Equipment control method and system, storage medium and electronic device

Abstract

The invention discloses an equipment control method and system, a storage medium and an electronic device, and relates to the technical field of smart home, and the method comprises the steps: determining universal features corresponding to a plurality of quantitative indexes according to a target data set, the target data set at least comprises real-time operation data of each piece of equipment in a target area, environment data of the target area and operation data of a target object on each piece of equipment, and the quantitative indexes at least comprise an energy-saving index, a use satisfaction index and an equipment life index; determining an actual quantification result corresponding to each quantification index according to the general characteristics, and determining a first weight coefficient corresponding to each quantification index according to the actual quantification result; and according to the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index, determining a control parameter of each device in the target area, and according to the plurality of control parameters, sending a control instruction to the target area so as to control each device in the target area according to the control instruction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart home, in particular to a device control method and system, a storage medium and an electronic device. BACKGROUND

[0002] With the popularization of the concept of smart home, people's demand for intelligentization of home lighting systems is increasing. Traditional lighting systems often cannot automatically adjust brightness according to the environment and use, resulting in energy waste and poor use experience.

[0003] Simple sensor detection and rule-based control strategies are often rigid and cannot flexibly adapt to various complex and variable environments and use scenarios. This can result in inaccurate matching of lighting brightness to actual needs, either too bright causing energy waste or too dark affecting use experience.

[0004] The related art method of adjusting the brightness of the light in the target area by sensor detection and rule-based control strategy is rigid and cannot flexibly adapt to various complex and variable environments and use scenarios. No effective solution has been proposed. SUMMARY

[0005] The embodiments of the present application provide a device control method and system, a storage medium and an electronic device to at least solve the problem that the related art method of adjusting the brightness of the light in the target area by sensor detection and rule-based control strategy is rigid and cannot flexibly adapt to various complex and variable environments and use scenarios.

[0006] According to one embodiment of the embodiments of the present application, a device control method is provided, comprising: determining a general feature corresponding to a plurality of quantitative indicators according to a target data set, wherein the target data set at least includes one of the following: real-time running data of each device in a target area, environment data of the target area and operation data of a target object on the each device, and the quantitative indicators at least include one of the following: energy saving indicators of the each device, use satisfaction indicators of the target object on the each device and device life indicators of the each device; determining an actual quantitative result corresponding to each quantitative indicator according to the general feature, and determining a first weight coefficient corresponding to the each quantitative indicator according to the actual quantitative result; determining a control parameter of each device in the target area according to the actual quantitative result corresponding to the each quantitative indicator and the first weight coefficient corresponding to the each quantitative indicator, and sending a control instruction to the target area according to a plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0007] In an example embodiment, determining the universal features corresponding to the plurality of quantitative indicators according to the target data set comprises: performing data encoding on the target data in each data subset to generate a feature vector corresponding to the target data, wherein the target data set comprises a plurality of data subsets, and the plurality of data subsets comprise at least one of the following: a first data subset containing the real-time operation data, a second data subset containing the environment data, and a third data subset containing the operation data; performing feature learning on the feature vector corresponding to each data subset to generate each first data feature corresponding to each data subset; screening a second data feature from the plurality of first data features, wherein the second data feature has a correlation greater than a preset threshold with any quantitative indicator, and determining the second data feature as the universal feature.

[0008] In an example embodiment, determining the actual quantitative result corresponding to each quantitative indicator according to the universal feature comprises: in a case where the plurality of quantitative indicators comprises the energy-saving indicator, calculating a theoretical minimum energy consumption corresponding to each device through the universal feature; obtaining real-time energy consumption data of each device in a first time period based on a preset step length, and determining an actual total energy consumption of each device in the first time period according to the real-time energy consumption data; calculating an energy-saving ratio corresponding to each device according to a first formula, and determining the energy-saving ratio of each device as a first quantitative result corresponding to the energy-saving indicator of each device, wherein the first formula is: energy-saving ratio = (1-actual total energy consumption / theoretical minimum energy consumption) x 100%, and the actual quantitative result comprises the first quantitative result.

[0009] In an example embodiment, determining the actual quantification result corresponding to each quantification index according to the general feature comprises: in the case that the plurality of quantification indexes comprises the use satisfaction index, collecting scores of a plurality of first objects on the running effect of each device, and performing a weighted average on the plurality of scores to determine a device score corresponding to each device, wherein the first object is an object that has used each device; determining a use frequency of the target object on each device according to the general feature, and determining a use frequency adjustment coefficient of the target object on each device according to a ratio of the use frequency to a preset use frequency; determining an environmental comfort parameter corresponding to the target area according to the general feature, and determining an environmental comfort coefficient corresponding to the target area according to a ratio of the environmental comfort parameter to a preset environmental comfort parameter; respectively acquiring a second weight coefficient corresponding to the device score, a third weight coefficient corresponding to the use frequency adjustment coefficient, and a fourth weight coefficient corresponding to the environmental comfort coefficient; calculating a user satisfaction of the target object after using each device according to a second formula, and determining the user satisfaction of the target object after using each device as a second quantification result corresponding to the use satisfaction index of each device, wherein the second formula is: user satisfaction = device score × second weight coefficient + use frequency adjustment coefficient × third weight coefficient + environmental comfort coefficient × fourth weight coefficient, and the actual quantification result comprises the second quantification result.

[0010] In an example embodiment, determining the actual quantification result corresponding to each quantification index according to the general feature comprises: in the case that the plurality of quantification indexes comprises the device life index, determining a running time of a key component of each device, a failure frequency of the key component, and a wear degree of the key component; determining a device loss coefficient, a wear coefficient, and a failure coefficient of each device according to the general feature; calculating a remaining device life of each device according to a third formula, and determining the remaining device life of each device as a third quantification result corresponding to the device life index of each device, wherein the third formula is: remaining device life = running time × device loss coefficient + wear degree × wear coefficient + failure degree × failure coefficient, and the actual quantification result comprises the third quantification result.

[0011] In an example embodiment, determining the first weight coefficient corresponding to each quantization index according to the actual quantization result comprises: in a case where the actual quantization result comprises a first quantization result corresponding to the energy saving index, a second quantization result corresponding to the use satisfaction index, and a third quantization result corresponding to the device life index, obtaining a first expected result corresponding to the energy saving index, a second expected result corresponding to the use satisfaction index, and a third expected result corresponding to the device life index respectively, and determining a priority coefficient 1 corresponding to the energy saving index, a priority coefficient 2 corresponding to the use satisfaction index, and a priority coefficient 3 corresponding to the device life index respectively; and calculating the first weight coefficient corresponding to each quantization index according to a fourth formula, wherein the fourth formula is:

[0012] i is 1 or 2 or 3.

[0013] In an example embodiment, determining the control parameter of each device in the target area according to the actual quantization result corresponding to each quantization index and the first weight coefficient corresponding to each quantization index comprises: performing weighted summation on the quantization result corresponding to each quantization index and the first weight coefficient corresponding to each quantization index to determine a comprehensive optimization target of each device; and determining the control parameter of each device according to the comprehensive optimization target.

