Electricity consumption management method and device based on artificial intelligence, and energy management system

Abstract

The invention discloses a power consumption management method and device based on artificial intelligence, and an energy management system, and is applied to the technical field of energy management. The energy management system comprises a state detection device and a plurality of intelligent switches, the state detection device is used for detecting information of each object in a current scene, and the intelligent switches are connected with the electricity load and used for connecting or disconnecting the electricity load and the power supply interface. The method comprises the steps of determining whether a target object exists in a current scene based on a preset artificial intelligence model; and if the target object does not exist, controlling a preset intelligent switch in the plurality of intelligent switches to be switched off. Whether the target object exists in the current scene or not is determined through the preset artificial intelligence model, the preset intelligent switch is switched off under the condition that the target object does not exist, real-time dynamic intelligent power consumption management can be achieved, electric energy waste is avoided, and the power consumption efficiency and the energy utilization rate are improved.

Description

Technical Field

[0001] The present application belongs to the field of energy management technology, and in particular relates to an artificial intelligence-based electricity management method, an artificial intelligence-based electricity management device, an energy management system, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the continuous development of human society, the demand for electric energy is increasing. The importance of electric energy in daily life is everywhere. Various electrical appliances in the home, such as lighting tools, refrigerators, air conditioners, etc., all rely on electric energy to operate. In order to achieve high efficiency, environmental protection and energy conservation, the country strongly encourages the reduction of electric energy loss and green energy production.

[0003] At present, relevant electricity management methods have the problems of wasting electricity and poor electricity efficiency. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an artificial intelligence-based electricity management method, an artificial intelligence-based electricity management device, an artificial intelligence-based energy management system, a computer-readable storage medium and a computer program product, which can avoid unnecessary energy consumption and improve electricity efficiency.

[0005] In a first aspect, the present application provides an artificial intelligence-based power management method, which is applied to an energy management system, wherein the energy management system includes a state detection device and a plurality of intelligent switches; the state detection device is used to detect information of each object in the current scene; the intelligent switch is connected to an electrical load, and is used to turn on or off the connection between the electrical load and the power supply interface, and the method includes:

[0006] Based on a preset artificial intelligence model, determine whether the target object exists in the current scene;

[0007] If the target object does not exist, a preset smart switch among the multiple smart switches is controlled to be disconnected.

[0008] In some embodiments, the state detection device includes a millimeter wave radar and / or a camera, the millimeter wave radar is used to obtain radar information of each object in the current scene, and the camera is used to obtain image information of each object in the current scene, and determining whether the target object exists in the current scene based on a preset artificial intelligence model includes:

[0009] Inputting the radar information into the preset artificial intelligence model, and outputting a first detection result;

[0010] Inputting the image information into the preset artificial intelligence model, and outputting a second detection result;

[0011] Inputting the radar information and the image information into the preset artificial intelligence model, and outputting a third detection result;

[0012] The first detection result, the second detection result, and the third detection result include whether the target object exists in the current scene.

[0013] In some embodiments, the radar information includes at least one of profile information, position information, and speed information, and the inputting the radar information into the preset artificial intelligence model and outputting the first detection result includes:

[0014] If, among the various objects, the position information and / or the speed information of multiple consecutive frames of any object changes, it is determined that the target object exists in the current scene; and / or,

[0015] If, among the various objects, the contour information of any object matches the contour of the target object, it is determined that the target object exists in the current scene.

[0016] In some embodiments, the energy management system further includes an environment detection device, the environment detection device is used to detect environmental parameters, and the method further includes:

[0017] In the case where the target object exists, the first target smart switch is controlled to be turned on or off based on the environmental parameter, and the first target smart switch matches the environmental parameter.

[0018] In some embodiments, based on the environmental parameter, controlling the corresponding first target smart switch to be turned on or off includes:

[0019] When the environmental parameter is within the set parameter range, disconnecting the first target intelligent switch;

[0020] When the environmental parameter is outside the set parameter range, the first target smart switch is turned on.

[0021] In some embodiments, the state detection device is used to detect the state information of the target object, characterized in that the method further includes:

[0022] In the case where the target object exists, based on the state information, the second target smart switch is controlled to be turned on or off, and the second target smart switch matches the state information.

[0023] In some embodiments, the state information includes a sleep state and an active state, and based on the state information, controlling the second target smart switch to be turned on or off includes:

[0024] When the target object is in a sleeping state, controlling the second target intelligent switch to be disconnected;

[0025] When the target object is in an active state, the second target smart switch is controlled to be turned on.

[0026] In some embodiments, the artificial intelligence-based electricity management method further includes:

[0027] Set a set time period;

[0028] When the current time is within the set time period, the state detection device is turned on.

[0029] In a second aspect, the present application provides an artificial intelligence-based power management device, which is applied to an energy management system, wherein the energy management system includes a state detection device and a plurality of intelligent switches; the state detection device is used to detect information of each object in the current scene; the intelligent switch is connected to the power load; the intelligent switch is used to turn on or off the connection between the power load and the power supply interface, and the device includes:

[0030] A determination module, used to determine whether a target object exists in the current scene based on a preset artificial intelligence model;

[0031] The control module is used for controlling a preset smart switch among the multiple smart switches to be disconnected if the target object does not exist.

