Equipment regulation and control method, air conditioning equipment and computer storage medium

Abstract

The invention discloses an equipment regulation and control method, air conditioning equipment and a computer storage medium, and relates to the technical field of equipment regulation and control. The equipment regulation and control method comprises the steps that when a decision condition is triggered, regulation and control strategies output by all agent models are obtained; the agent models comprise at least two of energy-saving, comfortable, healthy and electricity price agent models; determining a target regulation and control strategy according to the regulation and control strategy output by each agent model; and controlling operation of target equipment according to the target regulation and control strategy. The accuracy of equipment regulation and control can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of device regulation, and in particular to a device regulation method, an air conditioning device, and a computer storage medium. BACKGROUND

[0002] In the control process of related devices, since the needs of users in different scenarios are different, different regulation strategies are usually provided to related devices for different scenarios or needs.

[0003] Currently, the determination of regulation strategies in different scenarios or needs is usually achieved by formulating corresponding regulation rules for different scenarios or needs or by training corresponding agent models for different scenarios or needs.

[0004] However, since regulation rules cannot comprehensively cover all regulation conditions, and agent models can only give corresponding regulation strategies for one kind of need and cannot give corresponding regulation strategies for multiple needs, the regulation accuracy of the existing regulation mode is low. SUMMARY

[0005] The main purpose of the present application is to provide a device regulation method, an air conditioning device, and a computer storage medium, aiming to improve the accuracy of device regulation.

[0006] To achieve the above purpose, the present application provides a device regulation method, which comprises:

[0007] When a decision condition is triggered, regulation strategies output by each agent model are obtained; the agent model comprises at least two of energy saving, comfort, health, and electricity price agent models;

[0008] A target regulation strategy is determined according to the regulation strategies output by each agent model;

[0009] The target device is controlled to operate according to the target regulation strategy.

[0010] In an embodiment, the step of determining the target regulation strategy according to the regulation strategies output by each agent model comprises:

[0011] The regulation strategies output by each agent model are summarized to obtain a regulation strategy set;

[0012] Each agent model outputs a new regulation strategy according to the regulation strategy set;

[0013] The target regulation strategy is determined according to the new regulation strategies output by each agent model.

[0014] In an embodiment, the step of determining the target regulation strategy according to the regulation strategies output by each agent model comprises:

[0015] If the regulation strategies output by the agent models do not all contain parameter objects, the regulation strategies containing parameter objects are taken as parameter-type regulation strategies, and the regulation strategies not containing parameter objects are taken as non-parameter-type regulation strategies;

[0016] According to the parameter-type regulation strategies, a first preselected regulation strategy is determined, and according to the non-parameter-type regulation strategies, a second preselected regulation strategy is determined;

[0017] The first preselected regulation strategy and the second preselected regulation strategy are integrated to obtain the target regulation strategy.

[0018] In an embodiment, the step of determining the first preselected regulation strategy according to the parameter-type regulation strategies comprises:

[0019] A first target parameter value is calculated according to parameter values of parameter objects contained in the parameter-type regulation strategies;

[0020] The parameter values of the parameter objects contained in the parameter-type regulation strategies are adjusted to the first target parameter value to obtain adjusted parameter-type regulation strategies;

[0021] One of the adjusted parameter-type regulation strategies is selected as the first preselected regulation strategy.

[0022] In an embodiment, the step of determining the second preselected regulation strategy according to the non-parameter-type regulation strategies comprises:

[0023] It is determined whether the non-parameter-type regulation strategies are adopted;

[0024] The adopted non-parameter-type regulation strategies are integrated to obtain the second preselected regulation strategy.

[0025] In an embodiment, the step of determining the target regulation strategy according to the regulation strategies output by the agent models further comprises:

[0026] If the regulation strategies output by the agent models all contain parameter objects, a second target parameter value is calculated according to parameter values of parameter objects contained in the regulation strategies;

[0027] The parameter values of the parameter objects contained in the regulation strategies are adjusted to the second target parameter value to obtain adjusted regulation strategies;

[0028] One of the adjusted regulation strategies is selected as the target regulation strategy.

[0029] In an embodiment, the step of determining the target control strategy according to the control strategies output by the agent models further comprises:

[0030] If the control strategies output by the agent models are all the same, one of the control strategies output by the agent models is selected as the target control strategy.

[0031] In an embodiment, the step of determining the target control strategy according to the control strategies output by the agent models further comprises:

[0032] If the control strategies output by the agent models are not all the same, the priority of the control strategies output by the agent models is obtained.