[0014] According to another embodiment of the embodiment of the present application, a device control system is further provided, comprising: a bottom structure, a middle structure, and a top structure; the bottom structure is configured to determine a general feature corresponding to a plurality of quantization indexes according to a target data set, wherein the target data set at least comprises one of the following: real-time running data of each device in a target area, environment data of the target area, and operation data of a target object to the each device, and the quantization index at least comprises one of the following: an energy saving index of the each device, a use satisfaction index of the target object to the each device, and a device life index of the each device; the middle structure is configured to determine an actual quantization result corresponding to each quantization index according to the general feature, and determine a first weight coefficient corresponding to each quantization index according to the actual quantization result; and the top structure is configured to determine a control parameter of each device in the target area according to the actual quantization result corresponding to each quantization index and the first weight coefficient corresponding to each quantization index, and send a control instruction to the target area according to a plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0015] According to a further aspect of the embodiments of the present application, a computer readable storage medium is also provided, which stores a computer program. The computer program is configured to execute the device control method when running.

[0016] According to a further aspect of the embodiments of the present application, an electronic device is also provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor. The processor executes the device control method through the computer program.

[0017] According to a further aspect of the embodiments of the present application, a computer program product is also provided, which comprises a computer program. The computer program is executed by a processor to execute the method.

[0018] In the embodiments of the present application, the general characteristics of the multiple quantitative indicators including at least one of the energy saving indicators of each device, the use satisfaction indicators of each device by the target object and the device life indicators of each device are determined according to the target data set of at least one of the real-time running data of each device including the target region, the environmental data of the target region and the operation data of each device by the target object; the actual quantitative results corresponding to each quantitative indicator are determined according to the general characteristics, and the first weight coefficients corresponding to each quantitative indicator are determined according to the actual quantitative results; the control parameters of each device in the target region are determined according to the actual quantitative results corresponding to each quantitative indicator and the first weight coefficients corresponding to each quantitative indicator, and the control instructions are sent to the target region according to the multiple control parameters, so as to control each device in the target region according to the control instructions. That is, the actual quantitative results corresponding to each quantitative indicator and the first weight coefficients corresponding to each quantitative indicator are determined through the general characteristics in the embodiments of the present application; and the control parameters of each device are determined according to the actual quantitative results and the first weight coefficients, so as to control each device in the target region according to the control parameters. Through the embodiments of the present application, the problem that the method of adjusting the light brightness of the target region through the sensor detection and the rule-based control strategy adjustment in the related art is relatively rigid and cannot flexibly adapt to various complex and changeable environments and use scenarios can be solved, and then the actual results of all quantitative indicators and the corresponding weight coefficients are comprehensively considered, the optimized control parameters of each device in the target region are accurately calculated, the intelligent control of each device is realized, the best balance among the energy saving, the user satisfaction and the device life is ensured, and the devices in the target region can flexibly adapt to various changeable environments and use scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the present application.

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0021] Figure 1 is a hardware environment schematic diagram of a device control method according to an embodiment of the present application.

[0022] Figure 2 is a flowchart of a device control method according to an embodiment of the present application.

[0023] Figure 3 is an architecture diagram of a device control system according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the personnel in the technical field better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should be within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to include those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0026] According to an aspect of an embodiment of the present application, a device control method is provided. The device control method is widely applied to smart home (Smart Home), smart home, smart home device ecology, intelligence house (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, Figure 1 is a hardware environment schematic diagram of a device control method according to an embodiment of the present application, in which the above-mentioned device control method can be applied to, for example, Figure 1In the hardware environment shown in FIG. 1 , a central control device 102 and a server 104 are formed. Figure 1 As shown, the server 104 is connected to the central control device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data calculation services for the server 104.

[0027] The aforementioned network may include, but is not limited to, at least one of the following: a wired network and a wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, and a local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity) and Bluetooth. The central control device 102 may be, but is not limited to, a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing machine, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, smart curtains, smart audio and video, a smart socket, a smart speaker, a smart fresh air device, smart kitchen and bathroom equipment, smart bathroom equipment, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0028] In this embodiment, a device control method is provided. Figure 2 : is a flow chart of a device control method according to an embodiment of the present application, the flow includes the following steps:

[0029] Step S202: determining common features corresponding to a plurality of quantitative indicators based on a target data set, wherein the target data set includes at least one of the following: real-time operating data of each device in a target area, environmental data of the target area, and operation data of each device by a target subject; and the quantitative indicators include at least one of the following: an energy saving index of each device, an index of user satisfaction of the target subject with respect to each device, and an index of device life of each device;

[0030] It is understandable that the above-mentioned device may be a lighting device or other household device.

[0031] Step S204: determining an actual quantization result corresponding to each quantization indicator according to the general feature, and determining a first weight coefficient corresponding to each quantization indicator according to the actual quantization result;

[0032] In step S206, the control parameters of each device in the target region are determined according to the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index, and a control instruction is sent to the target region according to the plurality of control parameters, so as to control each device in the target region according to the control instruction.

[0033] Through the above steps, the general characteristics of the plurality of quantification indexes including at least one of the energy saving index of each device, the use satisfaction index of the target object to each device and the device life index of each device are determined according to the target data set including at least one of the real-time running data of each device in the target region, the environmental data of the target region and the operation data of the target object to each device; the actual quantification result corresponding to each quantification index is determined according to the general characteristics, and the first weight coefficient corresponding to each quantification index is determined according to the actual quantification result; the control parameters of each device in the target region are determined according to the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index, and a control instruction is sent to the target region according to the plurality of control parameters, so as to control each device in the target region according to the control instruction. That is, the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index are determined by the general characteristics in the embodiment of the present application; and the control parameters of each device are determined according to the actual quantification result and the first weight coefficient, so as to control each device in the target region according to the control parameters. Through the embodiment of the present application, the problem that the method of adjusting the light brightness of the target region by the sensor detection and the rule-based control strategy in the related art is relatively rigid and cannot flexibly adapt to various complex and changeable environments and use scenarios can be solved, and then the actual results of all quantification indexes and the corresponding weight coefficients are comprehensively considered, the optimized control parameters of each device in the target region are accurately calculated, the intelligent control of each device is realized, the best balance between energy saving, user satisfaction and device life is achieved, and the devices in the target region can flexibly adapt to various changeable environments and use scenarios.

[0034] Optionally, the general characteristics corresponding to the plurality of quantification indexes are determined according to the target data set in the step S202, including: data encoding the target data in each data subset to generate a feature vector corresponding to the target data, wherein the target data set includes a plurality of data subsets, and the plurality of data subsets include at least one of a first data subset containing the real-time running data, a second data subset containing the environmental data and a third data subset containing the operation data; feature learning the feature vector corresponding to each data subset to generate each first data feature corresponding to each data subset; filtering a second data feature with a correlation greater than a preset threshold from the plurality of first data features, and determining the second data feature as the general characteristics.

