that has entered the dust collection unit 100.

[0026] The electric vacuum cleaner 1 according to the first embodiment includes a control device 150 in the main body 70. The control device 150 controls the rotation speed of the rotary brush 11, the rotation speed of the blower 110, and the operation of the opening / closing part 124.

[0027] 6 is a functional block diagram showing the electric vacuum cleaner 1 and the control device 150 according to the first embodiment. The control device 150 has a determination unit 14, a control unit 151, and a storage unit 152.

[0028] The determination unit 14 acquires image data including dust information DI acquired by the camera 32. The dust information DI is information relating to the characteristics of dust sucked into the suction port 20 of the housing 10. The dust information DI may be, for example, the RGB values ​​of the dust contained in the image data. Alternatively, edges contained in the image data may be detected, and the characteristics of the dust may be determined based on the detected edges.

[0029] The control unit 151 controls the rotation speed of the first electric motor 30 connected to the rotary brush 11, and also controls the rotation speed of the second electric motor connected to the blower 110. Furthermore, the control device 150 controls the operation of the opening / closing unit 124 provided in the dust collecting unit 100.

[0030] The storage unit 152 accumulates the dirt information DI acquired by the camera 32. The storage unit 152 also stores a dirt type prediction model that indicates the predicted results of the type of dirt that will be sucked into the vacuum cleaner 1. The dirt type prediction model is information that is generated based on the dirt information DI. The dirt type prediction model indicates the type of dirt (dust, plastic, etc.) contained in the dirt sucked into the vacuum cleaner 1.

[0031] Control unit 151 according to the first embodiment controls open / close unit 124 based on the dust type prediction model stored in storage unit 152. Specifically, control unit 151 controls open / close unit 124 based on the dust type prediction model so that the first mode is entered when vacuum cleaner 1 has sucked in dust other than dust. The detailed operation of open / close unit 124 will be described later.

[0032] 6 shows only one example of the configuration of the vacuum cleaner 1 and the control device 150, and is not limited to Fig. 6. In Fig. 6, the vacuum cleaner 1 and the control device 150 are provided separately, but the control device 150 may be incorporated inside the vacuum cleaner 1 or the cleaner head 2.

[0033] The control device 150 is configured with at least one processor 160 and at least one memory 161, for example, as shown in FIG. 7. The processor 160 is, for example, a CPU (Central Processing Unit) that executes a program stored in the memory 161. In this case, the functions of the control unit 151 and the storage unit 152 are realized by software, firmware, or a combination of software and firmware. The software and firmware can be stored in the memory 161 as a program. With this configuration, a program for realizing the functions of the control device 150 is executed by a computer.

[0034] The memory 161 is a computer-readable recording medium, and is, for example, a volatile memory such as a random access memory (RAM) and a read only memory (ROM), a nonvolatile memory, or a combination of a volatile memory and a nonvolatile memory.

[0035] The control device 150 may be configured with a processing circuit 162 as dedicated hardware such as a single circuit or a composite circuit, as shown in Fig. 8. In this case, the functions of the control unit 151 and the storage unit 152 are realized by the processing circuit 162.

[0036] <Operation of the electric vacuum cleaner according to the first embodiment> A specific example of the operation of the electric vacuum cleaner 1 according to the present embodiment 1 will be described below. Fig. 9 is a flowchart showing the operation of the electric vacuum cleaner 1 according to the present embodiment 1.

[0037] In step S100, the camera 32 captures an image of the floor surface and obtains dust information DI, which is information relating to the characteristics of the dust sucked into the suction port 20 of the housing 10. The dust characteristics include, for example, the RGB values ​​of the dust contained in the image data, edges contained in the image data, etc.

