Battery detection method and device of visual doorbell, electronic equipment and storage medium

Abstract

The invention discloses a battery detection method and device for a visual doorbell, electronic equipment and a storage medium, and relates to the technical field of smart home, and the method comprises the steps: obtaining the door closing habit strength of a door opening object, the actual door closing strength of the object, and obtaining the door closing environment wind power when the door opening is detected; the door closing environment wind power comprises absolute wind power and wind power direction; determining the loosening action quantity of a battery of the visual doorbell under the action of the actual door closing force of the object and the door closing environment wind power; based on the loosening action amount and the door closing habit force, the door closing remaining times before the visual doorbell fails are determined; and outputting a battery loosening failure prompt under the condition that the remaining door closing frequency is smaller than a preset frequency threshold value. The technical problem of doorbell failure caused by battery loosening is solved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to a battery detection method, device, electronic device and storage medium for a video doorbell. Background Art

[0002] In the field of smart home and security, doorbells are an important communication and alarm device, and their stability and reliability are crucial to improving residential safety and convenience. Traditional doorbell systems are mostly powered by batteries. In daily use, due to frequent door opening and closing actions, especially when the door is closed too hard, it often impacts the doorbell device installed on the door, causing the battery casing to loosen. This looseness may affect the contact stability between the battery and the doorbell circuit board, which may cause the doorbell to fail.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a battery detection method, device, electronic device and storage medium for a video doorbell, aiming to solve the technical problem of doorbell failure caused by loose batteries.

[0005] To achieve the above-mentioned purpose, the present application provides a battery detection method for a video doorbell, comprising: when detecting that a door is opened, obtaining the habitual force of the door-opening object to close the door, the actual force of the door-closing object to close the door, and obtaining the wind force of the door-closing environment, wherein the wind force of the door-closing environment includes the absolute wind force and the wind force direction;

[0006] Determine the amount of loosening of the battery of the video doorbell under the actual force of the object closing the door and the wind force of the closing environment;

[0007] Based on the loosening action amount and the door closing habit strength, determining the remaining number of door closing times of the video doorbell before failure;

[0008] When the remaining number of door closing times is less than a preset number threshold, a battery loose failure prompt is output.

[0009] In one embodiment, when the door opening is detected, the step of obtaining the door closing habitual force of the door opening object comprises:

[0010] In the case of detecting a door opening, detecting a door opening type, wherein the door opening type includes an outside door opening type and an inside door opening type;

[0011] Acquire a target image outside the door corresponding to the door opening type, and determine facial features of a person outside the door in the target image outside the door;

[0012] When there is a target resident's facial feature corresponding to the facial feature of the person outside the door in the preset door-opening person database, the door-closing habitual strength of the door-opening object is determined based on the habitual strength data carried by the facial feature of the target resident;

[0013] When the target resident's facial features corresponding to the facial features of the person outside the door do not exist in the preset door-opening person database, the door-closing habit strength is determined based on the facial features of the person outside the door and the target door-opening image.

[0014] In one embodiment, when there is a target resident face feature corresponding to the face feature outside the door in the preset door-opening person database, the step of determining the door-closing habitual force of the door-opening object based on the habitual force data carried by the face feature of the target resident includes:

[0015] When the number of the facial features outside the door is greater than the preset single person threshold, and there are target facial features corresponding to multiple facial features outside the door in the preset door-opening person database, the average value of the habit strength data carried by each of the target facial features is used as the door-closing habit strength;

[0016] When the number of target facial features existing in the preset door-opening person database is equal to the preset single-person threshold, the habitual strength data carried by the target resident facial features is used as the door-closing habitual strength.

[0017] In one embodiment, when there is no target resident facial feature corresponding to the facial feature of the person outside the door in the preset door-opening person database, the step of determining the door-closing habit strength based on the facial feature of the person outside the door and the target door-opening image includes:

[0018] When there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is equal to the preset single-person threshold, calling a preset strength prediction model, identifying the gender type of the facial feature outside the door and determining the gender strength coefficient corresponding to the gender type, and extracting an initial human body contour from the target door-outside image;

[0019] Based on the acquired temperature of the day, determining a clothing coverage thickness coefficient, and adjusting the initial human body contour to obtain an actual human body contour according to the clothing coverage thickness coefficient, and determining a human body strength coefficient corresponding to the actual human body contour;

[0020] The gender strength coefficient and the human body strength coefficient are weighted and summed to obtain the habitual strength coefficient;

[0021] The product of the habitual force coefficient and the preset standard force is used as the door closing habitual force;

[0022] If there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is greater than the preset single-person threshold, the preset habit strength will be used as the door-closing habit strength.

[0023] In one embodiment, the step of obtaining the wind force in the closed door environment includes:

[0024] Acquire the wind force inside the door acquired by a first pressure sensor disposed inside the door, and acquire the wind force outside the door acquired by a second pressure sensor disposed outside the door;

[0025] Determine the absolute value of the difference between the wind force inside the door and the wind force outside the door as the absolute wind force;

[0026] Determine the wind direction according to the wind force inside the door and the wind force outside the door;

[0027] The wind direction and absolute wind force are used as the closed-door environment wind force.

[0028] In one embodiment, the step of determining the amount of loosening of the battery of the video doorbell under the influence of the actual force of the object closing the door and the wind force of the closing environment comprises:

[0029] Finding the absolute force coefficient of the absolute wind force in a preset wind force coefficient mapping relationship;

[0030] In the case where the wind direction is the same as the preset door closing direction of the door closing habitual force, the sum of the absolute force coefficient and the preset standard action coefficient is used as the wind force positive action coefficient, the product of the door closing habitual force and the wind force positive action coefficient is used as the door closing force, and the loosening action amount corresponding to the door closing force is determined;

[0031] When the wind direction is opposite to the preset door closing direction of the door closing habitual force, the difference between the absolute force coefficient and the preset standard action coefficient is taken as the wind reaction coefficient, the product of the door closing habitual force and the wind reaction coefficient is taken as the door closing force, and the loosening action amount corresponding to the door closing force is determined.

[0032] In one embodiment, the step of determining the remaining number of door closing times of the video doorbell before failure based on the loosening action amount and the door closing habit strength comprises:

[0033] Aggregate the loosening action amount and the cumulative looseness degree of the battery stored in the video doorbell to obtain the current looseness degree of the battery;

[0034] The difference between the preset loose failure threshold and the current looseness of the battery is used as the remaining looseness;

[0035] When the looseness detection mode of the video doorbell is a single occupancy detection mode, the ratio of the remaining looseness amount to the door closing habitual force is used as the remaining number of door closing times;

[0036] When the looseness detection mode of the video doorbell is a multi-occupancy detection mode, obtaining historical looseness data of the door where the video doorbell is located, searching for multiple target historical looseness degrees similar to the current looseness degree of the battery from the historical looseness data, and the difference between the target historical looseness degree and the current looseness degree of the battery is less than a preset minimum similarity threshold;

[0037] For each of the target historical looseness degrees, searching the target historical failure degree corresponding to the target historical looseness degree in the historical looseness data, and counting the number of historical door closings between the target historical looseness degree and the corresponding target historical failure degree;

[0038] The average value of each of the historical door closing times is taken as the remaining door closing times.

