Air conditioning equipment and execution plan processing methods

Abstract

This application relates to an air conditioning device and an execution plan processing method, belonging to the field of air conditioning device technology. The air conditioning device includes: an indoor unit, an outdoor unit, a communication device, and a controller. The controller is coupled to the communication device and configured to: receive instruction information sent by a terminal through the communication device; perform vector transformation on target adjustment task information, device information, and environmental information to obtain corresponding task vectors, and retrieve target information samples from a preset first database based on vector retrieval; determine the execution plan information of the air conditioning device; the execution plan information is obtained by a generative model based on the target adjustment task information, device information, environmental information, and target information samples; and control the operation of the indoor and outdoor units based on the execution time, so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value, and / or, the indoor humidity value is adjusted to the target humidity value. This application can improve the intelligence level of air conditioning devices.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of air conditioning equipment, in particular to an air conditioning equipment and an execution plan processing method. BACKGROUND

[0002] An air conditioning equipment is generally composed of an indoor unit and an outdoor unit, and can realize temperature regulation and humidity regulation functions.

[0003] In the conventional technology, the intelligent functions of the air conditioning equipment are mostly realized by simple models or manually written logic, and these intelligent functions are relatively simple. In the face of complex scenarios, such as the execution plan generation scenario of the air conditioning equipment, the current technology cannot realize it, resulting in a low degree of intelligence of the air conditioning equipment.

[0004] Therefore, there is a technical problem of a low degree of intelligence of the air conditioning equipment in the conventional technology. SUMMARY

[0005] The present application provides an air conditioning equipment and an execution plan processing method to solve the technical problem of a low degree of intelligence of the air conditioning equipment.

[0006] In a first aspect, some embodiments provide an air conditioning equipment, comprising: an indoor unit, an outdoor unit, a communication device, and a controller. The controller is coupled to the communication device and is configured to:

[0007] receive instruction information sent by a terminal through the communication device; the instruction information is used to obtain device information and environment information of the air conditioning equipment, and generate corresponding execution plan information in combination with target regulation task information; the target regulation task information includes a task completion time, a target temperature value, and / or a target humidity value; the device information includes at least one of a temperature regulation parameter and a humidity regulation parameter, and the environment information includes at least one of an indoor and outdoor temperature value and a humidity value;

[0008] perform vector conversion on the target regulation task information, the device information, and the environment information to obtain a corresponding task vector, and retrieve target information samples from a preset first database based on vector retrieval; the first database stores a plurality of information samples, and each information sample includes preselected environment regulation task information and corresponding air conditioning execution plan information thereof;

[0009] determine execution plan information of the air conditioning equipment; the execution plan information is obtained by a generative model based on the target regulation task information, the device information, the environment information, and the target information samples; and the execution plan information includes an execution time, the target temperature value, and / or the target humidity value;

[0010] control the indoor unit and the outdoor unit to operate based on the execution time, so as to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives.

[0011] Technical effects: receiving instruction information sent by the terminal through the communication device; the instruction information is used to obtain device information and environment information of the air conditioning equipment, and generate corresponding execution plan information in combination with target adjustment task information; the target adjustment task information includes a task completion time, a target temperature value and / or a target humidity value; the device information includes at least one of a temperature adjustment parameter and a humidity adjustment parameter, and the environment information includes at least one of an indoor and outdoor temperature value and a humidity value; then, the target adjustment task information, the device information and the environment information are vector converted to obtain a corresponding task vector, and target information samples are retrieved from a preset first database based on vector retrieval; the first database stores a plurality of information samples, and each information sample includes preselected environment adjustment task information and corresponding air conditioning execution plan information; then, the execution plan information of the air conditioning equipment is determined; the execution plan information is obtained by a generative model based on the target adjustment task information, the device information, the environment information and the target information samples; the execution plan information includes an execution time, a target temperature value and / or a target humidity value; finally, the indoor unit and the outdoor unit are controlled to operate based on the execution time, so as to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives. In this way, in the execution plan information generation scenario of the air conditioning equipment, the target adjustment task information, the device information, the environment information and the retrieved target information samples are comprehensively considered, which can effectively generate the execution plan information of the air conditioning equipment, so that the air conditioning equipment adjusts the indoor temperature value and / or the indoor humidity value by executing the execution plan information, to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives, to meet the target adjustment task information, thereby meeting the functional requirements of complex scenarios, and further improving the intelligent degree of the air conditioning equipment; meanwhile, in the case where the target adjustment task information is determined, the air conditioning equipment can automatically generate the corresponding execution plan information based on the received instruction information, and automatically adjust the indoor temperature value and / or the indoor humidity value to meet the target adjustment task information through the execution plan information, which is beneficial to further improve the intelligent degree of the air conditioning equipment.

[0012] In some embodiments of the present application, the controller is further configured to:

[0013] select a target generative model from the preset first generative model and the second generative model; the target generative model is one of the first generative model and the second generative model;

[0014] input the target adjustment task information, the device information, the environment information, and the target information sample into the target generative model, and generate the execution plan information of the air conditioning device by the target generative model.

[0015] Technical effects: When generating the execution plan information of the air conditioning device, the target generative model is selected from the preset first generative model and the second generative model, and the execution plan information of the air conditioning device is generated by the target generative model. That is, the corresponding execution plan information is generated by the adaptive target generative model, which can make the finally generated execution plan information more accurate, thereby improving the generation accuracy of the execution plan information and ensuring the intelligent degree of the air conditioning device.

[0016] In some embodiments of the present application, the controller is further configured to:

[0017] In a case where the similarity between the data vector corresponding to the target information sample and the task vector is greater than a preset similarity, the first generative model is used as the target generative model.

[0018] In a case where the similarity between the data vector corresponding to the target information sample and the task vector is less than or equal to the preset similarity, the second generative model is used as the target generative model.

[0019] Technical effects: By calculating the similarity between the data vector corresponding to the target information sample and the task vector, the target generative model required can be effectively selected from the first generative model and the second generative model, thereby improving the determination accuracy of the target generative model.

[0020] In some embodiments of the present application, the controller is further configured to:

[0021] In a case where the number of samples of the target information sample is greater than a first preset number, the first generative model is used as the target generative model.

[0022] In a case where the number of samples of the target information sample is less than or equal to the first preset number, the second generative model is used as the target generative model.

[0023] Technical effects: By calculating the similarity between the data vector corresponding to the target information sample and the task vector, the target generative model required can be effectively selected from the first generative model and the second generative model, thereby improving the determination accuracy of the target generative model.

[0024] In some embodiments of the present application, the controller is further configured to:

[0025] Based on the target adjustment task information, the equipment information, and the environmental information, target experience data is retrieved from a preset second database; the second database stores multiple experience data, each of which represents the inherent relationship between the pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information.

[0026] The target adjustment task information, the equipment information, the environmental information, the target information sample, and the target experience data are input into the target generative model, and the execution plan information of the air conditioning equipment is generated through the target generative model.

[0027] Technical Effects: First, based on the target adjustment task information, equipment information, and environmental information, target experience data is retrieved from a pre-set second database. Then, through a target-generative model, based on the target adjustment task information, equipment information, environmental information, target information samples, and target experience data, execution plan information for the air conditioning equipment is automatically generated. This facilitates the subsequent adjustment of indoor temperature and / or indoor humidity by the air conditioning equipment to meet the target adjustment task information, thereby further improving the intelligence level of the air conditioning equipment. At the same time, the comprehensive consideration of the target adjustment task information, equipment information, environmental information, target information samples, and target experience data when generating the execution plan information helps to further improve the accuracy of the generated execution plan information.

[0028] In some embodiments of this application, the controller is further configured to:

[0029] The target adjustment task information is determined to include temperature adjustment tasks and / or humidity adjustment tasks;

[0030] Based on the temperature regulation task and / or humidity regulation task, a search is performed in the second database to obtain the target experience data associated with temperature regulation and / or humidity regulation.

[0031] Technical effect: First, determine the temperature regulation task and / or humidity regulation task included in the target regulation task information. Then, based on the temperature regulation task and / or humidity regulation task, search the second database to obtain the target experience data associated with temperature regulation and / or humidity regulation. In this way, by comprehensively considering the temperature regulation task and / or humidity regulation task included in the target regulation task information and searching from the second database, it is beneficial to improve the accuracy of obtaining target experience data.

[0032] In some embodiments of this application, the controller is further configured to:

[0033] From the first database, select the first information sample with a preset quality identifier; the quality identifier represents the achievement rate of the selected environmental regulation task information in the corresponding information sample;

[0034] The first information sample is input into the third generative model, and empirical data is generated through the third generative model.

[0035] The generated experience data is stored in the second database.

[0036] Technical effect: First, the first information sample with the preset quality identifier is selected from the first database. Then, based on the first information sample, the third generative model generates experience data. The generated experience data is then stored in the second database. This helps to improve the accuracy of the generated experience data, thereby improving the accuracy of the experience data stored in the second database. At the same time, it helps to expand the experience data in the second database used to generate execution plan information.

[0037] In some embodiments of this application, the controller is further configured to:

[0038] Obtain the completion result of the execution plan information;

[0039] The execution plan information and the completion result of the execution plan information are stored in a preset third database; the third database is used to store the execution plan information and the completion result of the execution plan information within a set time range;

[0040] If the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline based on the execution plan information stored in the third database and the completion results of each execution plan information.

[0041] Technical effect: First, the execution plan information and the completion results of the execution plan information are stored in a preset third database. Then, if the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline based on the execution plan information stored in the third database and the completion results of each execution plan information. This is conducive to timely updating of the information samples in the first database and ensures the validity of the information samples in the first database.

[0042] In some embodiments of this application, the controller is further configured to:

[0043] Based on the completion results of the execution plan information in the third database and the target adjustment task information associated with the execution plan information, the quality identifier of the execution plan information is determined;

[0044] When the quality identifier is a preset quality identifier, the execution plan information is used as a first information sample and stored in the first database;

[0045] If the quality identifier differs from the preset quality identifier, the execution plan information is corrected to obtain corrected execution plan information. The corrected execution plan information is then used as a second information sample and stored in the first database.

[0046] Technical effect: First, adjust the task information based on the completion results of the execution plan information in the third database and the target information associated with the execution plan information, determine the quality label of the execution plan information, and perform different processing on the execution plan information in the third database according to the quality label, which can ensure the accuracy and effectiveness of the information samples stored in the first database.

[0047] In some embodiments of this application, the controller is further configured to:

[0048] The communication device obtains the equipment information and environmental information of the air conditioning equipment from a preset Internet of Things platform.

[0049] Technical effect: By acquiring equipment and environmental information of air conditioning equipment from the Internet of Things platform through communication devices, it is possible to effectively obtain the equipment and environmental information of air conditioning equipment. This facilitates subsequent adjustment of task information, equipment information, and environmental information based on the target, retrieves target information samples, and generates corresponding execution plan information, thereby ensuring the accuracy of the generated execution plan information.

[0050] In some embodiments of this application, the indoor unit includes a temperature sensor, a first heat exchanger, and a four-way valve; the outdoor unit includes a second heat exchanger and a compressor.