[0038] In step S102, the determination unit 14 determines the type of garbage based on the garbage information DI acquired in step S100. The type of garbage indicates whether or not the garbage sucked in by the vacuum cleaner 1 contains a predetermined number or more of garbage to be separated (e.g., plastic, rubber, metal, etc.). The predetermined value is numerical data, such as, for example, 10% of the garbage to be separated contained in the garbage information DI. The garbage to be separated and the predetermined value may be set in advance or manually set by the user. Furthermore, when the remaining charge of the battery 101 of the vacuum cleaner 1 becomes low, the predetermined value may be automatically set higher. This reduces the number of operations of the opening / closing unit 124 and suppresses power consumption, thereby conserving the remaining charge of the battery 101. If the determined type of garbage contains a predetermined number or more of garbage to be separated (e.g., plastic, rubber, metal, etc.), the process proceeds to step S104. If the determined type of garbage does not contain any garbage to be separated, the process proceeds to step S110.

[0039] In step S104, mode information about the interior of dust collection unit 100 is acquired. The mode information is information indicating whether the interior of dust collection unit 100 is in the first mode, second mode, or third mode. The mode information may be acquired, for example, by acquiring the output of a mechanical switch or a proximity sensor provided inside dust collection unit 100 and detecting the position of opening / closing unit 124. If the first mode is selected, the process proceeds to step S108. If the second mode or third mode is selected, the process proceeds to step S106. In step S106, control unit 151 operates opening / closing unit 124 to enter the first mode.

[0040] In step S108, the type of garbage is identified by the identification unit 14 based on the acquired garbage information DI. If the identified garbage type includes items to be separated (e.g., plastics), the process proceeds to step S104. If the identified garbage type does not include items to be separated, the process proceeds to step S110.

[0041] In step S110, control unit 151 operates opening / closing unit 124 to enter the second mode.

[0042] <Effects of the electric vacuum cleaner according to the first embodiment> The vacuum cleaner 1 according to the first embodiment can separate foreign matter such as plastic contained in garbage from dust. This eliminates the need for the user to manually separate plastics and other foreign matter from the garbage captured by the vacuum cleaner 1, thereby eliminating hygiene concerns such as the user's hands getting dirty. Another effect is that the captured garbage can be easily disposed of.

[0043] Embodiment 2 In the first embodiment, a configuration in which dust information DI is acquired using a camera 32 and the type of dust is identified has been described. In the second embodiment, a configuration in which dust information DI is acquired using a photoelectric sensor 33 and the type of dust is identified will be described. Note that a description of matters common to the first embodiment will be omitted, and only matters different from the first embodiment will be described.

[0044] 10 is a cross-sectional view showing the cleaner head 2 and extension tube 65 according to Embodiment 2. The cleaner head 2 has a photoelectric sensor 33.

[0045] The photoelectric sensor 33 has a light-emitting unit 50 that emits light and a light-receiving unit 51 that receives the light emitted from the light-emitting unit 50. The light-emitting unit 50 is, for example, an LED (Light Emitting Diode), etc. The light-receiving unit 51 detects the amount of light received.

[0046] When light emitted from the light-emitting unit 50 hits dust, the light is either reflected or blocked. The amount of light reflected from dust depends on the type of dust. In other words, the amount of light detected by the light-receiving unit 51 changes depending on the type of dust. The type of dust can be identified based on the amount of light detected by the light-receiving unit 51.

[0047] FIG. 11 is a functional block diagram showing the vacuum cleaner 1 and the control device 150 according to the second embodiment. The determination unit 14 acquires data including the dust information DI acquired by the photoelectric sensor 33. The dust information DI may be, for example, the ratio between the amount of light emitted by the light-emitting unit 50 and the amount of light received by the light-receiving unit 51. For example, when the only dust sucked into the suction port 20 is dust, the amount of light received by the light-receiving unit 51 is relatively small because normal dust is mainly black or gray. However, when dust to be separated is present, the light emitted from the light-emitting unit 50 hits a color other than black or gray, and the amount of light received by the light-receiving unit 51 increases or decreases compared to when the dust is only dust. By detecting this increase or decrease, the amount of dust to be separated is estimated.

[0048] 12 is a flowchart showing the operation of the vacuum cleaner 1 according to the present embodiment 2. In step S200, the photoelectric sensor 33 acquires dirt information DI, which is information relating to the characteristics of the dirt sucked into the suction opening 20 of the housing 10.

