CN113412609B

CN113412609B - Equipment control method, device, server and storage medium

Info

Publication number: CN113412609B
Application number: CN201980091634.3A
Authority: CN
Inventors: 范作
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2019-06-19
Filing date: 2019-06-19
Publication date: 2023-06-20
Anticipated expiration: 2039-06-19
Also published as: CN113412609A; WO2020252703A1

Abstract

The application discloses a device control method, a device, a server and a storage medium, wherein the device control method comprises the following steps: acquiring current condition data, wherein the current condition data is used for controlling first household equipment; when the current condition data meets a set control trigger condition, a trained training model is called, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the historical condition data at least comprises personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprises a control instruction for the first household equipment; inputting the current condition data into the training model to obtain a control instruction for the first household equipment; and controlling the first household equipment according to the control instruction. The method can improve the intelligent degree of the control of the household equipment.

Description

Equipment control method, device, server and storage medium

Technical Field

The application relates to the technical field of smart home, and in particular relates to a device control method, a device, a server and a storage medium.

Background

Along with the continuous development of science and technology and the continuous improvement of living standard of people, intelligent home gradually enters the field of vision of people. Currently, in the control of home devices (such as intelligent air conditioners, intelligent televisions and the like) in an intelligent home system, a user usually manually controls the home devices on site or remotely controls the home devices through a mobile terminal.

Disclosure of Invention

In view of the above problems, the present application provides a device control method, a device, an electronic device, and a storage medium, so as to improve the intelligent degree of home device control.

In a first aspect, an embodiment of the present application provides an apparatus control method, where the method includes: acquiring current condition data, wherein the current condition data is used for controlling first household equipment; when the current condition data meets a set triggering condition, a trained training model is called, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the condition data at least comprise personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprise control instructions for the first household equipment; inputting the current condition data into the training model to obtain a control instruction for the first household equipment; and controlling the first household equipment according to the control instruction.

In a second aspect, an embodiment of the present application provides an apparatus control device, including: the system comprises a data acquisition module, a model acquisition module, an instruction acquisition module and a control execution module, wherein the data acquisition module is used for acquiring current condition data, and the current condition data is used for controlling first household equipment; the model acquisition module is used for calling a trained training model when the current condition data meets a set trigger condition, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the condition data at least comprise personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprises a control instruction for the first household equipment; the instruction acquisition module is used for inputting the current condition data into the training model to obtain a control instruction for the first household equipment; the control execution module is used for controlling the first household equipment according to the control instruction.

In a third aspect, an embodiment of the present application provides a server, including: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more application programs configured to perform the device control method provided in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored therein program code that is callable by a processor to perform the device control method provided in the first aspect above.

According to the scheme, the current condition data for controlling the first household equipment is obtained, when the current condition data meets the set control trigger condition, the training model obtained through training according to the historical condition data and the equipment data when the first household equipment is operated is called, the historical condition data comprises personal data of a user, environment data and state data of the second household equipment, the equipment data comprises a control instruction for the first household equipment, then the current condition data is input into the training model to obtain the control instruction for the first household equipment, the first household equipment is controlled according to the control instruction, accordingly, the historical operation of the user on the household equipment is achieved, the operation instruction for the household equipment is predicted, automatic control on the household equipment is achieved, the intelligent degree of control of the household equipment is improved, the correlation with the user is high, the user requirement is met, and the user experience is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a schematic view of an application scenario provided in an embodiment of the present application.

Fig. 2 shows another application scenario set forth in the embodiment of the present application.

Fig. 3 shows a flow chart of a device control method according to one embodiment of the present application.

Fig. 4 shows a flow chart of a device control method according to another embodiment of the present application.

Fig. 5 shows a flow chart of a device control method according to a further embodiment of the present application.

Fig. 6 shows a block diagram of a device control apparatus according to an embodiment of the present application.

Fig. 7 is a block diagram of an electronic device for performing a device control method according to an embodiment of the present application.

Fig. 8 is a storage unit for storing or carrying program codes for implementing the device control method according to the embodiment of the present application.

Detailed Description

In order to enable those skilled in the art to better understand the present application, the following description will make clear and complete descriptions of the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application.

Along with the progress of the science and technology level, the intelligent home is deeply penetrated into each household, and is deeply favored by a plurality of families due to the convenience brought by the intelligent home. The intelligent home is a living environment which takes a home as a platform, integrates facilities related to home life by utilizing a comprehensive wiring technology, a network communication technology, a security technology, an automatic control technology and an audio-video technology, builds an efficient management system of home facilities and family schedule matters, improves the safety, convenience, comfort and artistry of the home, and realizes environmental protection and energy saving. The intelligent home is used for connecting various home equipment (such as an intelligent air conditioner, an intelligent lamp, an intelligent refrigerator, an intelligent washing machine and the like) in the home through the internet of things technology, and providing various controls such as home appliance control, illumination control, telephone remote control, indoor and outdoor remote control, anti-theft alarm, environment monitoring, heating and ventilation control, infrared forwarding, programmable timing control and the like.