[0051] The controller is also configured to:

[0052] Based on the execution time, the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve are started, and the indoor temperature value detected in real time by the temperature sensor is obtained. The operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve is controlled according to the indoor temperature value so that the indoor temperature value is adjusted to the target temperature value when the task completion time arrives.

[0053] Technical effect: First, the compressor, first heat exchanger, second heat exchanger, and four-way valve in the air conditioning equipment are started based on the execution time, and the indoor temperature value detected in real time by the temperature sensor is obtained. Then, the operating status of the compressor, first heat exchanger, second heat exchanger, and four-way valve is controlled according to the indoor temperature value, so that the indoor temperature value is adjusted to the target temperature value when the task completion time arrives. This achieves the purpose of automatically adjusting the indoor temperature value to the required target temperature value when the task completion time arrives, which is conducive to further improving the intelligence level of the air conditioning equipment.

[0054] In some embodiments of this application, the indoor unit further includes a humidity sensor for monitoring indoor humidity values;

[0055] The controller is also configured to:

[0056] Based on the indoor humidity value, the operating states of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve are adjusted so that the indoor humidity value is adjusted to the target humidity value when the task completion time arrives.

[0057] Technical effect: First, the humidity sensor in the air conditioning unit monitors the indoor humidity value. Then, based on the indoor humidity value, the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve in the air conditioning unit is adjusted so that the indoor humidity value is adjusted to the target humidity value when the task completion time arrives. This achieves the purpose of automatically adjusting the indoor humidity value to the required target humidity value when the task completion time arrives, which is conducive to further improving the intelligence level of the air conditioning unit.

[0058] Secondly, some embodiments also provide an execution plan processing method applied to an air conditioning device, the air conditioning device including an indoor unit, an outdoor unit, a communication device, and a controller; the controller is coupled to the communication device; the method includes:

[0059] The communication device receives instruction information sent by the terminal; the instruction information is used to obtain the equipment information and environmental information of the air conditioning equipment, and generate corresponding execution plan information in combination with the target adjustment task information; the target adjustment task information includes task completion time, target temperature value and / or target humidity value; the equipment information includes at least one of temperature adjustment parameters and humidity adjustment parameters, and the environmental information includes at least one of indoor and outdoor temperature values ​​and humidity values;

[0060] The target adjustment task information, the equipment information, and the environmental information are vector-converted to obtain the corresponding task vector, and the target information sample is retrieved from a preset first database based on vector retrieval; the first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information;

[0061] The execution plan information of the air conditioning equipment is determined; the execution plan information is obtained by a generative model based on the target adjustment task information, the equipment information, the environmental information, and the target information sample; the execution plan information includes the execution time, the target temperature value, and / or the target humidity value.

[0062] The indoor unit and the outdoor unit are controlled to operate based on the execution time, so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value, and / or the indoor humidity value is adjusted to the target humidity value.

[0063] Technical Effects: In the scenario of generating execution plan information for air conditioning equipment, by comprehensively considering target adjustment task information, equipment information, environmental information, and retrieved target information samples, and using all of this information as input to the generative model, the execution plan information of the air conditioning equipment can be generated more accurately. This allows the air conditioning equipment to adjust the indoor temperature and / or indoor humidity by executing the execution plan, ensuring that the indoor temperature reaches the target temperature value and / or the indoor humidity reaches the target humidity value when the task completion time arrives, thus meeting the functional requirements of complex scenarios. Simultaneously, given a defined target requirement, the air conditioning equipment obtains the corresponding execution plan information based on the received instruction information and automatically adjusts the indoor temperature and / or indoor humidity to meet the target requirement within the user's required timeframe, further enhancing the intelligence level of the air conditioning equipment. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a schematic diagram of the control architecture of an air conditioning device provided in some embodiments of this application;

[0066] Figure 2 A flowchart illustrating the execution plan processing method provided in some embodiments of this application;

[0067] Figure 3 This application provides schematic diagrams illustrating the input of target requirement information via a smartphone, as shown in some embodiments.

[0068] Figure 4 This is a schematic diagram illustrating the input of target demand information via a smart TV, provided for some embodiments of this application.

[0069] Figure 5 A flowchart illustrating the steps for generating execution plan information for an air conditioning device, provided in some embodiments of this application;

[0070] Figure 6 A flowchart illustrating the steps for determining a target generative model provided in some embodiments of this application;

[0071] Figure 7 A flowchart illustrating the steps for determining a target generative model provided in other embodiments of this application;

[0072] Figure 8 A flowchart illustrating the steps for generating execution plan information for an air conditioning device, provided for other embodiments of this application;

[0073] Figure 9 A flowchart illustrating the steps for retrieving target empirical data provided in some embodiments of this application;

[0074] Figure 10 A flowchart illustrating the steps of storing generated experience data in a second database, provided for some embodiments of this application;

[0075] Figure 11 A flowchart illustrating the steps for retrieving target information samples provided in some embodiments of this application;

[0076] Figure 12 A flowchart illustrating the steps for offline updating of a first database provided in some embodiments of this application;

[0077] Figure 13 A flowchart illustrating the steps of storing information samples in a first database, provided for some embodiments of this application;

[0078] Figure 14 Signaling interaction diagrams for execution plan processing methods provided in some embodiments of this application;

[0079] Figure 15 A flowchart illustrating a task execution prediction method that integrates various complex environmental data, provided in some embodiments of this application;

[0080] Figure 16A flowchart illustrating a task execution prediction method that integrates various complex environmental data, provided for other embodiments of this application;

[0081] Figure 17 This is a structural block diagram of an execution plan processing apparatus provided in some embodiments of this application. Detailed Implementation

[0082] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0083] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0084] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0085] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0086] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0087] In this application embodiment, air conditioning equipment generally refers to intelligent devices with temperature and / or humidity regulation functions, such as intelligent air conditioning equipment.

[0088] Figure 1 This is a schematic diagram of the control architecture of an air conditioning device provided in some embodiments of this application. For example... Figure 1 As shown, the control architecture of the air conditioning equipment includes a communication device 110, a controller 120, a detection component 130, an indoor unit 140, and an outdoor unit 150. The controller 120 is coupled to the communication device 110 and the detection component 130 respectively; the controller 120 controls the operation of the indoor unit 140 and the outdoor unit 150 respectively.

[0089] In some embodiments, the communication device 110 is a component used to communicate with external devices (such as terminals, IoT platforms, weather query platforms, etc.) or servers according to various communication protocol types. The air conditioning device may have multiple communication devices 110 depending on the supported communication methods. For example, when the air conditioning device supports wireless network communication, it may have a communication device 110 with WiFi functionality. When the air conditioning device supports Bluetooth connection communication, it needs to have a communication device 110 with Bluetooth functionality.

[0090] The communication device 110 enables the air conditioning unit to communicate with external devices or servers via wireless or wired connections. Wired connections utilize data cables, interfaces, or other components to connect the air conditioning unit to external devices. Wireless connections utilize wireless signals or wireless networks. The air conditioning unit can directly establish a connection with external devices or indirectly through gateways, routers, or connecting devices. For example, the communication device 110 receives instruction information from terminals (such as smartphones or smart TVs) carrying target adjustment task information (including task completion time, target temperature value, and / or target humidity value), and retrieves device information (including at least one of temperature and humidity adjustment parameters) and environmental information (including at least one of indoor and outdoor temperature and humidity values) from external devices (such as an IoT platform). Finally, it sends the target adjustment task information, device information, and environmental information to the controller 120.

[0091] In some embodiments, the detection component 130 refers to a component used to acquire environmental information of the air conditioning equipment, such as a temperature sensor, a humidity sensor, an air quality sensor, etc. For example, the detection component 130 detects the environmental information of the air conditioning equipment (including indoor environmental information and outdoor environmental information) to obtain the environmental information of the air conditioning equipment (including at least one of indoor and outdoor temperature values, humidity values, and indoor and outdoor air quality information), and sends the environmental information of the air conditioning equipment to the controller 120.

[0092] In some embodiments, the controller 120 may include at least one of a central processing unit, a voice processor, and a power processor, and a first to nth interface for input / output. The controller 120 controls the operation of the air conditioning equipment and responds to user operations through various software control programs stored in the memory. The controller 120 controls the overall operation of the air conditioning equipment. For example, the controller 120 is used to retrieve target information samples from a preset first database based on target adjustment task information, equipment information, and environmental information sent by the communication device 110 (or environmental information sent by the detection component 130). The first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information. Then, based on the target adjustment task information, equipment information, environmental information, and target information samples, the controller 120 obtains the air conditioning equipment's execution plan information (including execution time, target temperature value, and / or target humidity value). Finally, based on the execution time, the controller controls the indoor unit 140 and the outdoor unit 150 to operate so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value, and / or the indoor humidity value is adjusted to the target humidity value.

[0093] In some embodiments, the indoor unit 140 is one of the core components of the air conditioning equipment responsible for air handling such as heating and cooling. It is typically installed indoors and has multiple functions including air filtration, circulation, dehumidification, heating, and cooling. The indoor unit 140 includes a temperature sensor, a humidity sensor, a first heat exchanger, and a four-way valve. For example, under the action of the execution plan information from the controller 120, the indoor unit 140, in conjunction with the outdoor unit 150, adjusts the indoor temperature to a target temperature value and / or adjusts the indoor humidity to a target humidity value.

[0094] In some embodiments, the outdoor unit 150 is the part of the air conditioning system responsible for dissipating heat. It is typically installed outdoors and achieves cooling or heating of the air through refrigerant circulation and heat transfer, dissipating heat generated indoors to the outdoor air. The outdoor unit 150 includes a second heat exchanger and a compressor. For example, under the action of the execution plan information from the controller 120, the outdoor unit 150, in conjunction with the indoor unit 140, adjusts the indoor temperature to a target temperature value and / or adjusts the indoor humidity to a target humidity value.

[0095] In some embodiments, such as Figure 1 As shown, this application provides an air conditioning device, which may include an indoor unit 140, an outdoor unit 150, a detection component 130, a communication device 110, and a controller 120; wherein the controller 120 is coupled to the detection component 130 and the communication device 110 respectively.

[0096] like Figure 2 As shown, controller 120 is configured as follows:

[0097] Step S201: Receive instruction information sent by the terminal through the communication device 110; the instruction information is used to obtain the equipment information and environmental information of the air conditioning equipment, and generate corresponding execution plan information in combination with the target adjustment task information; the target adjustment task information includes the task completion time, target temperature value and / or target humidity value; the equipment information includes at least one of temperature adjustment parameters and humidity adjustment parameters, and the environmental information includes at least one of indoor and outdoor temperature values ​​and humidity values.

[0098] Step S202: Perform vector transformation on the target adjustment task information, equipment information and environmental information to obtain the corresponding task vector, and retrieve the target information sample from the preset first database based on vector retrieval; the first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information.

[0099] Step S203: Determine the execution plan information of the air conditioning equipment; the execution plan information is obtained by the generative model based on the target adjustment task information, equipment information, environmental information and target information samples; the execution plan information includes the execution time, target temperature value and / or target humidity value.