[0033] Based on the priority of the control strategies output by the agent models, the control strategy with the highest priority among the control strategies output by the agent models is selected as the target control strategy.

[0034] In an embodiment, the step of obtaining the control strategies output by the agent models comprises:

[0035] The environmental parameters of the workspace where the target device is located and the historical behavior data generated when the target user uses the target device are obtained.

[0036] The environmental parameters and the historical behavior data are input into the agent models to obtain the control strategies output by the agent models.

[0037] In an embodiment, the device control method further comprises:

[0038] The model behaviors of the agent models are subjected to natural language processing to obtain the model behavior logs of the agent models.

[0039] The model behavior logs of the agent models are stored in a preset log storage area.

[0040] In addition, to achieve the above-mentioned purposes, the present application further provides an air conditioning device, which comprises a memory, a processor, and a device control program stored in the memory and executable on the processor. The automatic control program is executed by the processor to implement the steps of the device control method as described above.

[0041] In addition, to achieve the above-mentioned purposes, the present application further provides a computer storage medium, which stores a device control program executable on a processor. The running program is called by the processor to implement the steps of the device control method as described above.

[0042] In addition, to achieve the above object, the present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the device regulation method as described above.

[0043] The present application provides a device regulation method. When a decision condition is triggered, the present application first acquires regulation strategies output by each agent model, wherein the agent model comprises at least two of an energy-saving agent model, a comfort agent model, a health agent model and a price agent model. Then, the present application determines a target regulation strategy according to the regulation strategies output by each agent model. Finally, the present application controls a target device to operate according to the target regulation strategy. Since the regulation strategies output by each agent model are regulation strategies given by each agent model for different demands, the present application determines a regulation strategy (i.e., the target regulation strategy) for controlling the target device to operate by combining the regulation strategies under various demands, so as to ensure that the target regulation strategy determined can adapt to multiple demands, thereby improving the accuracy of device regulation. BRIEF DESCRIPTION OF DRAWINGS

[0044] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative work.

[0046] Figure 1 A flowchart of the device regulation method of the present application embodiment;

[0047] Figure 2 A schematic diagram of the operation principle of the agent involved in the device regulation method of the present application embodiment;

[0048] Figure 3 A specific implementation structure diagram of the device regulation method of the present application embodiment;

[0049] Figure 4 A specific implementation flowchart of the device regulation method of the present application embodiment;

[0050] Figure 5 A structural schematic diagram of the hardware operation environment involved in the present application embodiment.

[0051] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0053] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0054] In the control process of the related device, due to the difference in the needs of users in different scenarios, different control strategies are usually needed to be provided to the related device for different scenarios or needs.

[0055] Currently, the determination of the control strategy in different scenarios or needs is usually realized by formulating corresponding control rules for different scenarios or needs, or by training corresponding agent models for different scenarios or needs.

[0056] However, since the control rules cannot comprehensively cover all control situations, and the agent models can only give corresponding control strategies for one kind of needs, but cannot give corresponding control strategies for multiple needs, the control accuracy of the existing control method is low.

[0057] The main solution of the present application is: when a decision condition is triggered, obtaining the control strategies output by each agent model; the agent model includes at least two of energy saving, comfort, health, and electricity price agent models; determining a target control strategy according to the control strategies output by each agent model; and controlling the target device to operate according to the target control strategy.

[0058] The present application determines the control strategy (i.e., the target control strategy) finally used to control the target device to operate by combining the control strategies in various needs, so as to ensure that the determined target control strategy can adapt to multiple needs, thereby improving the accuracy of device control.

[0059] The execution subject of the present embodiment can be an air conditioning device, which can be an air conditioner or other device that adjusts air by controlling itself, or a server, a central controller, a central controller, a line controller, or other device that adjusts air by controlling other devices, and the present embodiment does not make specific limitations thereon. The present embodiment and each of the following embodiments will be described below with the air conditioning device as an execution subject.

[0060] Based on this, the present application proposes a device control method of the first embodiment, please refer to Figure 1 , the device control method includes steps S10-S30:

[0061] Step S10, when a decision condition is triggered, obtaining the control strategies output by each agent model; the agent model includes at least two of energy saving, comfort, health, and electricity price agent models;

[0062] It should be noted that the decision condition is the basis for whether to regulate the target device, and the decision condition can include that a user frequently adjusts a control parameter of a device, a regional parameter of a region, or a control parameter of a system, and the like, and the embodiment is not specifically limited thereto. For example, the decision condition can be that the user frequently adjusts the temperature of the device to 20°C.

