Intelligent decision-making method and system based on large model

Abstract

The invention is suitable for the field of intelligent decision making, and provides an intelligent decision making method and system based on a large model, and the method comprises the steps: collecting a first outdoor environment parameter and a second outdoor environment parameter at regular time; acquiring position information and first environment parameters of a plurality of indoor intelligent windows, and generating airflow orientation information of the plurality of intelligent windows; based on the indoor and outdoor first environment parameters, the second environment parameters and the airflow orientation information of the multiple intelligent windows, an indoor ventilation control strategy is generated; acquiring an outdoor third environment parameter and indoor wind speed information in real time; and generating a ventilation control strategy adjusting instruction based on the outdoor third environment parameter and the indoor wind speed information. The method and the system have the beneficial effects that the method and the system judge the airflow orientation information of a plurality of indoor rooms or halls based on the multi-mode outdoor environment information, so that a specific indoor ventilation control strategy is generated; indoor unmanned intelligent ventilation control is achieved, and the flexible adjusting capacity and the decision-making capacity of the intelligent window are improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent decision-making, and in particular relates to an intelligent decision-making method and system based on a large model. Background Art

[0002] With the rapid development of science and technology and the improvement of life quality, smart home has become an important part of modern families. Smart home technology takes the Internet of Things as the key technology, integrates automatic control technology, computer technology, big data, artificial intelligence and cloud computing and other advanced technologies, and organically combines home appliance control, environmental monitoring, audio and video entertainment, information management and other functions to provide users with a more convenient, comfortable and intelligent life experience.

[0003] Traditional windows require manual operation and cannot be adjusted automatically according to environmental changes, which not only affects living comfort, but also fails to effectively save energy. Smart windows integrate advanced sensors, controllers, actuators and communication technologies to sense indoor and outdoor environmental parameters in real time, and automatically adjust the size and position of windows according to user habits and needs, thereby optimizing the indoor environment, improving living comfort, and effectively saving energy.

[0004] At present, the development of smart windows has made some progress, but there are still some technical bottlenecks and challenges. For example, the smart window has insufficient analytical ability when performing opening and closing degree control and adjustment, and its decision-making ability needs to be further optimized. In view of the above problems, it is urgent to develop an intelligent decision-making method and system based on a large model. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent decision-making method and system based on a large model, aiming to solve the problems raised in the above-mentioned background technology.

[0006] The present invention is implemented in this way. On the one hand, an intelligent decision-making method based on a large model comprises:

[0007] Regularly collect and identify outdoor first environmental parameters and second environmental parameters;

[0008] Acquire location information of multiple smart windows in the room and a first environmental parameter, and generate targeted association information of multiple smart windows;

[0009] Generate an indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the targeted association information of multiple smart windows;

[0010] Real-time collection of outdoor third environment parameters and indoor wind speed information;

[0011] Based on the outdoor third environmental parameter and the indoor wind speed information, a ventilation control strategy adjustment instruction is generated.

[0012] As a further solution of the present invention, the timed collection and identification of the first outdoor environmental parameter and the second outdoor environmental parameter specifically includes:

[0013] Collect real-time wind direction information and real-time air quality index;

[0014] Determine whether the real-time air quality index is within the excellent threshold range;

[0015] If the real-time air quality index is within the excellent threshold range, a long-term instruction is generated;

[0016] Determine whether the real-time air quality index is within the good threshold range;

[0017] If the real-time air quality index is within the excellent threshold range, a short-term instruction is generated.

[0018] As a further solution of the present invention, the acquiring of the location information of multiple smart windows in the room and the first environmental parameter to generate multiple smart window targeting association information specifically includes:

[0019] Collecting position information of multiple smart windows;

[0020] Based on the plurality of smart window position information, generating a plurality of smart window orientation information;

[0021] Determine whether the real-time wind direction information is consistent with the orientation information of multiple smart windows one by one;

[0022] If the real-time wind direction information is consistent with the orientation information of multiple smart windows, multiple diversion marks are generated;

[0023] Based on multiple diversion markers, multiple targeted smart windows are determined;

[0024] Based on the targeted smart window, a plurality of targeted smart window horizontal planes are generated;

[0025] Generate real-time wind direction slices based on real-time wind direction information;

[0026] The angle between the real-time wind direction section and the horizontal planes of multiple targeted smart windows is calculated to generate multiple conditional angle values.