[0100] Step S204: Based on the execution time, control the operation of indoor unit 140 and outdoor unit 150 to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives.

[0101] The instruction information refers to temperature and / or humidity adjustment instructions for air conditioning equipment, instructing the equipment to adjust the indoor temperature to the target temperature and / or humidity to the target humidity when the task completion time arrives. It should be noted that the instruction information carries target adjustment task information. Of course, the instruction information can also refer to air quality adjustment instructions, such as PM2.5 (particulate matter with a diameter of 2.5 micrometers or less) adjustment instructions.

[0102] Among these, target adjustment task information refers to temperature and / or humidity adjustment tasks for air conditioning equipment. Specifically, it refers to temperature control and / or humidity control requirements for air conditioning equipment, such as "I'll be home around 7 PM, set the temperature to 27 degrees Celsius," "I'll be home around 8 PM, set the temperature to 26 degrees Celsius," "Set the humidity to 50%," "I'll be home around 7 PM, set the humidity to 40%," "Set the temperature to 24 degrees Celsius," etc. Of course, target adjustment task information can also refer to air quality adjustment tasks for air conditioning equipment, such as PM2.5 control tasks.

[0103] The target adjustment task information includes at least the task completion time, target temperature value, and / or target humidity value. The task completion time refers to the completion time of the temperature adjustment task and / or humidity adjustment task. For example, for the target adjustment task information "I will be home around 7 pm, adjust the temperature to 27 degrees Celsius," the task completion time is 7 pm. Of course, the task completion time can also refer to the completion time of the air quality adjustment task (such as the PM2.5 adjustment task).

[0104] The target temperature value refers to the temperature that the room (such as the bedroom) should reach when the task is completed. For example, in the task information "I will get home around 7 pm, set the temperature to 27 degrees Celsius", the target temperature value is 27 degrees Celsius.

[0105] The target humidity value refers to the humidity level that should be achieved indoors (e.g., in the living room) when the task is completed. For example, in the task information "I will be home around 8 pm, adjust the humidity to 50%", the target humidity value is 50%.

[0106] The target air quality value can also be included in the target adjustment task information, such as the target PM2.5 value. The target air quality value refers to the air quality value that should be achieved indoors (e.g., in the living room) when the task completion time arrives; for example, in the target adjustment task information "I will get home around 8 pm, adjust the PM2.5 value to Y", the target PM2.5 value refers to Y.

[0107] In this context, the terminal refers to a device used to acquire information about the user's target adjustment tasks for the air conditioning equipment, such as smartphones, laptops, tablets, and smart TVs. The terminal can acquire this information in various ways, such as by referencing... Figure 3 Users can input "I'll be home around 8 o'clock, set the temperature to 26 degrees Celsius" via voice or text on the control page of the smart home control app on their smartphones; for example, refer to... Figure 4 Users can input "set the temperature to 24 degrees Celsius" via voice or text on the smart home control interface of their smart TV. Alternatively, users can input the desired temperature setting via the smart remote control of their air conditioner.

[0108] The terminal generates instruction information for the air conditioning equipment based on the user's target adjustment task information, and sends the instruction information to the communication device 110 in the air conditioning equipment. The communication device 110 then sends the received instruction information to the controller 120. Based on the instruction information, the controller 120 obtains the equipment information and environmental information of the air conditioning equipment through the communication device 110, and generates corresponding execution plan information in conjunction with the target adjustment task information.

[0109] The equipment information for air conditioning equipment includes at least one of temperature regulation parameters and humidity regulation parameters. Temperature regulation parameters refer to parameters related to the humidity regulation function of air conditioning equipment, such as fan speed regulation, mode selection, energy saving settings, cooling / heating capacity in the past few days, and average cooling / heating capacity in the past few days.

[0110] Humidity control parameters refer to parameters related to the humidity control function of air conditioning equipment, such as humidification settings, dehumidification settings, cooling / heating capacity for the past few days, and recent average cooling / heating capacity. Of course, air conditioning equipment information can also include air quality control parameters, such as PM2.5 control parameters. Furthermore, air conditioning equipment information can also include equipment operation information and equipment configuration information; equipment operation information refers to information related to the operation of the air conditioning equipment, specifically equipment status information, such as cooling / heating capacity for the past few days and recent average cooling / heating capacity. Equipment configuration information refers to information related to the configuration of the air conditioning equipment, such as energy efficiency rating, air conditioner capacity (horsepower), power, voltage, air circulation volume, and fan speed.

[0111] The environmental information includes at least one of the indoor and outdoor temperature and humidity values, such as indoor temperature, indoor humidity, outdoor temperature, and outdoor humidity. Of course, the environmental information may also include indoor and outdoor air quality values, such as indoor PM2.5 levels and outdoor PM2.5 levels.

[0112] The communication device 110 is used to obtain equipment information and environmental information of the air conditioning equipment from the Internet of Things platform; the detection component 130 is used to obtain environmental information of the air conditioning equipment. Furthermore, the environmental information used in retrieving target information samples and generating execution plan information for the air conditioning equipment can refer to the environmental information obtained by the communication device 110, the environmental information obtained by the detection component 130, or the aggregated environmental information. The aggregated environmental information is obtained by combining the environmental information obtained by the communication device 110 and the environmental information obtained by the detection component 130. This aggregated environmental information ensures the comprehensiveness and accuracy of the final environmental information, while avoiding the shortcomings of incomplete environmental information obtained solely by the communication device 110 or solely by the detection component 130.

[0113] The pre-selected environmental control task information refers to environmental control tasks that have been successfully executed. Specifically, it refers to environmental control tasks with an achievement rate greater than or equal to a preset achievement rate (e.g., 80%), such as successfully executed temperature control tasks, successfully executed humidity control tasks, and successfully executed air quality control tasks. The achievement rate of environmental control task information is used to characterize the task completion status based on the corresponding execution plan information, such as 95% or 70%.

[0114] Among them, the air conditioning execution plan information corresponding to the pre-selected environmental conditioning task information refers to the execution plan information generated for the pre-selected environmental conditioning task information.

[0115] The information sample refers to a sample that includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information, specifically task example data. Each information sample includes pre-selected environmental adjustment task information and the corresponding air conditioning execution plan information. For example, an information sample includes the pre-selected environmental adjustment task information "set the temperature to 26 degrees" and the corresponding air conditioning execution plan information "set the air conditioning temperature to 22 degrees, fan speed automatic, after 5 minutes, set the air conditioning temperature to 26 degrees, fan speed to level 1, estimated total time is 15 minutes".

[0116] The preset first database refers to a database that stores multiple information samples, specifically a task example database that stores multiple task example data, such as a formal task database. In this embodiment, the first database can be deployed locally on the air conditioner, or it can be deployed on an IoT platform or in the cloud. The air conditioning device can query the first database through information interaction with the IoT platform or the cloud.

[0117] Among them, target information samples refer to information samples associated with target adjustment task information, equipment information and environmental information. Specifically, they refer to information samples in the preset first database whose similarity to the corresponding data vector and task vector is greater than the similarity threshold, such as target task example data.

[0118] The task vectors corresponding to the target adjustment task information, equipment information, and environmental information include feature vectors corresponding to the target adjustment task information, equipment information, and environmental information. Specifically, they are obtained by concatenating these feature vectors. The execution plan information for the air conditioning equipment includes the specific execution steps and execution time, specifically including the execution time, target temperature value, and / or target humidity value. For example, "Set the air conditioning temperature to 20, fan speed automatic, after 5 minutes, adjust the air conditioning temperature to 24, fan speed to level 1, estimated total time is 15 minutes." Of course, the execution plan information for the air conditioning equipment can also include target air quality values, such as the target PM2.5 value.

[0119] The execution time refers to the start time of the air conditioning equipment. For example, for the instruction "I will get home around 7 pm, set the temperature to 27 degrees Celsius", the execution time might be 6:40 pm.

[0120] The execution plan information for air conditioning equipment is determined by comprehensively considering four types of data: target adjustment task information, equipment information, environmental information, and target information samples.

[0121] The generative model refers to a large-scale model used to generate execution plan information for air conditioning equipment, such as an execution plan generation model. Using the generative model, execution plan information for air conditioning equipment can be generated based on target adjustment task information, equipment information, environmental information, and target information samples. In this embodiment, the generative model can be deployed locally on the air conditioner, or on an IoT platform or in the cloud. The air conditioning equipment can use the generative model through information interaction with the IoT platform or cloud.

[0122] When executing the corresponding execution plan information, the controller 120 can control the operation of the indoor unit 140 and the outdoor unit 150 based on the execution time, so that when the task completion time arrives, the indoor unit 140 and the outdoor unit 150 will jointly adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value to meet the target adjustment task information, such as adjusting the indoor temperature value to 24 degrees and the indoor humidity value to 50%.

[0123] Specifically, refer to Figure 1When the controller 120 and the generative model are deployed on the air conditioning equipment, the communication device 110 receives instruction information for the air conditioning equipment sent by the terminal and sends the instruction information to the controller 120. The controller 120, based on the target adjustment task information carried in the instruction information, sends equipment information query requests and environmental information query requests to the communication device 110. The communication device 110, based on the equipment information query requests and environmental information query requests, obtains the temperature adjustment parameters and / or humidity adjustment parameters of the air conditioning equipment as equipment information, and obtains the indoor and outdoor temperature values ​​and / or humidity values ​​of the air conditioning equipment as environmental information, and then sends the equipment information and environmental information of the air conditioning equipment to the controller 120. If the controller 120 is communicationally connected to a detection component 130, the detection component 130 can also obtain the indoor and outdoor temperature values ​​and / or humidity values ​​of the air conditioning equipment based on the environmental information query requests sent by the controller 120, as environmental information of the air conditioning equipment, and send the environmental information to the controller 120. The controller 120 complements or cross-verifies environmental information acquired from different paths to obtain the final environmental information; it performs vector transformation on the target adjustment task information, equipment information, and environmental information to obtain task vectors corresponding to the target adjustment task information, equipment information, and environmental information; based on the task vectors, it performs vector retrieval in a preset first database storing multiple information samples to obtain target information samples associated with the target adjustment task information, equipment information, and environmental information; then, it inputs the target adjustment task information, equipment information, environmental information, and target information samples into a generative model to obtain the execution plan information of the air conditioning equipment, compared with... For example, the vectors corresponding to the target adjustment task information, the equipment information, the environment information, and the target information sample are concatenated to obtain the target vector. The target vector is then input into the generative model to obtain the execution plan information of the air conditioning equipment. Finally, the execution plan information of the air conditioning equipment is executed. Based on the execution time in the execution plan information, the indoor unit 140 and the outdoor unit 150 are controlled to operate, so that when the task completion time arrives, the indoor unit 140 and the outdoor unit 150 jointly adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value to meet the target adjustment task information.

[0124] For example, given the target adjustment task information "I will be home around 8 pm, please set the temperature to 24 degrees Celsius", the generated execution plan information is "Set the air conditioner temperature to 20 degrees Celsius, fan speed to automatic, and after 5 minutes, set the air conditioner temperature to 24 degrees Celsius, fan speed to level 1, with an estimated total time of 15 minutes". Then, controller 120 will control indoor unit 140 and outdoor unit 150 to operate at 7:45 pm to adjust the indoor temperature to 24 degrees Celsius when I arrive at 8 pm.