[0039] In addition, to achieve the above-mentioned purpose, the present application also provides a visual doorbell detection device, the device comprising:

[0040] An acquisition module, for acquiring the habitual force of the door-opening object, the actual force of the door-closing object, and the wind force of the door-closing environment when the door opening is detected, wherein the wind force of the door-closing environment includes the absolute wind force and the wind direction;

[0041] A loosening prediction module, used to determine the loosening amount of the battery of the video doorbell under the influence of the actual force of the object closing the door and the wind force of the closing environment;

[0042] A remaining determination module, for determining the remaining number of door closing times of the video doorbell before failure based on the loosening action amount and the door closing habitual strength;

[0043] The prompt module is used to output a battery loose failure prompt when the remaining number of door closing times is less than a preset number threshold.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides an electronic device, which includes: a memory, a processor, and a program of the battery detection method of the video doorbell stored in the memory and executable on the processor. When the program of the battery detection method of the video doorbell is executed by the processor, the steps of the battery detection method of the video doorbell as described above can be implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer-readable storage medium, on which is stored a program for implementing the battery detection method of a video doorbell. When the program of the battery detection method of the video doorbell is executed by a processor, the steps of the battery detection method of the video doorbell as described above are implemented.

[0046] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the battery detection method for a video doorbell as described above.

[0047] One or more technical solutions proposed in the present application have at least the following technical effects: the present application can obtain the habitual force of the door-opening object, the actual force of the door-closing object, and the wind force of the door-closing environment when detecting the door opening, and the wind force of the door-closing environment includes the absolute wind force and the wind direction. Since the habitual force of closing the door corresponding to different door-opening objects may be different, the actual force of the object of different door-opening objects may also be different, and the corresponding absolute wind force and wind direction when closing the door may be different. When the actual force of the object closing the door and the wind force of the door closing environment are different, the impact on the video doorbell on the door when closing the door is also different. Therefore, the present application predicts the loosening effect of the battery of the video doorbell under the influence of the actual force of the object closing the door and the wind force of the closing environment, and then determines the remaining number of closing times of the video doorbell before failure through the loosening effect and the habitual force of closing the door. Since the habitual force of closing the door can be used to describe the habitual closing force of the object opening the door, and the actual force of the object closing the door is expressed as the single force of the object opening the door, the remaining number of closing times is determined by combining the habitual force of closing the door and the loosening effect, which can improve the accuracy of the preset remaining number of closing times and avoid the situation where the remaining number of closing times is inaccurate due to the actual force of the object closing the door being too small or too large. Furthermore, when the remaining number of closing times is less than the preset number threshold, a battery loose failure prompt can be output, so that the battery of the video doorbell can be output before the battery loosens and fails due to the impact of closing the door, etc., so as to prompt the user to adjust the battery of the video doorbell and avoid the failure of the video doorbell due to loose batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 This is a flow chart of an embodiment of a battery detection method for a video doorbell of the present application;

[0051] Figure 2 A flowchart of another embodiment of the battery detection method of the video doorbell of the present application;

[0052] Figure 3 A schematic diagram of a scenario of an example of a battery detection method for a video doorbell of the present application;

[0053] Figure 4 This is a schematic diagram of the structure of a visual doorbell detection device according to an embodiment of the present application;

[0054] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the battery detection method of the video doorbell in the embodiment of the present application.

[0055] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] Based on this, the embodiment of the present application provides a battery detection method for a video doorbell, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of a battery detection method for a video doorbell of the present application. The method includes steps S10 to S40:

[0059] Step S10, when the door opening is detected, obtaining the closing force of the door opening object, the actual closing force of the door opening object, and the wind force of the door closing environment, which includes the absolute wind force and the wind direction;

[0060] It should be noted that the execution subject of this embodiment may be a video doorbell, which may include a camera, and the camera may capture a video or image outside the door where the video doorbell is located. The door opening object is a user who opens the door where the video doorbell is located. When the door where the video doorbell is located is opened, there will be a door closing action, so when the door opening is detected, the door closing habit strength and the door closing environment wind force of the door opening object can be obtained.

[0061] The closing habit force is the force used by the door-opening object to close the door where the video doorbell is located. Different door-opening objects have different closing habit forces. The closing environment wind force is used to describe the size and direction of the wind when closing the door where the video doorbell is located. The closing environment wind force includes absolute wind force and wind direction. The absolute wind force is used to describe the size of the environmental wind force. If the absolute wind force is the same but the wind direction is different, the force applied to the door where the video doorbell is located when closing the door is also different. The actual closing force of the object is the actual force detected by the door-opening object when closing the door. The actual force of the object can be detected by the pressure sensor set on the door handle of the door where the video doorbell is located.

[0062] Exemplarily, when a door opening is detected, the door-closing habitual force of the door-opening subject and the actual door-closing force of the subject are obtained, and the wind force of the door-closing environment is detected.

[0063] In a feasible embodiment, step S10 further includes: steps S11 to S14:

[0064] Step S11, when a door opening is detected, detecting the door opening type, the door opening type includes an outside door opening type and an inside door opening type;

[0065] Step S12, obtaining a target door exterior image corresponding to the door opening type, and determining the face features of the person outside the door in the target door exterior image;

[0066] It should be noted that the door opening type outside the door is characterized by the door opening object opening the door inside the door, and the door opening type inside the door is characterized by the door opening object opening the door outside the door.

[0067] The target outside door image is the outside door image captured by the video doorbell. When the door opening type is the outside door opening type, the target outside door image can be the outside door image captured by the video doorbell within the preset time before the door opening. When the door opening type is the inside door opening type, the target outside door image can be the outside door image captured by the video doorbell within the preset time after the door opening. The preset time can be set based on actual conditions. Within the preset time, the video doorbell can capture a video with a preset time, and multiple target outside door images can be determined from the video.

[0068] The step of detecting the door opening may include: based on the built-in voice recognition device of the video doorbell, it can be used to identify whether the door where the video doorbell is located is open. The voice recognition device can be used to identify the door lock sound of the video doorbell. When the door is opened, the door lock will rotate and make a sound. For the same door, the sound of the door lock opening is basically the same, so the door lock sound can be identified by the voice recognition device to detect whether the door where the video doorbell is located is open. Since there is not only the sound of the door lock when closing the door, but also the sound of the door hitting the door frame, it may be difficult to identify the door lock sound when closing the door. Therefore, this embodiment detects whether the door is opened by identifying the door lock sound when opening the door. After opening the door, there will be a closing action. Therefore, by detecting the door opening, it is possible to obtain the closing habit strength and the wind force of the closing environment, etc.