[0035] It can be understood that the above target data set covers the real-time running state of the device, environmental change information, and user operation records of the device, and these data are used to determine the general features corresponding to a plurality of quantitative indicators (energy saving indicators, user satisfaction indicators, and device life indicators). Specifically:

[0036] Each data subset (for example, real-time running data, environmental data, operation data, etc.) in the target data set is encoded, and the original numerical or text data is converted into a feature vector form that can be understood by a machine learning model. For example, a word embedding technique is used to convert user operation instructions into a vector, or environmental temperature and humidity values are encoded into a feature vector on a unified scale through data standardization.

[0037] Through a machine learning model, feature learning is performed on the feature vectors of each data subset, which can be achieved through algorithms such as convolutional neural networks, recurrent neural networks, or autoencoders. Further, first data features related to each quantitative indicator are identified and extracted.

[0038] After obtaining each first data feature, a correlation analysis or a statistical test (for example, Pearson correlation coefficient, mutual information, t-test, etc.) is performed to filter out second data features that have a correlation greater than a preset threshold with any quantitative indicator, and the second data features are determined as general features.

[0039] The general features used to determine the actual quantitative results corresponding to different quantitative indicators can be different. For example, in the case of determining the actual quantitative results corresponding to the energy saving indicator, the above general features can be environmental data features, statistical features of device usage duration, etc.; in the case of determining the actual quantitative results corresponding to the user satisfaction indicator, the above general features can be user operation time series features and device usage frequency features, environmental parameter change features, etc.; in the case of determining the device life indicator, the above general features can be running time features, wear degree change features, and failure frequency features.

[0040] In some optional embodiments, the general features of all data subsets can also be integrated to form a comprehensive feature set that comprehensively reflects the running environment of the lighting device and user demand.

[0041] Optionally, after determining the general features, the actual quantitative results corresponding to each quantitative indicator need to be determined. Specifically:

[0042] (1) Determining the first quantitative result corresponding to the energy saving indicator:

[0043] In the case that the plurality of quantification indexes include the energy saving index, a theoretical minimum energy consumption of each device is calculated by the general feature; real-time energy consumption data of each device in a first time period is obtained based on a preset step, and actual total energy consumption of each device in the first time period is determined according to the real-time energy consumption data; an energy saving ratio of each device is calculated according to a first formula, and the energy saving ratio of each device is determined as a first quantification result corresponding to the energy saving index of each device, wherein the first formula is: energy saving ratio = (1-actual total energy consumption / theoretical minimum energy consumption) x 100%, and the actual quantification result includes the first quantification result.

[0044] It can be understood that, using general features (which can include: environmental data features, statistical features of device use duration), analyzing device running state, environmental conditions and user behavior and the like information, through a pre-trained model or algorithm, the lowest energy consumption that each device can theoretically reach under current conditions is calculated. And set a predefined step (time interval), for example, every hour or every half hour, regularly obtain real-time energy consumption data of each device in the preset step.

[0045] After obtaining the real-time energy consumption data in a plurality of steps, the actual total energy consumption of each device in a certain period of time (for example: one week, one month) is calculated.

[0046] Using the actual total energy consumption and the theoretical minimum energy consumption, according to the first formula: energy saving ratio = (1-actual total energy consumption / theoretical minimum energy consumption) x 100%, the energy saving ratio of each device can be calculated. The energy saving ratio reflects the gap between the actual energy consumption of the device and the theoretical optimal energy consumption.

[0047] According to the calculated energy saving ratio, the first quantification result of each device under the energy saving index is determined.

[0048] (2) determining the second quantification result corresponding to the use satisfaction index:

[0049] In the case that the plurality of quantitative indicators includes the use satisfaction indicator, a plurality of scores of the first objects on the operation effect of each device are collected, and the plurality of scores are weighted and averaged to determine a device score corresponding to each device, wherein the first objects are objects that have used each device; the use frequency of the target object on each device is determined according to the general characteristics, and a use frequency adjustment coefficient of the target object on each device is determined according to a ratio of the use frequency to a preset use frequency; an environmental comfort parameter corresponding to the target area is determined according to the general characteristics, and an environmental comfort coefficient corresponding to the target area is determined according to a ratio of the environmental comfort parameter to a preset environmental comfort parameter; a second weight coefficient corresponding to the device score, a third weight coefficient corresponding to the use frequency adjustment coefficient, and a fourth weight coefficient corresponding to the environmental comfort coefficient are obtained respectively; the user satisfaction of the target object after using each device is calculated according to a second formula, and the user satisfaction of the target object after using each device is determined as a second quantitative result corresponding to the use satisfaction indicator of each device, wherein the second formula is: user satisfaction = device score x second weight coefficient + use frequency adjustment coefficient x third weight coefficient + environmental comfort coefficient x fourth weight coefficient, and the actual quantitative result includes the second quantitative result.

[0050] It can be understood that the scores of all users (first objects) who have used a specific device on the operation effect of the device are collected. These scores may be based on factors such as brightness, color temperature, and switching response speed of the device, and are submitted through platforms such as mobile phone applications or smart voice assistants. These scores are weighted and averaged to eliminate the abnormal influence of individual user scores, forming a device score of each device. The device score is a direct feedback of the user on the use experience of the device, reflecting the general performance of the device in the eyes of the user.

[0051] By analyzing the operation data (such as the number of times of turning on the light and the use time) of the user through general characteristics (which can include user operation time sequence characteristics and device use frequency characteristics), the use frequency of each device can be determined, and further according to the ratio of the use frequency to the preset "ideal" use frequency, the use frequency adjustment coefficient is calculated. The ideal use frequency refers to the use frequency that can balance the device life and user demand under given conditions. The use frequency adjustment coefficient reflects the gap between the actual use frequency and the ideal use frequency.

[0052] And the environmental comfort parameter of the target area is determined according to the general characteristics (which can include environmental parameter change characteristics) and environmental data (such as temperature, humidity, and illumination level). By comparing the actual environmental comfort parameter with the preset comfort standard parameter, the environmental comfort coefficient is calculated.

[0053] For the device score, the usage frequency adjustment coefficient, and the environmental comfort coefficient, second, third, and fourth weight coefficients corresponding thereto are obtained, respectively. These weight coefficients reflect the relative importance of each index to the overall usage satisfaction under different usage scenarios and user preferences.

[0054] According to a second formula: second quantization result = device score x second weight coefficient + usage frequency adjustment coefficient x third weight coefficient + environmental comfort coefficient x fourth weight coefficient, a second quantization result of the usage satisfaction index of each device by the user is comprehensively calculated.

[0055] (3) Determine the third quantization result corresponding to the device life index:

[0056] In the case where the plurality of quantization indexes includes the device life index, the running time of the key component of each device, the failure frequency of the key component, and the wear degree of the key component are determined; the device wear coefficient, the wear coefficient, and the failure coefficient of each device are determined according to the general characteristics; the remaining device life of each device is calculated according to a third formula, and the remaining device life of each device is determined as the third quantization result corresponding to the device life index of each device, wherein the third formula is: remaining device life = running time x device wear coefficient + wear degree x wear coefficient + failure degree x failure coefficient, and the actual quantization result includes the third quantization result.

