A cleaning machine control method, device, medium and equipment

Abstract

This invention relates to the field of data processing, and more particularly to a cleaning machine control method, apparatus, medium, and equipment, comprising: acquiring a video of the cleaning process of the object to be cleaned within a first preset time period and N images of the cleaning process within a second preset time period; obtaining body shape parameter data based on the N images of the cleaning process; obtaining first cleaning parameter data based on the body shape parameter data and a preset parameter lookup table, thereby improving the cleaning effect of the object to be cleaned; inputting the cleaning process video into a preset behavior recognition model to obtain the movement speed and behavior posture; obtaining the cleaning state type based on the movement speed and behavior posture; setting second cleaning parameter data based on the cleaning state type; and controlling the cleaning machine based on the first and second cleaning parameter data. By improving the accuracy of the first and second cleaning parameter data, the comfort of the object to be cleaned is ensured while achieving a highly efficient cleaning effect.

Description

Technical Field

[0001] This invention relates to the field of cleaning machine control, and in particular to a cleaning machine control method, device, medium, and equipment. Background Technology

[0002] With the continuous development and improvement of living standards, pets have become important members of families, and the demand for pet cleaning is also increasing. Since manual pet cleaning is tedious and some pets may cause injury to the cleaning staff during the cleaning process, automatic cleaning machines are gradually playing an increasingly important role in pet cleaning.

[0003] Existing cleaning machines set the cleaning parameters for the entire cleaning process based on the pet's species and degree of dirtiness, focusing only on the cleaning level or automation of the machine while ignoring the pet's feelings and condition. This may cause discomfort or panic in the pet during the cleaning process, making it prone to accidents and even harming the pet.

[0004] Therefore, in pet grooming scenarios, ensuring pet comfort while achieving efficient grooming results is a pressing issue that needs to be addressed. Summary of the Invention

[0005] To address the aforementioned technical problems, the present invention provides a cleaning machine control method, which includes the following steps:

[0006] S100: Based on the built-in acquisition device in the cleaning machine, acquire the cleaning process video of the object to be cleaned during the first preset time period, and N cleaning process images of the object to be cleaned during the second preset time period, where N is an integer greater than 0, the first preset time period refers to the time period from P preset time units before the current time point to the current time point, where P is an integer greater than 0, the second preset time period refers to the time period from the initial time point to Q preset time units after the initial time point, the initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the machine, where Q is an integer greater than 0.

[0007] S200: Based on N images of the cleaning process, obtain the shape parameter data of the object to be cleaned.

[0008] S300 obtains the first cleaning parameter data of the cleaning machine based on the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0009] The S400 inputs the video of the cleaning process into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned.

[0010] S500 obtains the cleaning status type of the object to be cleaned based on its movement speed and behavior posture. The cleaning status types include stationary state, normal state, abnormal state, and violent state.

[0011] S600 sets the second cleaning parameter data of the cleaning machine according to the cleaning status type. The second cleaning parameters include water output, water output speed, air volume and air speed.

[0012] S700 controls the cleaning machine based on the first cleaning parameter data and the second cleaning parameter data.

[0013] The present invention also provides a cleaning machine control device, which includes:

[0014] The data acquisition module is used to acquire, based on the built-in acquisition device in the cleaning machine, a video of the cleaning process of the object to be cleaned during a first preset time period, and N images of the cleaning process of the object to be cleaned during a second preset time period. Here, N is an integer greater than 0. The first preset time period refers to the time period from P preset time units before the current time point to the current time point, where P is an integer greater than 0. The second preset time period refers to the time period from the initial time point to Q preset time units after the initial time point. The initial time point refers to the time when the cleaning machine closes after the object to be cleaned enters the machine, where Q is an integer greater than 0.

[0015] The body shape analysis module is used to obtain the body shape parameter data of the object to be cleaned based on N images of the cleaning process.

[0016] The first parameter acquisition module is used to obtain the first cleaning parameter data of the cleaning machine based on the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0017] The behavior recognition module is used to input the video of the cleaning process into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned.

[0018] The status analysis module is used to obtain the cleaning status type of the object to be cleaned based on its movement speed and behavior. The cleaning status types include stationary state, normal state, abnormal state, and violent state.

[0019] The second parameter acquisition module is used to set the second cleaning parameter data of the cleaning machine according to the cleaning status type. The second cleaning parameters include water output, water output speed, air volume, and air speed.

