Monitoring method and device

Abstract

The invention discloses a monitoring method and device. The monitoring device comprises a movement detection unit and an AI decision unit, and the movement detection unit is used for detecting a moving object so as to obtain monitoring data based on a detection result; and the AI decision unit is used for controlling the on and off of the mobile detection unit by using an AI technology and based on the historical monitoring data and the current time information of the monitoring device. According to the invention, the power-saving performance of the monitoring device can be improved on the premise of considering the safety.

Description

Technical Field

[0001] The present application relates to the field of monitoring technology, and in particular to a monitoring method and a device thereof. Background Art

[0002] In the related art, after the motion frame shifting function of the monitoring device is turned on, a fixed strategy is used to wake up the monitoring device so that the monitoring device detects moving objects through the motion frame shifting function. For example, the motion detection function of the monitoring device is turned on every 4 minutes or every 1 minute.

[0003] Thus, when the related art always takes the measure of starting the mobile frame shifting function at fixed intervals, the power consumption will be relatively large, which is particularly inappropriate for devices with limited power (such as vehicle-mounted monitoring devices). Summary of the invention

[0004] The present application provides a monitoring method and a device thereof, which can improve the power saving performance of the monitoring device while taking safety into consideration.

[0005] To achieve the above object, the present application provides a monitoring device, which includes:

[0006] A motion detection unit, used to detect moving objects to obtain monitoring data based on the detection results;

[0007] The AI ​​decision-making unit is used to control the opening and closing of the motion detection unit based on the historical monitoring data and current time information of the monitoring device by using AI technology.

[0008] In one embodiment, the AI ​​decision unit is used to learn the usage habits of the object to which the monitoring device belongs using AI technology based on the historical monitoring data of the monitoring device, and determine the wake-up time of the motion detection unit based on the learning results and current time information.

[0009] The monitoring device of the present application is used to control the opening and closing of the motion detection unit based on the historical monitoring data and current time information of the monitoring device by using AI technology, that is, the present application can adaptively adjust the opening time of the motion frame shifting function of each monitoring device based on the usage habits of the object to which each monitoring device belongs. For example, if it is determined based on the historical monitoring data and current time information of the monitoring device that the current monitoring device and / or the object to which the monitoring device belongs is in a relatively safe state, the detection time interval will be appropriately extended to reduce the power consumption caused by the motion frame shifting function, thereby improving the power saving performance of the monitoring device while taking into account safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0011] Figure 1 It is a structural schematic diagram of an implementation method of the monitoring device of the present application;

[0012] Figure 2 It is a flow chart of the monitoring method adopted by the monitoring device of the present application;

[0013] Figure 3 It is a structural schematic diagram of an implementation method of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present application. In addition, unless otherwise specified (for example, "or in addition" or "or in an alternative"), the term "or" as used herein refers to a non-exclusive "or" (that is, "and / or"). Moreover, the various embodiments described herein are not necessarily mutually exclusive, because some embodiments can be combined with one or more other embodiments to form new embodiments.

[0015] In the related art, after the motion frame shifting function of the monitoring device is turned on, a fixed strategy is used to wake up the monitoring device so that the monitoring device detects moving objects through the motion frame shifting function. For example, the motion detection function of the monitoring device is turned on every 4 minutes or every 1 minute.

[0016] In this way, when the related art always takes the measure of opening the mobile frame shifting function at a fixed interval, the power consumption will be large, which is particularly inappropriate for devices with limited power (such as vehicle-mounted monitoring devices). In addition, the usage habits of each monitoring device are different, so it is not appropriate to set the mobile frame shifting function of the monitoring device in a fixed way.

[0017] Based on this, the present application proposes a monitoring device, which is used to control the opening and closing of a motion detection unit by utilizing AI technology and based on the historical monitoring data and current time information of the monitoring device. That is, the present application can adaptively adjust the opening time of the motion frame shifting function of each monitoring device based on the usage habits of the object to which each monitoring device belongs. For example, if it is determined based on the historical monitoring data and current time information of the monitoring device that the current monitoring device and / or the object to which the monitoring device belongs is in a relatively safe state, the detection time interval will be appropriately extended to reduce the power consumption caused by the motion frame shifting function, thereby improving the power saving performance of the monitoring device while taking into account safety.