[0032] In a third aspect, the present application provides an energy management system, the energy management system comprising:

[0033] A state detection device, wherein the state detection device is used to detect information of each object in the current scene;

[0034] A plurality of intelligent switches, wherein the intelligent switches are connected to electrical loads and are used to switch on or off the connection between the electrical loads and the power supply interface;

[0035] An energy controller, wherein the energy controller is used to execute the artificial intelligence-based electricity management method described in any of the above embodiments.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based electricity management method described in any of the above embodiments.

[0037] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the artificial intelligence-based electricity management method described in any of the above embodiments.

[0038] The artificial intelligence-based electricity management method, artificial intelligence-based electricity management device, energy management system, computer-readable storage medium and computer program product provided in the embodiments of the present application detect information of each object (such as a person, pet, etc.) in the current scene through a status detection device, and then upload the information to a preset artificial intelligence model for analysis to determine the existence of the target object. If the target object does not exist, it can be determined that the target object is out. At this time, if most of the power loads serving the target object in the current scene continue to work, additional energy consumption will be caused. Therefore, if the target object does not exist in the current scene, a preset smart switch among multiple smart switches can be disconnected to stop the power load connected to the preset smart switch, thereby avoiding unnecessary energy consumption and improving power efficiency.

[0039] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and / or additional aspects and advantages of the present application will become apparent and easily understood in the description of the embodiments in conjunction with the following drawings, in which:

[0041] Figure 1 This is an application scenario diagram of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0042] Figure 2 This is a first flow chart of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0043] Figure 3 This is a second flow chart of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0044] Figure 4 This is a third flow chart of the power management method based on artificial intelligence provided in the embodiment of the present application;

[0045] Figure 5 This is a fourth flow chart of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0046] Figure 6 This is a fifth flow chart of the power management method based on artificial intelligence provided in the embodiment of the present application;

[0047] Figure 7 This is a sixth flow chart of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0048] Figure 8This is a seventh flow chart of the power management method based on artificial intelligence provided in the embodiment of the present application;

[0049] Fig. 9 This is an eighth flow chart of the power management method based on artificial intelligence provided in the embodiment of the present application;

[0050] Fig.10 This is a ninth flow chart of the power management method based on artificial intelligence provided in an embodiment of the present application;

[0051] Fig.11 It is a module schematic diagram of an artificial intelligence-based power management device provided in an embodiment of the present application;

[0052] Fig.12 It is a schematic diagram of the structure of the energy controller provided in the embodiment of the present application. DETAILED DESCRIPTION

[0053] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0054] For ease of understanding, the technical background and application scenarios of this application are first introduced below:

[0055] Electricity management: refers to a series of operations such as planning, monitoring, and regulating the use of electric energy to ensure safe, efficient, reasonable, and economical electricity use.

[0056] Artificial intelligence: It is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0057] Energy management: Energy management is a systematic work involving many aspects, aiming to achieve efficient, economical and safe use of energy through scientific planning, effective monitoring and reasonable regulation.

[0058] (1) Key elements of electricity management

[0059] Power generation refers to the electrical energy generated by power generation equipment per unit time. It is a physical quantity that measures the rate at which power generation equipment converts other forms of energy (such as thermal energy, hydropower, solar energy, etc.) into electrical energy.

[0060] Electrical power refers to the amount of electrical energy consumed by the electrical load per unit time, reflecting the rate at which the electrical load converts electrical energy into other forms of energy (such as heat energy, light energy, mechanical energy, etc.).

[0061] Power planning: Rationally arrange power supply to avoid power shortage or surplus.

[0062] (2) Key elements of energy management

[0063] Clean energy: Increase the proportion of renewable energy (such as wind power, solar power, hydropower, etc.) and reduce dependence on fossil fuels.

[0064] Improve energy efficiency: By optimizing the energy use process and adopting advanced energy-saving technologies, energy can be maximized during conversion and use to reduce energy waste.

[0065] Ensure safety: Ensure a stable supply of energy to avoid serious impacts on the economy and society due to energy shortages, supply interruptions, etc.

[0066] Reduce costs: Through effective energy management, such as optimizing equipment operation to reduce energy consumption, the cost of energy procurement and use can be greatly reduced, and economic benefits can be improved.

[0067] See also Figure 1 , Figure 1 The application scenario of the power management method based on artificial intelligence provided in the embodiment of the present application includes an energy management system 100 and a power load 200. The energy management system 100 includes a state detection device 101, an energy controller 102, and an intelligent switch 103.

[0068] The state detection device 101 is a device for detecting information of each object in the current scene. For example, the state detection device 101 can detect information of each object in the current scene by scene scanning, by collecting scene images, etc. In this way, the state detection device 101 can realize real-time monitoring of information of each object in the current scene.

[0069] Optionally, the state detection device 101 may be a millimeter wave radar and / or a camera, etc.

[0070] For example, a millimeter-wave radar installed above a gate can effectively detect whether a target object is approaching; the radar can also be placed high in a corner, such as where the ceiling meets the wall, to maximize space coverage and detect the target object's range, direction of movement, and speed.