[0020] The cleaning machine control module is used to control the cleaning machine based on the first cleaning parameter data and the second cleaning parameter data.

[0021] The present invention also provides a non-transitory computer-readable storage medium storing at least one instruction or at least one program, wherein the at least one instruction or at least one program is loaded and executed by a processor to implement the above-described cleaning machine control method.

[0022] The present invention also provides an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0023] The present invention has at least the following beneficial effects: Based on the built-in acquisition device in the cleaning machine, a video of the cleaning process of the object to be cleaned during a first preset time period and N images of the cleaning process of the object to be cleaned during a second preset time period are acquired. Based on the N images, the body shape parameter data of the object to be cleaned is obtained. Based on the body shape parameter data and a preset parameter reference table, the first cleaning parameter data of the cleaning machine is obtained. By analyzing the images of the object to be cleaned during the initial period after entering the cleaning machine, the accuracy of the first cleaning parameter data is improved, thereby improving the cleaning effect. The cleaning process video is input into a preset behavior recognition model to obtain the movement speed and behavioral posture of the object to be cleaned. Based on the movement speed and behavioral posture, the cleaning state type of the object to be cleaned is obtained. Based on the cleaning state type, the second cleaning parameter data of the cleaning machine is set. The cleaning machine is controlled based on the first and second cleaning parameter data. Based on the cleaning process video of a period prior to the current time point, the movement speed and behavioral posture of the object to be cleaned at the current time are analyzed, improving the accuracy of the second cleaning parameter data. Thus, while achieving a highly efficient cleaning effect, the comfort of the object to be cleaned is ensured. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a cleaning machine control method provided in Embodiment 1 of the present invention;

[0026] Figure 2This is a schematic diagram of the structure of a cleaning machine control device provided in Embodiment 2 of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0029] Example 1

[0030] This embodiment provides a cleaning machine control method, which includes the following steps: Figure 1 As shown:

[0031] S100: Based on the built-in acquisition device in the cleaning machine, acquire the cleaning process video of the object to be cleaned during the first preset time period, and N cleaning process images of the object to be cleaned during the second preset time period, where N is an integer greater than 0, the first preset time period refers to the time period from P preset time units before the current time point to the current time point, where P is an integer greater than 0, the second preset time period refers to the time period from the initial time point to Q preset time units after the initial time point, the initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the machine, where Q is an integer greater than 0.

[0032] The items to be cleaned can refer to animals such as cats and dogs. The cleaning machine is used to clean and dry the items placed inside the machine. By controlling the rinsing angle range, rinsing height, water volume, and water speed of the cleaning machine, different degrees of cleaning can be achieved for the items to be cleaned. By controlling the blowing angle range, blowing height, blowing volume, and blowing speed of the cleaning machine, different degrees of drying can be achieved for the items to be cleaned.

[0033] The cleaning machine has a built-in data acquisition device, such as a camera, to capture video of the items being cleaned during the cleaning process. This data is then analyzed to determine the cleaning status of the items and to adjust the machine's parameters accordingly, thereby improving the comfort of the items being cleaned.

[0034] The first preset time period refers to the time period from P preset units of time before the current time point to the current time point. In other words, the first preset time period is a period of time before the current time point. As the data basis for analyzing the current state of the item to be cleaned, the parameters of the cleaning machine can be adjusted in a timely manner according to the current state of the item to be cleaned, thereby improving the comfort of the item to be cleaned throughout the cleaning process.

[0035] The second preset time period refers to the time period from the initial time point to Q preset time units after the initial time point. The initial time point refers to the time when the cleaning machine closes after the item to be cleaned enters the machine. In other words, the second preset time period is the period when the item to be cleaned has just entered the machine. At this time, the item to be cleaned has not yet undergone the cleaning and drying stages, and the state of the item to be cleaned is relatively stable. As a basis for measuring the size of the item to be cleaned, it can improve the accuracy of size acquisition, thereby improving the accuracy of parameter control of the cleaning machine, and thus improving the cleaning effect and comfort of the item to be cleaned.

[0036] The specific values ​​of the preset unit time, P, and Q can be set by the implementer according to the actual situation.

[0037] In one specific embodiment, S100 further includes the following steps:

[0038] S110: Based on the acquisition device, the initial cleaning video of the object to be cleaned within the second preset time period is obtained.