[0018] Specifically, Figure 1 As shown, a monitoring device 10 provided in one embodiment of the present application includes a motion detection unit 11 and an AI decision unit 12 .

[0019] The motion detection unit 11 is used to detect moving objects to obtain monitoring data based on the detection results. Optionally, when the motion detection unit 11 is turned on, it can identify changes in the image and detect the presence of moving objects; if the motion detection unit 11 finds that there is a moving picture, that is, when a moving object appears in the shooting picture, it can automatically record the video to obtain monitoring data.

[0020] The AI ​​decision unit 12 may be used to control the opening and closing of the motion detection unit 11 based on the historical monitoring data and current time information of the monitoring device 10 using AI technology.

[0021] Optionally, the AI ​​decision unit 12 can use AI technology and infer the current usage scenario of the object to which the monitoring device 10 belongs based on the historical monitoring data and current time information of the monitoring device 10, and control the opening and closing of the mobile detection unit 11 based on the current usage scenario. For example, when the current time information is 10:00am on Friday, and the historical monitoring data shows that the object where the monitoring device 10 was located at 10:00am on Friday before was located in the workplace of the user of the monitoring device 10, which is a relatively safe area, it can be inferred that the current usage scenario of the object to which the monitoring device 10 belongs is the workplace of the owner of the monitoring device 10, which is a relatively safe area, so that the mobile detection unit 11 can be turned on at a relatively low frequency. Optionally, the usage habits and preferences of the object to which the monitoring device 10 belongs can be learned based on the historical monitoring data of the monitoring device 10, so that the current usage scenario of the object to which the monitoring device 10 belongs can be analyzed and inferred based on the learning results, and the wake-up timing and / or detection time interval of the mobile detection unit 11 can be determined, and then the opening and closing of the mobile detection unit 11 can be controlled.

[0022] Furthermore, the monitoring device 10 is a vehicle-mounted monitoring device 10, that is, the object to which the monitoring device 10 belongs is a vehicle, then the AI ​​decision unit 12 can use AI technology and based on the data of the monitoring device 10, positioning sensors, radar sensors and other vehicle sensors, learn the usage habits of the object to which the monitoring device 10 belongs, thereby adjusting the wake-up timing and / or detection time interval of the mobile detection unit 11 based on the learned driving habits and preferences of the vehicle user.

[0023] Optionally, the AI ​​decision unit 12 can use AI technology to analyze and learn data from vehicle sensors (such as radar, cameras, GPS), and learn the owner's driving habits and preferences (such as the specific time and place at home or at the company) to adjust the wake-up time. The AI ​​decision unit 12 can perform AI analysis and reasoning to determine the best wake-up time. In this way, a flexible approach can be used to replace the current fixed wake-up mechanism such as a 4-minute wake-up mechanism, and the opening and closing of the motion detection unit 11 can be intelligently controlled, thereby protecting vehicle safety and saving power.

[0024] When the AI ​​decision unit 12 learns the vehicle usage habits, the positioning sensor can be used to provide the vehicle location information of historical time, so that the AI ​​decision unit 12 can learn the addresses where the vehicle often stops. And the AI ​​decision unit 12 combines the vehicle historical location information and time information to learn the address attributes of each frequently stopped address, that is, to learn whether each frequently stopped address is the home address of the vehicle user or the office address of the vehicle user.

[0025] When the AI ​​decision unit 12 learns the vehicle usage habits, the monitoring device 10 can be used to provide historical monitoring data so that the AI ​​decision unit 12 can use AI technology to learn the historical frequency of mobile images in each time period and / or historical object flow, etc. Object flow can refer to human flow and / or vehicle flow, etc.