In the smart home system, the conventional control manner for the home devices is mostly that the user manually performs control on site, or performs remote control on the home devices through a visual interface on a mobile terminal (for example, a mobile phone, a tablet, etc.), or performs delay control, or performs control by adopting a set scene, and of course, there is also a manner of performing speech control on the home devices.

Through long-term researches of the inventor, although the control modes of the household equipment are numerous, the user is still required to participate in the control process of the household equipment, the intelligent degree of the household equipment control is low, and the user experience is low. In order to solve the problems, the inventor proposes the device control method, the device, the electronic device and the storage medium provided by the embodiment of the application, by acquiring the current condition data, the current condition data is used for controlling the first household device, when the current condition data meets the set control trigger condition, the training model obtained by training the historical condition data and the device data according to the condition that the first household device is operated is called, then the current condition data is input into the training model to obtain a control instruction for the first household device, and the first household device is controlled according to the control instruction, so that the historical operation of the household device according to a user is realized, the operation instruction for the household device is predicted, the automatic control for the household device is realized, the intelligent degree of the control of the household device is improved, the correlation with the user is high, the user requirement is met, and the user experience is improved.

An application scenario of the embodiments of the present application will be described with reference to the accompanying drawings.

Referring to fig. 1, a schematic diagram of an application scenario of an apparatus control method provided in an embodiment of the present application is shown, where the application scenario includes an intelligent home system, and the intelligent home system may include a server 100, a home device 200, a gateway device 300, and a mobile terminal 400. The gateway device 300 and the mobile terminal 400 may be in communication connection with the server 100, and the home device 200 and the gateway device 300 establish a wireless connection, so that the mobile terminal 400 may perform data interaction with the home device 100 through the server 100 and the gateway device 300. Of course, the mobile terminal 400 may also implement data interaction between the mobile terminal 400 and the home device 200 by establishing a wireless connection with the gateway device 300.

Referring to fig. 2, another schematic diagram of an application scenario of the device control method provided in the embodiment of the present application is shown, where an intelligent home system of the application scenario includes a first cloud server 101, a second cloud server 102, a home device 200, a gateway device 300, and a mobile terminal 400. The mobile terminal 400 may be in communication connection with the first cloud server 101, so as to implement data interaction with the first cloud server 101. The home device 200 is in communication connection with the second cloud server 102 through the gateway device 300, so as to realize data interaction with the second cloud server 102. In addition, data interaction can be performed between the first cloud server 101 and the second cloud server 102, so that the mobile terminal 400 can implement data interaction with the home device 200 through the first cloud server 101, the second cloud server 102 and the gateway device 300.

The following describes the device control method according to the embodiment of the present application in detail.

Referring to fig. 3, an embodiment of the present application provides an apparatus control method, which may be applied to a server, and the apparatus control method may include:

step S110: and acquiring current condition data, wherein the current condition data is used for controlling the household equipment.

In this embodiment of the present application, the server may acquire current condition data, where the current condition data is used to control the first home device. The current condition data is data which is used for being input into a setting model by a server to obtain a control instruction of a predicted user to the first household equipment.

In some embodiments, the current condition data may include personal data of the user, environmental data, status data of the second home device, and the like. The personal data may be information data of the user, and may include current state, gender, taste, sex, academic, physical data, and the like of the user. The current state of the user can be whether the user is working, the mental state of the user, the mood state of the user and the like. Of course, the personal data described above is merely exemplary. The environmental data may be data of the user and/or the environment in which the first home device is located, for example, the environmental data may include location data, time data, weather data, personnel conditions in the home, and the like. The second home device may be another home device, and the state data of the second home device may be data indicating a current state of the second home device, for example, whether the second home device is in an operating state, an operating parameter, or the like. Of course, the specific current condition data may not be limited in the embodiment of the present application, and may also include, for example, an instruction sent by the user through the mobile terminal.

In some embodiments, the server may obtain the current condition data from the mobile terminal, the environment collection device, the first home device, the second home device, and other servers of the user. The server may communicate with a mobile terminal of a user, the mobile terminal may send collected condition data to the server, the condition data collected by the mobile terminal may include a located user position, a user state analyzed according to a collected user image, and the like, and of course, the condition data collected by a specific mobile terminal may not be limited. The environment collection device may be an environment collection device (e.g., a camera, various sensors, etc. in a home) in an environment where the first home device is located, and the server may obtain environment data collected by the environment collection device from the environment collection device. The server may obtain detected status data from the first home device and the second home device. The server may obtain corresponding data in the current condition data from other servers (e.g., third party servers), for example, may obtain weather data from a server for weather prediction, may also obtain the current taste of the user, the current favorite eating time, etc. from a server for food and beverage service. Of course, the manner in which the server specifically obtains the current condition data may not be limited.