[0057] It can be understood that the running time, failure frequency, and wear degree of the key component in each device are collected and monitored. The running time is the cumulative running hours of the device component since it is put into use, the failure frequency records the total number of failures of the component in the use cycle, and the wear degree is the evaluation of the current mechanical and electronic performance degradation of the component through device state monitoring and data analysis.

[0058] According to the collected key component state data and general characteristics (which can include: running time characteristics, wear degree change characteristics, and failure frequency characteristics), the device wear coefficient, the wear coefficient, and the failure coefficient of each device can be predicted and determined. The device wear coefficient reflects the speed of performance degradation of the whole device due to the increase of use time; the wear coefficient measures the degree of performance degradation of the device component due to wear; and the failure coefficient quantifies the risk of affecting the life of the device due to failure.

[0059] The remaining device life of each device is calculated by a third formula: remaining device life = running time x device wear coefficient + wear degree x wear coefficient + failure degree x failure coefficient.

[0060] According to the calculated remaining device life, the third quantization result of each device under the device life index is determined.

[0061] Optionally, the step S204 of determining the first weight coefficient corresponding to each quantitative index according to the actual quantitative result comprises: in the case that the actual quantitative result comprises the first quantitative result corresponding to the energy saving index, the second quantitative result corresponding to the use satisfaction index and the third quantitative result corresponding to the equipment life index, respectively acquiring the first expected result corresponding to the energy saving index, the second expected result corresponding to the use satisfaction index and the third expected result corresponding to the equipment life index, and respectively determining the priority coefficient 1 corresponding to the energy saving index, the priority coefficient 2 corresponding to the use satisfaction index and the priority coefficient 3 corresponding to the equipment life index; and calculating the first weight coefficient corresponding to each quantitative index according to a fourth formula, wherein the fourth formula is: i is 1 or 2 or 3.

[0062] It can be understood that the expected results (the first expected result, the second expected result and the third expected result) of the three indexes of energy saving, use satisfaction and equipment life are determined. The expected results can be ideal target values based on user preferences, environmental conditions and equipment states, for example: the expected minimum energy consumption, the highest user satisfaction score and the longest equipment life. At the same time, the priority coefficients (the priority coefficients 1, 2 and 3) of each index are assigned.

[0063] The first weight coefficient of each index is calculated by the fourth formula. The fourth formula combines the gap between the actual quantitative result and the expected result, and the priority coefficient of the index, and dynamically adjusts the weight of each index in the control decision. The smaller the gap (i.e. the actual result is closer to the expected result), and the higher the priority, the greater the corresponding weight coefficient, and vice versa.

[0064] By comparing the actual quantitative result with the expected result of the three indexes of energy saving, use satisfaction and equipment life, and the priority coefficient of each index, the importance of each index in the control decision is intelligently adjusted. The dynamic calculation of the first weight coefficient ensures that the system can optimize its control strategy in real time according to the current running state, user demand and equipment health condition, to achieve the best balance between energy saving efficiency, user satisfaction and equipment life.

[0065] Optionally, the step S206 of determining the control parameter of each device in the target area according to the actual quantitative result corresponding to each quantitative index and the first weight coefficient corresponding to each quantitative index comprises: weighting and summing the quantitative result corresponding to each quantitative index and the first weight coefficient corresponding to each quantitative index to determine the comprehensive optimization target of each device; and determining the control parameter of each device according to the comprehensive optimization target.

[0066] It can be understood that after determining the actual quantization result and the first weight coefficient, the control parameter of each device can be determined, specifically:

[0067] The actual quantization result of each quantization indicator (such as the energy saving ratio, the quantization result of the use satisfaction indicator, and the quantization result of the remaining device life) is weighted and summed with the corresponding first weight coefficient. For example, if the energy saving indicator is more important at a certain time, its corresponding weight coefficient will be higher, thereby occupying a larger proportion in the comprehensive optimization goal.

[0068] Based on the comprehensive optimization goal, the best control parameter of each device is further determined. This may include adjusting the brightness, color temperature, switching time, etc. of the device to minimize energy consumption as much as possible while meeting user satisfaction and prolonging device life. The determination of the control parameter needs to consider the optimization requirements of all quantization indicators, and find the best parameter configuration that meets the comprehensive optimization goal through optimization algorithms such as genetic algorithm, simulated annealing algorithm or deep learning algorithm.

[0069] The calculated control parameters are applied to the device in real time to adjust its running state. At the same time, the running data of the device, including energy consumption, user satisfaction and device health status, etc. are continuously collected to evaluate the actual effect of the control parameters.

[0070] In order to better understand the process of the above device control method, the implementation method flow of the above device control will be described in combination with the optional embodiments below, but not used to limit the technical solutions of the embodiments of the present application.

[0071] With the rapid progress of technology and the continuous improvement of people's living quality, smart home systems have gradually become an important part of modern families. However, the existing smart home control technology still has many limitations. Traditional single task control strategy is difficult to meet the optimization needs of energy saving, user satisfaction, device life and other aspects at the same time, resulting in that the overall control effect cannot reach the ideal state. For example, too much emphasis on energy saving may sacrifice user comfort and satisfaction, and simply pursuing the extension of device life may increase energy consumption cost. In addition, existing technologies lack sufficient flexibility and adaptability in dealing with complex and variable home environment and user needs, and cannot realize efficient cooperation and self-learning among various electrical devices. With the popularization of the concept of smart home, people's demand for intelligentization of home lighting systems is increasing. Traditional lighting systems often cannot automatically adjust the brightness according to the environment and use, resulting in energy waste and poor use experience.

[0072] Deep learning techniques have shown great potential in prediction and control, but due to their high computational complexity, their application in embedded devices for smart homes faces challenges. At the same time, the performance and resources of hardware are limited, and efficient algorithms and techniques are needed to achieve fast response and energy-saving control.

[0073] Some existing intelligent lighting systems may use simple sensor detection and rule-based control strategies. For example, by detecting ambient light intensity, turning on the light when it is below a certain threshold, and turning off the light when it is above a certain threshold, or adjusting the light brightness according to a pre-set time period. In terms of hardware acceleration, it may only use a general-purpose microcontroller without a hardware acceleration solution specifically optimized for lighting control. For multi-room lighting scheduling, it may only be based on a simple priority queue without fully considering the comprehensive balance of energy saving and user demand.

[0074] That is, the technical solutions in the related art may have the following problems: simple sensor detection and rule-based control strategies are usually rigid and cannot flexibly adapt to various complex and variable environments and use cases. This can result in inaccurate matching of lighting brightness to actual needs, either too bright causing energy waste or too dark affecting user experience. This not only affects the user's real-time control experience, but also can lead to poor lighting effects due to delayed processing. Using a general-purpose microcontroller for hardware control, its processing speed and performance often cannot meet the real-time requirements of lighting control. When the lighting brightness needs to be adjusted quickly, it may not respond in time, affecting the effectiveness of the entire lighting system. A simple priority queue is used for multi-room lighting scheduling, which lacks comprehensive consideration of energy saving and user diversity needs. This can lead to unnecessary energy waste in some cases or failure to prioritize key user needs, thereby reducing overall user satisfaction.