[0027] As a further solution of the present invention, the generation of the indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the airflow direction information of the plurality of smart windows specifically includes:

[0028] Collect the areas of multiple targeted smart windows, and calculate and send the opening area of ​​each targeted smart window based on multiple conditional angle values;

[0029] The calculation process of the opening area of ​​the targeted smart window is:

[0030] Oi=Ai·g(θi)

[0031] g(θ i )=cos n (θ i );

[0032] Where i is the i-th targeted smart window, θ is the conditional angle value of the i-th targeted smart window, A i is the area of ​​the i-th targeted smart window, O i is the opening area of ​​the i-th targeted smart window, g(θ i ) is the opening coefficient of the i-th targeted smart window determined according to θ, its value range is [0,1], and n is a positive real number.

[0033] As a further solution of the present invention, the generating of the ventilation control strategy adjustment instruction based on the outdoor third environmental parameter and the indoor wind speed information specifically includes:

[0034] Collect raindrop sensing values ​​and indoor wind speed values;

[0035] Determine whether the raindrop sensing value is greater than the rainfall threshold;

[0036] If the raindrop sensing value is greater than the rainfall threshold, a full-close control command is generated;

[0037] Determine whether the indoor wind speed value is greater than the wind speed threshold;

[0038] If the indoor wind speed value is greater than the wind speed threshold, calculate the difference ratio between the indoor wind speed value and the wind speed threshold;

[0039] Based on the difference ratio, a proportional closing control instruction is generated.

[0040] As a further solution of the present invention, on the other hand, an intelligent decision-making system based on a large model comprises:

[0041] A timing collection and identification module, used for timing collection and identification of a first outdoor environmental parameter and a second outdoor environmental parameter;

[0042] An acquisition module, used to acquire location information of multiple indoor smart windows and a first environmental parameter;

[0043] A first generating module is used to generate a plurality of smart window targeting association information;

[0044] The second generation module is used to generate an indoor ventilation control strategy;

[0045] Real-time acquisition module, used to collect outdoor third environment parameters and indoor wind speed information in real time;

[0046] The third generating module is used to generate a ventilation control strategy adjustment instruction based on the third outdoor environmental parameter and the indoor wind speed information.

[0047] As a further solution of the present invention, the timing acquisition identification module specifically includes:

[0048] A first collection unit, used to collect real-time wind direction information and real-time air quality index;

[0049] A first judgment unit, used to judge whether the real-time air quality index is within an excellent threshold range;

[0050] A first generating unit, configured to generate a long-term instruction if the real-time air quality index is within a superior threshold range;

[0051] The second judgment unit is used to judge whether the real-time air quality index is within a good threshold range;

[0052] The second generating unit is used to generate a short-term instruction if the real-time air quality index is within the excellent threshold range.

[0053] As a further solution of the present invention, the first generating module specifically includes:

[0054] A second collecting unit, used for collecting position information of multiple smart windows;

[0055] A third generating unit, configured to generate a plurality of smart window orientation information based on the plurality of smart window position information;

[0056] A third judgment unit is used to judge whether the real-time wind direction information is consistent with the orientation information of the multiple smart windows one by one;

[0057] A fourth generating unit, configured to generate a plurality of diversion marks if the real-time wind direction information is consistent with the orientation information of the plurality of smart windows;

[0058] A determination unit, configured to determine a plurality of targeted smart windows based on a plurality of diversion markers;

[0059] A fifth generating unit, configured to generate a plurality of targeted smart window horizontal planes based on the targeted smart window;

[0060] A sixth generating unit, configured to generate a real-time wind direction section based on the real-time wind direction information;

[0061] A calculation unit, used for calculating the angle between the real-time wind direction section and the horizontal planes of multiple targeted smart windows;

[0062] The seventh generating unit is used to generate a plurality of conditional angle values.