[0069] Exemplarily, a preset voice recognition model can be configured in the voice recognition device, and the preset voice recognition model is obtained by training the neural network model. The preset voice recognition model can be used to recognize the sound of a door lock. The preset voice recognition model can monitor the sound of the door where the video doorbell is located. When the preset voice recognition model recognizes that the sound is the sound of a door lock, it determines that the door is open, and then the image outside the door captured within a preset time before the door is opened can be obtained, and the image outside the door captured within a preset time after the door is opened can also be obtained.

[0070] The preset voice recognition model can monitor the sound of the door where the video doorbell is located during the first preset period, and sleep during the second preset period to reduce the power consumption of the video doorbell. The first preset period can be set based on actual conditions. For example, the first preset period can include the period from 7:00 to 9:00 a.m. on weekdays, the period from 11:00 to 14:00 on weekdays, and the period from 18:00 to 20:00 on weekdays. This embodiment does not specifically limit this. The second preset period can include the period from 1:00 a.m. to 5:00 a.m. The first preset period and the second preset period can be set based on preset conditions.

[0071] The training process of the preset speech recognition model may include: obtaining a first training sample and a first model to be trained, the first model to be trained may be a neural network model, the first training sample includes a speech sample and a door lock sound label, the speech sample is input into the first model to be trained, the first model to be trained outputs the door lock sound feature, and the first training loss between the door lock sound feature and the door lock sound label is calculated. If the first training loss is less than the preset loss threshold, the first model to be trained is used as the preset speech recognition model. If the first training loss is greater than or equal to the preset loss threshold, the speech sample is re-acquired, and the first model to be trained is iteratively trained until the first training loss is less than the preset loss threshold to obtain the preset speech recognition model.

[0072] In the case of detecting a door opening, a method for detecting the door opening type may include, for example, based on a door handle pressure sensor provided on the door handle of the door where the video doorbell is located, the door handle includes an outside door handle and an inside door handle, and both the outside door handle and the inside door handle include pressure sensors. When a pressure value collected by the pressure sensor of the outside door handle is greater than a preset door opening pressure threshold before the door lock sound is detected, the door opening type is determined to be an outside door opening. When a pressure value collected by the pressure sensor of the inside door handle is greater than the preset door opening pressure threshold before the door lock sound is detected, the door opening type is determined to be an inside door opening.

[0073] When the door opening type is inner door opening, the pressure value collected by the inner door handle can be used as the actual door closing force of the object, or the average of the pressure values ​​collected by the inner door handle and the outer door handle can be used as the actual door closing force of the object.

[0074] When the door opening type is external door opening, the pressure value collected by the external door handle can be used as the actual door closing force of the object. Alternatively, the average of the pressure values ​​collected by the internal door handle and the external door handle can be used as the actual door closing force of the object.

[0075] The facial features outside the door are the features of the face present in the target image outside the door. Feature extraction can be performed on the target image outside the door to identify whether there are facial features in the target image outside the door. For example, facial features may include features of the nose, glasses, eyes, mouth, eyebrows, and facial contours.

[0076] Step S13, when there is a target resident's facial feature corresponding to the facial feature of the person outside the door in the preset door-opening person database, determine the door-closing habitual force of the door-opening object based on the habitual force data carried by the facial feature of the target resident;

[0077] Step S14, when there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, determine the door closing habitual strength based on the facial feature outside the door and the target door outside image.

[0078] It should be noted that the preset door-opening person database stores the facial features of multiple residents corresponding to the door where the video doorbell is located, and the facial features of the residents of the room corresponding to the door where the video doorbell is located can be stored in the preset door-opening face database. The door-opening object can be a resident.

[0079] When there is a target resident facial feature corresponding to the target facial feature in the preset door-opening character database, it means that the person who opens the door where the video doorbell is located is a resident, and the habitual force of closing the door of the door-opening object can be directly obtained. The facial features of each resident stored in the preset door-opening database carry corresponding habitual force data. The habitual force data describes the habitual force of the resident corresponding to the resident facial feature when closing the door. The habitual force data corresponding to each resident facial feature can be the average value of the actual force of the resident facial feature when closing the door, or it can be the habitual force data collected by prompting the user when the video doorbell is installed. The target resident facial feature is the resident facial feature that matches the facial feature outside the door in the preset door-opening database.

[0080] When the target resident facial features corresponding to the target facial features do not exist in the preset door-opening person database, it means that the person opening the door where the video doorbell is located is not the resident, and the corresponding facial features cannot be found in the preset door opening task database. Therefore, based on the facial features of the person outside the door and the target image outside the door, the door closing habit strength of the user corresponding to the target image outside the door can be predicted.

[0081] Exemplarily, a search is performed to determine whether there are target resident facial features corresponding to the facial features outside the door in the preset door opening task database of the video doorbell. If there are target resident facial features corresponding to the facial features outside the door in the preset door opening task database, the habitual strength data carried by the target resident facial features are used as the door-closing habitual strength of the door-opening object. If there are no target resident facial features corresponding to the facial features outside the door in the preset door opening person database, the door-closing habitual strength is determined based on the facial features outside the door and the target door image.

[0082] Furthermore, the facial features of the residents can be entered into the video doorbell to be stored in the preset door-opening character database. For example, the video doorbell can receive the facial entry command of the user, and based on the facial entry command, turn on the camera of the video doorbell to collect the facial features of the residents, and when collecting the facial features of the residents, prompt the residents to collect the door-closing force (for example, the residents can be asked to close the door N times, and the average closing force of the N times is used as the habitual force data of the residents), so as to collect the habitual force data of the residents, and associate the habitual force data and facial features of the same residents and store them in the preset door-opening character database. This facilitates the subsequent more accurate determination of the door-opening object, and the more accurate determination of the door-closing habitual force of the door-opening object.

[0083] Furthermore, in a feasible embodiment, step S13 further includes:

[0084] Step S131, when the number of facial features outside the door is greater than the preset single person threshold, and there are multiple target facial features corresponding to the facial features outside the door in the preset door opening person database, the average value of the habit strength data carried by each target facial feature is used as the door closing habit strength;

[0085] Step S132, when the number of target facial features existing in the preset door-opening person database is equal to the preset single-person threshold, the habitual strength data carried by the target resident facial features is used as the door-closing habitual strength.

[0086] It should be noted that the preset single person threshold is 1. When the number of facial features outside the door is greater than 1, it means that the number of facial features outside the door in the target image outside the door is greater than 1, indicating that multiple people are entering the door at the same time. If there are multiple facial features outside the door corresponding to the target facial features in the preset door-opening person database, it means that multiple residents are about to enter the door at the same time. At this time, the average of the habit strength data carried by each target facial feature can be used as the door closing habit strength.