[0063] Additionally, it should be noted that the agent can also be referred to as an intelligent agent, an intelligent body, etc., which is a computer program that can autonomously take action to achieve a goal by perceiving its environment without being told by a person what to do at all times. Please refer to Figure 2 The capabilities of the agent can generally be embodied in four categories: decision-making, memory, tool use, and behavior execution. For example, the HVAC tool has image recognition, search, database retrieval, and other tools, and the agent can select tools according to user needs and context in a session of a central terminal such as a central control or an APP, and take action. The agent model can include, but is not limited to, at least two of an energy saving, comfort, health, and electricity price agent model. The energy saving agent model is used to meet the energy saving needs of the device, the comfort agent model is used to meet the comfort needs of the user, the health agent model is used to meet the health needs of the user, and the electricity price agent model is used to meet the electricity needs of the user.

[0064] In addition, it should be noted that the agent models in the embodiment can not only determine different regulation strategies by configuring different agent requirements, but also simulate the experience of real users by configuring different role agents to save the acquisition cost of user experience, and then improve the target device based on the user experience obtained by simulation.

[0065] In a possible implementation, step S10 can specifically include steps S11-S12:

[0066] Step S11, obtaining an environmental parameter of a working space where a target device is located and historical behavior data generated by a target user when using the target device;

[0067] It should be noted that the target device refers to a device that needs to be regulated, and the target device can be an air conditioner, a heater, a floor heater, a humidifier, and the like, and the embodiment is not specifically limited thereto. The environmental parameter refers to a parameter of an environment where the target device is located, and the environmental parameter can include an environmental temperature, an environmental humidity, and the like. The target user refers to a user using the target device, and the historical behavior data is used to record various control behaviors of the target user on the target device in the past period of time.

[0068] Step S12, inputting the environmental parameter and the historical behavior data into each agent model to obtain a regulation strategy output by each agent model.

[0069] In this embodiment, when determining its own control strategy, each agent model takes into account the historical behavior data generated by the target user when using the target device, so that each agent model can adapt to the behavioral habits of the target user to obtain a control strategy that better meets the user's needs.

[0070] In another feasible implementation, step S10 may specifically include: acquiring environmental parameters of a workspace where the target device is located, inputting the environmental parameters into each agent model, and obtaining a control strategy output by each agent model.

[0071] The above are merely two feasible implementations of step S10 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S10. For example, in other implementations, environmental parameters, historical behavior data, and memory stream data carried by each agent model can also be simultaneously input into each agent model to obtain the control strategy output by each agent model.

[0072] Step S20, determining a target control strategy based on the control strategies output by each agent model;

[0073] It should be noted that the target control strategy is a control strategy used to control the operation of the target device.

[0074] In a feasible implementation, step S20 may specifically include step S201:

[0075] Step S201 : If the control strategies output by the proxy models are the same, then one control strategy is selected from the control strategies output by the proxy models as the target control strategy.

[0076] It is understandable that if the control strategies given by each proxy model for different requirements are the same, then any one of the control strategies output by each proxy model can be selected as the target control strategy.

[0077] In another feasible implementation, step S20 may specifically include steps S202 to S203:

[0078] Step S202: if the control strategies output by the proxy models are not the same, obtaining the priority of the control strategies output by the proxy models;

[0079] It should be noted that the priority of the control policy is used to indicate the degree of attention that the target user attaches to the demand represented by its proxy model. The priority of the control policy can be the priority set by the proxy model.

[0080] The priorities of the agent models can be set according to the importance of different demands of the user, for example, it can be assumed that there are two demands of energy saving and comfort, and the user values the demand of comfort more, and thus the priority of the comfort agent model can be set to be higher than the priority of the energy saving agent model.

[0081] After the priorities of the agent models are set, the priorities of the agent models can also be adjusted flexibly according to the feedback of the user on the executed control strategy, for example, it is assumed that the control strategy output by the electricity price agent model is “reminding the user to increase the temperature of the equipment to save electricity bill”, and after the control strategy output by the electricity price agent model is executed, the behavior of the user of “increasing the temperature of the equipment” can be monitored in real time, if it is monitored that the user has made the behavior of “increasing the temperature of the equipment”, it indicates that the user is sensitive to the electricity bill recently, and thus the priority of the electricity price agent model can be increased.