[0026] Optionally, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical object flow at each time. Generally speaking, the wake-up frequency of the mobile detection unit 11 at a time when the historical object flow is high will be higher than the wake-up frequency at a time when the historical object flow is low. Alternatively, the wake-up timing of the mobile detection unit 11 can also be adjusted based on the appearance frequency of the historical moving pictures at each time. Generally speaking, the wake-up frequency of the mobile detection unit 11 at a time when the historical moving picture appearance frequency is high will be higher than the wake-up frequency at a time when the historical moving picture appearance frequency is low. And more preferably, the wake-up frequency of the mobile detection unit 11 at a time will be set higher than or equal to the appearance frequency of the historical moving pictures at that time. Of course, the wake-up timing of the mobile detection unit 11 can also be adjusted comprehensively based on the historical object flow at each time and the appearance frequency of the historical moving pictures.

[0027] Furthermore, the AI ​​decision unit 12 can combine the vehicle position information and the monitoring data of the historical time to learn the historical moving picture appearance frequency and / or historical object flow of each time at each frequently parked position. Furthermore, if the current position of the object to which the monitoring device 10 belongs is a frequently parked position, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical moving picture appearance frequency and / or historical object flow of the current time at the current position; if the historical moving picture appearance frequency and / or historical object flow of the current time at the current position is high, the wake-up frequency of the mobile detection unit 11 is set higher, that is, the detection time interval of the mobile detection unit 11 is set shorter; if the historical moving picture appearance frequency and / or historical object flow of the current time at the current position is low, the wake-up frequency of the mobile detection unit 11 is set lower, that is, the detection time interval of the mobile detection unit 11 is set longer.

[0028] Among them, the frequency of appearance of historical moving pictures at each time can be obtained according to the frequency of appearance of moving pictures at the time corresponding to each time in multiple time periods before the current time period. Correspondingly, the historical object flow at each time can also be obtained according to the object flow at the time corresponding to each time in multiple time periods before the current time period. In addition, the above time period can be set according to actual conditions, for example, to one week or one day. Of course, in some implementations, the time period can also be determined by the AI ​​decision unit 12 itself using AI technology and learning based on data from vehicle sensors such as the monitoring device 10, positioning sensors, and radar sensors.

[0029] When the AI ​​decision unit 12 uses AI technology to learn vehicle usage habits, the radar sensor can be used to provide information about whether there are other vehicles or obstacles around the vehicle to which the monitoring device 10 belongs, so that the AI ​​decision unit 12 can learn the density of objects such as vehicles at the location of the monitoring device 10, so that the AI ​​decision unit 12 can learn information such as the historical density of the area where the vehicles are located at various times. In this way, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical density of the area where the vehicles are located at various times. Generally speaking, the wake-up frequency of the mobile detection unit 11 at a time with a high historical density will be higher than the wake-up frequency at a time with a low historical density. Further, the AI ​​decision unit 12 can combine the vehicle position information and the radar sensor data to learn the historical density of each position at each time; further, if the current location of the object to which the monitoring device 10 belongs is a location where it often stops, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical density of the current time of the current location. Furthermore, the AI ​​decision unit 12 can combine the vehicle position information, historical monitoring data and radar sensor data to learn the historical density of each position at each time, as well as the historical frequency of appearance of moving pictures and / or historical object traffic, etc.; thus, if the current position of the object to which the monitoring device 10 belongs is the position where the vehicle to which the monitoring device 10 belongs often stops, the wake-up timing of the mobile detection unit 11 can be comprehensively adjusted based on the historical density of the current time of the current position, as well as the historical frequency of appearance of moving pictures and / or historical object traffic.