[0071] For example, the camera can be installed on the ceiling, wall, column and other locations, and can cover the entrances and exits, passages, halls and other areas, minimize the monitoring blind spots, provide all-round visual coverage, capture the details of each object, and realize real-time detection of people entering and leaving. Optionally, the radar is a millimeter wave radar. The millimeter wave radar includes an antenna component, a transmitting component, a receiving component and a signal processing component. First, the transmitting component generates a transmitting signal, and then the transmitting signal is sent through the antenna component. The transmitting signal is reflected after contacting each object in the scene. The antenna component receives the reflected signal after each object is reflected, and then the receiving component filters and demodulates the reflected signal of each object, and then the reflected signal of each object is processed by the signal processing component, and the position information, speed information and contour information of each object in the current scene can be obtained. The millimeter wave wavelength is short, the antenna size can be small, and it is easy to miniaturize and integrate, which is suitable for scenes such as homes. The millimeter wave spectrum resources are rich, which can avoid interference from other devices to a certain extent and maintain high accuracy of the detection results. Among them, the energy controller 102 is a device with data processing capabilities. For example, the energy controller 102 can be a processor of a terminal and / or a server. In this way, through the energy controller 102, when there is no target object in the current scene, the preset smart switches of the plurality of smart switches 103 can be controlled to be disconnected.

[0072] Among them, the terminal may include but is not limited to: smart phones (such as Android phones, IOS phones, etc.), tablet computers, laptops, desktop computers, portable personal computers, mobile Internet devices (Mobile Internet Devices, referred to as MID), intelligent voice interaction devices, smart home appliances, etc., and the embodiments of the present application do not limit this.

[0073] Among them, the server may include but is not limited to: an independent physical server, a server cluster or distributed system composed of multiple physical servers, a cloud server that provides cloud services, cloud computing, cloud functions, cloud storage, network services, cloud communications, security services, and basic cloud computing services such as big data and artificial intelligence platforms, etc. The embodiments of the present application do not limit this.

[0074] Among them, the smart switch 103 is a device connected to the power load 200, used to connect or disconnect the connection between the power load 200 and the power supply interface. For example, the smart switch 103 receives the instruction sent by the energy controller 102, and connects or disconnects the connection between the power load 200 and the power supply interface according to the instruction. In this way, through the smart switch 103, the power load 200 and the power supply interface can be quickly connected and disconnected, reducing unnecessary waste of electric energy.

[0075] Optionally, the smart switch 103 may be a Wi-Fi smart switch, a Bluetooth smart switch, or the like.

[0076] The electrical load 200 includes an air conditioner 201 , a humidity control device 202 , and a lighting device 203 .

[0077] Among them, the air conditioner 201 is a device for adjusting the indoor air environment, which mainly changes indoor temperature, humidity, air quality and other parameters through functions such as cooling, heating, ventilation and air purification.

[0078] Optionally, the air conditioner 201 may be a split air conditioner, a window air conditioner, a central air conditioner, or the like.

[0079] For example, a central air conditioner can install one or more hosts outdoors and multiple terminal devices indoors. The outdoor hosts are mainly responsible for cooling or heating, and the refrigerant or heat medium is transported to each indoor terminal through a pipeline. The indoor terminal delivers the processed air into the indoor space. Moreover, the air conditioning of the entire scene can be uniformly conditioned, and the temperature distribution is relatively uniform.

[0080] The humidity control device 202 is a device that can control and adjust the air humidity in an environment (such as indoors, warehouses, etc.), which can meet the needs of the target object for comfortable living, intact storage of items, stable industrial production, etc. The humidity control device 202 mainly includes a dehumidification device and a humidification device.

[0081] For example, the humidity control device 202 can remove excess moisture from the air and reduce the humidity of the air. For example, when the indoor humidity reaches more than 70%, making the target object feel stuffy and sticky, and may cause problems such as moldy walls and deformed furniture, the humidity control device 202 can reduce the humidity to a comfortable level.

[0082] The lighting device 203 is a device used to provide artificial light source to illuminate a specific area or environment.

[0083] Optionally, the lighting device 203 may be an incandescent lamp, a fluorescent lamp, a light emitting diode lamp, etc.

[0084] For example, an incandescent lamp heats the filament through electric current. When the current passes through the filament, the filament resistance generates heat, and the heat accumulation makes the filament glow. Incandescent lamps have good color rendering and can truly restore the color of objects. The light they emit is relatively soft, giving people a warm feeling. Incandescent lamps can be installed in the form of chandeliers directly above the dining table. This centralized lighting method can make food look more appetizing, while illuminating the dining area and creating a warm and comfortable dining atmosphere.

[0085] In some embodiments, the energy management system 100 further includes an environment detection device 104 .

[0086] The environment detection device 104 is a device for detecting the environment parameters in the current scene. For example, the environment detection device 104 can detect the environment parameters of the current scene through an optical sensor, an electrochemical sensor, etc. In this way, the environment detection device 104 can realize real-time detection of the environment parameters of the current scene.

[0087] Optionally, the environmental parameters of the current environment include at least one of temperature, humidity, light intensity, etc.

[0088] Optionally, the environment detection device 104 may be various sensors of temperature, humidity, light intensity, etc. and combinations thereof.

[0089] In some embodiments, the energy management system 100 further includes a power generation device 105 , an inverter 106 , and an energy storage device 107 .

[0090] The power generation device 105 is a device for converting other forms of energy into electrical energy. For example, the power generation device 105 can be a solar photovoltaic power generation device that directly converts solar energy into electrical energy using photovoltaic cells based on the photoelectric effect. In this way, the power generation device 105 can realize the production of clean energy, supply it to the power load, and improve the energy utilization rate.

[0091] Optionally, the power generation equipment 105 may be a solar photovoltaic power generation equipment, a solar thermal power generation equipment, or the like.