In some embodiments, the server may acquire the current condition data for controlling the first home device in real time, or may acquire the current condition data every set period of time, and the period of time for acquiring the current condition data may not be limited.

Step S120: when the current condition data meets a set triggering condition, a trained training model is called, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the condition data at least comprise personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprise control instructions for the first household equipment.

In this embodiment of the present application, after obtaining current condition data for controlling the first home device, the server may determine whether the current condition data meets a set trigger condition, so as to determine whether to predict a control instruction for controlling the first home device end by the user according to the current condition data.

In some embodiments, the server may determine whether the data of the setting type in the current condition data is consistent with the setting data corresponding to the setting type. In one embodiment, the server may obtain the data of the setting type in the current condition data and the setting data corresponding to the setting type, and then determine whether the data of the setting type is consistent with the setting data, and specifically determine whether fields, byte lengths, byte sizes, and the like of the two data are consistent. For example, it may be determined whether the time data in the current condition data is set time data to determine whether the current condition data satisfies the set trigger condition. If the data of the setting type in the current condition data is judged to be consistent with the setting data corresponding to the setting type, the fact that the current condition data meets the set trigger condition can be determined, and if the data of the setting type in the current condition data is judged to be inconsistent with the setting data corresponding to the setting type, the fact that the current condition data meets the set trigger condition can be determined. Of course, specific setting data may be, but not limited to, one value or a numerical range formed of a plurality of values.

In this embodiment of the present application, the trigger condition may be used as a trigger condition for predicting that the user will operate the intelligent device, and if the current condition data meets the set trigger condition, it may indicate that the user will operate the intelligent device, and if the current condition data does not meet the set trigger condition, it may indicate that the user will not operate the intelligent device.

Therefore, when the current condition data meets the set trigger condition, a trained training model can be obtained so as to predict a control instruction of the user for controlling the first household equipment according to the current condition data. The trained training model can be stored in a server, and the server can read and call the training model when the control instruction is required to be calculated according to the current condition data.

In some embodiments, the trained training model may be trained from historical condition data and device data of the first household device when operated. The historical condition data may include at least personal data of the user, environmental data, and status data of the second home device, and the device data may include at least control instructions for the first home device. That is, the historical condition data is consistent with the data content contained in the current condition data, so that the training model can calculate a control instruction conforming to the control habit of the first household device except the user according to the current condition data.

Wherein the history condition data corresponds to the device data. Each of the historical condition data may form a pair of data with each of the device data as input data to the initial model for training, and the device data as output data to the initial model for training. Thus, a data set for model training can be constructed based on the historical condition data and the device data at the time of the control operation of the first home device by the user in the past.

In some embodiments, the personal data in the historical condition data may include the current state, taste, sex, history, physical data, etc. of the user. The environmental data may be data of the mobile terminal of the user and/or the environment where the first home device is located, where the environmental data may include location data, time data, weather data, and the like, the location data may be specific to a location where the user is usually located, for example, a location of the user, a location of work, and the like, and the time data may be specific to a date, a time point, a holiday, and the like, so that a work habit of the user may be reflected. The status data of the other first home device may be data representing the status of the current second home device, for example, whether the second home device is in an operating state, an operating parameter, or the like. Of course, specific current condition data and device data may not be limiting in the embodiments of the present application. The device data may include, in addition to a control instruction for the first home device, device information, a device status, and the like of the device. The history condition data can be obtained from the mobile terminal, the first household equipment, the second household equipment, the environment acquisition device and the server of the third party, so that the history condition data which are related to the user, the environment and the second household equipment in the control of the first household equipment can be obtained, and the training model trained according to the history condition data and the equipment data can be more in line with the operation habit of the user, so that the training model is more accurate.

Further, the acquired historical condition data may be quantized into an input vector corresponding to the initial model, and the device data may be quantized into an output vector corresponding to the initial model. And then quantizing the data set into a vector set corresponding to the initial model, and inputting the vector set into the initial model for training, so that a trained training model, namely a model for predicting a control instruction for controlling the first household equipment, is obtained. The initial model may be a neural network model, such as BP (back propagation) neural network model, for example. Of course, the specific initial model is not limited, and for example, the initial model may be a decision tree model, or may be another neural network model.

Step S130: and inputting the current condition data into the training model to obtain a control instruction for the first household equipment.