[0030] When the AI ​​decision unit 12 uses AI technology to learn the usage habits of the vehicle, it can also combine the data of the gravity sensor to learn the usage habits. Among them, the gravity sensor can provide the historical vibration data of the vehicle so that the AI ​​decision unit 12 can learn the historical vibration conditions such as the historical vibration frequency and / or historical vibration intensity of the vehicle at various times, so as to facilitate the AI ​​decision unit 12 to learn the historical frequency of the appearance of surrounding moving objects of the vehicle at various times. In this way, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical frequency of the appearance of surrounding moving objects of the vehicle at various times. Generally speaking, the wake-up frequency of the mobile detection unit 11 at a time when the historical frequency of the appearance of moving objects is high will be higher than the wake-up frequency at a time when the historical frequency of the appearance of moving objects is low. Further, the AI ​​decision unit 12 can combine the vehicle position information and the data of the gravity sensor to learn the historical frequency of the appearance of surrounding moving objects at various positions at various times; further, if the current location of the object to which the monitoring device 10 belongs is a frequently parked location, the wake-up timing of the mobile detection unit 11 can be adjusted based on the historical frequency of the appearance of surrounding moving objects at the current time of the current location. Furthermore, the AI ​​decision unit 12 can combine the vehicle position information, historical monitoring data and gravity sensor data to learn the historical frequency of appearance of surrounding moving objects at each location and time, as well as the historical frequency of appearance of moving pictures and / or historical object flow, etc.; thus, if the current location of the object to which the monitoring device 10 belongs is the location where the vehicle to which the monitoring device 10 belongs often stops, the wake-up timing of the mobile detection unit 11 can be comprehensively adjusted based on the historical frequency of appearance of surrounding moving objects at the current time of the current location, as well as the historical frequency of appearance of moving pictures and / or historical object flow. Furthermore, the AI ​​decision unit 12 can combine the vehicle position information, historical monitoring data, radar sensor data and gravity sensor data to learn the historical density of each position at each time, the historical frequency of appearance of surrounding moving objects, and the historical frequency of appearance of moving pictures and / or historical object flow, etc.; thus, if the current position of the object to which the monitoring device 10 belongs is the position where the vehicle to which the monitoring device 10 belongs often stops, the wake-up timing of the mobile detection unit 11 can be comprehensively adjusted based on the historical density of the current time of the current position, the historical frequency of appearance of surrounding moving objects, and the historical frequency of appearance of moving pictures and / or historical object flow.

[0031] After the AI ​​decision unit 12 uses AI technology and learns the vehicle usage habits through the above data, it can obtain the historical reference data of the current location at the current time based on the current time information and the current positioning information (such as the above-mentioned historical density, the historical frequency of appearance of surrounding moving objects, and the historical frequency of appearance of moving pictures and / or historical object traffic, etc.), and then determine the wake-up timing and / or detection time interval of the mobile detection unit 11 based on the historical reference data of the current location at the current time, that is, control the opening and closing of the mobile detection unit 11 based on the historical reference data of the current location at the current time, so that the opening and closing of the mobile detection unit 11 is controlled according to the usage habits of the object to which the monitoring device 10 belongs, which can reduce the power consumption of the mobile detection unit 11 while taking into account safety.

[0032] Preferably, the AI ​​decision unit 12 can also use AI technology to comprehensively determine the wake-up time and / or detection time interval of the motion detection unit 11 based on the historical reference data of the current positioning at the current time and the current detection data of the radar sensor. Of course, in some implementations, the AI ​​decision unit 12 can also use AI technology to determine the wake-up time and / or detection time interval of the motion detection unit 11 based only on the historical reference data of the current positioning at the current time.

[0033] In an optional implementation, if the historical reference data of the current location at the current time cannot be obtained based on the current time information and the current location information due to the small amount of reference data, the mobile detection unit 11 can be awakened at a first time interval. The first time interval can be set according to the actual situation, such as 30s or 4min, etc., which is not limited here. More preferably, the first time interval can be set shorter, such as shorter than or equal to 4min, that is, when the amount of reference data is too small, it is considered that the current safety factor of the object to which the monitoring device 10 belongs is relatively low, so that the mobile detection unit 11 maintains a high frequency of awakening, so that the monitoring device 10 can obtain more learning materials as soon as possible, and the safety of the object to which the monitoring device 10 belongs can be improved.