[0039] S120, the initial cleaning video is segmented into frames according to the frame rate of the acquisition device to obtain M initial cleaning images corresponding to the initial cleaning video, where M≥N.

[0040] S130: For any initial cleaning image, obtain the first bounding box corresponding to the object to be cleaned in the current initial cleaning image.

[0041] S140, if the position of the first bounding box is within the preset position range of the current initial cleaning image, then the current initial cleaning image is determined as the cleaning process image.

[0042] S150: Traverse the M initial cleaned images to obtain N cleaned process images.

[0043] Since the object to be cleaned may move, run, or jump in the cleaning machine, its position may be different in different initial cleaning images. In order to improve the accuracy of the analysis of the object's shape, this embodiment filters M initial cleaning images and selects images in which the object appears within a preset position range as cleaning process images to analyze the object's shape information.

[0044] Specifically, the first bounding box corresponding to the object to be cleaned in each initial cleaning image is obtained based on the minimum bounding box algorithm. The initial cleaning images are then filtered by comparing the position of the first bounding box with a preset position range.

[0045] Those skilled in the art will know that any minimum bounding box algorithm in the prior art falls within the protection scope of this invention, and will not be elaborated further here.

[0046] As described above, based on the comparison between the first bounding box corresponding to the object to be cleaned and the preset position range in each initial cleaning image, N cleaning process images are selected from M initial cleaning images as the basis for analyzing the body shape information of the object to be cleaned, thereby improving the accuracy of obtaining the body shape parameter data of the object to be cleaned.

[0047] In one specific embodiment, the number of pixel columns in the current initial cleaned image is w, the number of pixel rows in the current initial cleaned image is h, and a coordinate system in pixels is established with the upper left corner of the current initial cleaned image as the origin. S140 further includes the following steps:

[0048] S141, Based on the coordinate system, obtain the first preset point A, the second preset point B, the third preset point C, and the fourth preset point D corresponding to the current initial cleaning image. The coordinates of the first preset point A are (β×w, α×h), the coordinates of the second preset point B are ((1-β)×w, α×h), the coordinates of the third preset point C are ((1-β)×w, (1-α)×h), and the coordinates of the fourth preset point D are (β×w, (1-α)×h). β refers to the preset column reduction coefficient, and α refers to the preset row reduction coefficient.

[0049] S142, In the current initial cleaning image, the rectangular range formed by the first preset point A, the second preset point B, the third preset point C and the fourth preset point D are determined as the preset position range of the current initial cleaning image.

[0050] The preset position range is the position range of a part of the initial cleaning image. Based on this, the objects to be cleaned in the selected cleaning process images are not occluded, and the complete shape information of the objects to be cleaned can be analyzed.

[0051] The specific values ​​of β and α can be set by the implementer according to the actual situation.

[0052] As described above, by obtaining the preset position range based on A, B, C, and D, the object to be cleaned in the filtered cleaning process image is not obscured, and the complete body shape information of the object to be cleaned can be analyzed, thereby improving the accuracy of obtaining the body shape parameter data of the object to be cleaned.

[0053] S200: Based on N images of the cleaning process, obtain the shape parameter data of the object to be cleaned.

[0054] In one specific embodiment, S200 further includes the following steps:

[0055] S210: Based on the acquisition device, obtain the distance between each cleaning process image and the acquisition device.

[0056] S220: For any cleaning process image, obtain the area of ​​the first bounding box in the current cleaning process image.

[0057] S230: Based on the area and distance, obtain the body shape score corresponding to the object to be cleaned in the current cleaning process image.

[0058] S240: Traverse N images of the cleaning process to obtain N body size scores corresponding to the object to be cleaned.

[0059] S250, the average value of the N body shape scores is used as the body shape parameter data of the object to be cleaned.

[0060] Among them, the greater the distance between the cleaning process image and the acquisition device and the area of ​​the first bounding box, the larger the size of the object to be cleaned.

[0061] In one specific implementation, the body shape score corresponding to the object to be cleaned in the i-th cleaning process image meets the following condition:

[0062] F i =(D i / D 0 )×((2 / (e^(-S i )))-1), where F i D refers to the body shape score of the object to be cleaned in the i-th cleaning process image. i D refers to the distance between the image of the i-th cleaning process and the acquisition device. 0 This refers to the maximum distance between the data collection device and the cleaning machine, S. i It refers to the area of ​​the first bounding box in the i-th cleaning process image, e is a natural constant, i = 1, 2, ..., N, and N is the total number of cleaning process images.