After the server acquires the trained training model, the current condition data can be used as input data to be input into the training model, and the training model can calculate a control instruction corresponding to the current condition data, namely a control instruction for controlling the first household equipment according to the current condition data.

In some embodiments, when the current condition data is input to the training model, the current condition data may be quantized into a vector corresponding to the training model, that is, a vector that may be used for training model calculation, and then the vector corresponding to the current condition data is input to the training model, so as to calculate a control instruction for controlling the first home device.

Step S140: and controlling the first household equipment according to the control instruction.

In the embodiment of the present application, after the server obtains the control instruction for controlling the first home device, the server may perform control matching with the control instruction on the first home device according to the control instruction, so as to implement automatic control on the first home device.

In some embodiments, the server may issue the control instruction to the first home device through the network, for example, send the control instruction to a router in the network where the first home device is located through the network, the control instruction is forwarded to the gateway device by the router, the gateway device forwards the control instruction to the first home device, and finally the first home device performs a processing operation matched with the control instruction according to the control instruction, so as to control the first home device.

According to the equipment control method, the current condition data are obtained and used for controlling the first household equipment, when the current condition data meet the set trigger conditions, the training model trained according to the historical condition data and the equipment data is utilized to calculate the control instruction matched with the current condition data, and then the first household equipment is controlled according to the control instruction, so that the historical data of the operation of the user on the household equipment is calculated according to the historical data of the operation of the user on the household equipment, the operation instruction of the subsequent user on the household equipment is calculated, the automatic control of the household equipment is realized, the intelligent degree of the control of the household equipment is improved, the historical condition data are related to the user, the environment and other household equipment, and therefore the control instruction calculated by the training model accords with the operation habit of the user on the household equipment, meets the user requirement, and the user experience is improved.

Referring to fig. 4, another embodiment of the present application provides a device control method, which may be applied to a server, and the device control method may include:

step S210: and acquiring historical condition data and equipment data when the first household equipment is operated, wherein the historical condition data corresponds to the equipment data.

In this embodiment of the present application, the server may acquire historical condition data and device data when the first home device is operated, so as to train the initial model according to the historical condition data and the device data. The historical condition data corresponds to the equipment data, and each historical condition data corresponds to each equipment data in the plurality of historical condition data and the plurality of equipment data corresponding to the first household equipment.

In some embodiments, the historical condition data includes at least personal data of the user, environmental data, and status data of the second home device. The personal data is data about the user's individual, and may include physical state, mood state, height, weight, taste, occupation, etc. of the user, and specific personal data may not be limited, and the personal data may be used to reflect habit, preference, etc. of the user. The environmental data may include time data, weather data, location data, air data, traffic data, etc., the environmental data relating to the user's environment and/or the first home device's environment. The second home device may be other home devices except the first home device, and the state data of the second home device may include an on state, an off state, an operating parameter, and the like of the second home device. The device data may at least include a control instruction corresponding to the current condition data, that is, a control instruction when the first home device is operated, and the state data may further include device information, parameters, types, and the like, so that training may be performed for different devices. Of course, the specific historical condition data and device data may not be limiting. In addition, the control instruction may be specific to control the working parameter of the first home device, for example, the control instruction corresponding to the lamp may be specific to a light emitting color, a light emitting brightness, etc., and the television may be specific to a playing channel, etc., so that the trained training model may predict the control instruction for specifically controlling the first home device.

In some embodiments, the current condition data and the device data when the first home device is controlled may be obtained from a mobile terminal of the user, an environment acquisition device, the first home device, the second home device, and a server of the third party platform. Of course, it may be obtained from a local database. Therefore, the data related to the user and the equipment can be obtained each time the user controls the first household equipment, and the range and the type of the data are more covered, so that an accurate training model can be trained later.

In this embodiment of the present application, after current condition data and device data are obtained, before training an initial model according to the current condition data and the device data, the server may further screen historical condition data and device data, and classify the screened historical condition data and device data.

In some embodiments, the server may screen effective data from historical condition data and device data according to a set screening rule, so as to remove invalid data, ensure accuracy of the data, and further improve accuracy of a training model. For example, the server may screen the number of times of controlling the first home device, and if the number of times of controlling the first home device is less than the set number of times in the same period of time, may determine that the current condition data and the device data are invalid when the first home device is controlled in the period of time. Of course, the specific screening rules are not limiting in the embodiments of the present application.

In some embodiments, when classifying the current condition data and the device data, the server may classify the device and the individual data, classify the personal data of the user and the environmental data of the environment where the user is located into data related to the user, and classify the environmental data of the environment where the first home device is located, the status data of the second home device and the device data of the first home device as data related to the device. For data related to devices, device types may also be classified, for example, into household appliances, gateways, sensors, smart cars, etc. Of course, the above classification is merely an example, and for example, the control instruction in the device data may be classified. The historical condition data and the equipment data are classified, the current condition data and the equipment data are marked according to the classified categories, and the marked and classified data are input into the initial model for training, so that the training model is more accurate.