[0049] In step S202, the type of garbage is identified by the identification unit 14 based on the garbage information DI acquired in step S200. If the identified garbage type includes items to be separated (e.g., plastic, rubber, metal, etc.), the process proceeds to step S204. If the identified garbage type does not include items to be separated, the process proceeds to step S210.

[0050] In step S204, it is determined whether the interior of dust collection unit 100 is in the first mode or the second mode. If opening / closing unit 124 is in the first mode, the process proceeds to step S208. If opening / closing unit 124 is in the second mode or the third mode, the process proceeds to step S206. In step S206, control unit 151 operates opening / closing unit 124 to enter the first mode.

[0051] In step S208, the type of garbage is determined by the determination unit 14 based on the acquired garbage information DI. If the determined type of garbage includes items to be separated (for example, plastic, rubber, metal, etc.), the process proceeds to step S204. If the determined type of garbage does not include items to be separated, the process proceeds to step S210.

[0052] In step S210, control unit 151 operates opening / closing unit 124 to enter the second mode.

[0053] <Effects of the electric vacuum cleaner according to the second embodiment> The vacuum cleaner 1 according to the second embodiment can separate foreign matter such as plastic contained in garbage from dust. This eliminates the need for the user to manually separate plastics and other foreign matter from the garbage captured by the vacuum cleaner 1, thereby eliminating hygiene concerns such as the user's hands getting dirty. Another effect is that the disposal of captured garbage can be simplified. Furthermore, compared to the camera 32 used as the means for acquiring the garbage information DI in the first embodiment, the photoelectric sensor 33 is used in the second embodiment to acquire the garbage information DI, allowing for a low-cost vacuum cleaner 1 to be configured.

[0054] Embodiment 3 In this third embodiment, in order to improve the accuracy of distinguishing the type of dust, a form will be described in which the type of dust is inferred using a learning device 200 and an inference device 210. Note that a description of matters common to the first embodiment will be omitted, and only matters different from the first embodiment will be described.

[0055] <Configuration of the learning device (learning phase)> 13 is a functional block diagram showing a learning device 200 according to Embodiment 3. The learning device 200 includes a learning data acquiring unit 201, a model generating unit 202, and a trained model storage unit 203.

[0056] The learning data acquisition unit 201 acquires, as learning data, dust image information, which is image information of dust sucked by the vacuum cleaner 1, and the type of dust.

[0057] Model generation unit 202 learns the types of dirt that vacuum cleaner 1 will suck up, based on the dirt image information output from learning data acquisition unit 201 and learning data created based on combinations of dirt types. That is, it generates a trained model that infers the optimum type of dirt to be sucked up by vacuum cleaner 1, based on the dirt image information and dirt type of vacuum cleaner 1. Here, the learning data is data that associates dirt image information and dirt types with each other.

[0058] Note that learning device 200 and inference device 210 are used to learn the type of dust sucked into vacuum cleaner 1, but may be separate devices connected to vacuum cleaner 1 via a network, for example. Learning device 200 and inference device 210 may also be built into vacuum cleaner 1. Furthermore, learning device 200 and inference device 210 may reside on a cloud server.

[0059] The learning algorithm used by the model generation unit 202 may be a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. As an example, a case where a neural network is applied will be described.

[0060] The model generation unit 202 learns the types of dust sucked up by the vacuum cleaner 1, for example, by so-called supervised learning in accordance with a neural network model. Here, supervised learning refers to a method in which pairs of input and result (label) data are provided to the learning device 200, and the learning device 200 learns the features of the learning data and infers the result from the input.

[0061] A neural network consists of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0062] For example, in a three-layer neural network as shown in Figure 14, when multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by weight W1 (w11-w16) and input to the middle layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result changes depending on the values ​​of weights W1 and W2.

[0063] In the third embodiment, the neural network learns the types of dust that the vacuum cleaner 1 sucks up by so-called supervised learning in accordance with the dust image information acquired by the learning data acquisition unit 201 and the learning data created based on the combination of dust types.