[0034] In another optional implementation, if the historical reference data of the current location at the current time cannot be obtained due to too little reference data because the current location is not an address frequently visited by the object to which the monitoring device 10 belongs, for example, if the historical reference data of the current location at the current time cannot be obtained because the number of times the current location appears in the detection data of the positioning sensor is less than the first threshold, then the motion detection unit 11 can be woken up at a first time interval, or woken up at a second time interval, the second time interval being shorter than the first time interval; if the historical reference data cannot be obtained due to too little reference data because the object to which the monitoring device 10 belongs does not often appear at the current location at the time corresponding to the current time, for example, if the historical reference data of the current location cannot be obtained because the number of times the object to which the monitoring device 10 belongs appears at the current location at the time corresponding to the current time is less than the second threshold, then the wake-up timing of the motion detection unit 11 can be determined based on the historical reference data of the current location at other times. The time corresponding to the current time is the time corresponding to the current time in multiple time periods before the current time period; for example, if the duration of a time period is 1 day and the current time is 10:00am, then the time corresponding to the current time is 10:00am every day. It is understandable that the first threshold and the second threshold can be set according to actual conditions and are not limited here. For example, the first threshold can be 3 or 5, and the second threshold can be 2 or 6.

[0035] In one example, determining the wake-up timing of the mobile detection unit 11 based on the historical reference data of the current positioning at other times can be understood as follows: if the historical reference data of the current positioning at different times are quite different, that is, there are fluctuations in the historical reference data of the current positioning at different times, then the mobile detection unit 11 can be woken up at the first time interval or the second time interval; if the historical reference data of the current positioning at different times are not much different, that is, the fluctuations in the historical reference data of the current positioning at different times can be ignored, then the wake-up timing of the mobile detection unit 11 can be determined based on the historical reference data of the current positioning at any time.

[0036] In another example, determining the wake-up timing of the mobile detection unit 11 based on the historical reference data of the current positioning at the rest of the time can be understood as: the wake-up timing of the mobile detection unit 11 can be determined based on the historical reference data of the current positioning at the first time, wherein the first time of the current positioning can refer to the time that is closest to the current time among the times when the historical reference data of the current positioning can be obtained.

[0037] In another example, determining the wake-up timing of the motion detection unit 11 based on the historical reference data of the current location at other times can be understood as: determining the wake-up timing of the motion detection unit 11 based on the historical reference data of the current location at any time except the current time.

[0038] In addition, the AI ​​decision unit 12 may also be provided with a feedback mechanism. That is, after the AI ​​decision unit 12 determines the wake-up timing of the motion detection unit 11 based on the learned usage habits, it may further adjust the wake-up timing (i.e., detection time interval) of the motion detection unit 11 based on the current detection result of the motion detection unit 11 and / or the current detection data of the gravity sensor and / or the radar.

[0039] Exemplarily, if the AI ​​decision unit 12 adjusts the wake-up timing of the mobile detection unit 11 based on the learned usage habits, and no moving object is found based on the current multiple detection results of the mobile detection unit 11, the detection time interval can be further extended, that is, the mobile detection unit 11 can be awakened at a lower frequency. Preferably, when the wake-up timing of the mobile detection unit 11 is adjusted by using the feedback mechanism, the detection data of the gravity sensor and / or radar in the current time period can also be referred to, that is, preferably, if the AI ​​decision unit 12 adjusts the wake-up timing of the mobile detection unit 11 based on the learned usage habits, no moving object is found based on the current multiple detection results of the mobile detection unit 11, and the detection data of the gravity sensor and / or radar in the current time period is not abnormal, the detection time interval can be further extended, that is, the mobile detection unit 11 can be awakened at a lower frequency. Optionally, the method of extending the detection time interval is not limited here. For example, the detection time interval can be extended by adding a fixed step length to the current detection time interval. For another example, the current detection time interval can be enlarged by a fixed ratio to obtain an extended detection time interval.