[0063] The present invention provides an intelligent decision-making method and system based on a large model. The method and system judge the airflow direction information of multiple rooms or halls indoors based on multimodal outdoor environmental information, and then generate a specific indoor ventilation control strategy to realize unmanned intelligent ventilation control indoors, thereby improving the flexible adjustment capability and decision-making ability of smart windows. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is the main flow chart of an intelligent decision-making method based on a large model.

[0065] Figure 2 The invention discloses a flow chart for regularly collecting and identifying a first outdoor environmental parameter and a second outdoor environmental parameter in an intelligent decision-making method based on a large model.

[0066] Figure 3 The invention discloses a flow chart for obtaining location information of multiple smart windows in a room and first environmental parameters in an intelligent decision-making method based on a large model to generate targeted association information of multiple smart windows.

[0067] Figure 4 The invention is a flowchart for generating an indoor ventilation control strategy based on first indoor and outdoor environmental parameters, second environmental parameters and airflow direction information of multiple smart windows in an intelligent decision-making method based on a large model.

[0068] Figure 5 The invention is a flow chart for generating ventilation control strategy adjustment instructions based on outdoor third environment parameters and indoor wind speed information in an intelligent decision-making method based on a large model.

[0069] Figure 6 It is the main structure diagram of an intelligent decision-making system based on a large model.

[0070] Figure 7 It is a structural block diagram of a timing acquisition and recognition module in an intelligent decision-making system based on a large model.

[0071] Figure 8 It is a structural block diagram of the first generation module in an intelligent decision-making system based on a large model. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0073] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0074] The present invention provides a large model-based intelligent decision-making method and system, which solves the technical problems in the background technology.

[0075] like Figure 1 As shown, it is a main flow chart of an intelligent decision-making method based on a large model provided by an embodiment of the present invention, and the intelligent decision-making method based on a large model includes:

[0076] Step S100: regularly collecting and identifying first and second outdoor environmental parameters;

[0077] Step S200: acquiring location information of multiple smart windows in the room and a first environmental parameter, and generating multiple smart window targeting association information;

[0078] Step S300: generating an indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the targeted association information of multiple smart windows;

[0079] Step S400: collecting outdoor third environmental parameters and indoor wind speed information in real time;

[0080] Step S500: Generate a ventilation control strategy adjustment instruction based on the third outdoor environmental parameter and the indoor wind speed information.

[0081] When this embodiment is applied, there are multiple rooms or halls distributed indoors, and each room or hall is provided with a smart window. The smart window is based on large model training and is connected and controlled by the same local area network. Each smart window is equipped with a window screen to intercept outdoor foreign matter or impurities. When making intelligent decisions on indoor ventilation, it is ensured that the window body and window screen of each smart window are in a closed state in advance, and the door body of each room or hall is in an open state, thereby ensuring the integrity of indoor ventilation. If there is no need to ventilate a room or hall, the door body of the room or hall can be closed in advance. First, the first outdoor environmental parameter and the second environmental parameter are collected and identified at regular intervals. The first environmental parameter is real-time wind direction information, and the second environmental parameter is real-time air quality index. At the same time, the position information of multiple smart windows indoors and the first environmental parameter are obtained. Based on the position information of multiple smart windows indoors and the first environmental parameter, analysis is performed. Calculate, under the real-time wind direction, the targeted correlation information of multiple smart windows, and then generate an indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and their identification results, and the targeted correlation information of multiple smart windows. When the indoor ventilation control strategy is generated, multiple smart windows can be fully opened synchronously. When multiple smart windows can be fully opened synchronously, multiple rooms or halls indoors can realize ventilation convection. When multiple rooms or halls indoors can realize ventilation convection, the outdoor third environmental parameter and indoor wind speed information are collected in real time. The third environmental parameter information is rainfall information. If it starts to rain outdoors, in order to prevent rainwater from falling into the room, a ventilation control strategy adjustment instruction will be generated. When the indoor wind speed is too high, a ventilation control strategy adjustment instruction will also be generated to prevent the indoor wind speed from being too high and causing damage to indoor items. After the ventilation control strategy adjustment instruction is generated, the opening degree of multiple smart windows will be closed or adjusted.