[0064] That is, the neural network learns by inputting dust image information to the input layer and adjusting the weights W1 and W2 so that the results output from the output layer approximate the type of dust.

[0065] The model generation unit 202 generates and outputs a trained model by performing the above-described learning.

[0066] The trained model storage unit 203 stores the trained model output from the model generation unit 202.

[0067] Next, the learning process performed by the learning device 200 will be described with reference to Fig. 15. Fig. 15 is a flowchart showing the learning process performed by the learning device 200 according to the third embodiment.

[0068] In step S300, the learning data acquisition unit 201 acquires dust image information and dust type. Note that although the dust image information and dust type are acquired simultaneously, it is sufficient if the dust image information and dust type are input in association with each other, and the dust image information and dust type data may be acquired at different times.

[0069] In step S302, the model generation unit 202 learns the types of dust sucked in by the vacuum cleaner 1 through so-called supervised learning in accordance with the dust image information acquired by the learning data acquisition unit 201 and the learning data created based on the combination of dust types, and generates a learned model.

[0070] In step S304, the trained model storage unit 203 stores the trained model generated by the model generation unit 202.

[0071] <Configuration of inference device (utilization phase)> 16 is a functional block diagram showing an inference device 210 according to the third embodiment. The inference device 210 includes a data acquisition unit 211 and an inference unit 212.

[0072] The data acquisition unit 211 acquires dust image information.

[0073] The inference unit 212 uses the trained model to infer the type of dust that will be sucked up by the vacuum cleaner 1. That is, by inputting the dust image information acquired by the data acquisition unit 211 into this trained model, it is possible to output the type of dust that will be sucked up by the vacuum cleaner 1 that is inferred from the dust image information.

[0074] In this third embodiment, it has been described that the type of dust that the vacuum cleaner 1 sucks up is output using a trained model trained by the model generation unit 202 of the vacuum cleaner 1, but it is also possible to obtain a trained model from an external source, such as another vacuum cleaner 1, and output the type of dust that the vacuum cleaner 1 sucks up based on this trained model.

[0075] Next, a process for obtaining the type of dust sucked by the vacuum cleaner 1 using the inference device 210 will be described with reference to Fig. 17. Fig. 17 is a flowchart showing the inference process of the inference device 210 according to the third embodiment.

[0076] In step S400, the data acquisition unit 211 acquires dust image information.

[0077] In step S402, the inference unit 212 inputs the dust image information into the trained model stored in the trained model storage unit 203, and obtains the type of dust that the vacuum cleaner 1 will suck up.

[0078] In step S404, the inference unit 212 outputs to the vacuum cleaner 1 the type of dust that the vacuum cleaner 1 will suck up, which is obtained from the trained model.

[0079] In step S406, the vacuum cleaner 1 uses the output type of dust that the vacuum cleaner 1 will suck in, and if dust that needs to be separated is sucked in, controls the open / close unit 124 to transfer the dust to the second collection unit 121. This makes it easier to dispose of the captured dust.

[0080] In the third embodiment, a case where supervised learning is applied to the learning algorithm used by the model generation unit 202 has been described, but the present invention is not limited to this. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0081] Furthermore, the model generation unit 202 may learn the type of dirt that the vacuum cleaner 1 sucks up according to learning data created for multiple vacuum cleaners 1. The model generation unit 202 may acquire learning data from multiple vacuum cleaners 1 used in the same area, or may learn the type of dirt that the vacuum cleaner 1 sucks up using learning data collected from multiple vacuum cleaners 1 operating independently in different areas. It is also possible to add or remove vacuum cleaners 1 from which learning data is collected as the target. Furthermore, the learning device 200 that has learned the type of dirt that a certain vacuum cleaner 1 sucks up may be applied to another vacuum cleaner 1, and the type of dirt that the vacuum cleaner 1 sucks up may be re-learned and updated for the other vacuum cleaner 1.

[0082] Furthermore, the learning algorithm used in the model generation unit 202 can be deep learning, which learns to extract the features themselves, or machine learning can be performed according to other known methods, such as genetic programming, functional logic programming, or support vector machines.