[0125] It should be noted that the controller 120 and the generative model can also be deployed on a server / cloud. The acquired target adjustment task information, equipment information, and environmental information are sent to the controller 120 deployed on the server / cloud via the communication device 110, or the acquired environmental information is sent to the controller 120 deployed on the server / cloud via the detection component 130. The controller 120 deployed on the server / cloud performs vector transformation on the target adjustment task information, equipment information, and environmental information to obtain task vectors corresponding to the target adjustment task information, equipment information, and environmental information. Based on the task vectors, a preset system storing multiple information samples is used... Vector retrieval is performed in the first database to obtain target information samples associated with target adjustment task information, equipment information, and environmental information. Then, the target adjustment task information, equipment information, environmental information, and target information samples are input into the generative model to obtain the execution plan information of the air conditioning equipment. The execution plan information is then executed, that is, based on the execution time in the execution plan information, the indoor unit 140 and outdoor unit 150 of the air conditioning equipment are controlled to operate, so that when the task completion time arrives, the indoor unit 140 and outdoor unit 150 jointly adjust the indoor temperature value to the target temperature value, and / or adjust the indoor humidity value to the target humidity value, so as to meet the target adjustment task information.

[0126] In real-world scenarios, the terminal can also send instruction information (carrying target adjustment task information) for the air conditioning equipment to the server / cloud (e.g., a cloud server). Upon receiving the instruction information, the server / cloud confirms the target adjustment task information and, based on this, retrieves the equipment and environmental information of the air conditioning device from the IoT platform. Then, it performs vector transformation on the target adjustment task information, equipment information, and environmental information to obtain a task vector corresponding to these elements. Based on this task vector, it performs a vector search in a pre-defined first database storing multiple information samples to obtain the target adjustment task... The system generates a target information sample that associates task information, equipment information, and environmental information. Then, it inputs the target adjustment task information, equipment information, environmental information, and the target information sample into a generative model to obtain the air conditioning equipment's execution plan information. Finally, it sends the execution plan information to the air conditioning equipment. The air conditioning equipment executes the received execution plan information, that is, based on the execution time in the execution plan information, it controls the operation of the indoor unit 140 and outdoor unit 150 of the air conditioning equipment, so that when the task completion time arrives, the indoor unit 140 and outdoor unit 150 jointly adjust the indoor temperature value to the target temperature value, and / or, adjust the indoor humidity value to the target humidity value, to meet the target adjustment task information. Alternatively, after generating the air conditioning equipment's execution plan information, the server / cloud directly executes the execution plan information, that is, based on the execution time in the execution plan information, it controls the operation of the indoor unit 140 and outdoor unit 150 of the air conditioning equipment, so that when the task completion time arrives, the indoor unit 140 and outdoor unit 150 jointly adjust the indoor temperature value to the target temperature value, and / or, adjust the indoor humidity value to the target humidity value, to meet the target adjustment task information.

[0127] The technical solution provided in this embodiment receives instruction information sent by a terminal through a communication device. The instruction information is used to obtain equipment information and environmental information of the air conditioning equipment, and generate corresponding execution plan information in combination with target adjustment task information. The target adjustment task information includes task completion time, target temperature value and / or target humidity value. The equipment information includes at least one of temperature adjustment parameters and humidity adjustment parameters, and the environmental information includes at least one of indoor and outdoor temperature values ​​and humidity values. Then, the target adjustment task information, equipment information and environmental information are vector-converted to obtain the corresponding task vector, and target information samples are retrieved from a preset first database based on vector retrieval. The first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information. Next, the execution plan information of the air conditioning equipment is determined. The execution plan information is obtained by a generative model based on the target adjustment task information, equipment information, environmental information and target information samples. The execution plan information includes execution time, target temperature value and / or target humidity value. Finally, the indoor unit and outdoor unit are controlled to operate based on the execution time, so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value, and / or the indoor humidity value is adjusted to the target humidity value. In this way, in the scenario of generating execution plan information for air conditioning equipment, by comprehensively considering the target adjustment task information, equipment information, environmental information, and retrieved target information samples, the execution plan information for air conditioning equipment can be effectively generated. This allows the air conditioning equipment to adjust the indoor temperature and / or indoor humidity by executing the execution plan information, so that when the task completion time arrives, the indoor temperature is adjusted to the target temperature value, and / or the indoor humidity is adjusted to the target humidity value, thereby satisfying the target adjustment task information, meeting the functional requirements of complex scenarios, and thus improving the intelligence level of the air conditioning equipment.

[0128] In some embodiments, such as Figure 5 As shown, controller 120 is also configured as follows:

[0129] Step S501: Select a target generative model from the preset first generative model and second generative model; the target generative model is one of the first generative model and the second generative model.

[0130] Step S502: Input the target adjustment task information, equipment information, environmental information and target information sample into the target generative model, and generate the execution plan information of the air conditioning equipment through the target generative model.

[0131] The first generative model refers to a small-scale model used to generate execution plan information for air conditioning equipment, specifically a small-scale execution plan generation model.

[0132] The second generative model refers to a larger-sized model than the first generative model used to generate execution plan information for air conditioning equipment; specifically, it refers to a large-sized execution plan generation model.

[0133] The model size of the first generative model is smaller than that of the second generative model.

[0134] Among them, the target generative model refers to the generative model associated with the retrieved target information samples, which is used to generate execution plan information for air conditioning equipment.

[0135] Specifically, refer to Figure 1 The controller 120 retrieves preset first and second generative models from the local database, and selects a generative model associated with the target information sample from the first and second generative models as the target generative model. Then, the target adjustment task information, equipment information, environmental information, and target information sample are input into the target generative model. Based on the target adjustment task information, equipment information, environmental information, and target information sample, the target generative model performs execution plan generation processing to obtain the execution plan information of the air conditioning equipment. For example, the vector corresponding to the target adjustment task, the vector corresponding to the equipment information, the vector corresponding to the environmental information, and the vector corresponding to the target information sample are concatenated to obtain the target vector, and the target vector is input into the target generative model to obtain the execution plan information of the air conditioning equipment.

[0136] The technical solution provided in this embodiment first selects a target generative model from the preset first generative model and second generative model when generating execution plan information for air conditioning equipment. Then, the execution plan information for air conditioning equipment is generated through the target generative model. That is, the corresponding execution plan information is generated by adapting the target generative model, which can make the final generated execution plan information more accurate, thereby improving the generation accuracy of execution plan information and ensuring the intelligence level of air conditioning equipment.

[0137] In some embodiments, such as Figure 6 As shown, controller 120 is also configured as follows:

[0138] Step S601: If the similarity between the data vector corresponding to the target information sample and the task vector is greater than the preset similarity, the first generative model is used as the target generative model.

[0139] Step S602: If the similarity between the data vector corresponding to the target information sample and the task vector is less than or equal to the preset similarity, the second generative model is used as the target generative model.

[0140] Here, the data vector corresponding to the target information sample refers to the feature vector corresponding to the target information sample.

[0141] Here, the task vector refers to the concatenated vector of feature vectors corresponding to target adjustment task information, equipment information, and environmental information. Similarity is used to characterize the degree of similarity. The preset similarity refers to a pre-set similarity level, such as 0.8. If the similarity is greater than the preset similarity, it indicates that the retrieved target information samples have a high degree of similarity, and a smaller first generative model is used; if the similarity is less than or equal to the preset similarity, it indicates that the retrieved target information samples have a low degree of similarity, and a larger second generative model is used.

[0142] It should be noted that the preset similarity is greater than the similarity threshold mentioned above.

[0143] Specifically, refer to Figure 1 The controller 120 acquires the feature vectors corresponding to the target adjustment task information, the device information, and the environment information, and concatenates these feature vectors to obtain the task vector. Next, it acquires the data vector corresponding to the target information sample and calculates the similarity between the data vector and the task vector, such as cosine similarity. Finally, it compares the similarity between the data vector and the task vector with a preset similarity. If the similarity is greater than the preset similarity, the first generative model is used as the target generative model; if the similarity is less than or equal to the preset similarity, the second generative model is used as the target generative model.

[0144] The technical solution provided in this embodiment can effectively select the required target generative model from the first generative model and the second generative model by calculating the similarity between the data vector corresponding to the target information sample and the task vector, thereby improving the accuracy of the target generative model determination.

[0145] In some embodiments, such as Figure 7 As shown, controller 120 is also configured as follows:

[0146] Step S701: If the number of target information samples is greater than the first preset number, the first generative model is used as the target generative model.

[0147] Step S702: If the number of samples of the target information sample is less than or equal to the first preset number, the second generative model is used as the target generative model.

[0148] Here, the first preset quantity refers to a first quantity threshold, such as 7. If the number of retrieved target information samples is greater than the first preset quantity, it means that the number of retrieved target information samples is relatively large, and a small-sized first generative model is used; if the number of retrieved target information samples is less than or equal to the first preset quantity, it means that the number of retrieved target information samples is relatively small, and a large-sized second generative model is used.

[0149] Specifically, refer to Figure 1 The controller 120 counts the number of retrieved target information samples and compares the number of retrieved target information samples with a first preset number. If the number of retrieved target information samples is greater than the first preset number, the first generative model is used as the target generative model; if the number of retrieved target information samples is less than or equal to the first preset number, the second generative model is used as the target generative model.

[0150] The technical solution provided in this embodiment can effectively select the required target generative model from the first generative model and the second generative model by statistically analyzing the sample size relationship between the retrieved target information sample and the first preset quantity, thereby improving the accuracy of the target generative model determination.

[0151] In some embodiments, such as Figure 8 As shown, controller 120 is also configured as follows:

[0152] Step S801: Based on the target adjustment task information, equipment information and environmental information, retrieve the target experience data from the preset second database; the second database stores multiple experience data, each of which represents the inherent relationship between the pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information.

[0153] Step S802: Input the target adjustment task information, equipment information, environmental information, target information sample and target experience data into the target generative model, and generate the execution plan information of the air conditioning equipment through the target generative model.

[0154] The pre-defined second database refers to the experience database, which stores multiple experience data. Experience data represents the inherent relationship between pre-selected environmental control task information and its corresponding air conditioning execution plan information (i.e., how to control the air conditioning equipment when executing the pre-selected environmental control task information). Specifically, it refers to temperature control experience and humidity control experience, such as "first adjust the temperature to 22 degrees, then adjust it to 26 degrees," "first adjust the temperature to 20 degrees, then adjust it to 24 degrees," "first adjust the humidity to 40%, then adjust it to 50%," "first adjust the air conditioning temperature to 22 degrees, automatic fan speed, and after 5 minutes, adjust the air conditioning temperature to 26 degrees and adjust the fan speed to level 1," and "first adjust the air conditioning temperature to 20 degrees, automatic fan speed, and after 5 minutes, adjust the air conditioning temperature to 24 degrees and adjust the fan speed to level 1," etc. Target experience data refers to experience data associated with target control task information, equipment information, and environmental information.