[0082] like Figure 2 As shown, as a preferred embodiment of the present invention, the timed collection and identification of the first outdoor environmental parameter and the second outdoor environmental parameter specifically includes:

[0083] Step S101: collecting real-time wind direction information and real-time air quality index;

[0084] Step S102: determining whether the real-time air quality index is within an excellent threshold range;

[0085] Step S103: If the real-time air quality index is within the excellent threshold range, a long-term instruction is generated;

[0086] Step S104: determining whether the real-time air quality index is within a good threshold range;

[0087] Step S105: If the real-time air quality index is within the excellent threshold range, a short-term instruction is generated;

[0088] When this embodiment is used, real-time wind direction information is first collected, and then the real-time air quality index, i.e., AQI, is based on the ambient air quality standards and the impact of various pollutants on human health, ecology, and environment, and simplifies the concentrations of several conventionally monitored air pollutants into a single conceptual index value form. The value range of AQI is from 0 to 500, which is used to indicate the degree of air pollution and air quality conditions, and is divided into different levels to evaluate the impact on human health, and to determine whether the real-time air quality index is in the excellent threshold range. The excellent threshold is set to 0-50. Within this range, the air quality is evaluated as excellent and has no impact on human health. At this time, the air quality is satisfactory, there is basically no air pollution, and all kinds of people can move normally. If the real-time air quality index is in the excellent threshold range, a long-term instruction is generated, and ventilation can be performed for a long time. The good threshold is set to 51-100. Within this range, the air quality is evaluated as good and has no significant impact on human health. However, certain pollutants in the air may have a weaker impact on the health of a very small number of extremely sensitive people. Therefore, it is recommended that a very small number of extremely sensitive people should reduce outdoor activities. If the real-time air quality index is within the excellent threshold range, a short-term instruction will be generated to ventilate for a short time.

[0089] like Figure 3 As shown, as a preferred embodiment of the present invention, the acquiring of the indoor location information of multiple smart windows and the first environmental parameter and the generation of multiple smart window targeting association information specifically includes:

[0090] Step S201: collecting position information of multiple smart windows;

[0091] Step S202: generating a plurality of smart window orientation information based on a plurality of smart window position information;

[0092] Step S203: determining whether the real-time wind direction information is consistent with the orientation information of the multiple smart windows one by one;

[0093] Step S204: if the real-time wind direction information is consistent with the orientation information of the multiple smart windows, generate multiple diversion marks;

[0094] Step S205: determining a plurality of targeted smart windows based on a plurality of diversion markers;

[0095] Step S206: generating a plurality of targeted smart window horizontal planes based on the targeted smart window;

[0096] Step S207: generating a real-time wind direction section based on the real-time wind direction information;

[0097] Step S208: calculating the angle between the real-time wind direction section and the horizontal planes of the multiple targeted smart windows, and generating multiple conditional angle values;

[0098] When this embodiment is applied, first, position information of multiple smart windows is collected, and based on the position information of multiple smart windows, orientation information of multiple smart windows is generated. It is determined one by one whether the real-time wind direction information is consistent with the orientation information of multiple smart windows. If the real-time wind direction information is consistent with the orientation information of multiple smart windows, it indicates that the real-time wind can be introduced into the room through a certain smart window, and multiple diversion marks are generated. Based on the multiple diversion marks, multiple targeted smart windows are determined. The targeted smart window is a smart window that can divert in real time. Based on the targeted smart window, multiple targeted smart window horizontal planes are generated. Based on the real-time wind direction information, a real-time wind direction section is generated. The angle between the real-time wind direction section and the horizontal planes of multiple targeted smart windows is calculated to generate multiple conditional angle values.