[0075] To solve the above problems, the optional embodiments of the present application provide a smart home collaborative control technology scheme based on multi-agent self-learning. The optional embodiments of the present application focus on the field of smart home control technology, and in particular, a smart home collaborative control scheme based on a multi-task learning and optimization framework, aiming to transform various home appliances in the home into intelligent agents with collaborative self-learning capabilities, achieving efficient and intelligent management of the home environment.

[0076] The optional embodiments of the present application realize more accurate and intelligent lighting brightness prediction and control by using a deep learning model combined with accurate sensor data collection to adapt to various complex environments and use scenarios. A hardware acceleration scheme specially designed for lighting control significantly improves the processing speed and performance of the hardware, ensuring the real-time and effectiveness of the lighting control. The multi-agent (Multiagent) technology is adopted combined with a carefully designed comprehensive priority calculation formula to realize the reasonable and intelligent scheduling of multi-room lighting, while ensuring energy saving, the diversified needs of users are met to the greatest extent, and the performance and user satisfaction of the intelligent lighting system are improved.

[0077] The deep learning model can be a compressed and optimized model, that is, advanced compression techniques such as pruning, distillation, and quantization can be used to optimize the deep learning model, thereby significantly reducing the calculation amount and greatly improving the response speed of the system, providing timely and accurate lighting control experience for users.

[0078] That is, the core goal of the optional embodiments of the present application is to provide an innovative intelligent home multi-task learning and optimization control system and method, which can accurately optimize multiple closely related but different targets at the same time, so that the home appliances in the home have the ability of autonomous learning and collaborative optimization like intelligent agents. Specifically:

[0079] (1) Clearly and accurately define multiple key optimization targets (i.e., multiple quantitative indicators) such as energy saving, user satisfaction, and device life, and develop accurate and quantifiable indicators and scientific and reasonable evaluation methods for each target.

[0080] (1) Energy saving index: The energy consumption data of the home appliance is monitored in real time and accurately by high-precision sensors, collected in hours, and the total energy consumption in a week is calculated. Compare it with the theoretical minimum energy consumption under the same conditions calculated based on advanced physical models considering device operating efficiency and environmental factors to obtain the energy saving ratio. The calculation formula of the energy saving ratio is: Energy saving ratio = (1- actual total energy consumption / theoretical minimum energy consumption) x 100%. The calculation of the theoretical minimum energy consumption takes into account the ideal operating efficiency of the device, environmental temperature, use time, and other factors.

[0081] (2) User satisfaction index (i.e., use satisfaction index): Based on the multi-dimensional feedback of users on the running effect of the home appliance, a comprehensive evaluation is made. In terms of direct evaluation, the user is asked to rate the running effect of the device from 1 to 5 stars through a mobile application; in terms of indirect feedback, data such as the use frequency of the device and changes in operation habits are analyzed. At the same time, environmental sensors are used to obtain parameters such as indoor temperature, humidity, and air quality, which are compared with the user's expected range to calculate the user's satisfaction. The calculation formula for user satisfaction is: User satisfaction = device score x second weight coefficient + use frequency adjustment coefficient x third weight coefficient + environmental comfort coefficient x fourth weight coefficient, wherein the second weight coefficient, the third weight coefficient, and the fourth weight coefficient are the corresponding weight coefficients obtained from a large amount of user data and experimental analysis, respectively reflecting the importance of direct scoring, use frequency, and environmental comfort in satisfaction evaluation.

[0082] (3) Device life index: Based on the running time, wear and tear, and failure frequency of the key components of the device, combined with the initial design life of the device and the past maintenance records, the reliability engineering principles and life prediction model are used to accurately evaluate the remaining life of the device. The calculation formula for the remaining life of the device is: running time x device wear coefficient + wear degree x wear coefficient + failure degree x failure coefficient.

[0083] (II) Innovatively adopt an adaptive dynamic weight adjustment strategy, according to the real-time progress and dynamic changes in importance of the target, flexibly and accurately allocate weights.

[0084] When the device is newly put into use in the initial stage, the energy saving weight is relatively high, set to 0.5. As the device usage time gradually increases, the components inside the device begin to wear to some extent, at which time the weight of the device life is gradually increased. For example, after the device has been used for three months, the energy saving weight is gradually reduced to 0.3, while the weight of the device life is correspondingly increased to 0.4.

[0085] If it is monitored that the user frequently adjusts the settings of certain home appliances in the near future, for example, the number of adjustments to a certain device within a week exceeds 5 times, which indicates that the user is not satisfied with the current running effect of the device. At this time, the weight of user satisfaction is quickly increased from 0.2 to 0.5 to ensure that the system can respond in time and optimize the running strategy of the device to meet the user's needs.

[0086] Weight adjustment algorithm: The difference between the current value and the expected value of each target, the change trend, and the pre-set priority rules are considered comprehensively, and the weight of each target is dynamically calculated through complex mathematical models and algorithms. The specific weight calculation formula is:

[0087] Wherein, the priority coefficient i is pre-set according to the general needs of the family users and the characteristics of the equipment, and reflects the relative importance of different targets in different scenarios.

[0088] (III) The multi-branch structure of the deep neural network is introduced for the first time, and a corresponding branch is constructed for each optimization task, and multi-task learning is achieved by sharing the bottom features and specific task layers.

[0089] Network structure: the bottom layer constructs a shared feature extraction layer, and advanced convolutional neural network or recurrent neural network technology is used to extract highly representative and universal features from the input mass data (such as real-time running parameters of household appliances, environmental data, and long-term operation records of users, etc.). The middle layer is carefully designed with multiple branch layers, each branch corresponds to a specific optimization task, and independent fully connected layers or convolutional layers are used to learn unique feature representations closely related to the task (the middle layer can perform the above step S204). The top layer sets the output layer, which uses multiple independent neurons or neuron groups to accurately output the prediction results or control instructions of each task (the top layer can perform the above step S206).

[0090] Training method: an efficient joint training method is used to optimize the loss functions of multiple tasks at the same time. The design of the loss function is closely based on the quantitative indicators and evaluation methods of each task. For example, for the energy saving task, the loss function is defined as the mean square error of the actual energy consumption and the target energy consumption; for the user satisfaction task, the loss function is set as the cross-entropy loss between the user evaluation score and the expected score. In this way, the model can find the optimal balance and synergy between multiple tasks.

[0091] In addition, the optional embodiments of the present application can also use traditional machine learning algorithms instead of deep learning algorithms, such as decision trees, random forests, etc., although the prediction ability may be relatively weak, but the computational complexity is low. However, this method may not be accurate enough when dealing with complex environments and use scenarios.