[0092] The inverter 106 is a device for converting direct current into alternating current. For example, the inverter 106 can convert the direct current generated by the solar panel into alternating current so as to be transmitted to the household power grid or directly used by household appliances. In this way, the inverter 106 can convert direct current that is not suitable for the electrical load 200 into alternating current that can be used by the electrical load 200, thereby reducing energy loss and improving energy efficiency.

[0093] Optionally, the inverter 106 may be a square wave, sine wave, modified sine wave, or other inverter.

[0094] The energy storage device 107 is a device for storing electrical energy and capable of charging and discharging. For example, the energy storage device 107 may be a lithium-ion battery with high energy density and long cycle life. Thus, the energy storage device 107 may be used to store excess electrical energy for subsequent use, thereby improving energy utilization.

[0095] Optionally, the energy storage device 107 may be a lithium-ion battery, a lead-acid battery, a sodium-sulfur battery, or the like.

[0096] Optionally, each device in the energy management system 100 can communicate via technologies such as Wi-Fi and / or Bluetooth and / or RS485 and / or Controller Area Network (CAN) communication protocol.

[0097] For example, the energy controller 102 can obtain the detection information of the status detection device 101, the detection information of the environment detection device 104, the power generation power of the power generation device 105 and the power consumption of the power load 200 through Wi-Fi, and can also control the charging and discharging of the energy storage device 107 and the conduction or disconnection of the smart switch 103 through Wi-Fi.

[0098] Among them, Wi-Fi technology is a wireless LAN access technology based on the IEEE802.11 protocol. Wi-Fi technology can provide a high data transmission rate without the need for wiring. Users can move freely within the coverage of the Wi-Fi signal and access the network, which facilitates mobile office and the use of smart devices. Almost all smart devices such as smartphones, tablets, and laptops support Wi-Fi connections.

[0099] Based on the introduction of the above-mentioned related scenarios, the embodiment of the present application provides an artificial intelligence-based power management method. The artificial intelligence-based power management method is introduced in detail below:

[0100] See also Figure 2 An artificial intelligence-based electricity management method provided in an embodiment of the present application is implemented by steps 011 and 012, which are described in detail below.

[0101] Step 011: Determine whether there is a target object in the current scene based on a preset artificial intelligence model;

[0102] Among them, the preset artificial intelligence model is a computing architecture built based on mathematical algorithms and data, which is used to analyze and process detection information and output results.

[0103] The current scene refers to a specific activity or state situation composed of various entities (including people, equipment, environmental factors, etc.) and their relationships within a specific time and space range. For example, the current scene can be a home interior, a store or a restaurant, or a fixed preset scene.

[0104] The target object refers to an object that is active in the current scene, or the target object may be a preset object, such as a person, an animal, a robot, etc. The target object may also be a specific object among the various objects, such as a preset object.

[0105] Specifically, a state detection device (such as millimeter-wave radar, visible light camera, etc.) is set in the current scene, which can collect information of each object in the current scene, and then upload it to the preset artificial intelligence model to determine whether there is a target object among the objects in the current scene.

[0106] For example, in a home indoor scene, the target object is a person, and determining whether the target object exists among the identified objects is to determine whether the person exists among the identified objects. For another example, in a store scene, the target object is a preset object (such as the owner of the store), and determining whether the target object exists among the identified objects is to determine whether the preset object exists among the identified objects.

[0107] Based on whether there is a target object in the current scene, clarify the power demand of the current scene. Whether there is a target object or not, the power demand is different. When there is no target object in the current scene, some power loads that meet the requirements of the scene when the target object exists (temperature requirements, humidity requirements, lighting requirements, etc.) do not need to run (for example, air conditioners, lighting devices, etc.). The power demand at this time is to turn off the relevant loads to reduce the waste of electricity; when there is a target object in the current scene, these power loads need to work normally to meet the requirements of the scene when the target object exists.

[0108] In this way, it is possible to accurately and reliably detect whether a target object exists in the current environment, facilitating subsequent power management.

[0109] Step 012: If the target object does not exist, a preset smart switch among the multiple smart switches is controlled to be disconnected.

[0110] The preset smart switch refers to a smart switch whose state is preset based on the target object existing in the current scene.

[0111] Specifically, the energy controller obtains the detection information of the state detection device, including whether there is a target object in the current scene, and then processes it, and then decides whether the preset smart switch is on or off. If there is no target object in the current scene, the energy controller controls the preset smart switch to be turned off, which can effectively reduce the standby power consumption of many loads.

[0112] For example, in a home indoor scene, the target object pre-sets a preset smart switch among multiple smart switches to turn on according to the power consumption situation when indoors. When the target object leaves the room, the energy controller controls the preset smart switch among the multiple smart switches to turn off.

[0113] In this way, the preset intelligent switch is disconnected based on the fact that the target object is not in the scene, so that the target object can reduce unnecessary power consumption.

[0114] The artificial intelligence-based electricity management method of the present application detects the information of each object in the current scene through a status detection device, and then uploads it to a preset artificial intelligence model for analysis to determine the existence of the target object. When the target object does not exist, it can be determined that the target object is out. At this time, if most of the power loads serving the target object in the current scene continue to work, it will bring additional energy consumption. Therefore, when the target object does not exist in the current scene, each preset smart switch among the multiple smart switches can be disconnected to stop the power loads connected to each preset smart switch, thereby avoiding unnecessary energy consumption and improving power efficiency.