[0063] As described above, based on the area and distance, the body shape score corresponding to the object to be cleaned in the current cleaning process image is obtained, thereby obtaining the body shape parameter data of the object to be cleaned, which improves the accuracy of the body shape parameter data.

[0064] S300 obtains the first cleaning parameter data of the cleaning machine based on the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0065] In the preset parameter comparison table, the larger the body size parameter, the greater the corresponding rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0066] The above-mentioned method, based on the shape parameter data of the object to be cleaned, retrieves the first cleaning parameter data of the cleaning machine from a preset parameter reference table, thereby improving the accuracy of the first cleaning parameter data and enhancing the cleaning and drying effect of the object to be cleaned.

[0067] The S400 inputs the video of the cleaning process into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned.

[0068] The preset behavior recognition model includes an encoder and a decoder. The encoder is used to extract features from the video of the cleaning process, and the decoder is used to analyze the extracted features and output the moving speed and behavior posture of the object to be cleaned. This is used to characterize the behavior information of the object to be cleaned for a period of time before the current time point and to analyze the current state of the object to be cleaned.

[0069] To improve the accuracy of acquiring movement speed and behavioral posture, the behavior recognition model can be pre-trained, and the cleaning process video can be processed based on the trained behavior recognition model. The training process of the behavior recognition model will not be elaborated here.

[0070] As described above, feature extraction and analysis are performed on the video of the cleaning process based on the preset behavior recognition model to obtain the moving speed and behavioral posture of the object to be cleaned. This information is used to characterize the behavior of the object to be cleaned over a period of time prior to the current point in time. By analyzing the current state of the object to be cleaned, the parameters of the cleaning machine can be adjusted in a timely manner based on the current state of the object, thereby improving the comfort of the object to be cleaned throughout the entire cleaning process.

[0071] S500 obtains the cleaning status type of the object to be cleaned based on its movement speed and behavior posture. The cleaning status types include stationary state, normal state, abnormal state, and violent state.

[0072] In one specific embodiment, the behavioral posture includes stable posture and unstable posture, and S500 further includes the following steps:

[0073] S510, if the moving speed is equal to the first preset speed threshold, then the cleaning state type of the object to be cleaned is determined to be a stationary state.

[0074] S520, if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is a stable posture, then the cleaning state type of the object to be cleaned is determined to be normal state.

[0075] S530, if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is an unstable posture, then the cleaning state type of the object to be cleaned is determined to be an abnormal state.

[0076] S540, if the moving speed is greater than the second preset speed threshold and the behavior posture is a stable posture, then the cleaning state type of the object to be cleaned is determined to be an abnormal state.

[0077] S550, if the moving speed is greater than the second preset speed threshold and the behavior posture is an unstable posture, then the cleaning state type of the object to be cleaned is determined to be a violent state.

[0078] The specific values ​​of the first preset speed threshold and the second preset speed threshold can be set by the implementer according to the actual situation. For example, the first preset speed threshold can be zero.

[0079] Stable posture can refer to the object being cleaned being in a sitting, standing, or lying position, while unstable posture can refer to the object being cleaned being in a running or jumping position.

[0080] Based on the movement speed and behavior, the cleaning status type of the object to be cleaned is obtained. Based on the current status of the object, the cleaning parameters of the cleaning machine can be controlled in a timely manner, thereby improving the comfort of the object throughout the cleaning process.

[0081] S600 sets the second cleaning parameter data of the cleaning machine according to the cleaning status type. The second cleaning parameters include water output, water output speed, air volume and air speed.

[0082] In one specific embodiment, S600 further includes the following steps:

[0083] S610, if the cleaning state type of the object to be cleaned is a static state or a violent state, then set the second cleaning parameter data of the cleaning machine to zero.

[0084] S620, if the cleaning status of the object to be cleaned is normal, the second cleaning parameter data of the cleaning machine is set to remain unchanged.

[0085] S630, if the cleaning status of the object to be cleaned is abnormal, the water output, water output speed, air volume and air speed of the cleaning machine will be reduced according to the preset ratio.