[0083] <Effects of the electric vacuum cleaner according to the third embodiment> By using the learning device 200 and the inference device 210, the electric vacuum cleaner 1 according to the third embodiment can improve the accuracy of distinguishing the type of dust.

[0084] Embodiment 4 In the first embodiment, a configuration has been described in which dust information DI is acquired by camera 32 and the type of dust is determined based on the acquired dust information DI. In the fourth embodiment, a configuration will be described in which the suction power of vacuum cleaner 1 is controlled based on acquired cleaning surface information SI. Note that a description of matters common to the first embodiment will be omitted, and only matters different from the first embodiment will be described.

[0085] FIG. 18 is a functional block diagram showing the electric vacuum cleaner 1 and control device 150 according to the fourth embodiment. The camera 32 acquires dirt information DI and cleaned surface information SI. The discrimination unit 14 acquires image data including the dirt information DI and cleaned surface information SI acquired by the camera 32. The cleaned surface information SI is information relating to the characteristics of the surface to be cleaned that faces the suction port 20 of the cleaner head 2. The cleaned surface information SI may be, for example, the RGB values ​​of the surface to be cleaned contained in the image data. Alternatively, edges contained in the image data may be detected, and the characteristics of the surface to be cleaned may be discriminated based on the detected edges.

[0086] The memory unit 152 stores the dirt information DI and the surface information SI to be cleaned acquired by the camera 32. The memory unit 152 also stores a surface type prediction model that indicates the predicted result of the type of surface to be cleaned that faces the suction port 20 of the cleaner head 2. The surface type prediction model is information that is generated based on the surface information SI to be cleaned. The surface type prediction model indicates the type of surface to be cleaned that faces the suction port 20 (flooring, tatami, carpet, etc.).

[0087] A specific example of the operation of the electric vacuum cleaner 1 according to the present embodiment 4 will now be described. Fig. 19 is a flowchart showing the operation of the electric vacuum cleaner 1 according to the present embodiment 4.

[0088] In step S500, the camera 32 captures an image of the floor surface and obtains dust information DI and surface information SI, which is information about the characteristics of the surface to be cleaned that faces the suction port 20 of the cleaner head 2. The characteristics of the surface to be cleaned include, for example, the RGB values ​​of the surface to be cleaned contained in the image data, edges contained in the image data, etc.

[0089] In step S502, the discrimination unit 14 determines an appropriate suction power based on the surface to be cleaned information SI acquired in step S500. The control unit 151 controls the rotation speed of the rotating brush 11 or the rotation speed of the blower 110 so that the determined suction power is achieved. For example, if the user was cleaning a wooden floor with the suction power in "weak mode," and the discrimination unit 14 determines that the acquired surface to be cleaned information SI has changed from wooden floor to carpet, the control unit 151 changes the suction power to "strong mode."

[0090] In step S504, the type of garbage is identified by the identification unit 14 based on the garbage information DI acquired in step S500. If the identified garbage type includes items to be separated (for example, plastic, rubber, metal, etc.), the process proceeds to step S506. If the identified garbage type does not include items to be separated, the process proceeds to step S512.

[0091] In step S506, mode information inside dust collection unit 100 is acquired. If it is the first mode, the process proceeds to step S510. If it is the second mode or the third mode, the process proceeds to step S508. In step S508, control unit 151 operates opening / closing unit 124 to set the first mode.

[0092] In step S510, the type of garbage is determined by the determination unit 14 based on the acquired garbage information DI. If the determined type of garbage includes items to be separated (for example, plastic, rubber, metal, etc.), the process proceeds to step S506. If the determined type of garbage does not include items to be separated, the process proceeds to step S512.

[0093] In step S512, the control unit 151 operates the opening / closing unit 124 to enter the second mode.

[0094] <Effects of the electric vacuum cleaner according to the fourth embodiment> The vacuum cleaner 1 according to the fourth embodiment can change the suction power to an appropriate level depending on the condition of the surface to be cleaned. This eliminates the need for the user to change the suction power depending on the type of surface to be cleaned, thereby improving user convenience.