[0115] See also Figure 3 In some embodiments, step 011 includes:

[0116] Step 0111: input radar information into a preset artificial intelligence model, and output a first detection result, where the first detection result includes whether a target object exists in the current scene;

[0117] The radar information is data information of each object in the current scene collected by the millimeter wave radar. Optionally, the radar information includes at least one of contour information, position information and speed information. Contour information refers to the external boundary shape information used to describe an object or a human body.

[0118] Among them, the first detection result is the detection result output by the preset artificial intelligence model after the radar information is input into the preset artificial intelligence model. The first detection result includes whether there is a target object in the current scene.

[0119] Specifically, the radar information of each object in the current scene detected by the millimeter-wave radar is input into a preset artificial intelligence model, which can output a first detection result to determine whether there is a target object in the current scene.

[0120] Step 0112: input image information into a preset artificial intelligence model, and output a second detection result, where the second detection result includes whether a target object exists in the current scene;

[0121] The image information is data information of each object in the current scene collected by the camera.

[0122] Among them, the second detection result is the detection result output by the preset artificial intelligence model after the image information is input into the preset artificial intelligence model, and the second detection result includes whether there is a target object in the current scene.

[0123] Specifically, the image information of each object in the current scene detected by the camera is input into a preset artificial intelligence model, which can output a second detection result to determine whether there is a target object in the current scene.

[0124] Step 0113: Input radar information and image information into a preset artificial intelligence model, and output a third detection result, where the third detection result includes whether there is a target object in the current scene.

[0125] Among them, the third detection result is the detection result output by the preset artificial intelligence model after the radar information and image information are input into the preset artificial intelligence model. The third detection result includes whether there is a target object in the current scene.

[0126] Specifically, the radar information of each object in the current scene detected by the millimeter wave radar and the image information of each object in the current scene detected by the camera are input into a preset artificial intelligence model, which can output a third detection result to determine whether there is a target object in the current scene.

[0127] In this way, by inputting the information of each object detected by the state detection device into a preset artificial intelligence model, it is possible to determine faster and more accurately whether there is a target object in the current scene.

[0128] See also Figure 4 In some embodiments, step 0111 includes:

[0129] Step 01111: outputting a first detection result based on whether position information and / or speed information of a plurality of consecutive frames of any object changes in each object;

[0130] Specifically, after the radar information of each object in the current scene detected by the millimeter-wave radar is input into the preset artificial intelligence model, the position information and / or speed information in the radar information of each object is analyzed. If the position information and / or speed information of multiple consecutive frames of any object changes, the first detection result is output that the target object exists in the current scene; if the position information and / or speed information of multiple consecutive frames of any object does not change, the first detection result is output that the target object does not exist in the current scene.

[0131] Step 01112: Among the various objects, based on matching the contour information of any object with the contour of the target object, a first detection result is output.

[0132] Specifically, after the radar information of each object in the current scene detected by the millimeter-wave radar is input into the preset artificial intelligence model, the contour information in the radar information of each object is analyzed. If the contour information of any object matches the contour of the target object, the first detection result is output that the target object exists in the current scene; if the contour information of any object does not match the contour of the target object, the first detection result is output that the target object does not exist in the current scene.

[0133] Step 01113: Among the objects, if the position information and / or speed information of multiple consecutive frames of any object changes, and / or the contour information of any object matches the contour of the target object, output a first detection result.

[0134] Specifically, after the radar information of each object in the current scene detected by the millimeter-wave radar is input into the preset artificial intelligence model, the radar information of each object is analyzed. If the position information and / or speed information of multiple consecutive frames of any object changes, and / or the contour information of any object matches the contour of the target object, then the first detection result is output that the target object exists in the current scene; if the position information and / or speed information of multiple consecutive frames of any object does not change, and the contour information of any object does not match the contour of the target object, then the first detection result is output that the target object does not exist in the current scene.

[0135] In this way, it is possible to accurately determine whether there is a target object in the current scene.

[0136] See also Figure 5 In some embodiments, the power management method based on artificial intelligence further includes:

[0137] Step 013: In the case where the target object exists, based on the environmental parameters, the first target intelligent switch is controlled to be turned on or off, and the first target intelligent switch matches the environmental parameters.

[0138] Environmental parameters are indicators of various physical, chemical and biological factors used to describe and quantify environmental status and characteristics. Environmental parameters include at least one of temperature, humidity and light intensity.

[0139] The first target smart switch refers to a smart switch that matches the environmental parameters of the current scene. For example, the power load corresponding to the first target smart switch corresponding to temperature is an air conditioner, the power load corresponding to the first target smart switch corresponding to humidity is a humidity control device, and the power load corresponding to the first target smart switch corresponding to light intensity is a lighting device. It can be understood that the difference in the environmental parameters of the target object will lead to different power requirements of the target object.

[0140] Specifically, when there is a target object in the current scene, the environmental detection device collects various environmental parameters of the current scene, the energy controller obtains various environmental parameters of the current scene, and the energy controller controls the conduction or disconnection of the first target intelligent switch corresponding to each environmental parameter based on the various environmental parameters of the current scene.

[0141] For example, the millimeter-wave radar detects whether there is a target object in the scene, the light intensity sensor detects the light intensity value of the current scene, and then uploads it to the energy controller for processing. The energy controller controls the on and off of the electrical load related to the light intensity to meet the demand.