[0082] In step S203, the control strategy with the highest priority among the control strategies output by the agent models is taken as the target control strategy based on the priorities of the control strategies output by the agent models.

[0083] It can be understood that if the control strategies output by each agent model are not the same for different demands, and the importance of the user to different demands is not the same, the control strategy with the highest priority among the control strategies output by the agent models can be taken as the target control strategy to meet the demand valued most by the target user.

[0084] The above are only two feasible implementation manners of step S20 provided by the embodiment, and the embodiment does not specifically limit the specific implementation manner of step S20. For example, in other implementation manners, different manners of determining the target control strategy can also be executed according to whether the control strategies output by the agent models contain parameter objects.

[0085] In step S30, the target equipment is controlled to operate according to the target control strategy.

[0086] The embodiment provides a device control method, when the decision condition is triggered, the embodiment first acquires the control strategies output by the agent models, wherein the agent models include at least two of energy saving, comfort, health and electricity price agent models; then the target control strategy is determined according to the control strategies output by the agent models; and then the target equipment is controlled to operate according to the target control strategy. Since the control strategies output by each agent model are the control strategies for different demands respectively, the embodiment determines the control strategy (i.e. the target control strategy) for controlling the target equipment to operate by combining the control strategies under various demands, so that the target control strategy determined can adapt to multiple demands, and the accuracy of device control is improved.

[0087] For example, to help understand the implementation process of this embodiment, please refer to Figure 3 Specifically, under the same dimension, each agent model will output different control strategies based on the needs it represents. Then, by weighing the control strategies output by each agent model, the control strategy that is ultimately used to control the operation of the target device can be determined.

[0088] In a feasible implementation, step S20 may specifically include steps S21 to S23:

[0089] Step S21: If the control strategies output by the agent models do not all contain parameter objects, then the control strategies containing parameter objects are regarded as parametric control strategies, and the control strategies not containing parameter objects are regarded as non-parametric control strategies;

[0090] It should be noted that the parameter object refers to the control parameter of the target device, and the parameter object may be temperature, humidity, wind speed, etc. For each control strategy containing a parameter object, the parameter objects contained in each are consistent.

[0091] Step S22, determining a first preselected control strategy based on each of the parametric control strategies, and determining a second preselected control strategy based on each of the non-parametric control strategies;

[0092] It should be noted that the first preselected control strategy refers to a parameter-based control strategy for controlling the operation of the target device, and the second preselected control strategy refers to a non-parametric control strategy for controlling the operation of the target device.

[0093] As an example, according to each of the parameter-based control strategies, the step of determining the first preselected control strategy may specifically include steps S221 to S223:

[0094] Step S221, calculating a first target parameter value according to the parameter values ​​of the parameter objects included in each of the parameter-type control strategies;

[0095] When calculating the first target parameter value based on the parameter values ​​of the parameter objects included in each parameter-type control strategy, the average value of the parameter values ​​of the parameter objects included in each parameter-type control strategy can be calculated to obtain the first target parameter value; the mode of the parameter values ​​of the parameter objects included in each parameter-type control strategy can also be used as the first target parameter value; the average value of the parameter values ​​of the parameter objects included in each parameter-type control strategy that has the same control trend for the parameter objects can also be calculated to obtain the first target parameter value.

[0096] For example, it can be assumed that the regulation strategy output by the energy saving agent model is "suggesting the user to increase the set temperature of the device to 24℃", the regulation strategy output by the comfort agent model is "suggesting the user to decrease the set temperature of the device to 20℃", and the regulation strategy output by the health agent model is "suggesting the user to increase the set temperature of the device to 25℃", then, without considering the regulation trend of the set temperature of each agent model, the average of the temperature values of the set temperature contained in the regulation strategies output by the energy saving agent model, the comfort agent model and the health agent model can be taken as the first target parameter value, that is, (24℃+20℃+25℃) / 3=23℃ is taken as the first target parameter value; when the regulation trend of the set temperature of each agent model is considered, since the regulation trend of the set temperature of the regulation strategies output by the energy saving agent model and the health agent model is to increase, and the regulation trend of the set temperature of the regulation strategy output by the comfort agent model is to decrease, the average of the temperature values of the set temperature contained in the regulation strategies output by the energy saving agent model and the health agent model can be taken as the first target parameter value, that is, (24℃+25℃) / 2=24.5℃ is taken as the first target parameter value.