[0087] When the number of facial features outside the door is equal to the preset single-person threshold, and the target facial feature corresponding to the facial feature outside the door exists in the preset door-opening person database, it means that only one resident has entered the door at this time, and the habit strength data carried by the target facial feature can be used as the habit strength for closing the door.

[0088] When the number of facial features outside the door is greater than the preset single-person threshold, the number of target facial features may be 1. At this time, the habit strength data carried by the target facial feature is also used as the door closing habit strength.

[0089] In a feasible embodiment, step S14 further includes steps S141 to S144:

[0090] Step S141, when there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is equal to the preset single-person threshold, calling the preset strength prediction model, identifying the gender type of the facial feature outside the door and determining the gender strength coefficient corresponding to the gender type, and extracting the initial human body contour from the target door-outside image;

[0091] It should be noted that the preset force prediction model is used to predict the habitual force coefficient of the person in the target door outside image. The preset force prediction model can be obtained by training the neural network model. The gender of the person in the target door outside image can be identified by the facial features of the person outside the door. The gender type can be divided into female type and male type. The door closing force corresponding to different genders may also be different. When the gender type of the facial features of the person outside the door is determined, the corresponding gender force coefficient can be directly determined based on the gender type. For example, when it is a female type, the second force coefficient is determined to be the gender force coefficient, and when it is a male type, the first force coefficient is determined to be the gender force coefficient. The first force coefficient is characterized as a male force coefficient, and the second force coefficient is characterized as a female force coefficient. The first force coefficient can be greater than the second force coefficient. The first force coefficient and the second force coefficient can be preset in advance. The initial human body contour is characterized as the contour of the human body in the target door outside image.

[0092] Step S142, determining the clothing coverage thickness coefficient based on the acquired temperature of the day, and adjusting the initial human body contour to obtain the actual human body contour according to the clothing coverage thickness coefficient, and determining the human body strength coefficient corresponding to the actual human body contour;

[0093] It should be noted that the temperature of the day can be the temperature on the day the door is opened, and the temperature of the day can be obtained from the cloud corresponding to the video doorbell. For example, the temperature of the day the door is opened can be queried in the cloud. In other embodiments, the date of the day the door is opened can also be obtained, and based on the date and the region where the video doorbell is located, the season of the day the door is opened is determined, and the average temperature of the season is used as the temperature of the day.

[0094] The clothing coverage thickness coefficient is used to describe the thickness of the clothes worn by the person corresponding to the initial human body contour, and the clothing coverage thickness coefficient is proportional to the thickness of the clothes worn by the corresponding task. Based on the clothing coverage thickness coefficient, the initial human body contour can be adjusted to obtain the actual human body contour. The actual human body contour is used to describe the actual human body contour and can be used to describe the body shape of the person. The corresponding door closing force may also be different for different body shapes of the person, so this embodiment can more accurately determine the human body force coefficient corresponding to the actual human body contour by identifying the actual human body contour, thereby facilitating the determination of the corresponding door closing habit force.

[0095] When the temperature is different, the thickness of the clothes people wear will also be different. In order to avoid misjudgment of the body shape of the person due to the clothes, this embodiment determines the clothing coverage thickness coefficient corresponding to the temperature of the day through the temperature of the day, and adjusts the initial human body contour based on the clothing coverage thickness coefficient to obtain the actual human body contour. The influence of the thickness of the clothes worn by the person on the human body strength coefficient can be reduced, thereby facilitating the improvement of the accuracy of the human body strength coefficient. Each temperature can have a corresponding clothing coverage thickness coefficient, and the mapping relationship between the temperature and the corresponding clothing coverage thickness coefficient can be stored in the preset temperature coefficient mapping relationship. After determining the temperature of the day, the clothing coverage thickness coefficient can be found in the preset temperature coefficient mapping relationship, and the preset temperature coefficient mapping relationship can be stored in the preset strength prediction model.

[0096] For example, in summer, when the temperature is high and exceeds the preset high temperature threshold, the clothing coverage thickness coefficient can be 0. When the temperature exceeds the preset high temperature threshold, the clothing worn for the task can be ignored, so the clothing coverage thickness coefficient can be 0 or other values. This embodiment does not make specific limitations on this. When the temperature exceeds the preset high temperature threshold, the initial human body contour can be directly used as the actual human body contour. In winter, when the temperature is low, the clothing coverage thickness coefficient can be a value such as 0.3. Based on the clothing coverage thickness coefficient, the initial human body contour can be reduced to obtain the actual human body contour. The ratio of the area size within the actual human body contour to the area within the initial human body contour is the clothing coverage thickness coefficient.

[0097] Step S143, performing weighted summation on the gender force coefficient and the human body force coefficient to obtain the habit force coefficient;

[0098] Step S144, taking the product of the habitual force coefficient and the preset standard force as the door closing habitual force.

[0099] It should be noted that the habitual force coefficient can be used to describe the strength of the person in the target door outside image, and the preset standard force can be set based on the actual situation. This embodiment does not specifically limit this. For example, the preset standard force can be the average force of the historical force data corresponding to the video doorbell, and the historical force data can be the historical door closing habit force corresponding to the video doorbell. By using the average force data of the historical force data as the preset standard force, the accuracy of predicting the door closing habit force of the person in the target door outside image can also be improved. Because the facial features corresponding to the person in the target door outside image are not stored in the preset door opening person database, the person in the target door outside image may be a person who often opens and closes the door where the video doorbell is located. Therefore, when the average force data of the historical force data is used as the preset standard force, it may be closer to the door closing force of the person in the target door outside image. The preset standard force can be customized, etc.

[0100] The habit force coefficient is a positive value, and the habit force coefficient can be less than 1 or greater than 1. Both the gender force coefficient and the human body force coefficient are positive values, and both the gender force coefficient and the human body force coefficient can be less than 1 or greater than 1, and this embodiment does not specifically limit this. For example, the first force coefficient can be greater than 1, and the second force coefficient can be less than 1. When the area size within the actual human body contour is greater than the preset contour threshold, the human body force coefficient can be greater than 1, and when the area within the actual human body contour is less than the preset contour threshold, the human body force coefficient can be less than 1. When the area size within the actual human body contour is greater than the preset contour threshold, it means that the human body corresponding to the actual human body contour is larger, and the force of closing the door may also be relatively large, so the human body force coefficient can be greater than 1. When the area size within the actual human body contour is less than the preset contour threshold, it means that the human body corresponding to the actual human body contour is smaller, and the force of closing the door may also be relatively small, so the human body force coefficient can be less than 1. The preset force prediction model can be used to determine the habit force coefficient.