[0092] Through the above carefully constructed multi-task learning and optimization framework, the deep comprehensive optimization control of the smart home system can be realized, the energy utilization efficiency can be significantly improved, the user satisfaction can be greatly improved, and the service life of the equipment can be effectively prolonged, so as to create a smart, comfortable, energy-saving and efficient home environment for users.

[0093] According to an optional embodiment of the present application, in an actual smart home scene, through high-precision sensors distributed in various corners of the home, real-time running data of home appliances, environmental data (such as temperature, humidity, illumination, etc.), and user detailed operation data (such as operation time, operation mode selection, etc.) are comprehensively collected. These rich data are transmitted in real time to the central control server through a high-speed and stable communication network (such as WiFi6 or 5G network).

[0094] After receiving these data, the trained multi-task learning model in the central control server first uses the underlying shared feature extraction layer to preprocess and extract general features from the data. Then, the multiple branch layers in the middle layer further process and learn the extracted features according to their respective tasks.

[0095] Based on the current input data and dynamically calculated weight distribution, the model uses complex mathematical operations and logical reasoning to accurately calculate the optimal control parameters for each home appliance. These control parameters are sent to the corresponding home appliances through a safe and reliable communication protocol (such as Zigbee or Bluetooth 5.2), realizing real-time and accurate control of home appliances.

[0096] At the same time, the entire smart home system continuously collects newly generated data and uses these new data to update and optimize the model online. Through advanced online learning algorithms (such as variants of stochastic gradient descent or adaptive matrix estimation optimization algorithms), the model can quickly adapt to subtle changes in the environment and user needs, and always maintain the best control performance and optimization effect.

[0097] According to another optional embodiment of the present application, suppose there is a smart home that includes lighting devices in multiple rooms. The requirement is to automatically adjust the light brightness according to the use of different rooms and environmental light to achieve energy-saving and comfortable lighting effect.

[0098] First, use sensors to collect environmental light intensity data (L) and personnel activity data (A, such as determining whether there is someone through infrared sensors) for each room.

[0099] Environmental light intensity calculation formula: L = k1 × natural light intensity + k2 × other light source interference intensity (k1, k2 are weight coefficients);

[0100] Second, based on the collected data, use a deep learning model to predict the ideal light brightness (B) required for each room.

[0101] Prediction model: B = f(L, A), where f is a deep learning function.

[0102] Third, quantization technology can be used to compress control signals, reducing data transmission volume and improving transmission efficiency.

[0103] Finally, in terms of hardware acceleration, a dedicated lighting control chip is used, which accelerates the algorithm as follows: processing speed = c*frequency (c is a constant).

[0104] In addition, in terms of hardware, a general high-performance processor can also be used instead of a specially designed lighting control acceleration chip.

[0105] 5. The lighting device is upgraded to an intelligent body, and intelligent scheduling is realized through Multiagent technology. For example, when multiple rooms have demands at the same time, resources are allocated according to priority, and the priority calculation formula is P = m*urgency + n*energy saving demand (m and n are weight coefficients).

[0106] Through the above technical integration scheme, intelligent, energy-saving and efficient control of the smart home lighting system can be realized.

[0107] Through the above optional embodiments, a dedicated hardware acceleration scheme is designed for smart home lighting control to improve processing speed and real-time response. At the same time, Multiagent technology is used to realize intelligent scheduling of multi-room lighting agents, and a comprehensive priority calculation formula is used to balance energy saving and user demand.

[0108] In addition, in terms of multi-room scheduling, the optional embodiments of the present application can also use a centralized control architecture instead of Multiagent technology, and a central controller is used to uniformly process the scheduling requests of all rooms.

[0109] That is, the optional embodiments of the present application can quickly process lighting control instructions and realize real-time and sensitive lighting adjustment to improve user experience because a dedicated hardware acceleration scheme is designed. Because Multiagent technology and a comprehensive priority calculation method are used for intelligent scheduling, resources can be reasonably allocated in a multi-room lighting scene to achieve the best balance between energy saving and meeting user demand, improve energy utilization efficiency and user satisfaction. In summary, the optional embodiments of the present application have the advantages of low cost, high accuracy, fast response, energy saving and good user experience.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software on a general hardware platform as necessary, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that makes a contribution, and the computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device) to execute the method of each embodiment of the present application.

[0111] Figure 3 is an architecture diagram of a device control system according to an embodiment of the present application; as shown in Figure 3 , comprising:

[0112] a bottom structure 32, configured to determine a general feature corresponding to a plurality of quantitative indicators according to a target data set, wherein the target data set at least includes one of the following: real-time running data of each device in a target area, environment data of the target area, and operation data of a target object on the each device, and the quantitative indicators at least include one of the following: an energy saving indicator of the each device, a use satisfaction indicator of the target object on the each device, and a device life indicator of the each device;

[0113] a middle structure 34, configured to determine an actual quantitative result corresponding to each quantitative indicator according to the general feature, and determine a first weight coefficient corresponding to the each quantitative indicator according to the actual quantitative result;

[0114] a top structure 36, configured to determine a control parameter of each device in the target area according to the actual quantitative result corresponding to the each quantitative indicator and the first weight coefficient corresponding to the each quantitative indicator, and send a control instruction to the target area according to a plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0115] Through the system, the general characteristics of the plurality of quantitative indexes including at least one of an energy saving index of each device, a use satisfaction index of the target object to each device and a device life index of each device are determined according to the target data set of at least one of the real-time running data of each device in the target area, the environmental data of the target area and the operation data of the target object to each device; the actual quantitative result corresponding to each quantitative index is determined according to the general characteristics, and the first weight coefficient corresponding to each quantitative index is determined according to the actual quantitative result; the control parameter of each device in the target area is determined according to the actual quantitative result corresponding to each quantitative index and the first weight coefficient corresponding to each quantitative index, and the control instruction is sent to the target area according to the plurality of control parameters, so as to control each device in the target area according to the control instruction. That is, the actual quantitative result corresponding to each quantitative index and the first weight coefficient corresponding to each quantitative index are determined by the general characteristics in the embodiment of the application; and the control parameter of each device is determined according to the actual quantitative result and the first weight coefficient, so as to control each device in the target area according to the control parameter. Through the embodiment of the application, the problem that the method of adjusting the light brightness of the target area by the sensor detection and the rule-based control strategy in the related art is relatively rigid and cannot flexibly adapt to various complex and changeable environments and use scenarios can be solved, and then the actual result and the corresponding weight coefficient of all quantitative indexes are comprehensively considered, the optimized control parameter of each device in the target area is accurately calculated, the intelligent control of each device is realized, the best balance among energy saving, user satisfaction and device life is ensured, and the devices in the target area can flexibly adapt to various changeable environments and use scenarios.