[0097] In step S222, the parameter values of the parameter objects contained in each of the parameter type regulation strategies are adjusted to the first target parameter value, to obtain adjusted parameter type regulation strategies;

[0098] In step S223, one of the adjusted parameter type regulation strategies is selected as the first preselected regulation strategy.

[0099] As an example, according to each of the non-parameter type regulation strategies, the step of determining the second preselected regulation strategy can include steps S224-S225:

[0100] In step S224, it is determined whether each of the non-parameter type regulation strategies is adopted.

[0101] Whether each of the non-parameter type regulation strategies is adopted can be determined by the priority of each of the non-parameter type regulation strategies. Specifically, the priority of each of the non-parameter type regulation strategies is obtained, and based on the priority of each of the non-parameter type regulation strategies, each of the non-parameter type regulation strategies with a priority greater than a preset priority is taken as an adopted non-parameter type regulation strategy. Each of the non-parameter type regulation strategies can also be displayed on a corresponding interface, and then the non-parameter type regulation strategy selected by the user on the interface is taken as an adopted non-parameter type regulation strategy.

[0102] Since the non-parameter type regulation strategy does not directly affect the control parameter of the target device, the non-parameter type regulation strategy that is not adopted can be selected not to be executed, or can be selected to be executed without loss of efficiency, and the present embodiment does not make specific limitation thereon.

[0103] Step S225, integrating the accepted non-parametric control strategies to obtain the second pre-selected control strategy.

[0104] Step S23, integrating the first pre-selected control strategy and the second pre-selected control strategy to obtain the target control strategy.

[0105] In another possible implementation, step S20 can specifically include steps S24-S26:

[0106] Step S24, if the control strategies output by the agent models all contain parameter objects, calculating a second target parameter value according to the parameter values of the parameter objects contained in the control strategies;

[0107] When the second target parameter value is calculated according to the parameter values of the parameter objects contained in the control strategies, the average of the parameter values of the parameter objects contained in the control strategies can be calculated to obtain the second target parameter value; or the mode of the parameter values of the parameter objects contained in the control strategies can be taken as the second target parameter value; or the average of the parameter values of the parameter objects contained in the control strategies that have the same control trend for the parameter objects can be calculated to obtain the second target parameter value.

[0108] Step S25, adjusting the parameter values of the parameter objects contained in the control strategies to the second target parameter value to obtain adjusted control strategies;

[0109] Step S26, selecting one of the adjusted control strategies as the target control strategy.

[0110] The above are only two possible implementations of step S20 provided by the embodiment, and the embodiment does not specifically limit the specific implementation of step S20. For example, in other implementations, the target control strategy can also be determined according to whether the user has an execution demand for the non-parametric control strategy, specifically, if the user does not have an execution demand for the non-parametric control strategy, the first pre-selected control strategy determined in step S22 can be directly taken as the target control strategy.

[0111] Based on the first embodiment, a second embodiment of the device control method of the application is provided, in which step S20 can include steps S021-S023:

[0112] Step S021, aggregating the control strategies output by the agent models to obtain a control strategy set;

[0113] Step S022, each of the agent models outputting a new control strategy according to the control strategy set;

[0114] In a possible implementation, step S022 can specifically include: obtaining the environmental parameters of the workspace where the target device is located, and the historical behavior data generated by the target user when using the target device; inputting the environmental parameters, the historical behavior data, and the set of regulation strategies into each agent model to obtain the new regulation strategy output by each agent model.

[0115] In another possible implementation, to ensure that the new regulation strategy output by each agent model can more comprehensively take into account various demands, the memory flow data carried by each agent model can also be used as the input of each agent model. Specifically, step S022 can include: obtaining the environmental parameters of the workspace where the target device is located, the historical behavior data generated by the target user when using the target device, and the memory flow data carried by each agent model; inputting the environmental parameters, the historical behavior data, the set of regulation strategies, and the memory flow data carried by each agent model into each agent model to obtain the new regulation strategy output by each agent model.

[0116] The above are only two possible implementations of step S022 provided by this embodiment, and this embodiment does not specifically limit the specific implementation of step S022.

[0117] Step S023: determining the target regulation strategy according to the new regulation strategies output by each agent model.

[0118] This embodiment is the same as the target regulation strategy mode provided by the first embodiment in determining the target regulation strategy according to the new regulation strategies output by each agent model, and thus will not be described herein.

[0119] It can be understood that the essence of this embodiment is the process of obtaining the regulation strategy of each agent model through two rounds of game, and in other embodiments, each agent model can also obtain the regulation strategy through three or more rounds of game.