[0040] In another example, if the AI ​​decision unit 12 adjusts the wake-up timing of the mobile detection unit 11 based on the learned usage habits, and a moving object is found based on the current multiple detection results of the mobile detection unit 11, the detection time interval can be shortened, that is, the mobile detection unit 11 can be woken up at a higher frequency. And / or, if the AI ​​decision unit 12 adjusts the wake-up timing of the mobile detection unit 11 based on the learned usage habits, and finds that the detection data of the gravity sensor and / or radar when the mobile detection unit 11 is in the off state is abnormal for many times, the detection time interval can be shortened, that is, the mobile detection unit 11 can be woken up at a higher frequency. And / or, if the AI ​​decision unit 12 adjusts the wake-up timing of the mobile detection unit 11 based on the learned usage habits, and finds that the detection data of the gravity sensor and / or radar when the mobile detection unit 11 is in the off state is abnormal for many times, the subsequent opening time of the mobile detection unit 11 can be adjusted so that the opening time of the mobile detection unit 11 and the time when the detection data of the gravity sensor and / or radar is abnormal can match. For example, the detection data of the gravity sensor and / or radar are abnormal at 10:07, 10:17, and 10:27. Although the detection interval of the mobile detection unit 11 is 10 minutes, the mobile detection unit 11 is turned on at 10:00, 10:10, 10:20, and 10:30, respectively, that is, the turning-on time of the mobile detection unit 11 does not match the time when the detection data of the gravity sensor and / or radar are abnormal. In this way, the next turning-on time of the mobile detection unit 11 can be advanced from 10:40 to 10:37, and the mobile detection unit 11 is subsequently turned on at an interval of 10 minutes. Optionally, the above-mentioned method of shortening the detection time interval is not limited here. For example, the detection time interval can be shortened by subtracting a fixed step size from the current detection time interval. For another example, the current detection time interval can be reduced by a fixed ratio to obtain a shortened detection time interval.

[0041] It can be understood that after a period of time of learning vehicle usage habits through relevant data, while determining the wake-up timing and / or detection time interval of the mobile detection unit 11 based on the current time information and the learning results, the current monitoring data, time information, positioning information, radar detection data, vibration detection data and other current detection data can also be collected, and the vehicle usage habits can be learned again based on the continuously collected detection data, so that the learned vehicle usage habits are closer to the actual vehicle usage habits, thereby facilitating accurate judgment of the wake-up timing of the mobile detection unit 11.

[0042] Optionally, in the early stage of using the monitoring device 10, the motion detection function of the monitoring device 10 can be turned on at fixed intervals, for example, the motion detection unit 11 of the monitoring device 10 is awakened at every first interval or second interval. Figure 2As shown, after waking up the motion detection function of the monitoring device 10, dynamic information (which may refer to dynamic images, etc.) and the time when the dynamic information appears, vehicle vibration information and vibration time, etc. can be collected, and then the motion detection function of the monitoring device 10 can be turned off. The AI ​​decision unit 12 can use AI technology to learn usage habits based on the dynamic information and vibration information collected in the initial use. The AI ​​decision unit 12 can decide when to wake up (i.e., turn on) the motion detection function of the monitoring device 10 based on the latest learning results, and decide when to turn off the motion detection function of the monitoring device 10; while the motion detection function of the monitoring device 10 is turned on, the monitoring device 10 will also collect dynamic information and the time when the dynamic information appears, vehicle vibration information and vibration time, etc., and the AI ​​decision unit 12 will also use AI technology to learn usage habits again based on the newly collected dynamic information and vibration information, that is, During the use of the monitoring device 10, the AI ​​decision unit 12 continuously learns the usage habits and usage scenarios of the object to which the monitoring device 10 belongs, and the AI ​​decision unit 12 will decide when to wake up the motion detection function of the monitoring device 10 and when to turn off the motion detection function of the monitoring device 10 based on the latest learning results. In this way, through continuous data collection and learning, the usage habits learned by the AI ​​decision unit 12 of the monitoring device 10 using AI technology are closer to the actual usage habits of the vehicle, thereby facilitating accurate judgment of the wake-up timing of the motion detection unit 11, so as to turn off the motion detection function of the camera in appropriate occasions and achieve the goal of power saving.

[0043] In addition, when the vehicle is in a stopped state, the above strategy can be used to control the opening and closing of the motion detection unit 11, so as to improve the power saving efficiency while taking into account the vehicle safety when the vehicle power supply is limited.

[0044] The present application also provides a monitoring method, which includes the following steps: controlling the on and off of the motion detection function of the monitoring device based on the historical monitoring data and current time information of the monitoring device. The specific content of this step can be referred to the relevant description of the AI ​​decision unit, which will not be repeated here.