[0155] Specifically, refer to Figure 1 The controller 120 retrieves the target adjustment task information, equipment information, and environmental information from a pre-set second database containing multiple sets of experience data, based on the target adjustment task information, equipment information, and environmental information. This retrieves the experience data associated with the target adjustment task information, equipment information, and environmental information, and uses it as target experience data. Then, the controller inputs the target adjustment task information, equipment information, environmental information, target information samples, and target experience data into a target generative model. Through the target generative model, based on the target adjustment task information, equipment information, environmental information, target information samples, and target experience data, an execution plan is generated to obtain the execution plan information for the air conditioning equipment. For example, the controller 120 concatenates the feature vectors corresponding to the target adjustment task information, equipment information, environmental information, target information samples, and target experience data to obtain a target vector, which is then input into the target generative model to obtain the execution plan information for the air conditioning equipment.

[0156] The technical solution provided in this embodiment first retrieves target experience data from a preset second database based on target adjustment task information, equipment information, and environmental information. Then, through a target generative model, it automatically generates execution plan information for the air conditioning equipment based on the target adjustment task information, equipment information, environmental information, target information samples, and target experience data. This facilitates the subsequent adjustment of indoor temperature and / or indoor humidity by the air conditioning equipment to meet the target adjustment task information, thereby further improving the intelligence level of the air conditioning equipment. At the same time, when generating the execution plan information, the comprehensive consideration of target information samples, equipment information, environmental information, target information samples, and target experience data helps to further improve the accuracy of the generated execution plan information.

[0157] In some embodiments, such asFigure 9 As shown, controller 120 is also configured as follows:

[0158] Step S901: Determine the temperature control task and / or humidity control task included in the target control task information.

[0159] Step S902: Based on the temperature regulation task and / or humidity regulation task, a search is performed in the second database to obtain target experience data associated with temperature regulation and / or humidity regulation.

[0160] Since the target adjustment task information includes the target temperature value and / or the target humidity value, the temperature adjustment task and / or humidity adjustment task included in the target adjustment task information can be determined based on the target adjustment task information.

[0161] The temperature regulation task is used to characterize the dimension of the indoor environment that needs to be regulated by air conditioning equipment as temperature, such as a temperature regulation topic. The humidity regulation task is used to characterize the dimension of the indoor environment that needs to be regulated by air conditioning equipment as humidity, such as a humidity regulation topic. For example, if temperature regulation is involved, relevant experience in temperature regulation is retrieved; if humidity is involved, relevant experience in humidity regulation is retrieved.

[0162] Specifically, refer to Figure 1 The controller 120 first parses the target adjustment task information to obtain the temperature adjustment task and / or humidity adjustment task included in the target adjustment task information. Then, based on the temperature adjustment task and / or humidity adjustment task, it searches in the preset second database to obtain empirical data with a correlation greater than the preset correlation between the temperature adjustment task and / or humidity adjustment task, which is used as the target empirical data associated with temperature adjustment and / or humidity adjustment.

[0163] The technical solution provided in this embodiment first determines the temperature regulation task and / or humidity regulation task included in the target regulation task information, and then searches the second database based on the temperature regulation task and / or humidity regulation task to obtain target experience data associated with temperature regulation and / or humidity regulation. In this way, by comprehensively considering the temperature regulation task and / or humidity regulation task included in the target regulation task information and searching from the second database, it is beneficial to improve the accuracy of obtaining target experience data.

[0164] In some embodiments, such as Figure 10 As shown, controller 120 is also configured as follows:

[0165] Step S1001: Select first information samples with preset quality identifiers from the first database; the quality identifier represents the achievement rate of the selected environmental regulation task information in the corresponding information sample.

[0166] Step S1002: Input the first information sample into the third generative model, and generate empirical data through the third generative model.

[0167] Step S1003: Store the generated experience data in the second database.

[0168] The selected environmental adjustment task information includes information on successfully executed environmental adjustment tasks and information on failed environmental adjustment tasks; information on failed environmental adjustment tasks refers to environmental adjustment tasks whose achievement rate is less than the preset achievement rate (e.g., 80%).

[0169] The first database includes information on successfully executed environmental control tasks and their corresponding air conditioning execution plans, as well as information on failed environmental control tasks and their corresponding revised air conditioning execution plans.

[0170] The quality identifier of an information sample is used to characterize the achievement rate of the environmental regulation task information included in that information sample, such as 95% or 80%. The preset quality identifier is used to characterize a preset achievement rate, such as 90%. It should be noted that each information sample stored in the first database corresponds to a quality identifier, i.e., a corresponding achievement rate.

[0171] The first information sample refers to an information sample in the first database whose quality identifier is a preset quality identifier. Specifically, it refers to an information sample in the first database whose achievement rate of environmental regulation task information is greater than or equal to a preset achievement rate. Furthermore, if the quality score of an information sample is greater than or equal to a preset score, that information sample can also be identified as the first information sample.

[0172] The third generative model refers to the experience data generation model, specifically used to generate corresponding experience data based on the first information sample. Of course, experience data can also be generated by the third generative model based on the information sample and historical experience data. Historical experience data refers to historical experience regarding the environmental regulation tasks of air conditioning equipment, such as historical experience in temperature regulation and humidity regulation.

[0173] Specifically, refer to Figure 1The controller 120 selects information samples with preset quality identifiers from the information samples in the first database according to the quality identifiers corresponding to the information samples in the first database, and uses them as the first information samples. Then, the first information samples are input into the third generative model. The third generative model performs empirical data generation processing based on the first information samples to obtain new empirical data. For example, the feature vector of the first information samples is input into the third generative model, and the third generative model generates new empirical data based on the feature vector of the first information samples. Finally, the generated empirical data is stored in the second database.

[0174] In addition, the controller 120 can also acquire historical experience data of environmental regulation task information of the air conditioning equipment, and input the first information sample and historical experience data into the third generative model. Based on the first information sample and historical experience data, the third generative model performs experience data generation processing to obtain new experience data. For example, it concatenates the feature vector corresponding to the first information sample and the feature vector corresponding to the historical experience data to obtain a combined vector, and inputs the combined vector into the third generative model. Based on the combined vector, the third generative model generates new experience data. Finally, the generated experience data is stored in the second database.

[0175] The technical solution provided in this embodiment first selects a first information sample with a preset quality identifier from the first database, and then generates experience data based on the first information sample through a third generative model. The generated experience data is then stored in the second database, which helps to improve the accuracy of the generated experience data, thereby improving the accuracy of the experience data stored in the second database. At the same time, it helps to expand the experience data in the second database used to generate execution plan information.

[0176] In some embodiments, such as Figure 11 As shown, controller 120 is also configured as follows:

[0177] Step S1101: Determine the task vector corresponding to the target adjustment task information, equipment information, and environmental information.

[0178] Step S1102: Based on the task vector, perform a search in the first database to obtain target information samples associated with the task vector.

[0179] Specifically, refer to Figure 1The controller 120 first acquires the feature vectors corresponding to the target adjustment task information, the device information, and the environment information. Then, it concatenates these feature vectors to obtain the task vectors corresponding to the target adjustment task information, the device information, and the environment information. Next, based on the task vectors, it searches in a preset first database to obtain information samples whose similarity to the corresponding data vectors is greater than a similarity threshold. These samples are then used as target information samples associated with the task vectors.

[0180] The technical solution provided in this embodiment first determines the task vector corresponding to the target adjustment task information, equipment information, and environmental information, and then searches the first database based on the task vector to obtain the target information sample associated with the task vector. In this way, by comprehensively considering the task vector corresponding to the target adjustment task information, equipment information, and environmental information, and searching from the first database, it is beneficial to improve the accuracy of obtaining the target information sample.

[0181] In some embodiments, such as Figure 12 As shown, controller 120 is also configured as follows:

[0182] Step S1201: Obtain the completion result of the execution plan information.

[0183] Step S1202: Store the execution plan information and the completion result of the execution plan information in a preset third database; the third database is used to store the execution plan information and the completion result of the execution plan information within a set time range.

[0184] Step S1203: If the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline based on the execution plan information stored in the third database and the completion results of each execution plan information.

[0185] The completion result of the execution plan information is used to characterize the completion status of the execution plan information, such as 80%, 90%, etc.

[0186] The preset third database refers to a temporary task example database (i.e., a temporary database), which stores execution plan information and the completion results of the execution plan information.

[0187] The "set time range" refers to a defined time period, such as one day, three days, or one week. It should be noted that the third-party database is primarily used to store execution plan information and its completion results within the set time range, serving as a temporary storage for these information.

[0188] Specifically, refer to Figure 1 After the controller 120 executes the corresponding execution plan information, the controller 120 obtains the completion result of the execution plan information and stores the execution plan information and the completion result of the execution plan information in a preset third database. Then, the number of execution plan information stored in the third database is counted in real time. If the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline according to the execution plan information stored in the third database and the completion result of each execution plan information, so as to store the execution plan information that meets the requirements into the first database.

[0189] The technical solution provided in this embodiment first stores the execution plan information and the completion results of the execution plan in a preset third database. Then, when the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline according to the execution plan information stored in the third database and the completion results of each execution plan. This facilitates timely updates to the information samples in the first database and ensures the validity of the information samples in the first database.

[0190] In some embodiments, such as Figure 13 As shown, controller 120 is also configured as follows:

[0191] Step S1301: Determine the quality identifier of the execution plan information based on the completion results of the execution plan information in the third database and the target adjustment task information associated with the execution plan information.

[0192] Step S1302: If the quality identifier is a preset quality identifier, the execution plan information is used as the first information sample and the first information sample is stored in the first database.

[0193] Step S1303: If the quality identifier is different from the preset quality identifier, the execution plan information is corrected to obtain the corrected execution plan information. The corrected execution plan information is used as the second information sample and stored in the first database.

[0194] Among them, the quality identifier of the execution plan information is used to characterize the achievement rate of the execution plan information, and is specifically determined based on the completion results of the execution plan information and the target adjustment task information associated with the execution plan information.

[0195] Among them, the preset quality identifier is used to represent the preset achievement rate, such as 80%. The quality identifier of the execution plan information is the preset quality identifier, used to represent that the achievement rate of the execution plan information is greater than or equal to the preset achievement rate. The quality identifier of the execution plan information is different from the preset quality identifier, used to represent that the achievement rate of the execution plan information is less than the preset achievement rate.

[0196] The first information sample refers to the execution plan information whose corresponding quality identifier is the preset quality identifier, specifically the first task example data. The second information sample refers to the revised execution plan information, specifically the second task example data; the revised execution plan information is obtained by correcting execution plan information whose quality identifier differs from the preset quality identifier.