[0101] Exemplarily, the facial features of the person outside the door and the target image outside the door can be input into a preset force prediction model to identify the gender type of the facial features of the person outside the door and determine the gender force coefficient corresponding to the gender type, and extract the initial human body contour from the target image outside the door; based on the acquired temperature of the day, determine the clothing coverage thickness coefficient, and according to the clothing coverage thickness coefficient, adjust the initial human body contour to obtain the actual human body contour, and determine the human body force coefficient corresponding to the actual human body contour; perform weighted summation of the gender force coefficient and the human body force coefficient to obtain the habitual force coefficient; and use the product of the habitual force coefficient and the preset standard force as the habitual force for closing the door.

[0102] The training process of the preset force prediction model may include: obtaining a second training sample and a second model to be trained, the second model to be trained may be a neural network model, the second training sample includes a training image sample and a door-closing habit force label, the training image sample includes a face sample and an image sample outside the door corresponding to the face sample, the training image sample is input to the second model to be trained, the second model to be trained outputs a habit force coefficient feature, and the second training loss between the habit force coefficient feature and the door-closing habit force label is calculated. If the second training loss is less than a preset loss threshold, the second model to be trained is used as the preset force prediction model. If the second training loss is greater than or equal to the preset loss threshold, the training image sample is re-acquired, and the second model to be trained is iteratively trained until the second training loss is less than the preset loss threshold to obtain the preset force prediction model.

[0103] Step S145, when there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is greater than the preset single-person threshold, the preset habitual force is used as the door-closing habitual force.

[0104] It should be noted that when the number of facial features outside the door is greater than the preset single-person threshold, it may be difficult to identify the initial body contour of a single person, and then the wrong door-closing habit force may be predicted. Therefore, at this time, the preset habit force can be directly used as the door-closing habit force to improve the accuracy of the door-closing habit force prediction.

[0105] Step S20, determining the amount of loosening of the battery of the video doorbell under the effect of the actual force of the object closing the door and the wind force of the closing environment;

[0106] Step S30, determining the remaining number of door closing times before the video doorbell becomes ineffective based on the amount of loosening action and the strength of the door closing habit;

[0107] It should be noted that the loosening effect is the looseness of the battery under the influence of the closing habitual force and the wind force in the closing environment, and the remaining number of closing times is characterized by the remaining number of closing times before the battery of the video doorbell fails due to looseness. When the remaining number of closing times is 0, it means that the video doorbell is about to fail due to battery loosening. This embodiment predicts the actual force that the video doorbell may receive in the future through the closing habitual force of the door-opening object, and determines the remaining number of closing times of the video doorbell before failure through the closing habitual force and the current loosening effect, thereby facilitating a more accurate prediction of the remaining number of closing times of the video doorbell before failure.

[0108] Step S40: When the remaining number of door closing times is less than a preset number threshold, a battery loose failure prompt is output.

[0109] It should be noted that the preset number threshold can be set based on actual conditions. For example, the preset number threshold can be 5 or 6, etc., so that a battery loose failure prompt can be output in advance before the battery fails due to looseness, thereby avoiding battery failure due to looseness and preventing the video doorbell from failing.

[0110] The battery loose failure prompt can be a voice prompt, a light prompt, or a voice plus light prompt. For example, the voice prompt can be "Battery is loose, please pay attention to whether the battery casing is loose", etc. The light prompt can be continuous flashing, etc.

[0111] Exemplarily, the amount of loosening effect is determined based on the actual force with which the subject closes the door and the wind force in the closing environment, and the remaining number of door closings before failure of the video doorbell is determined based on the amount of loosening effect and the closing force habit. When the remaining number of door closings is less than a preset threshold, a battery loosening failure prompt is output.

[0112] The present application can obtain the habitual force of the door-opening object, the actual force of the door-closing object, and the wind force of the door-closing environment by detecting the door opening, and the wind force of the door-closing environment includes the absolute wind force and the wind direction. Because the habitual force of closing the door corresponding to different door-opening objects may be different, the actual force of the object of different door-opening objects may also be different, and the absolute wind force and wind direction corresponding to the door closing may be different. When the actual force of the door closing of the object and the wind force of the door closing environment are different, the impact on the video doorbell on the door when closing the door is different. Therefore, the present application predicts the door closing of the object. Under the influence of the actual force and the wind force in the door closing environment, the loosening effect of the battery of the video doorbell can be used to determine the remaining number of door closings before the video doorbell fails. Since the door closing habitual force can be used to describe the door opening force of the object's habitual door opening, and the actual force of the object's door closing is expressed as the single door opening force of the object, the remaining number of door closings can be determined by combining the door closing habitual force and the loosening effect. This can improve the accuracy of the preset remaining number of door closings and avoid the situation where the remaining number of door closings is inaccurate due to the single object's actual door closing force being too small or too large. Furthermore, when the remaining number of door closings is less than the preset number threshold, a battery loose failure prompt can be output, so that the battery of the video doorbell can be output before the battery loosens and fails due to the impact of closing the door, etc., so as to prompt the user to adjust the battery of the video doorbell and avoid the failure of the video doorbell due to loose batteries.

[0113] Further, see Figure 2 In a feasible embodiment, step S10 further includes steps X10 to X40:

[0114] Step X10, obtaining the wind force inside the door collected by a first pressure sensor disposed inside the door, and obtaining the wind force outside the door collected by a second pressure sensor disposed outside the door;

[0115] Step X20, determining the absolute value of the difference between the wind force inside the door and the wind force outside the door as the absolute wind force;

[0116] Step X30, determining the wind direction according to the wind force inside the door and the wind force outside the door;

[0117] Step X40, taking the wind direction and absolute wind force as the door closing environment wind force.

[0118] It should be noted that the first pressure sensor can be installed inside the door where the video doorbell is located, and the second pressure sensor can be installed outside the door where the video doorbell is located. The inside of the door refers to the side facing the room, and the outside of the door refers to the side outside the room. The installation positions of the first pressure sensor and the sensor inside the door can be different, and the installation positions of the second pressure sensor and the sensor outside the door can also be different. This facilitates more accurate determination of the absolute wind force and more accurate determination of the door opening type.

[0119] The wind force inside the door is collected by the first pressure sensor, and the wind force outside the door is collected by the second pressure sensor. The absolute wind force is the absolute value of the difference between the wind force inside the door and the wind force outside the door. The absolute wind force may also be 0, that is, there is no wind when the door is opened and / or closed, and the absolute wind force may be 0 at this time.

[0120] When the absolute wind force is greater than or equal to the preset wind force threshold, a prompt to close the door carefully can be output to remind the user that the current wind force is too strong and the door needs to be closed gently to avoid excessive impact force on the video doorbell and reduce the probability of battery loosening.

[0121] The wind direction may be from inside the door to outside, or from outside the door to inside. You can compare the wind force inside the door with the wind force outside the door to determine the wind direction.