[0116] In one example embodiment, the bottom structure 32 is further configured to encode the target data in each data subset to generate a feature vector corresponding to the target data, wherein the target data set includes a plurality of data subsets, and the plurality of data subsets include at least one of a first data subset containing the real-time running data, a second data subset containing the environmental data, and a third data subset containing the operation data; the feature vector corresponding to each data subset is learned to generate each first data feature corresponding to each data subset; the second data feature having a correlation greater than a preset threshold with any quantitative index is filtered out from the plurality of first data features, and the second data feature is determined as the general characteristics.

[0117] In an example embodiment, the middle layer structure 34 is further configured to, when the plurality of quantification indexes comprises the energy saving index, calculate a theoretical minimum energy consumption of each device according to the general feature; obtain real-time energy consumption data of each device in a first time period based on a preset step length, and determine an actual total energy consumption of each device in the first time period according to the real-time energy consumption data; calculate an energy saving ratio of each device according to a first formula, and determine the energy saving ratio of each device as a first quantification result corresponding to the energy saving index of each device, wherein the first formula is: energy saving ratio = (1-actual total energy consumption / theoretical minimum energy consumption) x 100%, and the actual quantification result comprises the first quantification result.

[0118] In an example embodiment, the middle layer structure 34 is further configured to determine an actual quantification result corresponding to each quantification index according to the general feature, comprising: when the plurality of quantification indexes comprises the use satisfaction index, collecting scores of a plurality of first objects on the running effect of each device, and performing weighted average on the plurality of scores to determine a device score corresponding to each device, wherein the first object is an object that has used each device; determining a use frequency of the target object on each device according to the general feature, and determining a use frequency adjustment coefficient of the target object on each device according to a ratio of the use frequency to a preset use frequency; determining an environmental comfort parameter corresponding to the target area according to the general feature, and determining an environmental comfort coefficient corresponding to the target area according to a ratio of the environmental comfort parameter to a preset environmental comfort parameter; respectively obtaining a second weight coefficient corresponding to the device score, a third weight coefficient corresponding to the use frequency adjustment coefficient, and a fourth weight coefficient corresponding to the environmental comfort coefficient; calculating a user satisfaction of the target object after using each device according to a second formula, and determining the user satisfaction of the target object after using each device as a second quantification result corresponding to the use satisfaction index of each device, wherein the second formula is: user satisfaction = device score x second weight coefficient + use frequency adjustment coefficient x third weight coefficient + environmental comfort coefficient x fourth weight coefficient, and the actual quantification result comprises the second quantification result.

[0119] In an example embodiment, the middle layer structure 34 is further configured to, in a case where the plurality of quantification indexes comprises the equipment life index, determine a running time of a key component of each of the equipment, a failure frequency of the key component, and a wear degree of the key component; determine an equipment loss coefficient, a wear coefficient, and a failure coefficient of each of the equipment according to the general characteristics; calculate a remaining equipment life of each of the equipment according to a third formula, and determine the remaining equipment life of each of the equipment as a third quantification result corresponding to the equipment life index of each of the equipment, wherein the third formula is: remaining equipment life = running time × equipment loss coefficient + wear degree × wear coefficient + failure degree × failure coefficient, and the actual quantification result comprises the third quantification result.

[0120] In an example embodiment, the middle layer structure 34 is further configured to, in a case where the actual quantification result comprises a first quantification result corresponding to the energy saving index, a second quantification result corresponding to the use satisfaction index, and a third quantification result corresponding to the equipment life index, respectively acquire a first expected result corresponding to the energy saving index, a second expected result corresponding to the use satisfaction index, and a third expected result corresponding to the equipment life index, and respectively determine a priority coefficient 1 corresponding to the energy saving index, a priority coefficient 2 corresponding to the use satisfaction index, and a priority coefficient 3 corresponding to the equipment life index; calculate a first weight coefficient corresponding to each of the quantification indexes according to a fourth formula, wherein the fourth formula is: i is 1 or 2 or 3.

[0121] In an example embodiment, the top layer structure 36 is further configured to perform weighted summation on the quantification result corresponding to each of the quantification indexes and the first weight coefficient corresponding to each of the quantification indexes to determine a comprehensive optimization target of each of the equipment; and determine a control parameter of each of the equipment according to the comprehensive optimization target.

[0122] Embodiments of the present application also provide a storage medium comprising a stored program, wherein the program performs any of the above methods when executed.

[0123] Optionally, in the present embodiment, the storage medium can be configured to store program code for performing the following steps:

[0124] S1, determining general characteristics corresponding to a plurality of quantification indexes according to a target data set, wherein the target data set comprises at least one of the following: real-time running data of each of the equipment in a target area, environment data of the target area, and operation data of a target object on the equipment; and the quantification indexes comprise at least one of the following: an energy saving index of each of the equipment, a use satisfaction index of the target object on each of the equipment, and an equipment life index of each of the equipment.

[0125] S2, determine an actual quantification result corresponding to each quantification index according to the general feature, and determine a first weight coefficient corresponding to each quantification index according to the actual quantification result;

[0126] S3, determine a control parameter of each device in the target area according to the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index, and send a control instruction to the target area according to the plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0127] Embodiments of the present application also provide an electronic device, comprising a memory and a processor, the memory storing a computer program, and the processor being configured to execute the computer program to perform the steps in any of the above method embodiments.

[0128] Optionally, the electronic device can further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0129] Optionally, in the embodiment, the processor can be configured to perform the following steps through the computer program:

[0130] S1, determine general features corresponding to a plurality of quantification indexes according to a target data set, wherein the target data set at least comprises one of the following: real-time running data of each device in a target area, environment data of the target area, and operation data of a target object on the each device, and the quantification indexes at least comprise one of the following: an energy-saving index of the each device, a use satisfaction index of the target object on the each device, and a device life index of the each device;

[0131] S2, determine an actual quantification result corresponding to each quantification index according to the general feature, and determine a first weight coefficient corresponding to each quantification index according to the actual quantification result;

[0132] S3, determine a control parameter of each device in the target area according to the actual quantification result corresponding to each quantification index and the first weight coefficient corresponding to each quantification index, and send a control instruction to the target area according to the plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0133] Embodiments of the present application also provide a computer program product, comprising a computer program, which is executed by a processor to perform the steps in any of the above method embodiments.

[0134] Optionally, in the embodiment, the computer program product can be executed by the processor to perform the following steps:

[0135] S1, determining a general feature corresponding to a plurality of quantitative indexes according to a target data set, wherein the target data set at least includes one of the following: real-time running data of each device in a target area, environment data of the target area, and operation data of a target object on the each device, and the quantitative indexes at least include one of the following: an energy saving index of the each device, a use satisfaction index of the target object on the each device, and a device life index of the each device;

[0136] S2, determining an actual quantitative result corresponding to each quantitative index according to the general feature, and determining a first weight coefficient corresponding to the each quantitative index according to the actual quantitative result;

[0137] S3, determining a control parameter of each device in the target area according to the actual quantitative result corresponding to the each quantitative index and the first weight coefficient corresponding to the each quantitative index, and sending a control instruction to the target area according to a plurality of control parameters, so as to control each device in the target area according to the control instruction.