Step S220: and inputting the historical condition data and the equipment data into an initial model, and training the initial model to obtain a trained training model.

In some embodiments, the server may build an initial model, although the initial model may be stored locally in advance. When the initial model is trained, historical condition data and equipment data can be input into the initial model, and the initial model is trained. The current condition data and the device data are in one-to-one correspondence, the current condition data can be quantized into input vectors, the device data can be quantized into output vectors, and then a plurality of input vectors and output vectors which are in one-to-one correspondence are input into an initial model for training, so that a trained training model, namely a model for predicting control instructions for controlling the first household device, is obtained. In addition, after the trained training model is obtained, the accuracy of the trained training model can be verified, whether the output information of the trained target detection model based on the input data meets the preset requirement or not can be judged, if the output result of the trained training model based on the input data does not meet the set requirement, the data set formed by the current condition data and the equipment data can be re-acquired to train the initial model, or the data set can be re-acquired to correct the trained training model, and the limitation is not limited.

In some embodiments, the initial model may be a neural network model or a decision tree model. The specific manner of training the initial model is not limited, for example, when the initial model is a neural network model, the neural network model may be trained based on ssd algorithm, the master-rcnn algorithm, yolo algorithm, and the like, which will not be described herein.

Step S230: and acquiring current condition data for controlling the first household equipment.

In the embodiment of the present application, step S230 may refer to the content of the above embodiment, which is not described herein.

Step S240: when the current condition data meets a set trigger condition, a trained training model is obtained, the training model is obtained according to historical condition data and equipment data when the first household equipment is operated, the historical condition data at least comprise personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprise control instructions for the first household equipment.

In the embodiment of the present application, the set triggering conditions may include: the time data is at least one of set time data, the position data is set position data, the weather data is set weather data, the second home device is set state, and the condition data includes a trigger instruction input by a user.

It can be understood that the triggering condition is used as a triggering condition for determining that the user can operate the intelligent device, if the current condition data meets the triggering condition, the current condition data needs to be input into the training model, and a control instruction corresponding to the current condition data is calculated so as to control the first home device. For example, in one scenario, a user typically leaves work at six points, and then the six points may trigger calculation of a control instruction for the intelligent automobile, so that the user may experience an in-vehicle environment in which parameters have been set after getting on the automobile, and the set parameters correspond to current condition data. For another example, in one scenario, if the current weather data is weather data corresponding to strong-illumination weather, the calculation of the control command for the intelligent curtain may be triggered so that the merging degree of the curtains accords with the condition corresponding to the current condition data and the control habit of the user. For another example, in one scenario, when an intelligent bathroom heater in a bathroom is turned on, a control instruction for the water heater may be triggered to be calculated, so that the working parameters of the water heater correspond to the current condition data and conform to the control habit of a user for the water heater. Of course, the above scenario is merely exemplary.

The condition data includes a trigger instruction input by a user, and the trigger instruction may be input by the user through the mobile terminal, so that the server calculates a control instruction corresponding to the first home device corresponding to the trigger instruction, and subsequently controls the first home device according to the control instruction. Under the condition that a user manually inputs a trigger instruction, after calculating the control instruction, the server can control the first household equipment according to the control instruction at a time point corresponding to the trigger instruction. For example, the user may send a trigger instruction of "six points on tomorrow eat" to the server through the mobile terminal, and the server may calculate a control instruction for the cooking robot according to the current condition data, and control the cooking robot according to the control instruction in five points on tomorrow.

In some embodiments, the above triggering conditions may also be used in combination, and may be specifically set according to different devices and scenarios. For example, when the simultaneous time data is set time data, the position data is set position data, the weather data is set weather data, and the second home device is set state, it is determined that the current condition data satisfies the trigger condition.

When the current condition data is determined to meet the set trigger condition, the trained training model can be obtained, so that a control instruction for the first household equipment is calculated according to the current condition data.

Step S250: and inputting the current condition data into the training model to obtain a control instruction for the first household equipment.

In the embodiment of the present application, step S250 may refer to the content of the above embodiment, which is not described herein.

Step S260: and controlling the first household equipment according to the control instruction.

In this embodiment of the present application, after obtaining the control instruction by using the training model and the current condition data, the server may control the first home device according to the control instruction.

In some embodiments, controlling the first home device according to the control instruction may include:

the control instruction is sent to gateway equipment in a network where the first household equipment is located, the gateway equipment is used for sending the control instruction to the first household equipment, and the control instruction is used for indicating the first household equipment to perform operation corresponding to the control instruction.