[0099] like Figure 4 As shown, as a preferred embodiment of the present invention, the generation of the indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the airflow direction information of multiple smart windows specifically includes:

[0100] Step S301: collecting areas of multiple targeted smart windows;

[0101] Step S302: Calculate and send the opening area of ​​each targeted smart window based on multiple conditional angle values;

[0102] The calculation process of the opening area of ​​the targeted smart window is:

[0103] Oi=Ai·g(θi)

[0104] g(θ i )=cos n (θ i );

[0105] Where i is the i-th targeted smart window, θ is the conditional angle value of the i-th targeted smart window, A i is the area of ​​the i-th targeted smart window, O i is the opening area of ​​the i-th targeted smart window, g(θ i ) is the opening coefficient of the i-th targeted smart window determined according to θ, its value range is [0,1], and n is a positive real number.

[0106] It should be understood that the areas of multiple targeted smart windows are collected, and the opening area of ​​each targeted smart window is calculated and sent based on multiple conditional angle values. Each targeted smart window opens a specified area according to the instruction, where g(θ i ), when the angle is 0 degrees (i.e. the window faces the wind direction), the maximum opening coefficient is 1, and when the angle is close to 90 degrees or greater, the opening coefficient gradually decreases to 0. n is a positive real number used to adjust the sensitivity of θ to the opening coefficient. When n = 1, cos n (θ i) directly reflects the basic influence of θ on ventilation efficiency. When n increases, a slightly larger θ will lead to a rapid decrease in the opening coefficient, indicating that it is more sensitive to changes in θ.

[0107] like Figure 5 As shown, as a preferred embodiment of the present invention, the generation of ventilation control strategy adjustment instructions based on the third outdoor environmental parameter and the indoor wind speed information specifically includes:

[0108] Step S501: collecting raindrop sensing values ​​and indoor wind speed values;

[0109] Step S502: determining whether the raindrop sensing value is greater than a rainfall threshold;

[0110] Step S503: if the raindrop sensing value is greater than the rainfall threshold, a full closing control instruction is generated;

[0111] Step S504: determining whether the indoor wind speed value is greater than the wind speed threshold;

[0112] Step S505: If the indoor wind speed value is greater than the wind speed threshold, calculate the difference ratio between the indoor wind speed value and the wind speed threshold;

[0113] Step S506: generating a proportional closing control instruction based on the difference ratio;

[0114] When this embodiment is applied, the raindrop sensing value and the indoor wind speed value are first collected to determine whether the raindrop sensing value is greater than the rainfall threshold. If the raindrop sensing value is greater than the rainfall threshold, it indicates that the outdoor rainfall is large and rainwater will fall into the room, and a complete closing control instruction is generated. At the same time, it is determined whether the indoor wind speed value is greater than the wind speed threshold. If the indoor wind speed value is greater than the wind speed threshold, the difference ratio between the indoor wind speed value and the wind speed threshold is calculated, and based on the difference ratio, an equal-proportional closing control instruction is generated to close a number of targeted smart windows in equal proportion.

[0115] like Figure 6 As shown, as another preferred embodiment of the present invention, on the other hand, an intelligent decision-making system based on a large model, the system comprises:

[0116] A timing collection and identification module 100, for timing collection and identification of a first outdoor environmental parameter and a second outdoor environmental parameter;

[0117] An acquisition module 200 is used to acquire location information of multiple indoor smart windows and a first environmental parameter;

[0118] A first generating module 300 is used to generate a plurality of smart window targeting association information;

[0119] The second generating module 400 is used to generate an indoor ventilation control strategy;

[0120] A real-time acquisition module 500 is used to acquire outdoor third environmental parameters and indoor wind speed information in real time;