[0086] The specific value of the preset ratio can be set by the implementer according to the actual situation. For example, the preset ratio can be 20%, 50%, 80%, etc.

[0087] When the cleaning status of the item to be cleaned is abnormal, the water output, water output speed, air volume, and air speed of the cleaning machine are reduced according to a preset ratio to reduce the stimulation of the item to be cleaned by the water and air in the cleaning machine.

[0088] The above-mentioned second cleaning parameter data of the cleaning machine is set according to the cleaning status type, which improves the comfort of the cleaning items throughout the cleaning process.

[0089] S700 controls the cleaning machine based on the first cleaning parameter data and the second cleaning parameter data.

[0090] In one specific embodiment, S700 further includes the following steps:

[0091] S710: If the second cleaning parameter data of the cleaning machine is equal to zero, then the cleaning machine is turned off.

[0092] S720, if the second cleaning parameter data of the cleaning machine is greater than zero, then the rinsing angle range, rinsing height, blowing angle range and blowing height of the cleaning machine are controlled according to the first cleaning parameter data, and the water output, water output speed, air volume and air speed of the cleaning machine are controlled according to the second cleaning parameter data.

[0093] If the second cleaning parameter data of the cleaning machine is equal to zero, that is, the cleaning state type of the object to be cleaned is a static state or a violent state, the cleaning machine is turned off so that the cleaning machine staff or relevant personnel can check the condition of the object to be cleaned.

[0094] As described above, the cleaning machine acquires a video of the cleaning process of the object to be cleaned during a first preset time period, and N images of the object during a second preset time period, based on the built-in acquisition device. From these N images, the object's body shape parameters are obtained. Using these body shape parameters and a preset parameter lookup table, the machine's first cleaning parameter data is obtained. Analyzing the object's body shape using images from the initial period after entering the machine improves the accuracy of the first cleaning parameter data, thus enhancing the cleaning effect. The cleaning process video is input into a preset behavior recognition model to obtain the object's movement speed and posture. Based on these, the cleaning state type is determined. The machine's second cleaning parameter data is set based on the cleaning state type. The machine is controlled based on both the first and second cleaning parameter data. Analyzing the object's movement speed and posture from cleaning process videos from a period prior to the current time improves the accuracy of the second cleaning parameter data, thereby ensuring both efficient cleaning and the object's comfort.

[0095] Example 2

[0096] This second embodiment provides a cleaning machine control device, which includes, for example: Figure 2 As shown:

[0097] The data acquisition module 21 is used to acquire, according to the built-in acquisition device in the cleaning machine, a video of the cleaning process of the object to be cleaned during a first preset time period, and N images of the cleaning process of the object to be cleaned during a second preset time period. Here, N is an integer greater than 0, the first preset time period refers to the time period from P preset units of time before the current time point to the current time point, where P is an integer greater than 0, and the second preset time period refers to the time period from the initial time point to Q preset units of time after the initial time point. The initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the cleaning machine, where Q is an integer greater than 0.

[0098] The body shape analysis module 22 is used to obtain the body shape parameter data of the object to be cleaned based on N images of the cleaning process.

[0099] The first parameter acquisition module 23 is used to acquire the first cleaning parameter data of the cleaning machine based on the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0100] The behavior recognition module 24 is used to input the video of the cleaning process into the preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned.

[0101] The state analysis module 25 is used to obtain the cleaning state type of the object to be cleaned based on the movement speed and behavior posture. The cleaning state types include stationary state, normal state, abnormal state and violent state.

[0102] The second parameter acquisition module 26 is used to set the second cleaning parameter data of the cleaning machine according to the cleaning status type. The second cleaning parameters include water output, water output speed, air volume and air speed.

[0103] The cleaning machine control module 27 is used to control the cleaning machine according to the first cleaning parameter data and the second cleaning parameter data.

[0104] In one specific embodiment, the data acquisition module 21 further includes:

[0105] The video acquisition submodule is used to acquire the initial cleaning video of the object to be cleaned within a second preset time period, based on the acquisition device.

[0106] The image acquisition submodule is used to perform frame segmentation processing on the initial cleaning video according to the frame rate corresponding to the acquisition device, and obtain M initial cleaning images corresponding to the initial cleaning video, where M≥N.