[0138] Optionally, in the embodiment, the storage medium can include but is not limited to: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various storage program codes.

[0139] Optionally, specific examples in the embodiment can refer to examples described in the above embodiments and optional implementation manners, and the embodiment will not be described here.

[0140] Obviously, those skilled in the art should understand that each module or each step of the present application described above can be realized by a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be realized by program codes executable by the computing device, so that they can be stored in the storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into each integrated circuit module, or multiple modules or steps can be manufactured into a single integrated circuit module. Thus, the present application is not limited to any specific hardware and software combination.

[0141] The above merely describes the preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, some improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A device control method, characterized in that: include: Determining common features corresponding to a plurality of quantitative indicators based on a target data set, wherein the target data set includes at least one of the following: real-time operating data of each device in a target area, environmental data of the target area, and operation data of each device by a target subject; and the quantitative indicators include at least one of the following: an energy-saving index of each device, an index of target subject's satisfaction with each device, and an index of device life of each device; Determining an actual quantization result corresponding to each quantization indicator according to the general feature, and determining a first weight coefficient corresponding to each quantization indicator according to the actual quantization result; Determine the control parameters of each device in the target area according to the actual quantization result corresponding to each quantization indicator and the first weight coefficient corresponding to each quantization indicator, and send a control instruction to the target area according to multiple control parameters to control each device in the target area according to the control instruction.

2. The device control method according to claim 1, wherein: Determine the common features corresponding to multiple quantitative indicators based on the target dataset, including: Performing data encoding on target data in each data subset to generate a feature vector corresponding to the target data, wherein the target data set includes: a plurality of data subsets, the plurality of data subsets including at least one of the following: a first data subset including the real-time operation data, a second data subset including the environmental data, and a third data subset including the operation data; Performing feature learning on the feature vector corresponding to each data subset to generate each first data feature corresponding to each data subset; A second data feature having a correlation with any quantitative indicator greater than a preset threshold is screened out from the plurality of first data features, and the second data feature is determined as the common feature.

3. The device control method according to claim 1, wherein: Determining the actual quantitative results corresponding to each quantitative indicator based on the general characteristics includes: In a case where the multiple quantitative indicators include the energy-saving indicator, calculating the theoretical minimum energy consumption corresponding to each device by using the common feature; Acquire real-time energy consumption data of each device in a first time period based on a preset step size, and determine the actual total energy consumption of each device in the first time period according to the real-time energy consumption data; The energy-saving ratio corresponding to each device is calculated according to the first formula, and the energy-saving ratio of each device is determined as the first quantitative result corresponding to the energy-saving index of each device, wherein the first formula is: energy-saving ratio = (1-actual total energy consumption / theoretical minimum energy consumption) × 100%, and the actual quantitative result includes: the first quantitative result.

4. The device control method according to claim 1, wherein: Determining the actual quantitative results corresponding to each quantitative indicator based on the general characteristics includes: In a case where the multiple quantitative indicators include the usage satisfaction indicator, collecting scores of multiple first subjects on the operating effect of each device, and performing weighted averaging on the multiple scores to determine a device score corresponding to each device, wherein the first subjects are subjects who have used each device; Determining a usage frequency of each device by the target object according to the common feature, and determining a usage frequency adjustment coefficient of each device by the target object according to a ratio of the usage frequency to a preset usage frequency; Determining an environmental comfort parameter corresponding to the target area according to the general feature, and determining an environmental comfort coefficient corresponding to the target area according to a ratio of the environmental comfort parameter to a preset environmental comfort parameter; respectively obtaining a second weight coefficient corresponding to the device score, a third weight coefficient corresponding to the usage frequency adjustment coefficient, and a fourth weight coefficient corresponding to the environmental comfort coefficient; The user satisfaction of the target object after using each device is calculated according to the second formula, and the user satisfaction of the target object after using each device is determined as the second quantitative result corresponding to the usage satisfaction index of each device, wherein the second formula is: user satisfaction = device score × second weight coefficient + usage frequency adjustment coefficient × third weight coefficient + environmental comfort coefficient × fourth weight coefficient, and the actual quantitative result includes: the second quantitative result.

5. The device control method according to claim 1, wherein: Determining the actual quantitative results corresponding to each quantitative indicator based on the general characteristics includes: In the case where the multiple quantitative indicators include the equipment life indicator, determining the operating time of the key components of each device, the number of failures of the key components, and the degree of wear of the key components; determining the equipment loss coefficient, wear coefficient, and failure coefficient of each device based on the common characteristics; The remaining equipment life of each device is calculated according to a third formula, and the remaining equipment life of each device is determined as a third quantified result corresponding to the equipment life index of each device, wherein the third formula is: remaining equipment life = operating time × equipment loss coefficient + wear degree × wear coefficient + fault degree × fault coefficient, and the actual quantified result includes: the third quantified result.

6. The device control method according to claim 1, wherein: Determining a first weight coefficient corresponding to each of the quantization indicators according to the actual quantization result includes: In a case where the actual quantified result includes a first quantified result corresponding to the energy-saving index, a second quantified result corresponding to the user satisfaction index, and a third quantified result corresponding to the equipment life index, respectively obtaining a first expected result corresponding to the energy-saving index, a second expected result corresponding to the user satisfaction index, and a third expected result corresponding to the equipment life index, and respectively determining a priority coefficient 1 corresponding to the energy-saving index, a priority coefficient 2 corresponding to the user satisfaction index, and a priority coefficient 3 corresponding to the equipment life index; The first weight coefficient corresponding to each quantitative indicator is calculated according to the fourth formula, wherein the fourth formula is: i is 1 or 2 or 3.

7. The device control method according to claim 1, wherein: Determining the control parameter of each device in the target area according to the actual quantization result corresponding to each quantization indicator and the first weight coefficient corresponding to each quantization indicator includes: Performing a weighted summation on the quantization result corresponding to each quantization indicator and the first weight coefficient corresponding to each quantization indicator to determine a comprehensive optimization target for each device; The control parameters of each device are determined according to the comprehensive optimization target.

8. A device control system, characterized in that: include: A bottom layer structure, a middle layer structure, and a top layer structure: the bottom layer structure is used to determine common features corresponding to multiple quantitative indicators based on a target data set, wherein the target data set includes at least one of the following: real-time operating data of each device in a target area, environmental data of the target area, and operation data of each device by a target subject; and the quantitative indicators include at least one of the following: an energy-saving index of each device, an index of target subject's satisfaction with the use of each device, and an index of the device life of each device; The middle-level structure is used to determine an actual quantization result corresponding to each quantization indicator according to the general feature, and determine a first weight coefficient corresponding to each quantization indicator according to the actual quantization result; The top-level structure is used to determine the control parameters of each device in the target area based on the actual quantization result corresponding to each quantization indicator and the first weight coefficient corresponding to each quantization indicator, and send a control instruction to the target area based on multiple control parameters to control each device in the target area according to the control instruction.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the method according to any one of claims 1 to 7 is executed when the program is executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images