[0122] Exemplarily, when the door opening is detected, the wind force inside the door collected by the first pressure sensor is obtained, and the wind force outside the door collected by the second pressure sensor is obtained. The wind force inside the door collected by the first pressure sensor and the wind force outside the door collected by the second pressure sensor can be stored on the video doorbell for a period of time, so that when the door opening is detected, the separation outside the door and the wind force inside the door at the last moment of the door opening can be obtained. The absolute value of the difference between the wind force inside the door and the separation outside the door is taken as the absolute wind force. When the wind force inside the door is greater than the wind force outside the door, the wind force direction is determined to be from inside the door to outside the door. When the wind force inside the door is less than the wind force outside the door, the wind force direction is determined to be from outside the door to inside the door.

[0123] This embodiment can accurately determine the impact of the ambient wind force on door closing by determining the absolute wind force and wind force direction, so that the remaining number of door closing times can be accurately determined subsequently.

[0124] In a feasible embodiment, step S20 further includes steps S21 to S23:

[0125] Step S21, searching for the absolute force coefficient of the absolute wind force in a preset wind force coefficient mapping relationship;

[0126] Step S22, when the wind direction is the same as the preset door closing direction of the door closing habitual force, the sum of the absolute force coefficient and the preset standard action coefficient is used as the wind force positive action coefficient, the product of the door closing habitual force and the wind force positive action coefficient is used as the door closing force, and the loosening action amount corresponding to the door closing force is determined;

[0127] Step S23, when the wind direction is opposite to the preset door closing direction of the door closing habitual force, the difference between the absolute force coefficient and the preset standard action coefficient is taken as the wind reaction coefficient, the product of the door closing habitual force and the wind reaction coefficient is taken as the door closing force, and the loosening action amount corresponding to the door closing force is determined.

[0128] It should be noted that the preset wind force coefficient mapping relationship stores the absolute force coefficients corresponding to multiple absolute wind forces, and the door closing force is the force exerted on the door by the door closing environment wind force and the actual door closing force of the object. When the wind direction of the door closing environment wind force is the same as the door closing direction, the door closing environment wind force will be added to the actual door closing force of the object, that is, the door closing force will become larger. When the wind direction of the door closing environment wind force is different from the door closing direction, the door closing environment wind force can weaken the actual door closing force of the object, so that the door closing force on the door can be reduced relative to the actual door closing force of the object.

[0129] The loosening effect is characterized by the loosening effect of the battery of the video doorbell under the force of closing the door. Different closing forces correspond to different loosening effects.

[0130] The accumulated looseness of the battery is used to describe the looseness of the battery before the closing force is applied to the door. Each time the corresponding closing force is applied to the door, the accumulated looseness of the battery can be updated. For example, the loosening action of the closing force can be added to the accumulated looseness of the battery to obtain the current looseness of the battery. The current looseness of the battery is used to describe the looseness of the battery after the closing force is applied to the door.

[0131] The absolute force coefficient is used to describe the magnitude of the absolute wind force. The larger the absolute force coefficient, the greater the absolute wind force. The preset standard action coefficient can be 1. If the absolute wind force is the same, the actual force of the door closing is also the same, but the wind direction is different, then the corresponding door closing force will also be different.

[0132] The preset door closing direction can be determined based on the door closing type of the door where the video doorbell is located. For the same door, the door closing type is fixed. For example, the door closing type of some doors may be from the outside to the inside, and the door closing type of some doors may be from the inside to the outside. Figure 3 , Figure 3 Among them, M1 is the door where the video doorbell is located, K1 is the door frame, F1 indicates from inside the door to outside the door, and F2 indicates from outside the door to inside the door.

[0133] Exemplarily, when the preset door closing direction is from outside the door to inside the door, when the wind direction is from outside the door to inside the door, it is determined that the wind direction is the same as the preset door closing direction of the actual force of the object door closing, and when the wind direction is from inside the door to outside the door, it is determined that the wind direction is opposite to the preset door closing direction of the actual force of the object door closing. When the preset door closing direction is from inside the door to outside the door, when the wind direction is from outside the door to inside the door, it is determined that the wind direction is opposite to the preset door closing direction of the actual force of the object door closing, and when the wind direction is from inside the door to outside the door, it is determined that the wind direction is the same as the preset door closing direction of the actual force of the object door closing. The wind positive action coefficient is characterized by a value greater than 1, and the wind negative action coefficient is a value less than 1.

[0134] The wind reaction coefficient is used to attenuate the actual force of the object closing the door, and the wind positive action coefficient is used to enhance the actual force of the object closing the door. By determining the wind reaction coefficient and the wind action coefficient, this embodiment can more accurately determine the impact of absolute wind force on the impact of the video doorbell closing the door. When the wind direction is opposite to the preset closing direction, it can be convenient to reduce the impact on the video doorbell. When the wind direction is the same as the preset closing direction, the impact on the video doorbell will be increased.

[0135] In a feasible embodiment, step S24 further includes steps S241 to S246:

[0136] Step S241, aggregating the loosening action amount and the cumulative looseness degree of the battery stored in the video doorbell to obtain the current looseness degree of the battery;

[0137] Step S242, taking the difference between the preset loose failure threshold and the current looseness of the battery as the remaining looseness;

[0138] Step S243, when the looseness detection mode of the video doorbell is the single occupancy detection mode, the ratio of the remaining looseness amount to the door closing habitual force is used as the remaining number of door closing times;

[0139] It should be noted that the preset loose failure threshold can be determined based on actual conditions. The preset loose failure threshold is the maximum looseness of the battery. When the current looseness of the battery is greater than or equal to the preset loose failure threshold, it means that the looseness of the battery will cause the battery to fail, and then cause the video doorbell to fail. The remaining looseness is used to describe the remaining looseness of the battery of the video doorbell before failure. The loose detection mode includes a single-person occupancy detection mode and a multi-person occupancy detection mode. The single-person occupancy detection mode is characterized by one person living in the door corresponding to the video doorbell. The multi-person occupancy detection mode is characterized by multiple people living in the door corresponding to the video doorbell. The user can customize whether the video doorbell works in the single-person occupancy detection mode or the multi-person occupancy detection mode. In the single-person occupancy detection mode, the person who opens the door where the video doorbell is located is generally the same person, so the ratio of the remaining looseness to the habitual force of closing the door can be directly used as the remaining number of door closings.

[0140] Step S244, when the looseness detection mode of the video doorbell is a multi-occupancy detection mode, obtain the historical looseness data of the door where the video doorbell is located, and search for multiple target historical looseness degrees similar to the current looseness degree of the battery from the historical looseness data, and the difference between the target historical looseness degree and the current looseness degree of the battery is less than a preset minimum similarity threshold;

[0141] Step S245, for each target historical looseness degree, searching the historical looseness data for the target historical failure degree corresponding to the target historical looseness degree, and counting the historical door closing times between the target historical looseness degree and the corresponding target historical failure degree;

[0142] Step S246, taking the average of each historical door closing number as the remaining door closing number.