It can be understood that when the first home device communicates with the server through the gateway device, the server may send the control instruction to the gateway device, so that the gateway device may issue the control instruction to the first home device, and the first home device may perform an operation corresponding to the control instruction according to the control instruction, thereby implementing control over the first home device.

In some embodiments, when the server is not the vendor server corresponding to the first home device, the server may communicate with the vendor server corresponding to the first home device. The control instruction is sent to a manufacturer server corresponding to the first household equipment, the manufacturer server sends the control instruction to the gateway equipment, and the gateway equipment issues the control instruction to the first household equipment, so that the control of the first household equipment is realized.

Of course, the above manner in which the server transmits the control instruction to the first home device may not be limited, for example, in some scenarios, if the server can directly communicate with the first home device, the server may also directly send the control instruction to the first home device.

In this embodiment of the present application, the server may further continuously correct the training model, so that a control instruction calculated by the training model is more accurate.

In some embodiments, the correction of the training model by the server may include: after the first household equipment is controlled according to the control instruction, judging whether the control instruction is wrong or not; if there is an error, the training model is corrected.

The server can detect whether the control operation of the user on the first household equipment is acquired within a set time length after the first household equipment is controlled; if the control operation of the user on the first household equipment is obtained, determining that the control instruction is wrong; and if the control operation of the user on the first household equipment is not obtained, determining that the control instruction is correct.

It can be understood that if the control instruction is wrong, the user can know that the control of the first home device is wrong, and the user can control the first home device. Therefore, after the first home device is controlled according to the control instruction, whether the control of the user on the first home device is obtained within the set duration can be detected, and specifically whether the first home device or the mobile terminal for controlling the first home device receives the operation of the user on the first home device can be detected. Of course, the specific set time period and the manner of detecting whether the control command is erroneous may not be limited, and the set time period may be, for example, 5 minutes or 10 minutes.

And correcting the training model when the control command is determined to be in error. Specifically, a control instruction corresponding to a control operation of the first home device by a user and condition data during the control operation can be obtained, and then the control instruction corresponding to the control operation and the condition data during the control operation are input into the training model to train the training model. The specific training method is not described herein. Of course, when it is determined that the control command is error-free, correction of the training model is not required. In the embodiment of the present application, the manner of correcting the training model may not be limited.

Of course, if the control operation of the user on the first home device is obtained within the set period after the first home device is controlled according to the control instruction, a control instruction corresponding to the control operation may be generated, and the first home device is controlled based on the control instruction corresponding to the control operation. Specifically, the first home device is controlled based on the control instruction corresponding to the control operation, and the manner of controlling the first home device according to the calculated control instruction may be referred to, which is not described herein. In addition, if the control operation of the first home device by the user is acquired within the set period of time after the first home device is controlled according to the control instruction, the first home device is required to stop the operation performed according to the calculated control instruction before, in addition to the control of the home device again. Therefore, the operation stopping instruction can also be sent to the first household equipment so as to control the first household equipment to stop the previous operation, and the conflict caused by different control instructions is avoided.

According to the equipment control method, the initial training model is trained by utilizing the historical condition data and the equipment data when the first household equipment is operated, the trained training model is obtained, the current condition data for controlling the first household equipment is obtained, when the current condition data meets the set triggering condition, the training model is utilized to calculate the control instruction matched with the current condition data, and then the first household equipment is controlled according to the control instruction, so that the operation instruction of the subsequent user on the first household equipment is calculated according to the historical data of the user on the first household equipment, the automatic control on the first household equipment is realized, the intelligent degree of the household equipment control is improved, the historical condition data is related to the user, the environment and other household equipment, and the control instruction calculated by the training model accords with the operation habit of the user on the household equipment and meets the user requirement. In addition, the training model is continuously corrected, so that the accuracy of calculating the control instruction by the training model is improved, and the user experience is improved.

Referring to fig. 5, still another embodiment of the present application provides a device control method, which may be applied to a server, and the device control method may include:

step S310: and receiving an automatic control request sent by the mobile terminal.

In this embodiment of the present application, the first home device may be in an automatic control mode, and the automatic control mode of the first home device may be selected by a user according to a requirement.

In some embodiments, the server may control whether the mode of automatic control of the first home device is turned on according to a request sent by the mobile terminal of the user. The mobile terminal may send an automatic control request or a control closing request, where the automatic control request may instruct the server to start the automatic control mode, and the control closing request may instruct the server to close the automatic control mode. The mobile terminal may display an interface of an application program for controlling the first home device, where the interface may include a setting page of an automatic control mode, so that a user may send an automatic control request or a control closing request to the server through the setting page. The automatic control mode is used for the server to automatically send a control instruction to the first household equipment according to the corresponding strategy so as to control the first household equipment. When the first household equipment is in an automatic control mode, the first household equipment can execute corresponding control instructions sent by the server according to corresponding strategies under the condition that the user does not need to carry out on-site manual control or remote control through the mobile terminal, and control operation corresponding to the control instructions is completed, so that automatic control of the first household equipment is realized.