[0107] The bounding box acquisition submodule is used to obtain the first bounding box corresponding to the object to be cleaned in the current initial cleaning image for any initial cleaning image.

[0108] The image filtering submodule is used to determine the current initial cleaning image as the cleaning process image if the position of the first bounding box is within a preset position range of the current initial cleaning image.

[0109] The image traversal submodule is used to traverse M initial cleaning images and obtain N cleaning process images.

[0110] In one specific implementation, the number of pixel columns in the current initial cleaned image is w, the number of pixel rows in the current initial cleaned image is h, and a coordinate system in pixels is established with the top left corner of the current initial cleaned image as the origin. The image filtering submodule further includes:

[0111] The preset point acquisition unit is used to acquire the first preset point A, the second preset point B, the third preset point C, and the fourth preset point D corresponding to the current initial cleaning image according to the coordinate system. The coordinates of the first preset point A are (β×w, α×h), the coordinates of the second preset point B are ((1-β)×w, α×h), the coordinates of the third preset point C are ((1-β)×w, (1-α)×h), and the coordinates of the fourth preset point D are (β×w, (1-α)×h). β refers to the preset column reduction coefficient, and α refers to the preset row reduction coefficient.

[0112] The preset position range acquisition unit is used to determine the rectangular range formed by the first preset point A, the second preset point B, the third preset point C and the fourth preset point D in the current initial cleaning image as the preset position range of the current initial cleaning image.

[0113] In one specific embodiment, the body shape analysis module 22 further includes:

[0114] The distance acquisition submodule is used to obtain the distance between each cleaning process image and the acquisition device, based on the acquisition device.

[0115] The area acquisition submodule is used to obtain the area of ​​the first bounding box in any cleaning process image.

[0116] The first body size score submodule is used to obtain the body size score of the object to be cleaned in the current cleaning process image based on its area and distance.

[0117] The second body size score submodule is used to traverse N images of the cleaning process and obtain the N body size scores corresponding to the object to be cleaned.

[0118] The body shape parameter data acquisition submodule is used to determine the average of N body shape scores as the body shape parameter data of the object to be cleaned.

[0119] In one specific implementation, the behavioral pose includes stable pose and unstable pose, and the state analysis module 25 further includes:

[0120] The first state analysis submodule is used to determine the cleaning state type of the object to be cleaned as a stationary state if the moving speed is equal to the first preset speed threshold.

[0121] The second state analysis submodule is used to determine the cleaning state type of the object to be cleaned as normal if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is a stable posture.

[0122] The third state analysis submodule is used to determine the cleaning state type of the object to be cleaned as an abnormal state if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is an unstable posture.

[0123] The fourth state analysis submodule is used to determine the cleaning state type of the object to be cleaned as an abnormal state if the moving speed is greater than the second preset speed threshold and the behavior posture is a stable posture.

[0124] The fifth state analysis submodule is used to determine the cleaning state type of the object to be cleaned as a violent state if the moving speed is greater than the second preset speed threshold and the behavior posture is an unstable posture.

[0125] In one specific embodiment, the second parameter acquisition module 26 further includes:

[0126] The first parameter acquisition submodule is used to set the second cleaning parameter data of the cleaning machine to zero if the cleaning state type of the object to be cleaned is static or violent.

[0127] The second parameter acquisition submodule is used to set the second cleaning parameter data of the cleaning machine to remain unchanged if the cleaning status type of the object to be cleaned is normal.

[0128] The third parameter acquisition submodule is used to reduce the water output, water output speed, air volume, and air speed of the cleaning machine according to a preset ratio if the cleaning status of the object to be cleaned is an abnormal state.

[0129] In one specific embodiment, the cleaning machine control module 27 further includes:

[0130] The first control submodule is used to shut down the cleaning machine if the second cleaning parameter data of the cleaning machine is equal to zero.

[0131] The second control submodule is used to control the rinsing angle range, rinsing height, blowing angle range, and blowing height of the cleaning machine according to the first cleaning parameter data if the second cleaning parameter data of the cleaning machine is greater than zero, and to control the water output, water output speed, air volume, and air speed of the cleaning machine according to the second cleaning parameter data.