[0143] It should be noted that in a multi-person occupancy mode, there are generally multiple objects where the video doorbell is located. If the remaining number of door closings is determined simply based on the door closing habitual force and remaining looseness of any one object, or the average value of the door closing habitual force and remaining looseness corresponding to each resident, it is easy to lead to inaccurate remaining number of door closings.

[0144] The historical looseness data can be used to describe the historical looseness degree of the battery of the video doorbell. It can be understood that the historical looseness data may include multiple sets of data, each set of data may include the loosening process of the video doorbell's battery from never loosening to battery failure, each loosening process includes multiple historical looseness degrees, for each set of data, the historical looseness degrees may be in a sequentially increasing relationship.

[0145] The target historical looseness is a historical looseness similar to the current looseness of the battery. When the historical looseness is equal to the current looseness of the battery, or the difference between the historical looseness and the current looseness of the battery is less than a preset similarity threshold, the historical looseness is determined to be the target historical looseness.

[0146] The target historical failure degree is the looseness degree when the battery fails during the loosening process corresponding to the target historical looseness degree. Each target historical looseness degree can correspond to a target historical failure degree. For each target historical looseness degree, when the target historical looseness degree changes to the target historical failure degree, there can also be multiple historical looseness degrees between the target historical looseness degree and the target historical failure degree. The number of historical looseness degrees that exist is: the number of historical door closing times between the target historical looseness degree and the corresponding target historical failure degree. Since when closing the door, the loosening action amount under the closing force and the cumulative looseness degree of the battery are aggregated to obtain the current looseness degree of the battery, each generation of the current looseness degree of the battery is equivalent to a door closing action, and the historical looseness data includes multiple groups of data, each group of data can include multiple historical looseness degrees, and the historical looseness degree is equivalent to the historical current looseness degree of the battery, so each historical looseness degree corresponds to a door closing action.

[0147] Therefore, we can count the number of historical looseness degrees between the target historical looseness degree and the corresponding target historical failure degree, and use the number of historical looseness degrees as the number of historical closing times.

[0148] Exemplarily, the difference between a preset loose failure threshold and the current looseness of the battery is taken as the remaining looseness; the historical looseness data of the door where the video doorbell is located is obtained, and multiple target historical looseness levels that are similar to the current looseness of the battery are searched from the historical looseness data, and the difference between the target historical looseness level and the current looseness level of the battery is less than a preset minimum similarity threshold; for each target historical looseness level, the target historical failure level corresponding to the target historical looseness level is searched in the historical looseness data, and the number of historical looseness levels between the target historical looseness level and the corresponding target historical failure level is counted, and the number is taken as the historical number of door closings; the average of each historical number of door closings is taken as the remaining number of door closings.

[0149] This embodiment can count the average of each historical number of door closing times as the remaining number of door closing times, so that the remaining number of door closing times can be determined more accurately. Even if the remaining looseness of the battery of the video doorbell is known, the subsequent door closing force may not be the same in the multi-occupancy mode, and the door closing force may fluctuate. The video doorbell may fail before the remaining number of door closing times is reset. This embodiment determines the historical number of door closings corresponding to the historical looseness data, so that the remaining number of door closings under the current looseness of the battery can be more accurately fitted to the door where the video doorbell is located, thereby improving the accuracy of the remaining number of door closings, so that it is convenient to prompt the user more promptly in the future that there is a risk of battery looseness and failure, thereby ensuring the effectiveness of the video doorbell.

[0150] This application also provides a visual doorbell detection device, please refer to Figure 4 , the video doorbell detection device includes:

[0151] The acquisition module 10 is used to acquire the closing force of the door-opening object, the actual closing force of the door-opening object, and the wind force of the door-closing environment when the door-opening object is detected, and the wind force of the door-closing environment includes the absolute wind force and the wind direction;

[0152] A loosening prediction module 20, used to determine the loosening amount of the battery of the video doorbell under the effect of the actual force of the object closing the door and the wind force of the closing environment;

[0153] A remaining determination module 30, for determining the remaining number of door closing times of the video doorbell before failure based on the amount of loosening action and the force of the door closing habit;

[0154] The prompt module 40 is used to output a battery loose failure prompt when the remaining number of door closing times is less than a preset number threshold.

[0155] The video doorbell detection device provided in the present application adopts the battery detection method of the video doorbell in the above-mentioned embodiment, aiming to solve the technical problem of doorbell failure caused by loose batteries. Compared with the prior art, the beneficial effects of the battery detection method of the video doorbell provided in the embodiment of the present application are the same as the beneficial effects of the battery detection method of the video doorbell provided in the above-mentioned embodiment, and other technical features in the video doorbell detection device are the same as the features disclosed in the above-mentioned embodiment method, which are not repeated here. The embodiment of the present application provides an electronic device, which can be a playback device, and the electronic device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that at least one processor can execute the battery detection method of the video doorbell in the above-mentioned embodiment.

[0156] Reference below Figure 5, which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0157] like Figure 5 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In RAM 1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device may allow the electronic device to communicate wirelessly or wired with other devices to exchange data. Although the electronic device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have instead.

[0158] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1009, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0159] The electronic device provided by the present application adopts the battery detection method of the video doorbell in the above-mentioned embodiment 1 to solve the technical problem of the doorbell failure caused by loose batteries. Compared with the prior art, the beneficial effect of the product flow data distribution provided by the embodiment of the present application is the same as the beneficial effect of the battery detection method of the video doorbell provided by the above-mentioned embodiment, and the other technical features in the video doorbell detection device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here. It should be understood that the various parts of the present disclosure can be implemented by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples. The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims. The present embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the battery detection method of the video doorbell in the above-mentioned embodiment 1. The computer-readable storage medium provided in the embodiment of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, equipment or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable EPROM (Electrical Programmable Read Only Memory) or flash memory, an optical fiber, a portable compact disk CD-ROM (compact disc read-only memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution device, device or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency, radio frequency), etc., or any suitable combination of the above. The above-mentioned computer-readable storage medium may be contained in an electronic device; it may also exist alone without being assembled into an electronic device.The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: when detecting the opening of the door, obtains the habitual closing force of the door-opening object, the actual closing force of the object, and the wind force of the door-closing environment, wherein the wind force of the door-closing environment includes the absolute wind force and the wind direction; determines the loosening effect of the battery of the video doorbell under the influence of the actual closing force of the object and the wind force of the door-closing environment; determines the remaining number of door closings of the video doorbell before failure based on the loosening effect and the habitual door closing force; and outputs a battery loosening failure prompt when the remaining number of door closings is less than a preset number threshold.

[0160] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a LAN (local area network) or WAN (Wide Area Network), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0161] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0162] The modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The name of the module does not, in some cases, constitute a limitation on the unit itself. The computer-readable storage medium provided in the present application stores computer-readable program instructions for executing the above-mentioned battery detection method for the video doorbell, aiming to solve the technical problem of doorbell failure caused by loose batteries. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the embodiments of the present application are the same as the beneficial effects of the battery detection method for the video doorbell provided in the above-mentioned embodiments, which will not be repeated here.