[0045] See also Figure 3 , Figure 3It is a structural diagram of a computer-readable storage medium in an embodiment of the present application. The computer-readable storage medium 30 of the embodiment of the present application stores instructions / program data 31, and when the instructions / program data 31 are executed, the method provided by any embodiment of the monitoring device of the present application and any non-conflicting combination is realized. Among them, the instructions / program data 31 can form a program file and be stored in the above-mentioned storage medium 30 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) executes all or part of the steps of each embodiment method of the present application. The aforementioned storage medium 30 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0046] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0047] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0048] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0049] The above are only implementation methods of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A monitoring device, characterized in that: The monitoring device comprises: A motion detection unit, used to detect moving objects to obtain monitoring data based on the detection results; The AI ​​decision-making unit is used to control the opening and closing of the motion detection unit based on the historical monitoring data and current time information of the monitoring device by using AI technology.

2. The monitoring device according to claim 1, characterized in that: The AI ​​decision unit is used to learn the usage habits of the object to which the monitoring device belongs by using AI technology based on the historical monitoring data of the monitoring device, and determine the wake-up time of the motion detection unit based on the learning results and current time information.

3. The monitoring device according to claim 2, characterized in that: The object to which the monitoring device belongs is a vehicle, and the vehicle is provided with a positioning sensor, a radar sensor and / or a gravity sensor. The AI ​​decision unit is used to learn the usage habits of the object to which the monitoring device belongs by utilizing AI technology based on the detection data of the positioning sensor, radar sensor and / or gravity sensor and the historical monitoring data, and determine the wake-up timing of the motion detection unit based on the learning results and current time information.

4. The monitoring device according to claim 3, characterized in that: The AI ​​decision unit is used to determine the wake-up time of the motion detection unit by using AI technology and based on the learning result, current time information, and current positioning information of the positioning sensor.

5. The monitoring device according to claim 4, characterized in that: The AI ​​decision unit is used to obtain historical reference data of the current location at the current time by using AI technology based on the current time information and the current location information, and determine the wake-up time of the motion detection unit based on the historical reference data of the current location at the current time; The historical reference data of the current location at the current time includes the historical density of the current location at the current time, the historical frequency of appearance of surrounding moving objects, and the historical frequency of appearance of moving pictures and / or historical object traffic.

6. The monitoring device according to claim 5, characterized in that: The AI ​​decision unit is used to wake up the motion detection unit at a first time interval when the historical reference data of the current location at the current time cannot be obtained because the number of the current location in the detection data of the positioning sensor is less than the first threshold; and / or, The AI ​​decision unit is used to determine the wake-up timing of the motion detection unit based on the historical reference data of the current location at other times when the historical reference data of the current location at the current time cannot be obtained because the number of times the object to which the monitoring device belongs appears in the current location at the time corresponding to the current time is less than a second threshold.

7. The monitoring device according to claim 2, characterized in that: The object to which the monitoring device belongs is a vehicle, and the vehicle is provided with a radar sensor and / or a gravity sensor. After the AI ​​decision unit determines the wake-up timing of the mobile detection unit based on the learning result and the current time information, the AI ​​decision unit uses AI technology and adjusts the wake-up timing of the mobile detection unit based on the current detection result of the mobile detection unit and / or the current detection data of the gravity sensor and / or the radar.

8. The monitoring device according to claim 7, characterized in that: The AI ​​decision unit lowers the wake-up frequency of the motion detection unit in response to the current multiple detection results of the motion detection unit showing that no moving object is found; and / or, The AI ​​decision unit increases the wake-up frequency of the motion detection unit in response to the motion detection unit detecting a moving object in the current multiple detection results; and / or, The AI ​​decision unit is used to increase the wake-up frequency of the motion detection unit in response to finding that the detection data of the gravity sensor and / or the radar are abnormal for many times when the motion detection unit is in the off state.

9. A monitoring method, characterized in that: The method comprises: The AI ​​technology is used to control the turning on and off of the motion detection function of the monitoring device based on the historical monitoring data and current time information of the monitoring device.

10. A computer-readable storage medium having instructions / program data stored thereon, characterized in that: The instructions / program data implement the steps of the method of claim 9 when executed.

Images