[0142] For example, when the target object is in different environmental parameters, the power demand of the target object also changes dynamically. When the current scene temperature cannot meet the target object's needs, the energy controller controls the first target intelligent switch corresponding to the air conditioner to turn on or off to adjust the temperature; when the current scene humidity cannot meet the target object's needs, the energy controller controls the first target intelligent switch corresponding to the humidity adjustment device to turn on or off to adjust the humidity.

[0143] In this way, when the target object exists in the current scene, the on and off of the first target intelligent switch corresponding to each environmental parameter is controlled based on the environmental parameters of the current scene, so that the power demand of the target object can be met more accurately and flexibly.

[0144] See also Figure 6 In some embodiments, optionally, step 013 includes:

[0145] Step 0131: when the environmental parameter is within the set parameter range, disconnect the first target smart switch;

[0146] The set parameter range is the corresponding environmental parameter value range that the target object sets through the energy controller to meet its own needs. The set parameter range includes the set temperature range, humidity range and light intensity range.

[0147] Specifically, after the energy controller obtains the environmental parameters collected by the environmental detection equipment, it compares the obtained environmental parameters with the corresponding set parameter range. If the environmental parameters of the target object are within the set parameter range, the corresponding first target smart switch is controlled to be disconnected.

[0148] For example, when the temperature in the current scene where the target object is located meets the requirements, and the temperature of the environmental parameter obtained by the energy controller is within the set temperature range, the energy controller controls the first target intelligent switch corresponding to the temperature to disconnect, and the air conditioner stops running. When the humidity in the current scene where the target object is located meets the requirements, and the environmental humidity is within the set humidity parameter range, the energy controller controls the first target intelligent switch of the corresponding humidity adjustment device to disconnect, and the humidity adjustment device stops running.

[0149] In this way, when the environmental parameter is within the set parameter range, the needs of the target object are met, so the corresponding first target smart switch is turned off to reduce unnecessary power consumption.

[0150] Step 0132: When the environmental parameter is outside the set parameter range, turn on the first target intelligent switch.

[0151] Specifically, the energy controller obtains the environmental parameters collected by the environmental detection device, and compares the obtained environmental parameters with the corresponding set parameter range. If the environmental parameters of the target object are outside the set parameter range, the corresponding first target smart switch is controlled to be turned on.

[0152] For example, when the light intensity in the current scene where the target object is located cannot meet the demand, the light intensity of the environmental parameters obtained by the energy controller is outside the set light intensity range, then the energy controller controls the first target intelligent switch corresponding to the light intensity to turn on, and the lighting device turns on to meet the power demand of the target object.

[0153] In this way, when the environmental parameters are outside the set parameter range, the needs of the target object are not met, so turning on the corresponding first target smart switch can better meet the power demand of the target object.

[0154] See also Figure 7 In some embodiments, the power management method based on artificial intelligence further includes step 014:

[0155] Step 014: In the case where the target object exists, based on the state information, the second target intelligent switch is controlled to be turned on or off, and the second target intelligent switch matches the state information.

[0156] Among them, the state information is information that characterizes the state of the target object. For example, the state information is information corresponding to the posture of the target object, such as the state information is divided into a sleeping state and an active state. Different postures of the target object correspond to different states of the target object. If the target object is in a lying posture and continues for a preset time (such as 15 minutes, 30 minutes, etc.), it can be determined that the target object is in a sleeping state, and when the target object is in other postures (such as sitting, standing, lying down for a time shorter than a preset time, etc.), it is determined that the target object is in an active state.

[0157] The second target smart switch refers to a smart switch that matches the state information of the target object. It can be understood that when the target object is in different states, the requirements for the environment (such as temperature requirements, humidity requirements, lighting requirements, etc.) are different.

[0158] Specifically, when there is a target object in the current scene, the state detection device determines whether the state of the target object is a sleeping state or an active state based on the detected information. Different states correspond to different power requirements of the target object and correspond to different second target smart switches. The energy controller controls the on and off of the second target smart switch based on the current state of the target object to meet the power requirements of the target object.

[0159] For example, when the target object is in a sleeping state, the target object's demand for light intensity is reduced. At this time, the energy controller controls the second target intelligent switch corresponding to the light intensity to disconnect based on the acquired state information of the target object as a sleeping state, thereby meeting the demand of the target object.

[0160] In this way, based on different states of the target object and corresponding to different power demands, the second target intelligent switch is controlled to be turned on or off, which can better meet the power demands of the target object.

[0161] In some embodiments, the preset smart switch and the second target smart switch are smart switches defined and configured by the target object through the energy controller, or smart switches corresponding to power loads with a priority lower than the preset priority.

[0162] Specifically, due to the differences in power consumption requirements that may exist among different target objects, during the settings, the target object can customize the corresponding relationship between multiple smart switches and loads according to its own needs.

[0163] Alternatively, different power loads have different operation priorities, and the higher the priority, the higher the need for the power load to keep running. For example, the power loads include power loads that need to run continuously, power loads that run on a scheduled basis (such as lighting devices), and power loads that run on demand (such as humidity control devices), and the priorities are reduced in order.

[0164] When there is no target object in the current scene, the preset smart switch is the smart switch corresponding to the power load with a priority lower than the preset priority (such as the power load that runs on demand); when there is a target object in the current scene and the target object is in a sleep state, the second target smart switch is the smart switch corresponding to the power load with a priority lower than the preset priority (such as the power load that runs on demand).

[0165] Adjust the priority relationship between the smart switches corresponding to different power loads in order to achieve better usage effects.