[0163] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the battery detection method for a video doorbell as described above. The computer program product provided by the present application is intended to solve the technical problem of doorbell failure caused by loose batteries. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as the beneficial effects of the battery detection method for a video doorbell provided by the above embodiment, which will not be repeated here. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, are similarly included in the patent processing scope of the present application.

Claims

1. A battery detection method for a video doorbell, characterized in that: The method includes: When a door opening is detected, the closing force of the door-opening object, the actual closing force of the door-opening object, and the wind force of the door-closing environment are obtained, and the wind force of the door-closing environment includes the absolute wind force and the wind direction; Determine the amount of loosening of the battery of the video doorbell under the actual force of the object closing the door and the wind force of the closing environment; Based on the loosening action amount and the door closing habit strength, determining the remaining number of door closing times of the video doorbell before failure; When the remaining number of door closing times is less than a preset number threshold, a battery loose failure prompt is output.

2. The method according to claim 1, characterized in that When the door opening is detected, the step of obtaining the door closing habitual force of the door opening object comprises: In the case of detecting a door opening, detecting a door opening type, wherein the door opening type includes an outside door opening type and an inside door opening type; Acquire a target image outside the door corresponding to the door opening type, and determine facial features of a person outside the door in the target image outside the door; When there is a target resident's facial feature corresponding to the facial feature of the person outside the door in the preset door-opening person database, the door-closing habitual strength of the door-opening object is determined based on the habitual strength data carried by the facial feature of the target resident; When the target resident's facial features corresponding to the facial features of the person outside the door do not exist in the preset door-opening person database, the door-closing habit strength is determined based on the facial features of the person outside the door and the target door-opening image.

3. The method according to claim 2, characterized in that When there is a target resident face feature corresponding to the face feature outside the door in the preset door-opening person database, the step of determining the door-closing habitual force of the door-opening object based on the habitual force data carried by the face feature of the target resident comprises: When the number of the facial features outside the door is greater than the preset single person threshold, and there are target facial features corresponding to multiple facial features outside the door in the preset door-opening person database, the average value of the habit strength data carried by each of the target facial features is used as the door-closing habit strength; When the number of target facial features existing in the preset door-opening person database is equal to the preset single-person threshold, the habitual strength data carried by the target resident facial features is used as the door-closing habitual strength.

4. The method according to claim 2, characterized in that In the case that the target resident face feature corresponding to the face feature of the person outside the door does not exist in the preset door-opening person database, the step of determining the door-closing habit strength based on the face feature of the person outside the door and the target door-opening image comprises: When there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is equal to the preset single-person threshold, calling a preset strength prediction model, identifying the gender type of the facial feature outside the door and determining the gender strength coefficient corresponding to the gender type, and extracting an initial human body contour from the target door-outside image; Based on the acquired temperature of the day, determining a clothing coverage thickness coefficient, and adjusting the initial human body contour to obtain an actual human body contour according to the clothing coverage thickness coefficient, and determining a human body strength coefficient corresponding to the actual human body contour; The gender strength coefficient and the human body strength coefficient are weighted and summed to obtain the habitual strength coefficient; The product of the habitual force coefficient and the preset standard force is used as the door closing habitual force; If there is no target resident facial feature corresponding to the facial feature outside the door in the preset door-opening person database, and the number of facial features outside the door is greater than the preset single-person threshold, the preset habit strength will be used as the door-closing habit strength.

5. The method according to claim 1, characterized in that The step of obtaining the wind force of the door closing environment comprises: Acquire the wind force inside the door acquired by a first pressure sensor disposed inside the door, and acquire the wind force outside the door acquired by a second pressure sensor disposed outside the door; Determine the absolute value of the difference between the wind force inside the door and the wind force outside the door as the absolute wind force; Determine the wind direction according to the wind force inside the door and the wind force outside the door; The wind direction and absolute wind force are used as the closed-door environment wind force.

6. The method according to claim 1, characterized in that The step of determining the amount of loosening of the battery of the video doorbell under the effect of the actual force of the object closing the door and the wind force of the closing environment comprises: Finding the absolute force coefficient of the absolute wind force in a preset wind force coefficient mapping relationship; In the case where the wind direction is the same as the preset door closing direction of the door closing habitual force, the sum of the absolute force coefficient and the preset standard action coefficient is used as the wind force positive action coefficient, the product of the door closing habitual force and the wind force positive action coefficient is used as the door closing force, and the loosening action amount corresponding to the door closing force is determined; When the wind direction is opposite to the preset door closing direction of the door closing habitual force, the difference between the absolute force coefficient and the preset standard action coefficient is taken as the wind reaction coefficient, the product of the door closing habitual force and the wind reaction coefficient is taken as the door closing force, and the loosening action amount corresponding to the door closing force is determined.

7. The method according to claim 1, characterized in that The step of determining the remaining number of door closing times of the video doorbell before failure based on the loosening action amount and the door closing habit strength comprises: Aggregate the loosening action amount and the cumulative looseness degree of the battery stored in the video doorbell to obtain the current looseness degree of the battery; The difference between the preset loose failure threshold and the current looseness of the battery is used as the remaining looseness; When the looseness detection mode of the video doorbell is a single occupancy detection mode, the ratio of the remaining looseness amount to the door closing habitual force is used as the remaining number of door closing times; When the looseness detection mode of the video doorbell is a multi-occupancy detection mode, obtaining historical looseness data of the door where the video doorbell is located, searching for multiple target historical looseness degrees similar to the current looseness degree of the battery from the historical looseness data, and the difference between the target historical looseness degree and the current looseness degree of the battery is less than a preset minimum similarity threshold; For each of the target historical looseness degrees, searching the target historical failure degree corresponding to the target historical looseness degree in the historical looseness data, and counting the number of historical door closings between the target historical looseness degree and the corresponding target historical failure degree; The average value of each of the historical door closing times is taken as the remaining door closing times.

8. A visual doorbell detection device, characterized in that: The device comprises: An acquisition module, for acquiring the habitual force of the door-opening object, the actual force of the door-closing object, and the wind force of the door-closing environment when the door opening is detected, wherein the wind force of the door-closing environment includes the absolute wind force and the wind direction; A loosening prediction module, used to determine the loosening amount of the battery of the video doorbell under the influence of the actual force of the object closing the door and the wind force of the closing environment; A remaining determination module, for determining the remaining number of door closing times of the video doorbell before failure based on the loosening action amount and the door closing habitual strength; The prompt module is used to output a battery loose failure prompt when the remaining number of door closing times is less than a preset number threshold.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the battery detection method of the video doorbell described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which is stored a program for implementing a battery detection method for a video doorbell. The program for implementing a battery detection method for a video doorbell is executed by a processor to implement the steps of the battery detection method for a video doorbell as described in any one of claims 1 to 7.

Images