[0121] The third generating module 600 is used to generate a ventilation control strategy adjustment instruction based on the third outdoor environmental parameter and the indoor wind speed information;

[0122] When this embodiment is applied, the timed acquisition and identification module regularly acquires and identifies the first outdoor environmental parameter and the second outdoor environmental parameter, the acquisition module acquires the position information of multiple indoor smart windows and the first environmental parameter, the first generation module generates targeted association information of multiple smart windows, the second generation module generates an indoor ventilation control strategy, the real-time acquisition module acquires the third outdoor environmental parameter and indoor wind speed information in real time, and based on the third outdoor environmental parameter and the indoor wind speed information, the third generation module generates a ventilation control strategy adjustment instruction.

[0123] like Figure 7 As shown, as another preferred embodiment of the present invention, the timing acquisition identification module 100 specifically includes:

[0124] The first collection unit 101 is used to collect real-time wind direction information and real-time air quality index;

[0125] The first judgment unit 102 is used to judge whether the real-time air quality index is within the excellent threshold range;

[0126] The first generating unit 103 is used to generate a long-term instruction if the real-time air quality index is within the excellent threshold range;

[0127] The second judgment unit 104 is used to judge whether the real-time air quality index is within a good threshold range;

[0128] The second generating unit 105 is used to generate a short-term instruction if the real-time air quality index is within the excellent threshold range.

[0129] When this embodiment is applied, the first collection unit collects real-time wind direction information and real-time air quality index, the first judgment unit judges whether the real-time air quality index is within the excellent threshold range, if the real-time air quality index is within the excellent threshold range, the first generation unit generates a long-term instruction, the second judgment unit judges whether the real-time air quality index is within the good threshold range, if the real-time air quality index is within the excellent threshold range, the second generation unit generates a short-term instruction.

[0130] like Figure 8 As shown, as another preferred embodiment of the present invention, the first generating module 300 specifically includes:

[0131] The second collecting unit 301 is used to collect position information of multiple smart windows;

[0132] The third generating unit 302 is used to generate a plurality of smart window orientation information based on the plurality of smart window position information;

[0133] The third judgment unit 303 is used to judge whether the real-time wind direction information is consistent with the orientation information of the multiple smart windows one by one;

[0134] The fourth generating unit 304 is used to generate a plurality of diversion marks if the real-time wind direction information is consistent with the plurality of smart window orientation information;

[0135] A determination unit 305, configured to determine a plurality of targeted smart windows based on a plurality of diversion markers;

[0136] A fifth generating unit 306, configured to generate a plurality of targeted smart window horizontal planes based on the targeted smart window;

[0137] The sixth generating unit 307 is used to generate a real-time wind direction section based on the real-time wind direction information;

[0138] A calculation unit 308, used to calculate the angle between the real-time wind direction section and the horizontal planes of the multiple targeted smart windows;

[0139] The seventh generating unit 309 is used to generate a plurality of conditional angle values.

[0140] When this embodiment is applied, the second acquisition unit 301 acquires multiple smart window position information, based on the multiple smart window position information, the third generation unit 302 generates multiple smart window orientation information, the third judgment unit 303 judges one by one whether the real-time wind direction information is consistent with the multiple smart window orientation information, if the real-time wind direction information is consistent with the multiple smart window orientation information, the fourth generation unit 304 generates multiple diversion marks, based on the multiple diversion marks, the determination unit 305 determines multiple targeted smart windows, based on the targeted smart windows, the fifth generation unit 306 generates multiple targeted smart window horizontal planes, based on the real-time wind direction information, the sixth generation unit 307 generates a real-time wind direction section, the calculation unit 308 calculates the angle between the real-time wind direction section and the multiple targeted smart window horizontal planes, and the seventh generation unit 309 generates multiple conditional angle values.