[0166] For example, the target object can customize the corresponding smart switches of lighting devices, air conditioners, etc. through the energy controller, and can also adjust the priority of the smart switch corresponding to the air conditioner to be placed above the smart switch of the humidity control device.

[0167] In this way, the target object's customized power load corresponds to the smart switch and their mutual priorities, which can facilitate the subsequent energy controller to perform corresponding operations and better meet the power demand of the target object.

[0168] See also Figure 8 In some embodiments, optionally, step 014 includes:

[0169] Step 0141: when the target object is in a sleeping state, controlling the second target intelligent switch to be turned off;

[0170] Specifically, when the energy controller obtains that the detection result of the state detection device is the sleep state, the energy controller controls the second target smart switch corresponding to the sleep state to disconnect the power supply.

[0171] For example, when the target object is in a sleeping state, the demand for the use of lighting devices and the like is reduced, and the energy controller can control the second target smart switch corresponding to the sleeping state to disconnect the power supply to save energy.

[0172] In this way, based on the sleep state of the target object, the second target intelligent switch is controlled to be disconnected, thereby reducing power waste while better meeting the current needs of the target object.

[0173] Step 0142: When the target object is in an active state, control the second target smart switch to be turned on.

[0174] Specifically, when the energy controller obtains that the detection result of the state detection device is an active state, the energy controller controls the second target smart switch corresponding to the active state to be turned on.

[0175] For example, when the target object is in an active state, the demand for the use of humidity adjustment devices and the like increases, and the energy controller can control the second target intelligent switch corresponding to the active state to turn on, thereby improving the power efficiency while meeting the power demand of the target object.

[0176] In this way, based on the activity state of the target object, controlling the second target intelligent switch to be turned on can better meet the current needs of the target object and improve the utilization rate of electric energy.

[0177] See also Fig. 9 In some embodiments, the power management method based on artificial intelligence further includes steps 015 and 016:

[0178] Step 015: Set the set time period;

[0179] The set time period refers to the time period during which there is a need for status detection of the target object.

[0180] Specifically, when the status detection device is running continuously, it will also bring additional power consumption. In some time periods (such as working time outside), the target object is basically outside the scene, and in other time periods (such as sleeping time at night), the target object is basically in the scene. At this time, it is unnecessary to detect whether there is a target object in the scene. Therefore, the target object can customize the set time period according to its own needs.

[0181] In this way, by setting the set time period, unnecessary load standby time of the status detection device can be reduced, avoiding waste of electric energy.

[0182] Step 016: When the current time is within the set time period, turn on the status detection device.

[0183] Specifically, when the current time is within the set time period, the state detection device is turned on for detection. When the current time is outside the set time period, the state detection device is kept off. In this way, the state detection device is operated on demand, which can further reduce the additional power consumption caused by the continuous operation of the state detection device.

[0184] In this way, by detecting that the set time period reaches the start state detection device, unnecessary load standby time can be reduced and waste of electric energy can be reduced.

[0185] See also Fig.10 In some embodiments, the power management method based on artificial intelligence further includes steps 017 and 018:

[0186] Step 017: Obtain the power generation power of the power generation equipment and the power consumption of the power load;

[0187] Specifically, the energy controller obtains the power generation power of the power generation equipment and the power consumption of the power load, and can count the flow of energy in real time to facilitate subsequent power consumption management.

[0188] Step 018: Based on the power generation and power consumption, the energy storage device is controlled to charge and discharge.

[0189] Specifically, the energy controller obtains the power generation power of the power generation equipment and the power consumption of the power load, compares the two, and based on the comparison result, sends instructions to the energy storage device to control its charging and discharging.

[0190] Optionally, if the power generation of the power generation equipment is greater than the power consumption of the power load, the energy storage equipment is controlled to charge; if the power generation of the power generation equipment is less than the power consumption of the power load, the energy storage equipment is controlled to discharge and supply the power load. If the power generation of the power generation equipment is exactly equal to the power consumption of the power load, the power generated by the power generation equipment is preferentially supplied to the power load.

[0191] Optionally, if the generated power is greater than the consumed power and the energy storage device has stored full power, the excess power will be transmitted to the power grid to reduce energy loss.

[0192] For example, when there is sufficient sunshine, the power generation efficiency of the solar photovoltaic power generation equipment is high and is greater than the power consumption of electrical loads such as air conditioners. The energy controller then controls the energy storage device to store the excess power generation. If the energy storage device is full, the excess power generation will be transmitted to the power grid.

[0193] In this way, by comparing the power generation and power consumption and controlling the charging and discharging of the energy storage equipment, it is possible to achieve efficient use of clean energy, reduce electricity costs, and improve overall electricity efficiency.

[0194] According to the method described in the above embodiment, the present application embodiment also provides an artificial intelligence-based power management device 300, which is used to execute the steps in the artificial intelligence-based power management method. Fig.11 , Fig.11 : is a module diagram of an artificial intelligence-based power management device 300 provided in an embodiment of the present application. The artificial intelligence-based power management device 300 includes:

[0195] A determination module 310 is used to determine whether there is a target object in the current scene;

[0196] The control module 320 is used to control a preset smart switch among the multiple smart switches to be disconnected when there is no target object; when there is a target object, control the first target smart switch to be turned on or off based on environmental parameters, and the first target smart switch matches the environmental parameters.