[0132] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0133] Example 3

[0134] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, which stores at least one instruction or at least one program segment, wherein the at least one instruction or at least one program segment is loaded and executed by a processor to implement the following steps:

[0135] S100: Based on the built-in acquisition device in the cleaning machine, acquire the cleaning process video of the object to be cleaned during the first preset time period, and N cleaning process images of the object to be cleaned during the second preset time period, where N is an integer greater than 0, the first preset time period refers to the time period from P preset time units before the current time point to the current time point, where P is an integer greater than 0, the second preset time period refers to the time period from the initial time point to Q preset time units after the initial time point, the initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the machine, where Q is an integer greater than 0.

[0136] S200: Based on N images of the cleaning process, obtain the shape parameter data of the object to be cleaned.

[0137] S300 obtains the first cleaning parameter data of the cleaning machine based on the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range, and blowing height.

[0138] The S400 inputs the video of the cleaning process into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned.

[0139] S500 obtains the cleaning status type of the object to be cleaned based on its movement speed and behavior posture. The cleaning status types include stationary state, normal state, abnormal state, and violent state.

[0140] S600 sets the second cleaning parameter data of the cleaning machine according to the cleaning status type. The second cleaning parameters include water output, water output speed, air volume and air speed.

[0141] S700 controls the cleaning machine based on the first cleaning parameter data and the second cleaning parameter data.

[0142] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0143] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0144] Example 4

[0145] Embodiment 4 of the present invention provides an electronic device, which includes a processor and a non-transitory computer-readable storage medium as described in Embodiment 3 of the present invention.

[0146] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for controlling a cleaning machine, characterized in that, The cleaning machine control method includes the following steps: S100, according to the built-in acquisition device in the cleaning machine, acquire the cleaning process video of the object to be cleaned within a first preset time period, and N cleaning process images of the object to be cleaned within a second preset time period, where N is an integer greater than 0, the first preset time period refers to the time period from P preset units of time before the current time point to the current time point, where P is an integer greater than 0, the second preset time period refers to the time period from the initial time point to Q preset units of time after the initial time point, where the initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the cleaning machine, where Q is an integer greater than 0; S200, based on the N images of the cleaning process, obtain the body shape parameter data of the object to be cleaned; S300, based on the body shape parameter data and the preset parameter comparison table, the first cleaning parameter data of the cleaning machine is obtained, wherein the preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters, and the first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range and blowing height; S400, the video of the cleaning process is input into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned; S500, based on the moving speed and the behavior posture, obtain the cleaning state type of the object to be cleaned, wherein the cleaning state type includes a stationary state, a normal state, an abnormal state, and a violent state. S600, according to the cleaning state type, set the second cleaning parameter data of the cleaning machine, wherein the second cleaning parameters include water output, water output speed, air volume and air speed; S700, control the cleaning machine according to the first cleaning parameter data and the second cleaning parameter data.

2. The cleaning machine control method according to claim 1, characterized in that, S100 also includes the following steps: S110, according to the acquisition device, the initial cleaning video of the object to be cleaned within a second preset time period is obtained; S120, the initial cleaning video is segmented into frames according to the frame rate corresponding to the acquisition device to obtain M initial cleaning images corresponding to the initial cleaning video, where M≥N; S130, for any initial cleaning image, obtain the first bounding box corresponding to the object to be cleaned in the current initial cleaning image; S140, if the position of the first bounding box is within the preset position range of the current initial cleaning image, then the current initial cleaning image is determined as the cleaning process image; S150: Traverse the M initial cleaned images to obtain N cleaned process images.

3. The cleaning machine control method according to claim 2, characterized in that, The number of pixel columns in the current initial cleaned image is w, and the number of pixel rows in the current initial cleaned image is h. A coordinate system in pixels is established with the top left corner of the current initial cleaned image as the origin. S140 also includes the following steps: S141, according to the coordinate system, obtain the first preset point A, the second preset point B, the third preset point C and the fourth preset point D corresponding to the current initial cleaning image, wherein the coordinates of the first preset point A are (β×w, α×h), the coordinates of the second preset point B are ((1-β)×w, α×h), the coordinates of the third preset point C are ((1-β)×w, (1-α)×h), and the coordinates of the fourth preset point D are (β×w, (1-α)×h), where β refers to the preset column reduction coefficient and α refers to the preset row reduction coefficient; S142, in the current initial cleaning image, the rectangular range formed by the first preset point A, the second preset point B, the third preset point C and the fourth preset point D are determined as the preset position range of the current initial cleaning image.