[0095] Variation 1. In the first embodiment, a configuration has been described in which the first collection section 120, the second collection section 121, the first opening 122, the second opening 123, and the opening / closing section 124 are provided in the dust collection section 100. As in the first modification, the first collection section 140, the second collection section 141, the first opening 142, the second opening 143, and the opening / closing section 144 can also be provided in the suction pipe 60 instead of the dust collection section 100.

[0096] 20-21 are cross-sectional views showing suction pipe 60 according to Modification 1. FIG. 20 shows a state in which opening / closing section 144 blocks first collection section 140. FIG. 21 shows a state in which opening / closing section 144 blocks second collection section 141. Inside suction pipe 60, first collection section 140 that captures dust contained in garbage and second collection section 141 that captures garbage other than dust are formed. Suction pipe 60 also has a first opening 142 facing first collection section 140 and a second opening 143 formed by opening a portion of the side wall of suction pipe 60. Suction pipe 60 also has an opening / closing section 144 that opens and closes to block either first opening 142 or second opening 143.

[0097] Variation 2. In the first embodiment, a configuration has been described in which the first collection section 120, the second collection section 121, the first opening 122, the second opening 123, and the opening / closing section 124 are provided in the dust collection section 100. As in the second modification, the first collection section 170, the second collection section 171, the first opening 172, the second opening 173, and the opening / closing section 174 can also be provided in the extension tube 65 instead of the dust collection section 100.

[0098] 22 and 23 are cross-sectional views showing an extension tube 65 according to Modification 2. FIG. 22 shows a state in which the open-close unit 174 closes the first collection unit 170. FIG. 23 shows a state in which the open-close unit 174 closes the second collection unit 171. Inside the extension tube 65, the first collection unit 170 that collects dust contained in dirt and the second collection unit 171 that collects dirt other than dust are formed. The extension tube 65 also has a first opening 172 facing the first collection unit 170 and a second opening 173 formed by opening a portion of the side wall of the extension tube 65. The extension tube 65 also has an open-close unit 174 that opens and closes to close either the first opening 172 or the second opening 173.

[0099] Variation 3. Figure 24 is a cross-sectional view showing the cleaner head 2 and extension tube 65 according to Modification 3. As Modification 3, as shown in Figure 24, the housing 10 may be provided with an illumination unit 22 that illuminates the floor surface. The camera 32 may also be an infrared camera. Furthermore, both the illumination unit 22 and the infrared camera may be provided.

[0100] Variation 4. In the first embodiment, the camera 32 is provided on the cleaner head 2, but the location where the camera 32 is provided is not limited to the cleaner head 2, and the camera 32 may be provided anywhere in the vacuum cleaner 1. The camera 32 may also be provided somewhere in the room where the vacuum cleaner 1 is used. When image data is acquired by the camera 32 provided in the room, it may be communicated with the control device 150 by a communication means using any communication standard, for example, Bluetooth (registered trademark).

[0101] Variation 5. In the first to fourth embodiments, the electric vacuum cleaner 1 has been described as being of an upright cordless type, but the type of the electric vacuum cleaner 1 according to the present disclosure is not limited to this. For example, the electric vacuum cleaner 1 may be of a wired canister type.

[0102] The features of the above-described embodiments and modifications can be combined with each other. [Explanation of symbols]

[0103] REFERENCE SIGNS LIST 1 electric vacuum cleaner, 2 vacuum cleaner head, 10 housing, 11 rotating brush, 14 discrimination unit, 20 suction port, 22 lighting unit, 32 camera, 33 photoelectric sensor, 40 lens, 41 imaging element, 60 suction pipe, 65 extension pipe, 70 main body unit, 120, 140, 170 first collection unit, 121, 141, 171 second collection unit, 122, 142, 172 first opening, 123, 143, 173 second opening, 124, 144, 174 opening / closing unit, 90 suction unit, 100 dust collection unit, 151 control unit, 200 learning device, 201 learning data acquisition unit, 202 model generation unit, 210 inference device, 211 data acquisition unit, 212 Reasoning Department.