[0141] In the above-mentioned embodiment of the present invention, a large model-based intelligent decision-making method is provided, and a large model-based intelligent decision-making system is provided. There are multiple rooms or halls distributed indoors, and each room or hall is provided with a smart window. The smart window is trained based on the large model and is connected and controlled by the same local area network. Each smart window is equipped with a window screen to intercept outdoor foreign matter or impurities. When making intelligent decisions on indoor ventilation, it is ensured that the window body and window screen of each smart window are in a closed state in advance, and the door body of each room or hall is in an open state, thereby ensuring the integrity of indoor ventilation. If there is no need to ventilate a room or hall, the door body of the room or hall can be closed in advance. First, the outdoor first environmental parameter and the second environmental parameter are collected and identified at regular intervals. The first environmental parameter is real-time wind direction information, and the second environmental parameter is real-time air quality index. At the same time, the position information of multiple smart windows in the room and the first environmental parameter are obtained. Based on the position information of multiple smart windows in the room and the first environmental parameter, the targeted correlation information of multiple smart windows under the real-time wind direction is analyzed and calculated, and then Based on the first and second indoor and outdoor environmental parameters and their identification results, as well as the targeted association information of multiple smart windows, an indoor ventilation control strategy is generated. When the indoor ventilation control strategy is generated, multiple smart windows can be fully opened synchronously. When multiple smart windows can be fully opened synchronously, multiple rooms or halls can realize ventilation convection. When multiple rooms or halls can realize ventilation convection, the third outdoor environmental parameter and indoor wind speed information are collected in real time. The third environmental parameter information is rainfall information. If it starts to rain outdoors, a ventilation control strategy adjustment instruction will be generated to prevent rain from falling into the room. When the indoor wind speed is too high, a ventilation control strategy adjustment instruction will also be generated to prevent the indoor wind speed from being too high and causing damage to indoor items. After the ventilation control strategy adjustment instruction is generated, the opening degree of multiple smart windows will be closed or adjusted. The method and system judge the airflow direction information of multiple rooms or halls indoors based on multi-modal outdoor environmental information, and then generate a specific indoor ventilation control strategy to realize unmanned intelligent ventilation control indoors, thereby improving the flexible adjustment ability and decision-making ability of smart windows.

[0142] In order to load the above-mentioned method and system and enable it to run smoothly, the system, in addition to the various modules mentioned above, may also include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, processors and memories, etc.

[0143] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the system, and various interfaces and lines are used to connect various parts.

[0144] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent decision-making method based on a large model, characterized in that: The method comprises: Regularly collect and identify outdoor first environmental parameters and second environmental parameters; Acquire location information of multiple smart windows in the room and a first environmental parameter, and generate targeted association information of multiple smart windows; Generate an indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the targeted association information of multiple smart windows; Real-time collection of outdoor third environment parameters and indoor wind speed information; Based on the outdoor third environmental parameter and the indoor wind speed information, a ventilation control strategy adjustment instruction is generated.

2. The intelligent decision-making method based on a large model according to claim 1 is characterized in that: The timed collection and identification of the first outdoor environmental parameter and the second outdoor environmental parameter specifically includes: Collect real-time wind direction information and real-time air quality index; Determine whether the real-time air quality index is within the excellent threshold range; If the real-time air quality index is within the excellent threshold range, a long-term instruction is generated; Determine whether the real-time air quality index is within the good threshold range; If the real-time air quality index is within the excellent threshold range, a short-term instruction is generated.

3. The intelligent decision-making method based on a large model according to claim 2 is characterized in that: The acquiring of the location information of multiple smart windows in the room and the first environmental parameter to generate multiple smart window targeting association information specifically includes: Collecting position information of multiple smart windows; Based on the plurality of smart window position information, generating a plurality of smart window orientation information; Determine whether the real-time wind direction information is consistent with the orientation information of multiple smart windows one by one; If the real-time wind direction information is consistent with the orientation information of multiple smart windows, multiple diversion marks are generated; Based on multiple diversion markers, multiple targeted smart windows are determined; Based on the targeted smart window, a plurality of targeted smart window horizontal planes are generated; Generate real-time wind direction slices based on real-time wind direction information; The angle between the real-time wind direction section and the horizontal planes of multiple targeted smart windows is calculated to generate multiple conditional angle values.