[0197] It should be noted that the specific details of each module unit in the above-mentioned artificial intelligence-based power management device have been described in detail in the embodiment of the above-mentioned artificial intelligence-based power management method, and will not be repeated here.

[0198] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0199] In some embodiments, the artificial intelligence-based power management device in the embodiments of the present application can be implemented in hardware, such as an energy controller, or an electronic device or a component thereof, such as an integrated circuit or chip; the artificial intelligence-based power management device can also be implemented in software, such as as an application installed in an electronic device.

[0200] Please refer again Figure 1The energy management system 100 provided in the embodiment of the present application includes a state detection device 101, which is used to detect whether there is a target object in the current scene; a plurality of intelligent switches 103, which are connected to the power load 200 and are used to turn on or off the connection between the power load 200 and the power supply interface; an energy controller 102, which is used to execute the various processes of the embodiment of the above-mentioned artificial intelligence-based power management method.

[0201] In some embodiments, see Fig.12 , Fig.12 4 is a schematic diagram of the structure of the energy controller provided in the embodiment of the present application. The energy controller 400 includes a processor 410 and a memory 420. The memory 420 stores a computer program 430 that can be run on the processor 410. When the program 430 is executed by the processor 410, each process of the embodiment of the power management method based on artificial intelligence is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0202] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the embodiment of the above-mentioned artificial intelligence-based electricity management method are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0203] The processor may be a processor in the electronic device in the above embodiment. The computer readable storage medium may be a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0204] Computer readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other solid-state memory technology, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that computer storage media are not limited to the above.

[0205] The embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned power management method based on artificial intelligence when executed by a processor. The processor may be a processor in the electronic device in the above-mentioned embodiment. When the computer program is executed by the processor, each process of the embodiment of the power management method based on artificial intelligence is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0206] It is understandable that in the specific implementation of this application, data related to user identity or characteristics is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0207] In the description of this specification, the descriptions with reference to the terms "certain embodiments", "in an example", "exemplarily", etc., mean that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0208] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0209] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A power management method based on artificial intelligence, characterized in that: Applied to an energy management system, the energy management system includes a state detection device and a plurality of intelligent switches; the state detection device is used to detect information of each object in the current scene; The intelligent switch is connected to the electrical load; The intelligent switch is used to connect or disconnect the power load from the power supply interface. The method includes: Based on a preset artificial intelligence model, determining whether there is a target object in the current scene; If the target object does not exist, a preset smart switch among the multiple smart switches is controlled to be disconnected.

2. The power management method based on artificial intelligence according to claim 1 is characterized in that: The state detection device includes a millimeter wave radar and / or a camera, the millimeter wave radar is used to obtain radar information of each object in the current scene, and the camera is used to obtain image information of each object in the current scene. The determining whether the target object exists in the current scene based on a preset artificial intelligence model includes: Inputting the radar information into the preset artificial intelligence model, and outputting a first detection result, wherein the first detection result includes whether the target object exists in the current scene; Inputting the image information into the preset artificial intelligence model, and outputting a second detection result, wherein the second detection result includes whether the target object exists in the current scene; The radar information and the image information are input into the preset artificial intelligence model, and a third detection result is output, where the third detection result includes whether the target object exists in the current scene.

3. The power management method based on artificial intelligence according to claim 2 is characterized in that: The radar information includes at least one of profile information, position information and speed information, and the inputting the radar information into the preset artificial intelligence model and outputting the first detection result includes: Among the objects, outputting the first detection result based on whether the position information and / or speed information of a plurality of consecutive frames of any object changes; and / or, The first detection result is output based on whether the contour information of any object among the objects matches the contour of the target object.

4. The power management method based on artificial intelligence according to claim 1 is characterized in that: The energy management system further includes an environment detection device, and the environment detection device is used to detect environmental parameters. The method further includes: In the case where the target object exists, the first target smart switch is controlled to be turned on or off based on the environmental parameter, and the first target smart switch matches the environmental parameter.

5. The power management method based on artificial intelligence according to claim 4 is characterized in that: Based on the environmental parameter, controlling the corresponding first target smart switch to be turned on or off includes: When the environmental parameter is within a set parameter range, disconnecting the first target smart switch; When the environmental parameter is outside the set parameter range, the first target smart switch is turned on.

6. According to the power management method based on artificial intelligence in claim 1, the state detection device is used to detect the state information of the target object, characterized in that: The method further comprises: In the case where the target object exists, based on the state information, the second target smart switch is controlled to be turned on or off, and the second target smart switch matches the state information.

7. The power management method based on artificial intelligence according to claim 6 is characterized in that: The state information includes a sleep state and an active state. Based on the state information, controlling the second target smart switch to be turned on or off includes: When the target object is in a sleeping state, controlling the second target intelligent switch to be disconnected; When the target object is in an active state, the second target smart switch is controlled to be turned on.

8. The power management method based on artificial intelligence according to claim 1 is characterized in that: The power management method based on artificial intelligence also includes: Set a set time period; When the current time is within the set time period, the state detection device is turned on.

9. An energy management system, characterized in that: include: A state detection device, wherein the state detection device is used to detect whether there is a target object in the current scene; A plurality of intelligent switches, wherein the intelligent switches are connected to electrical loads and are used to switch on or off the connection between the electrical loads and the power supply interface; An energy controller, wherein the energy controller is used to execute the artificial intelligence-based electricity management method described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the artificial intelligence-based electricity management method described in any one of claims 1 to 8 is implemented.

Images