[0197] Specifically, refer to Figure 1 The controller 120 calculates the achievement rate of the execution plan information in the third database based on the completion results of the execution plan information and the target adjustment task information associated with the execution plan information. For example, it determines the achievement rate of the execution plan information in the third database based on the difference between the completion results of the execution plan information in the third database and the target adjustment task information associated with the execution plan information. Then, it determines the quality identifier of the execution plan information based on the achievement rate. For example, if the achievement rate of the execution plan information is greater than or equal to the preset achievement rate, the quality identifier of the execution plan information is confirmed as the preset quality identifier; if the achievement rate of the execution plan information is less than the preset achievement rate, the quality identifier of the execution plan information is confirmed as the preset quality identifier. The quality identifier differs from the preset quality identifier. Finally, the quality identifier of the execution plan information is identified. If the quality identifier of the execution plan information is the preset quality identifier, the execution plan information is used as the first information sample and directly stored in the first database. If the quality identifier of the execution plan information differs from the preset quality identifier, correction suggestion information for the execution plan information is obtained. Based on the correction suggestion information, the execution plan information is corrected to obtain the corrected execution plan information. Then, the corrected execution plan information is used as the second information sample and stored in the first database, so that the first database contains both valid first and second information samples.

[0198] The technical solution provided in this embodiment first determines the quality identifier of the execution plan information based on the completion results of the execution plan information in the third database and the target adjustment information associated with the execution plan information. Then, based on the quality identifier, different processing is performed on the execution plan information in the third database, which can ensure the accuracy and effectiveness of the information samples stored in the first database.

[0199] In some embodiments, such as Figure 1As shown, controller 120 is also configured as follows:

[0200] The communication device 110 obtains equipment information and environmental information of the air conditioning equipment from a preset Internet of Things platform.

[0201] The pre-set IoT platform refers to smart gateways, smart home controllers, etc., which store equipment information and environmental information of air conditioning devices.

[0202] Among them, IoT devices (such as air conditioning equipment and other smart home devices) regularly report their own device information, indoor environmental information and / or outdoor environmental information to the IoT platform.

[0203] Specifically, refer to Figure 1 The controller 120 sends device information query requests and environmental information query requests to a preset IoT platform via the communication device 110. The preset IoT platform directly obtains the device information and environmental information (including indoor and outdoor environmental information) of the air conditioning equipment from the local database based on the device information query requests and environmental information query requests, or monitors the device information and environmental information of the air conditioning equipment in real time, and returns the device information and environmental information of the air conditioning equipment to the communication device 110. Finally, the device information and environmental information of the air conditioning equipment are returned to the controller 120 via the communication device 110.

[0204] In addition, when the controller 120 is connected to the detection component 130, the controller 120 can also send an environmental information query request to the detection component 130. The detection component 130 can obtain the indoor and outdoor environmental information of the air conditioning equipment from the local database according to the environmental information query request, and use it as the environmental information of the air conditioning equipment. Alternatively, it can detect the indoor and outdoor environmental information of the air conditioning equipment in real time, obtain the indoor and outdoor environmental information of the air conditioning equipment, and obtain the environmental information of the air conditioning equipment based on the indoor and outdoor environmental information of the air conditioning equipment, and return the environmental information of the air conditioning equipment to the controller 120.

[0205] The technical solution provided in this embodiment obtains the equipment information and environmental information of the air conditioning equipment from the Internet of Things platform through a communication device. This ensures that the equipment information and environmental information of the air conditioning equipment can be effectively obtained, which facilitates the subsequent retrieval of target information samples based on the target adjustment task information, equipment information, and environmental information, and the generation of corresponding execution plan information, thereby ensuring the accuracy of the execution plan information generation.

[0206] In some embodiments, such as Figure 1 As shown, the indoor unit 140 includes a temperature sensor, a first heat exchanger, and a four-way valve; the outdoor unit 150 includes a second heat exchanger and a compressor. The controller 120 is further configured as follows:

[0207] The system controls the start-up of the compressor, first heat exchanger, second heat exchanger, and four-way valve based on the execution time, and obtains the indoor temperature value detected in real time by the temperature sensor. Based on the indoor temperature value, the system controls the operating status of the compressor, first heat exchanger, second heat exchanger, and four-way valve to adjust the indoor temperature value to the target temperature value when the task completion time arrives.

[0208] Specifically, refer to Figure 1 After obtaining the execution plan information of the air conditioning equipment, the controller 120 controls the first heat exchanger and four-way valve in the indoor unit 140, as well as the second heat exchanger and compressor in the outdoor unit 150, to start based on the execution time in the execution plan information. It also obtains the indoor temperature value detected in real time by the temperature sensor in the indoor unit 140. Then, based on the detected indoor temperature value, it controls the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value in the execution plan information, such as adjusting the indoor temperature value to 24 degrees.

[0209] The technical solution provided in this embodiment first controls the start-up of the compressor, first heat exchanger, second heat exchanger, and four-way valve in the air conditioning equipment based on the execution time, and obtains the indoor temperature value detected in real time by the temperature sensor. Then, it controls the operating status of the compressor, first heat exchanger, second heat exchanger, and four-way valve according to the indoor temperature value, so that when the task completion time arrives, the indoor temperature value is adjusted to the target temperature value. This achieves the purpose of automatically adjusting the indoor temperature value to the required target temperature value when the task completion time arrives, which is conducive to further improving the intelligence level of the air conditioning equipment.

[0210] In some embodiments, such as Figure 1 As shown, the indoor unit 140 also includes a humidity sensor for monitoring indoor humidity levels; the controller 120 is further configured to:

[0211] Based on the indoor humidity level, adjust the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve to adjust the indoor humidity level to the target humidity level when the task completion time arrives.

[0212] Specifically, refer to Figure 2After obtaining the execution plan information of the air conditioning equipment, the controller 120 controls the first heat exchanger and four-way valve in the indoor unit 140, as well as the second heat exchanger and compressor in the outdoor unit 150, to start based on the execution time in the execution plan information. It also obtains the indoor humidity value monitored in real time by the humidity sensor in the indoor unit 140. Then, based on the monitored indoor humidity value, it adjusts the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve so that when the task completion time arrives, the indoor humidity value is adjusted to the target humidity value in the execution plan information, such as adjusting the indoor humidity value to 50%.

[0213] The technical solution provided in this embodiment first monitors the indoor humidity value through a humidity sensor in the air conditioning equipment, and then adjusts the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve in the air conditioning equipment according to the indoor humidity value, so as to adjust the indoor humidity value to the target humidity value when the task completion time arrives. This achieves the purpose of automatically adjusting the indoor humidity value to the required target humidity value when the task completion time arrives, which is conducive to further improving the intelligence level of the air conditioning equipment.

[0214] In some embodiments, such as Figure 1 As shown, an execution plan processing method is provided, which can be applied to, for example... Figure 1 The air conditioning equipment shown, such as Figure 1 As shown, the air conditioning equipment may include an indoor unit 140, an outdoor unit 150, a detection component 130, a communication device 110, and a controller 120; the controller 120 is coupled to the detection component 130 and the communication device 110 respectively; the method may include the following steps:

[0215] Step S201: Receive instruction information sent by the terminal through the communication device 110; the instruction information is used to obtain the equipment information and environmental information of the air conditioning equipment, and generate corresponding execution plan information in combination with the target adjustment task information; the target adjustment task information includes the task completion time, target temperature value and / or target humidity value; the equipment information includes at least one of temperature adjustment parameters and humidity adjustment parameters, and the environmental information includes at least one of indoor and outdoor temperature values ​​and humidity values.

[0216] Step S202: Perform vector transformation on the target adjustment task information, equipment information and environmental information to obtain the corresponding task vector, and retrieve the target information sample from the preset first database based on vector retrieval; the first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information.

[0217] Step S203: Determine the execution plan information of the air conditioning equipment; the execution plan information is obtained by the generative model based on the target adjustment task information, equipment information, environmental information and target information samples; the execution plan information includes the execution time, target temperature value and / or target humidity value.

[0218] Step S204: Control the operation of the indoor and outdoor units based on the execution time, so as to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives.

[0219] It should be noted that the specific implementation process of the above-mentioned execution plan processing method can be found in [reference needed]. Figure 14 The relevant embodiments of the air conditioning equipment shown will not be described in detail here.

[0220] The technical solution provided in this embodiment, in the scenario of generating execution plan information for air conditioning equipment, comprehensively considers target adjustment task information, equipment information, environmental information, and retrieved target information samples. This effectively generates execution plan information for the air conditioning equipment, enabling it to adjust indoor temperature and / or humidity values ​​by executing this plan. When the task completion time arrives, the indoor temperature and / or humidity will be adjusted to the target value to satisfy the target adjustment task information, thus meeting the functional requirements of complex scenarios and improving the intelligence level of the air conditioning equipment. Furthermore, when the target adjustment task information is determined, the air conditioning equipment can automatically generate corresponding execution plan information based on the received instruction information and automatically adjust the indoor temperature and / or humidity values ​​to meet the target adjustment task information, further enhancing the intelligence level of the air conditioning equipment.

[0221] In some embodiments, the above execution plan processing method may further include the following steps:

[0222] Select a target generative model from the preset first generative model and second generative model; the target generative model is one of the first generative model and the second generative model; input the target adjustment task information, equipment information, environmental information and target information sample into the target generative model, and generate the execution plan information of the air conditioning equipment through the target generative model.

[0223] In some embodiments, the above execution plan processing method may further include the following steps:

[0224] If the similarity between the data vector corresponding to the target information sample and the task vector is greater than the preset similarity, the first generative model is used as the target generative model; if the similarity between the data vector corresponding to the target information sample and the task vector is less than or equal to the preset similarity, the second generative model is used as the target generative model.

[0225] In some embodiments, the above execution plan processing method may further include the following steps:

[0226] If the number of target information samples is greater than the first preset number, the first generative model is used as the target generative model; if the number of target information samples is less than or equal to the first preset number, the second generative model is used as the target generative model.

[0227] In some embodiments, the above execution plan processing method may further include the following steps:

[0228] Based on the target adjustment task information, equipment information, and environmental information, target experience data is retrieved from the preset second database. The second database stores multiple experience data, each of which represents the intrinsic relationship between the pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information. The target adjustment task information, equipment information, environmental information, target information samples, and target experience data are input into the target generative model, and the execution plan information of the air conditioning equipment is generated through the target generative model.

[0229] In some embodiments, the above execution plan processing method may further include the following steps:

[0230] The target adjustment task information includes temperature adjustment tasks and / or humidity adjustment tasks; based on the temperature adjustment tasks and / or humidity adjustment tasks, a search is performed in the second database to obtain target experience data associated with temperature adjustment and / or humidity adjustment.

[0231] In some embodiments, the above execution plan processing method may further include the following steps:

[0232] First information samples with preset quality identifiers are selected from the first database; the quality identifier represents the achievement rate of the selected environmental regulation task information in the corresponding information sample; the first information samples are input into the third generative model, and empirical data is generated through the third generative model; the generated empirical data is stored in the second database.

[0233] In some embodiments, the above execution plan processing method may further include the following steps:

[0234] Obtain the completion results of the execution plan information; store the execution plan information and the completion results of the execution plan information in a preset third database; the third database is used to store the execution plan information and the completion results of the execution plan information within a set time range; if the number of execution plan information stored in the third database is greater than the second preset number, the first database is updated offline according to the execution plan information stored in the third database and the completion results of each execution plan information.