4. The cleaning machine control method according to claim 2, characterized in that, S200 also includes the following steps: S210, Based on the acquisition device, the distance between each cleaning process image and the acquisition device is obtained; S220, for any cleaning process image, obtain the area of ​​the first bounding box in the current cleaning process image; S230, based on the area and the distance, obtain the body size score corresponding to the object to be cleaned in the current cleaning process image; S240, Traverse N images of the cleaning process to obtain N body size scores corresponding to the object to be cleaned; S250, the average value of the N body shape scores is determined as the body shape parameter data of the object to be cleaned.

5. The cleaning machine control method according to claim 1, characterized in that, The behavioral posture includes stable posture and unstable posture, and S500 also includes the following steps: S510, if the moving speed is equal to the first preset speed threshold, then the cleaning state type of the object to be cleaned is determined to be a stationary state. S520, if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is a stable posture, then the cleaning state type of the object to be cleaned is determined to be normal state. S530, if the moving speed is greater than the first preset speed threshold and less than or equal to the second preset speed threshold, and the behavior posture is an unstable posture, then the cleaning state type of the object to be cleaned is determined to be an abnormal state. S540, if the moving speed is greater than the second preset speed threshold and the behavior posture is a stable posture, then the cleaning state type of the object to be cleaned is determined to be an abnormal state. S550, if the moving speed is greater than the second preset speed threshold and the behavior posture is an unstable posture, then the cleaning state type of the object to be cleaned is determined to be a violent state.

6. The cleaning machine control method according to claim 5, characterized in that, The S600 also includes the following steps: S610, if the cleaning state type of the object to be cleaned is a static state or a violent state, then the second cleaning parameter data of the cleaning machine is set to zero. S620, if the cleaning state type of the object to be cleaned is normal, then the second cleaning parameter data of the cleaning machine is set to remain unchanged; S630, if the cleaning state type of the object to be cleaned is an abnormal state, then reduce the water output, water output speed, air volume and air speed of the cleaning machine according to a preset ratio.

7. The cleaning machine control method according to claim 6, characterized in that, The S700 also includes the following steps: S710, if the second cleaning parameter data of the cleaning machine is equal to zero, then the cleaning machine is turned off; S720, if the second cleaning parameter data of the cleaning machine is greater than zero, then the rinsing angle range, rinsing height, blowing angle range and blowing height of the cleaning machine are controlled according to the first cleaning parameter data, and the water output, water output speed, air volume and blowing speed of the cleaning machine are controlled according to the second cleaning parameter data.

8. A cleaning machine control device, characterized in that, The cleaning machine control device includes: The data acquisition module is used to acquire, according to the built-in acquisition device in the cleaning machine, a video of the cleaning process of the object to be cleaned within a first preset time period, and N images of the cleaning process of the object to be cleaned within a second preset time period, where N is an integer greater than 0, the first preset time period refers to the time period from P preset units of time before the current time point to the current time point, where P is an integer greater than 0, the second preset time period refers to the time period from the initial time point to Q preset units of time after the initial time point, where the initial time point refers to the time point when the cleaning machine closes after the object to be cleaned enters the machine, where Q is an integer greater than 0; The body shape analysis module is used to obtain the body shape parameter data of the object to be cleaned based on the N images of the cleaning process. The first parameter acquisition module is used to acquire the first cleaning parameter data of the cleaning machine according to the body shape parameter data and the preset parameter comparison table. The preset parameter comparison table includes the comparison relationship between the body shape parameters and the first cleaning parameters. The first cleaning parameters include the rinsing angle range, rinsing height, blowing angle range and blowing height. The behavior recognition module is used to input the video of the cleaning process into a preset behavior recognition model to obtain the moving speed and behavior posture of the object to be cleaned; The state analysis module is used to obtain the cleaning state type of the object to be cleaned based on the moving speed and the behavior posture, wherein the cleaning state type includes a stationary state, a normal state, an abnormal state, and a violent state. The second parameter acquisition module is used to set the second cleaning parameter data of the cleaning machine according to the cleaning state type, wherein the second cleaning parameters include water output, water output speed, air volume and air speed. The cleaning machine control module is used to control the cleaning machine according to the first cleaning parameter data and the second cleaning parameter data.

9. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the cleaning machine control method as described in any one of claims 1-7.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images