In some embodiments, the mode of automatic control of the first home device may be a request or an instruction sent by the mobile terminal of the user, and the mode may be turned on or turned off. When the automatic control mode is started, the server can automatically execute the corresponding strategy and issue a control instruction to the first household equipment. Of course, when the first home device is in the automatic control mode, the first home device may be controlled manually by the user, for example, the user may still control the first home device on site through a key on the first home device, or may control the first home device through an application program running on the mobile terminal.

Step S320: and responding to the automatic control request, and controlling the first household equipment to be in an automatic control mode.

After receiving the automatic control request sent by the mobile terminal of the user, the server can respond to the automatic control request to control the first household equipment to be in an automatic control mode. The first household equipment is in an automatic control mode, and the server continuously collects condition data to determine whether to calculate a control instruction by using a training model to control the first household equipment. And when the first household equipment is not in the automatic control mode, the server does not calculate a control instruction by using the condition data and the training model, and the first household equipment is controlled.

Step S330: when the first household equipment is in an automatic control mode, current condition data for controlling the first household equipment are acquired.

Step S340: when the current condition data meets a set trigger condition, a trained training model is obtained, the training model is obtained according to historical condition data and equipment data when the first household equipment is operated, the historical condition data at least comprise personal data, environment data of a user and state data of second household equipment, and the equipment data at least comprise control instructions for the first household equipment.

Step S350: and inputting the current condition data into the training model to obtain a control instruction for the first household equipment.

In the embodiment of the present application, the step S330, the step S340 and the step S350 may refer to the content of the above embodiment, which is not described herein.

Step S360: and sending prompt content to the mobile terminal of the user, wherein the prompt content is used for prompting whether to perform the operation corresponding to the control instruction on the first household equipment.

In this embodiment of the present application, after the control instruction for controlling the first home device is calculated by using the training model, the user may be further prompted whether to perform control corresponding to the control instruction on the first home device. Specifically, the prompting content is sent to the mobile terminal of the user, and the prompting content is used for prompting whether to perform the operation corresponding to the control instruction on the first home equipment.

In some embodiments, the server may obtain the number of times of the control operation of the user on the first home device in the set period between the current times, so as to determine whether to send the prompt content to the mobile terminal of the user according to the number of times, and prompt the user. The current time is the time when the control instruction is obtained by using the training model. It can be understood that if the number of times of the control operation of the user on the first home device is greater in the set period of time between the current times, it means that the user controls the first home device more by using manual control, and at this time, the control instruction calculated by using the training model is used to control the first home device, which may not meet the requirement of the user.

Further, the server may determine whether the acquired number of times is greater than the set number of times, and if so, indicate that the number of times of the control operation of the user on the first home device is greater in the set period of time between the current times. If the number of times is not greater than the set number of times, the number of times of the control operation of the user on the first household equipment in the set time period before the current time is not more. Therefore, when the acquired times are judged to be larger than the set times, the prompt content can be sent to the mobile terminal of the user. The specific setting times and setting time period are not limited, and for example, the setting times may be 5 times, 10 times, etc., and the setting time period may be a time period within 2 days before the current time, a time period within 3 days before the current time, etc.

Step S370: and when a determining instruction sent by the mobile terminal is received, controlling the first household equipment according to the control instruction.

In the embodiment of the application, after sending the prompt content to the mobile terminal of the user, the server may detect whether a determination instruction sent by the mobile terminal is received. If a determining instruction sent by the mobile terminal is received, the server can control the first home equipment according to the control instruction. The determining instruction indicates that the user determines that the first household device needs to be controlled according to the control instruction. For example, the determining instruction may be a determining instruction detected by the prompt interface after the mobile terminal receives the prompt content and displays the prompt interface according to the prompt content. And if the server does not receive the determining instruction returned by the mobile terminal, the first household equipment is not controlled according to the control instruction.

According to the equipment control method, the first household equipment is set to be in an automatic control mode, current condition data for controlling the first household equipment is obtained for the first household equipment in the automatic control mode, when the current condition data meets a set triggering condition, a training model trained according to historical condition data and equipment data is utilized to calculate a control instruction matched with the current condition data, and then the first household equipment is controlled according to the control instruction, so that historical data of operation of the first household equipment by a user is achieved, operation instructions of subsequent users on the first household equipment are calculated, and when the number of times of manual control of the latest users is large, prompt content is sent to a mobile terminal of the user to prompt whether the user executes operation corresponding to the control instruction on the first household equipment, when the determination instruction is received, the first household equipment is controlled according to the control instruction, automatic control on the household equipment is achieved, the intelligent degree of control of the household equipment is improved, the historical condition data is related to the user, the environment and other household equipment, the control instruction calculated by the training model accords with the operation habit of the user on the household equipment, and the user's operation experience is improved, and the user's requirements are met.