[0235] In some embodiments, the above execution plan processing method may further include the following steps:

[0236] Based on the completion results of the execution plan information in the third database and the target adjustment task information associated with the execution plan information, the quality identifier of the execution plan information is determined. If the quality identifier is the preset quality identifier, the execution plan information is used as the first information sample and stored in the first database. If the quality identifier is different from the preset quality identifier, the execution plan information is corrected to obtain the corrected execution plan information. The corrected execution plan information is used as the second information sample and stored in the first database.

[0237] In some embodiments, the above execution plan processing method may further include the following steps:

[0238] The device obtains equipment information and environmental information of the air conditioning equipment from a pre-set Internet of Things platform through a communication device.

[0239] In some embodiments, the above execution plan processing method may further include the following steps:

[0240] The system controls the start-up of the compressor, first heat exchanger, second heat exchanger, and four-way valve based on the execution time, and obtains the indoor temperature value detected in real time by the temperature sensor. Based on the indoor temperature value, the system controls the operating status of the compressor, first heat exchanger, second heat exchanger, and four-way valve to adjust the indoor temperature value to the target temperature value when the task completion time arrives.

[0241] In some embodiments, the above execution plan processing method may further include the following steps:

[0242] Based on the indoor humidity level, adjust the operating status of the compressor, the first heat exchanger, the second heat exchanger, and the four-way valve to adjust the indoor humidity level to the target humidity level when the task completion time arrives.

[0243] In some embodiments, such as Figure 15 As shown, to more clearly describe the signaling interaction process between the various modules of the air conditioning equipment, this application also provides another execution plan processing method, which may include the following steps:

[0244] Step 1: Each IoT device periodically reports its own device information and environmental information (including indoor and / or outdoor environmental information) to the IoT platform. The IoT devices may include the air conditioning units to be controlled.

[0245] Step 2: The terminal obtains the user's command information for the air conditioning equipment.

[0246] The instruction information carries target adjustment task information, which includes task completion time, target temperature value and / or target humidity value.

[0247] Step 3: The terminal sends the instruction information for the air conditioning equipment to the communication device 110.

[0248] Step 4: The communication device 110 sends the instruction information to the controller 120.

[0249] Step 5: The controller 120 sends the device information query request and the environmental information query request to the communication device 110 according to the instruction information.

[0250] Step 6: The communication device 110 sends the device information query request and the environmental information query request to the aforementioned Internet of Things platform.

[0251] Step 7: The IoT platform returns the equipment information and environmental information (including indoor environmental information and / or outdoor environmental information) of the air conditioning equipment to the communication device 110.

[0252] Step 8: The communication device 110 returns the information received from the Internet of Things platform to the controller 120.

[0253] Step 9: If the controller 120 is connected to the detection component 130, the controller 120 will also send an environmental information query request to the detection component 130.

[0254] Step 10: The detection component 130 acquires environmental information of the air conditioning equipment, including indoor environmental information and / or outdoor environmental information.

[0255] Step 11: The detection component 130 returns the environmental information of the air conditioning equipment to the controller 120.

[0256] Among them, the environmental information of the air conditioning equipment (including indoor and outdoor environmental information) is obtained from the Internet of Things platform through the communication device 110, and the environmental information of the air conditioning equipment is obtained through the detection component 130. The environmental information obtained through different paths is mutually supplemented or interactively verified to ensure the completeness and accuracy of the final environmental information.

[0257] Step 12: The controller 120 retrieves target experience data from the preset second database (experience database) based on the target adjustment task information, equipment information and environmental information.

[0258] Step 13: The controller 120 retrieves target information samples (such as target task example data) from the preset first database (task example database) based on the target adjustment task information, equipment information and environmental information.

[0259] Step 14: The controller 120 selects the target generative model from the preset first generative model and second generative model.

[0260] The model size of the first generative model is smaller than that of the second generative model. When the similarity of the target information samples is high or the number is large, the controller 120 selects the first generative model as the target generative model; otherwise, it selects the second generative model as the target generative model.

[0261] Step 15: The controller 120 inputs the target adjustment task information, equipment information, environmental information, target information sample and target experience data into the target generative model, and generates the execution plan information of the air conditioning equipment (including execution time, target temperature value and / or target humidity value) through the target generative model.

[0262] The first database, second database, first generative model, and second generative model can all be set on the server / cloud or on the local device where the controller 120 is located (i.e., the air conditioning device). When the first database, second database, first generative model, and second generative model can all be set on the server / cloud, steps 12-15 need to be updated so that the controller 120 sends relevant information to the server / cloud and receives the air conditioning device's execution plan information returned by the server / cloud.

[0263] Step 16: The controller 120 controls the operation of the indoor unit 140 and the outdoor unit 150 based on the execution time, so as to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives.

[0264] Step 17: The controller 120 obtains the completion result of the execution plan information of the aforementioned air conditioning equipment; and stores the execution plan information and the completion result of the execution plan information in a preset third database (temporary database).

[0265] Step 18: If the number of execution plan information stored in the third database by the controller 120 is greater than the second preset number, the controller 120 performs an offline update on the first database based on the execution plan information in the third database and the completion results of each execution plan information.

[0266] For example, the controller 120 determines the quality identifier of the execution plan information based on the completion result of the execution plan information in the third database and the target adjustment task information associated with the execution plan information; if the quality identifier is a preset quality identifier (such as when the quality score is greater than or equal to the preset score), the execution plan information is stored in the first database as a first information sample (such as first task example data); if the quality identifier is different from the preset quality identifier (such as when the quality score is less than the preset score), the execution plan information is corrected, and the corrected execution plan information is stored in the first database as a second information sample (such as second task example data).

[0267] Step 19: The controller 120 selects the first information sample from the first database.

[0268] Step 20: The controller 120 inputs the first information sample and historical experience data into the third generative model, and generates new experience data through the third generative model; the generated new experience data is stored in the second database, so as to continuously expand the key experience in the second database used to generate air conditioning plan information.

[0269] In the above steps, the communication device 110, controller 120, and detection component 130 can be local components of the air conditioning equipment or server / cloud components. If they are local components of the air conditioning equipment, the above interaction sequence is intended to reflect the interaction process between the terminal, the air conditioning equipment, and the IoT platform; if they are server / cloud components, the above interaction sequence is intended to reflect the interaction process between the terminal, the server / cloud, the air conditioning equipment, and the IoT platform.

[0270] It should be noted that if the communication device 110, controller 120 and detection component 130 in the above steps are server-side / cloud-based components, some of the above steps may include multiple steps or may be adapted, but they still fall within the inventive concept scope of the above embodiments of this application.

[0271] The technical solution provided in this embodiment, in the scenario of generating execution plan information for air conditioning equipment, comprehensively considers target adjustment task information, equipment information, environmental information, and retrieved target information samples and target experience data. This effectively generates execution plan information for the air conditioning equipment, enabling it to adjust indoor temperature and / or indoor humidity values ​​by executing this plan. When the task completion time arrives, the indoor temperature and / or humidity will be adjusted to the target temperature and / or humidity values ​​to meet the target adjustment task information, thus satisfying the functional requirements of complex scenarios and improving the intelligence level of the air conditioning equipment. Furthermore, when the target adjustment task information is determined, the air conditioning equipment can automatically generate corresponding execution plan information based on the received instruction information and automatically adjust the indoor temperature and / or indoor humidity values ​​to meet the target adjustment task information, further enhancing the intelligence level of the air conditioning equipment.

[0272] In some embodiments, to more clearly illustrate the execution plan processing method provided in the embodiments of this application, the following specific embodiment will be used to describe the execution plan processing method in detail. References Figure 15 This application also provides a task execution prediction method that integrates various complex environmental data. This method involves the field of large language models, and the main scenario is intelligent air conditioning control. It mainly adopts an online learning scheme, combined with the capabilities of multi-size models, to autonomously iterate and generate execution plans. For example, relying on large models, based on indoor and outdoor air data and equipment status and configuration, it intelligently predicts the plans and corresponding times for achieving different air requirements under different conditions, providing professional technical support for the realization of whole-house intelligence for air conditioning intelligent agents. This method has two improvements: (1) Large model knowledge distillation: calling a larger-scale language model to iteratively generate high-quality prediction example data; (2) Online retrieval and reasoning: based on user needs and environmental information, retrieving similar example data, concatenating the retrieved example data with the current context to prompt the large model, and generating execution plans and corresponding times. The specific content is as follows:

[0273] like Figure 16 As shown, the task execution prediction method that integrates various complex environmental data mainly consists of the following three steps:

[0274] Step 1: Initialize the task library

[0275] The main process is as follows:

[0276] 1. Real data generation: Professionals construct a small amount of data through experiments or experience, and provide a detailed thought process for the generation process.

[0277] 2. Larger model generation: Combine real data to generate a certain amount of new scenarios and new data.

[0278] 3. Data calibration: Professionals simulate and revise new scenarios and new data, marking and correcting errors in plans and thought processes.

[0279] 4. Repeat 2 / 3 until data of the desired magnitude and diversity are generated.

[0280] Data example:

[0281] User request: "Set the temperature to 24",

[0282] Current temperature and humidity: "Indoor temperature 30, outdoor temperature 32…",

[0283] "Machine Status": "Recent Average Cooling Capacity xx…",

[0284] "Plan": "Set the air conditioner temperature to 20 degrees Celsius, fan speed on automatic. After 5 minutes, adjust the air conditioner temperature to 24 degrees Celsius, fan speed to level 1. Estimated total time: 15 minutes."

[0285] II. Online Plan Generation

[0286] The main process is as follows:

[0287] 1. Key experience retrieval: Based on the task theme, for example, if it involves temperature regulation, retrieve relevant experience; if it involves humidity regulation, retrieve relevant experience.

[0288] 2. Task Example Retrieval: Vectorize tasks and retrieve relevant task examples through vector retrieval.

[0289] 3. Model Selection: Based on the task example retrieval results, different model sizes are selected. When task examples are highly relevant or there are many similar examples, a small-sized model is used to generate the plan; otherwise, a large-sized model is used to ensure the effectiveness of plan generation.

[0290] 4. Plan Generation: Combine user needs, environmental conditions, Class 1 / 2 task examples, and key experiences and feed them into the large model to generate an execution plan and timeline.

[0291] 5. Task storage: The generated plan and the data after execution are fed back in real time and put into the temporary task library.

[0292] III. Offline Task Library Processing

[0293] The main process is as follows:

[0294] 1. Trigger: When the data in the temporary task library accumulates to a certain amount, the offline processing mechanism is triggered.

[0295] 2. Project Quality Inspection: Based on the completion status of the project and user feedback, a completion score will be given, and preliminary correction plans will be provided. Projects with high scores will be included in the official database as Category 1 tasks.

[0296] 3. Plan Revision and Inclusion: Tasks with low completion scores will have their execution plans adjusted manually based on revision suggestions and then included in the official task library (Category 2).

[0297] Key experience summary: By combining historical experience with the current formal library's Class 1 tasks, a large model is suggested, and key experience is generated.

[0298] like Figure 17 As shown, this application also provides another method for predicting task execution by fusing various complex environmental data, the details of which are as follows:

[0299] 1. Input user needs through a smart home app on your phone or a smart TV, such as "I'll be home around 8 o'clock, please set the temperature to 26 degrees Celsius," or input user needs through the smart remote control of the air conditioner.