[0120] This embodiment optimizes the output of each agent model by using the regulation strategies output by all agent models, so that the new regulation strategy output by each agent model can meet the demand of the agent model itself and also take into account the demand of other agent models. Therefore, the target regulation strategy determined according to the new regulation strategy output by each agent model can more comprehensively adapt to various demands, thereby further improving the accuracy of device regulation.

[0121] For example, to facilitate understanding of the implementation process of this embodiment, taking the case that the user frequently adjusts the temperature of the device to 20℃ as an example, each agent model can perform the following two rounds of dialogue game:

[0122] First round of dialogue:

[0123] (a) Energy-saving agent model: The role specification of prompting the preset energy-saving goal of the project, the embedded algorithm function library and the user behavior library, the energy-saving agent learns from the indoor temperature frequently over temperature through regular data reporting, and suggests reminding the user to adjust the temperature after reaching the temperature or calling the algorithm library to reduce the frequency to prevent over temperature. Thus, the energy-saving agent model outputs the control strategy of "suggesting reminding the user to adjust the temperature after reaching the temperature or calling the algorithm library to reduce the frequency to prevent over temperature".

[0124] (b) Comfort agent model: The role specification of prompting the preset comfort goal of the project, the comfort agent learns from the user frequently adjusting to 20°C through regular data reporting, and suggests reminding the user to adjust the temperature after reaching the temperature. Thus, the energy-saving agent model outputs the control strategy of "suggesting reminding the user to adjust the temperature after reaching the temperature".

[0125] (c) Health agent model: The role specification of prompting the preset health goal of the project, the health agent learns from the knowledge base about the national and enterprise standards of air health that 20°C is harmful to people in this environment, and suggests the user to adjust the temperature. Thus, the health agent model outputs the control strategy of "suggesting the user to adjust the temperature".

[0126] (d) Electricity price agent model: The role specification of prompting the preset electricity price goal of the project, the electricity price agent learns from the room photovoltaic equipment, the real-time external power grid electricity price, and the charging and discharging strategy, finds that the energy storage is full and the power consumption is continuous, and suggests reminding the user that the electricity price is high. Thus, the electricity price agent model outputs the control strategy of "suggesting reminding the user that the electricity price is high".

[0127] The control strategies output by each agent model in the first round of dialogue are summarized to obtain a control strategy set, and the control strategy set is input into each agent model to carry out the second round of dialogue of each agent model:

[0128] (a) Energy-saving agent model: Although the user frequently adjusts to 20°C, the actual indoor temperature is already at 15°C, and the air conditioner still continues to cool at high frequency although it has reached the temperature, in order to save energy, it is suggested to let the user adjust the temperature to 24°C. Thus, the energy-saving agent model outputs the control strategy of "suggesting the user to adjust the temperature to 24°C".

[0129] (b) Comfort agent model: Based on the user statistics setting temperature, 20°C is set the most number of times, so it can be judged that the user's setting preference is 20°C, and it is suggested to let the user adjust the temperature to 20°C. Thus, the comfort agent model outputs the control strategy of "suggesting the user to adjust the temperature to 20°C".

[0130] (c) Health agent model: According to the "National Indoor Air Quality Standard", 15°C is already too low, and it is suggested to remind the user to adjust the setting temperature to the comfortable 26°C. Thus, the health agent model outputs the control strategy of "suggesting the user to adjust the temperature to 26°C".

[0131] (d) Electricity price agent model: According to the real-time electricity price, the optimized electricity price space is inferred, and the user can be reminded to use the energy scheduling to save the electricity price. Thus, the electricity price agent model outputs the regulation strategy of "reminding the user to use the energy scheduling to save the electricity price".

[0132] It should be noted that the above examples are only used to assist in understanding the present application and do not constitute a limitation on the device regulation method of the present application. Based on the technical concept, more forms of simple transformation are within the protection scope of the present application.

[0133] Based on the above first embodiment and / or second embodiment, a third embodiment of the device regulation method of the present application is proposed. In the third embodiment, the device regulation method further comprises steps S40-S50:

[0134] Step S40: performing natural language processing on the model behaviors of each agent model to obtain the model behavior logs of each agent model.

[0135] Step S50: storing the model behavior logs of each agent model into a preset log storage area.