Claims

1. a housing having a suction port facing the surface to be cleaned; a rotating brush provided in the housing; an acquisition unit that acquires dust information including characteristics of dust sucked into the suction port; a determination unit that determines the type of dust based on the dust information acquired by the acquisition unit, Vacuum cleaner head.

2. the dust information includes dust image information including image information of the dust; A cleaner head according to claim 1.

3. the acquisition unit includes an image capture unit for acquiring the dust-image information; A cleaner head according to claim 2.

4. The photographing unit includes a lens that passes external light into the photographing unit, and an image sensor that converts the light that enters through the lens into image data. A cleaner head according to claim 3.

5. The photographing unit is an infrared camera. A cleaner head according to claim 4.

6. The housing has a lighting unit that illuminates the floor surface. A cleaner head according to claim 4.

7. the acquisition unit includes a photoelectric sensor for acquiring the dust information, A cleaner head according to claim 1.

8. A cleaner head according to any one of claims 1 to 7; an extension tube having a hollow tubular shape and one end of which is connected to the housing; a suction pipe connected to the other end of the extension pipe; a main body connected to the other end of the suction pipe and configured to generate suction air; a dust collecting unit that collects dust contained in the suction air drawn into the main body; A control unit that controls the rotary brush. Electric vacuum cleaner.

9. the dust collecting unit has a first collecting unit that collects dust contained in the waste, a first opening that faces the first collecting unit, a second opening that is formed by opening a part of a side wall of the dust collecting unit, a second collecting unit that communicates with the second opening, and an opening / closing unit that opens and closes to close either the first opening or the second opening, the control unit controls the opening and closing of the opening / closing unit based on the type of dust determined by the determination unit.

9. The vacuum cleaner according to claim 8.

10. The acquisition unit further acquires cleaning surface information including characteristics of the cleaning surface; the control unit controls the suction force generated by the main body unit based on the cleaning surface information acquired by the acquisition unit.

10. The vacuum cleaner according to claim 9.

11. the suction pipe has a first collecting section that collects dust contained in the waste, a first opening that faces the first collecting section, a second opening that is formed by opening a part of a side wall of the dust collecting section, the second collecting section that communicates with the second opening, and an opening / closing section that opens and closes to close either the first opening or the second opening, the control unit controls the opening and closing of the opening / closing unit based on the type of dust determined by the determination unit.

9. The vacuum cleaner according to claim 8.

12. the extension pipe has a first collecting section that collects dust contained in the waste, a first opening that faces the first collecting section, a second opening that is formed by opening a part of a side wall of the dust collecting section, the second collecting section that communicates with the second opening, and an opening / closing section that opens and closes to close either the first opening or the second opening, the control unit controls the opening and closing of the opening / closing unit based on the type of dust determined by the determination unit.

9. The vacuum cleaner according to claim 8.

13. The opening and closing portion is configured in a mesh shape with a plurality of openings.

10. The vacuum cleaner according to claim 9.

14. The opening and closing portion is configured in a mesh shape with a plurality of openings.

12. The vacuum cleaner of claim 11.

15. The opening and closing portion is configured in a mesh shape with a plurality of openings.

13. The vacuum cleaner of claim 12.

16. a learning data acquisition unit that acquires dust image information, which is image information of dust sucked into the vacuum cleaner, and the type of dust; a model generation unit that generates a trained model for inferring the type of dust sucked by the vacuum cleaner from the dust image information, using the training data acquired by the training data acquisition unit. Learning device.

17. a data acquisition unit that acquires dust image information, which is image information of dust sucked by the vacuum cleaner; an inference unit that outputs the type of dust from the dust image information input from the data acquisition unit, using a trained model for inferring the type of dust sucked by the vacuum cleaner from the dust image information; An inference device comprising:

18. The learning device according to claim 16 ; and the inference device according to claim 17. Electric vacuum cleaner.

Images