[0300] 2. Obtain information about air conditioning equipment through IoT (Internet of Things), such as heating / cooling capacity for the past few days; obtain indoor data information through IoT, such as indoor temperature, humidity, PM2.5, etc.; obtain outdoor data information through weather queries, such as outdoor temperature, humidity, PM2.5, etc.

[0301] 3. Based on user demand information, air conditioning equipment information, indoor data information, and outdoor data information, key experience is retrieved and then refined using a large model.

[0302] 4. Based on user demand information, air conditioning equipment information, indoor data information, and outdoor data information, perform task example retrieval and fine-ranking through a large model.

[0303] 5. Select the corresponding large model based on the retrieved task examples. If there are relevant examples, generate an execution plan using the large model; otherwise, generate an execution plan using an even larger model.

[0304] 6. Return the execution plan to the initiating device, such as a mobile phone or smart TV, and ask the user to confirm the execution plan.

[0305] 7. If the user confirms the execution plan or modifies the execution plan, the confirmed or modified execution plan will be executed via the air conditioning task timer. If the user does not confirm the execution plan, or the execution plan fails, the execution plan will be stored in the task library.

[0306] 8. After the task is completed, report the results and mark the task according to the results, such as success or failure.

[0307] 9. Store the labeled tasks in the task library.

[0308] The technical solution provided in this embodiment can achieve the following technical effects: (1) Less labeled data and lower cost: Traditional solutions require a lot of experiments to obtain a lot of data, and it is difficult to guarantee diversity; This application only requires a small amount of real data to start, and adopts an iterative data generation method to obtain more diverse high-quality data, and does not require too much; (2) Diverse coverage scenarios and strong generalization: Based on high-quality example data, key experiences are summarized, and the most relevant task prompts are dynamically added to improve the accuracy of large models for unseen scenarios; (3) Simple implementation: No need for manual feature extraction or large-scale data training.

[0309] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0310] Based on the same inventive concept, this application also provides an execution plan processing apparatus for implementing the execution plan processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more execution plan processing apparatus embodiments provided below can be found in the limitations of the execution plan processing method described above, and will not be repeated here.

[0311] In some embodiments, such as Figure 1 As shown, an execution plan processing apparatus 1700 is provided, which can be applied to, for example... Figure 1 The air conditioning equipment shown, such as ​ As shown, the air conditioning equipment may include an indoor unit 140, an outdoor unit 150, a detection component 130, a communication device 110, and a controller 120; the controller 120 is coupled to both the detection component 130 and the communication device 110; the device may include:

[0312] The information receiving module 1710 is used to receive instruction information sent by the terminal through the communication device; the instruction information is used to obtain the equipment information and environmental information of the air conditioning equipment, and generate corresponding execution plan information in combination with the target adjustment task information; the target adjustment task information includes the task completion time, the target temperature value and / or the target humidity value; the equipment information includes at least one of the temperature adjustment parameters and the humidity adjustment parameters, and the environmental information includes at least one of the indoor and outdoor temperature values ​​and humidity values.

[0313] The sample acquisition module 1720 is used to perform vector transformation on the target adjustment task information, equipment information and environmental information to obtain the corresponding task vector, and retrieve the target information sample from the preset first database based on vector retrieval; the first database stores multiple information samples, each of which includes pre-selected environmental adjustment task information and its corresponding air conditioning execution plan information.

[0314] The information determination module 1730 is used to determine the execution plan information of the air conditioning equipment; the execution plan information is obtained by the generative model based on the target adjustment task information, equipment information, environmental information and target information samples; the execution plan information includes the execution time, target temperature value and / or target humidity value.

[0315] The control and adjustment module 1740 is used to control the operation of the indoor and outdoor units based on the execution time, so as to adjust the indoor temperature value to the target temperature value and / or adjust the indoor humidity value to the target humidity value when the task completion time arrives.

[0316] Each module in the aforementioned execution plan processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.

[0317] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0318] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0319] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0320] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0321] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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 application.

[0322] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An air conditioning apparatus characterized by comprising: The air conditioner comprises: an indoor unit; an outdoor unit; a communication device; a controller coupled to the communication device and configured to: receive instruction information sent by a terminal through the communication device; the instruction information is used to obtain device information and environment information of the air conditioner and generate corresponding execution plan information in combination with target regulation task information; the target regulation task information comprises a task completion time, a target temperature value and / or a target humidity value; the device information comprises at least one of a temperature regulation parameter and a humidity regulation parameter, and the environment information comprises at least one of a temperature value and a humidity value indoors and outdoors; perform vector conversion on the target regulation task information, the device information and the environment information to obtain a corresponding task vector, and retrieve target information samples corresponding to the task vector from a preset first database based on vector retrieval; the first database stores a plurality of information samples, and each information sample comprises preselected environment regulation task information and corresponding air conditioner execution plan information; determine execution plan information of the air conditioner; the execution plan information is obtained by a generative model based on the target regulation task information, the device information, the environment information and the target information samples; the execution plan information comprises an execution time, the target temperature value and / or the target humidity value; control the indoor unit and the outdoor unit to operate based on the execution time, so as to adjust an indoor temperature value to the target temperature value and / or adjust an indoor humidity value to the target humidity value when the task completion time arrives; the controller is further configured to: select a target generative model from preset first and second generative models; the target generative model is one of the first and second generative models; the first generative model refers to a small-size model for generating execution plan information of an air conditioner; the second generative model refers to a larger-size model for generating execution plan information of an air conditioner relative to the first generative model; input the target regulation task information, the device information, the environment information and the target information samples into the target generative model, and generate the execution plan information of the air conditioner by the target generative model.

2. The air conditioning apparatus according to claim 1, wherein the controller is further configured to: in a case where a similarity between a data vector corresponding to the target information sample and the task vector is greater than a preset similarity, use the first generative model as the target generative model; in a case where the similarity between the data vector corresponding to the target information sample and the task vector is less than or equal to the preset similarity, use the second generative model as the target generative model.

3. The air conditioning apparatus according to claim 1, wherein the controller is further configured to: in a case where a sample quantity of the target information sample is greater than a first preset quantity, use the first generative model as the target generative model; in a case where the sample quantity of the target information sample is less than or equal to the first preset quantity, use the second generative model as the target generative model.

4. The air conditioning apparatus according to claim 1, wherein The controller is further configured to: retrieve target experience data from a preset second database according to the target adjustment task information, the device information and the environment information; the second database stores a plurality of experience data, and each experience data represents an internal relationship between preselected environment adjustment task information and corresponding air conditioner execution plan information; input the target adjustment task information, the device information, the environment information, the target information sample and the target experience data into the target generative model, and generate the execution plan information of the air conditioner device through the target generative model.

5. The air conditioning apparatus according to claim 4, wherein The controller is further configured to: determine a temperature adjustment task and / or a humidity adjustment task contained in the target adjustment task information; retrieve the target experience data associated with temperature adjustment and / or humidity adjustment in the second database according to the temperature adjustment task and / or the humidity adjustment task.

6. The air conditioning apparatus according to claim 4, wherein The controller is further configured to: filter, from the first database, a first information sample with a preset quality identifier; the quality identifier represents an achievement rate of selected environment adjustment task information in the corresponding information sample; input the first information sample into a third generative model, and generate experience data through the third generative model; store the generated experience data into the second database.

7. The air conditioning apparatus according to claim 1, wherein The controller is further configured to: obtain a completion result of the execution plan information; store the execution plan information and the completion result of the execution plan information into a preset third database; the third database is used to store the execution plan information and the completion result of the execution plan information within a set time range; in a case where the number of execution plan information stored in the third database is greater than a second preset number, update the first database offline according to the execution plan information stored in the third database and the completion result of each execution plan information.

8. The air conditioning apparatus according to claim 7, wherein The controller is further configured to: determine a quality identifier of the execution plan information according to the completion result of the execution plan information in the third database and the target adjustment task information associated with the execution plan information; in a case where the quality identifier is a preset quality identifier, take the execution plan information as a first information sample, and store the first information sample into the first database; in a case where the quality identifier is different from the preset quality identifier, correct the execution plan information to obtain corrected execution plan information, take the corrected execution plan information as a second information sample, and store the second information sample into the first database.

9. The air conditioning apparatus according to any one of claims 1 to 8, characterized by The controller is further configured to: obtain device information and environment information of the air conditioner device from a preset Internet of Things platform through the communication device.

10. The air conditioning apparatus according to any one of claims 1 to 8, characterized by The indoor unit comprises a temperature sensor, a first heat exchanger and a four-way valve; the outdoor unit comprises a second heat exchanger and a compressor; The controller is further configured to: The compressor, the first heat exchanger, the second heat exchanger and the four-way valve are controlled based on the execution time, and a real-time indoor temperature value detected by the temperature sensor is obtained, and the running state of the compressor, the first heat exchanger, the second heat exchanger and the four-way valve is controlled according to the indoor temperature value, so that the indoor temperature value is adjusted to the target temperature value when the task completion time arrives.

11. The air conditioning apparatus according to claim 10, wherein The indoor unit further comprises a humidity sensor for monitoring an indoor humidity value. The controller is further configured to: According to the indoor humidity value, the running state of the compressor, the first heat exchanger, the second heat exchanger and the four-way valve is adjusted, so that the indoor humidity value is adjusted to the target humidity value when the task completion time arrives.

12. A method of performing a plan process, characterized by, The application is applied to an air conditioning device, which comprises an indoor unit, an outdoor unit, a communication device and a controller. The controller is coupled with the communication device. The method comprises: The communication device receives instruction information sent by a terminal; the instruction information is used to obtain device information and environment information of the air conditioning device, and generate corresponding execution plan information in combination with target regulation task information; the target regulation task information comprises a task completion time, a target temperature value and / or a target humidity value; the device information comprises at least one of a temperature regulation parameter and a humidity regulation parameter, and the environment information comprises at least one of an indoor and outdoor temperature value and a humidity value; The target regulation task information, the device information and the environment information are vector converted to obtain a corresponding task vector, and target information samples are retrieved from a preset first database based on vector retrieval; the first database stores a plurality of information samples, and each information sample comprises preselected environment regulation task information and corresponding air conditioning execution plan information thereof; The execution plan information of the air conditioning device is determined; the execution plan information is obtained by a generative model based on the target regulation task information, the device information, the environment information and the target information samples; the execution plan information comprises an execution time, the target temperature value and / or the target humidity value; The indoor unit and the outdoor unit are controlled to run based on the execution time, so that the indoor temperature value is adjusted to the target temperature value and / or the indoor humidity value is adjusted to the target humidity value when the task completion time arrives. The determining the execution plan information of the air conditioning equipment comprises: selecting a target generative model from preset first and second generative models; the target generative model is one of the first and second generative models; inputting the target adjustment task information, the equipment information, the environment information and the target information sample into the target generative model, and generating the execution plan information of the air conditioning equipment through the target generative model; the first generative model refers to a small-size model for generating the execution plan information of the air conditioning equipment; and the second generative model refers to a larger-size model for generating the execution plan information of the air conditioning equipment relative to the first generative model.

Images