[0136] The model behaviors of each agent model are recorded by natural language in the present embodiment to enhance the explainability of each agent model. The model behavior logs of each agent model are obtained and stored into a preset log storage area. Thus, the user can quickly know which processing is performed by each agent model when outputting the regulation strategy by checking the model behavior logs of each agent model stored in the log storage area.

[0137] By way of example, to assist in understanding the implementation process of the device regulation method obtained by combining the above embodiments, please refer to Figure 4 , in particular:

[0138] After starting the multi-agent control service, the user behavior data is first counted, and then it is judged whether the counted user behavior data meets the decision trigger condition. If the counted user behavior data does not meet the decision trigger condition, the step of counting the user behavior data is returned to be executed. If the counted user behavior data meets the decision trigger condition, the constructed agent models are controlled to perform multi-round game to obtain the regulation strategies output by each agent model. Then, in the regulation strategies output by each agent model, the target regulation strategy is determined according to the regulation strategies containing the parameter object and the adopted regulation strategies not containing the parameter object. Finally, the target device is controlled to operate according to the determined target regulation strategy. Among the regulation strategies output by each agent model, the adopted regulation strategies not containing the parameter object can be selected to not execute the strategy or to execute the lossless benefit.

[0139] It should be noted that the present example is only used to assist in understanding the present application and does not constitute a limitation on the device regulation method of the present application. Based on this technical concept, more forms of simple transformation are within the protection scope of the present application.

[0140] The present application also provides an air conditioning device, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the device regulation method in the above embodiments.

[0141] Reference will be made to the following description of the embodiments of the present application. Figure 5 which shows a structural schematic diagram of an air conditioning device suitable for implementing the embodiments of the present application. The air conditioning device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 5 The air conditioning device shown is only an example and should not bring any limitation on the function and use range of the embodiments of the present application.

[0142] As Figure 5As shown, the air conditioning device can include a processing device 101 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 102 or a program loaded from a storage device 103 into a random access memory (RAM) 104. In the RAM 104, various programs and data required for operation of the air conditioning device are also stored. The processing device 101, the ROM 102, and the RAM 104 are connected to each other through a bus 105. An input / output (I / O) interface 106 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 106: an input device 107 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 108 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 103 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 109. The communication device 109 can allow the air conditioning device to communicate wirelessly or wired with other devices to exchange data. Although the air conditioning device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or less systems can be implemented or have instead.

[0143] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 103, or installed from the ROM 102. When the computer program is executed by the processing device 101, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0144] The air conditioning device provided by the embodiments of the present disclosure adopts the device control method in the above embodiments, which can improve the accuracy of device control. Compared with the prior art, the air conditioning device provided by the embodiments of the present disclosure has the same beneficial effects as the device control method provided by the above embodiments, and other technical features in the air conditioning device are the same as the features disclosed in the above method, which will not be repeated here.

[0145] It should be understood that parts of the embodiments of the present disclosure can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any appropriate manner in one or more embodiments or examples.

[0146] The above merely provides the specific implementation of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application should be subject to the protection scope of the claims.

[0147] The embodiments of the present application also provide a computer storage medium storing an operation program of an intelligent home system, which can run on a processor, and computer readable program instructions are used to execute the device regulation method in the above embodiments.

[0148] The computer storage medium provided by the embodiments of the present application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination of the above. More specific examples of the computer storage medium can include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments, the computer storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer storage medium can be transmitted by any suitable medium, including but not limited to: electric wire, optical cable, RF (Radio Frequency: radio frequency), etc., or any suitable combination of the above.

[0149] The above computer storage medium can be contained in the air conditioning device; or can exist separately without being assembled into the air conditioning device.

[0150] The above computer storage medium carries one or more programs, which, when executed by the air conditioning device, cause the air conditioning device to: obtain the regulation strategies output by each agent model when the decision condition is triggered; the agent model includes at least two of the energy saving, comfort, health and electricity price agent models; determine a target regulation strategy according to the regulation strategies output by each agent model; and control the target device to operate according to the target regulation strategy.

[0151] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0152] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0153] The modules involved in the embodiments of the present application can be implemented in the manner of software or in the manner of hardware. Among them, the name of the module does not constitute a limitation to the unit itself in some cases.

[0154] The readable storage medium provided by the embodiments of the present application is a computer storage medium, which stores computer readable program instructions for executing the device regulation method, and can improve the accuracy of device regulation. Compared with the prior art, the computer storage medium provided by the embodiments of the present application has the same beneficial effects as the device regulation method provided by the above embodiments, and will not be described here.