4. The intelligent decision-making method based on a large model according to claim 3 is characterized in that: The generating of the indoor ventilation control strategy based on the first indoor and outdoor environmental parameters, the second environmental parameters and the airflow direction information of the plurality of smart windows specifically includes: Collecting the areas of multiple targeted smart windows; Based on multiple conditional angle values, the opening area of ​​each targeted smart window is calculated and sent; The calculation process of the opening area of ​​the targeted smart window is: Oi=Ai·g(θi) g(θ i )=cos n (i i ); Where i is the i-th targeted smart window, θ is the conditional angle value of the i-th targeted smart window, A i is the area of ​​the i-th targeted smart window, O i is the opening area of ​​the i-th targeted smart window, g(θ i ) is the opening coefficient of the i-th targeted smart window determined according to θ, its value range is [0,1], and n is a positive real number.

5. The intelligent decision-making method based on a large model according to claim 1, characterized in that: The generating of the ventilation control strategy adjustment instruction based on the outdoor third environmental parameter and the indoor wind speed information specifically includes: Collect raindrop sensing values ​​and indoor wind speed values; Determine whether the raindrop sensing value is greater than the rainfall threshold; If the raindrop sensing value is greater than the rainfall threshold, a full-close control command is generated; Determine whether the indoor wind speed value is greater than the wind speed threshold; If the indoor wind speed value is greater than the wind speed threshold, calculate the difference ratio between the indoor wind speed value and the wind speed threshold; Based on the difference ratio, a proportional closing control instruction is generated.

6. An intelligent decision-making system based on a large model, characterized in that: The intelligent decision-making method based on a large model as described in any one of claims 1 to 5 is applied, wherein the system comprises: A timing collection and identification module, used for timing collection and identification of a first outdoor environmental parameter and a second outdoor environmental parameter; An acquisition module, used to acquire location information of multiple indoor smart windows and a first environmental parameter; A first generating module is used to generate a plurality of smart window targeting association information; The second generation module is used to generate an indoor ventilation control strategy; Real-time acquisition module, used to collect outdoor third environment parameters and indoor wind speed information in real time; The third generating module is used to generate a ventilation control strategy adjustment instruction based on the third outdoor environmental parameter and the indoor wind speed information.

7. The intelligent decision-making system based on a large model according to claim 6 is characterized in that: The timing acquisition and identification module specifically includes: A first collection unit, used to collect real-time wind direction information and real-time air quality index; A first judgment unit, used to judge whether the real-time air quality index is within an excellent threshold range; A first generating unit, configured to generate a long-term instruction if the real-time air quality index is within a superior threshold range; The second judgment unit is used to judge whether the real-time air quality index is within a good threshold range; The second generating unit is used to generate a short-term instruction if the real-time air quality index is within the excellent threshold range.

8. The intelligent decision-making system based on a large model according to claim 7 is characterized in that: The first generation module specifically includes: A second collecting unit, used for collecting position information of multiple smart windows; A third generating unit, configured to generate a plurality of smart window orientation information based on the plurality of smart window position information; A third judgment unit is used to judge whether the real-time wind direction information is consistent with the orientation information of the multiple smart windows one by one; A fourth generating unit, configured to generate a plurality of diversion marks if the real-time wind direction information is consistent with the orientation information of the plurality of smart windows; A determination unit, configured to determine a plurality of targeted smart windows based on a plurality of diversion markers; A fifth generating unit, configured to generate a plurality of targeted smart window horizontal planes based on the targeted smart window; A sixth generating unit, configured to generate a real-time wind direction section based on the real-time wind direction information; A calculation unit, used for calculating the angle between the real-time wind direction section and the horizontal planes of multiple targeted smart windows; The seventh generating unit is used to generate a plurality of conditional angle values.

Images