[0155] The embodiment of the present application further provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the device regulation method as described above.

[0156] The computer program product provided by the embodiment of the present application can improve the accuracy of device regulation. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present application are the same as those of the device regulation method provided by the above embodiment, and are not described herein.

[0157] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation using the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, is also included in the patent processing scope of the present application.

Claims

1. A device regulation method, characterized by, The device regulation method comprises: When a decision condition is triggered, obtaining regulation strategies output by each agent model; the agent model comprises at least two of an energy-saving agent model, a comfort agent model, a health agent model and a price agent model; According to the regulation strategies output by each agent model, determining a target regulation strategy; According to the target regulation strategy, controlling the target device to operate.

2. The method of claim 1, wherein, The step of determining the target regulation strategy according to the regulation strategies output by each agent model comprises: Summarizing the regulation strategies output by each agent model to obtain a regulation strategy set; Each agent model outputs a new regulation strategy according to the regulation strategy set; According to the new regulation strategies output by each agent model, determining the target regulation strategy.

3. The method of claim 1, wherein, The step of determining the target regulation strategy according to the regulation strategies output by each agent model comprises: If the regulation strategies output by each agent model do not all contain parameter objects, taking each regulation strategy containing a parameter object as a parameter-type regulation strategy and taking each regulation strategy not containing a parameter object as a non-parameter-type regulation strategy; According to each parameter-type regulation strategy, determining a first preselected regulation strategy, and according to each non-parameter-type regulation strategy, determining a second preselected regulation strategy; Integrating the first preselected regulation strategy and the second preselected regulation strategy to obtain the target regulation strategy.

4. The method of claim 3, wherein, The step of determining the first preselected regulation strategy according to each parameter-type regulation strategy comprises: According to parameter values of parameter objects contained in each parameter-type regulation strategy, calculating a first target parameter value; Adjusting the parameter values of the parameter objects contained in each parameter-type regulation strategy to the first target parameter value to obtain adjusted parameter-type regulation strategies; Selecting one parameter-type regulation strategy from the adjusted parameter-type regulation strategies as the first preselected regulation strategy.

5. The method of claim 3, wherein, The step of determining the second preselected regulation strategy according to each non-parameter-type regulation strategy comprises: Determining whether each non-parameter-type regulation strategy is adopted; Integrating the adopted non-parameter-type regulation strategies to obtain the second preselected regulation strategy.

6. The method of claim 1, wherein, The step of determining the target regulation strategy according to the regulation strategies output by each agent model further comprises: If the regulation strategies output by each agent model all contain parameter objects, according to parameter values of parameter objects contained in each regulation strategy, calculating a second target parameter value; Adjusting the parameter values of the parameter objects contained in each regulation strategy to the second target parameter value to obtain adjusted regulation strategies; Selecting one regulation strategy from the adjusted regulation strategies as the target regulation strategy.

7. The method of claim 1, wherein, The step of determining the target regulation strategy according to the regulation strategies output by each agent model further comprises: If the regulation strategies output by each agent model are all the same, selecting one regulation strategy from the regulation strategies output by each agent model as the target regulation strategy.

8. The method of claim 1, wherein, The step of determining the target regulation strategy according to the regulation strategies output by each agent model further comprises: If the regulation strategies output by each agent model are not all the same, obtaining priorities of the regulation strategies output by each agent model; Based on the priority of the regulation strategies output by each agent model, the regulation strategy with the highest priority among the regulation strategies output by each agent model is taken as the target regulation strategy.

9. The method of any one of claims 1 to 8, wherein, The step of obtaining the regulation strategies output by each agent model comprises: obtaining environmental parameters of a workspace where the target device is located and historical behavior data generated when a target user uses the target device; inputting the environmental parameters and the historical behavior data into each agent model to obtain the regulation strategies output by each agent model.

10. The method of any one of claims 1 to 8, wherein, The device regulation method further comprises: performing natural language processing on the model behaviors of each agent model to obtain model behavior logs of each agent model; storing the model behavior logs of each agent model into a preset log storage area.

11. An air conditioning apparatus characterized by comprising: The device regulation method comprises a memory, a processor, and a device regulation program stored in the memory and executable on the processor, and the device regulation program, when executed by the processor, implements the steps of the device regulation method according to any one of claims 1 to 10.

12. A computer storage medium, characterized in that The device regulation program executable on the processor is stored, and the control program is called by the processor to implement the steps of the device regulation method according to any one of claims 1 to 10.

Images