Referring to fig. 6, fig. 6 is a block diagram illustrating a device control apparatus 500 according to an embodiment of the present application. The device control apparatus 500 is applied to a server, and will be described with respect to the apparatus shown in fig. 6, the device control apparatus 500 includes: a data acquisition module 510, a model acquisition module 520, an instruction acquisition module 530, and a control execution module 540. The data obtaining module 510 is configured to obtain current condition data, where the current condition data is used to control a first home device; the model obtaining module 520 is configured to invoke a trained training model when the current condition data meets a set trigger condition, where the training model is obtained by training according to historical condition data and device data when the first home device is operated, the condition data includes at least personal data, environment data of a user, and status data of a second home device, and the device data includes at least a control instruction for the first home device; the instruction obtaining module 530 is configured to input the current condition data into the training model, to obtain a control instruction for the first home device; the control execution module 540 is configured to control the first home device according to the control instruction.

In some embodiments, the environmental data includes at least time data, date data, location data, and weather data, and the set trigger condition includes: the time data is at least one of set time data, the date data is set date data, the position data is set position data, the weather data is set weather data, and the second home device is set.

In some embodiments, the device control apparatus 500 may further include: and a model training module. The data obtaining module 510 is further configured to obtain historical condition data and device data when the first home device is operated, where the historical condition data corresponds to the device data. The model training module is used for inputting the historical condition data and the equipment data into an initial model, and training the initial model to obtain the trained training model.

Further, the device control apparatus 500 may further include: and the data screening module and the data classifying module are used for screening the data. The data screening module is used for screening the historical condition data and the equipment data; the data classification module is used for classifying the screened historical condition data and the device data.

In some embodiments, the data obtaining module 510 may obtain historical condition data and device data when the home device is operated, and may include: and acquiring historical condition data and equipment data when the first household equipment is operated from the mobile terminal, the environment acquisition device, the first household equipment, the second household equipment and the server of the third party platform.

In some implementations, the control execution module 540 may be specifically configured to: the control instruction is sent to gateway equipment in a network where the first home equipment is located, the gateway equipment is used for sending the control instruction to the first home equipment, and the control instruction is used for indicating the first home equipment to perform operation corresponding to the control instruction.

Further, the control execution module 540 sends the control instruction to a gateway device in the network where the home device is located, which may include: and sending the control instruction to a manufacturer server corresponding to the first household equipment, wherein the manufacturer server is used for sending the control instruction to gateway equipment in a network where the first household equipment is located.

In some embodiments, the device control apparatus 500 may further include: and a model correction module. The model correction module may be for: after the first household equipment is controlled according to the control instruction, judging whether the control instruction is wrong or not; and if the error exists, correcting the training model.

Further, the model correction module determining whether the control instruction is wrong may include: detecting whether the control operation of a user on the first household equipment is acquired within a set time length after the first household equipment is controlled; and if the control operation of the user on the first household equipment is obtained, determining that the control instruction is wrong.

Further, the model correction module corrects the training model, which may include: acquiring a control instruction corresponding to the control operation and condition data when the control operation is performed; and inputting a control instruction corresponding to the control operation and condition data during the control operation into the training model, and training the training model.

In some embodiments, the control execution module 550 may be specifically configured to: sending prompt content to a mobile terminal of a user, wherein the prompt content is used for prompting whether to perform operation corresponding to the control instruction on the first household equipment; and when a determining instruction sent by the mobile terminal is received, controlling the first household equipment according to the control instruction.

Further, the control execution module 550 sends the prompt content to the mobile terminal of the user, which may include: acquiring the number of times of control operation of a user on the first household equipment in a set time period before the current time, wherein the current time is the time when the control instruction is obtained; and if the number of times is greater than the set number of times, sending prompt contents to the mobile terminal of the user.

In some embodiments, the device control apparatus 500 may further include a request receiving module and a request responding module. The request receiving module is used for receiving an automatic control request sent by the mobile terminal; the request response module is used for responding to the automatic control request and controlling the first household equipment to be in an automatic control mode.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus and modules described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.

In several embodiments provided herein, the coupling of the modules to each other may be electrical, mechanical, or other.

In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.

In summary, according to the scheme provided by the application, the current condition data for controlling the first household device is obtained, when the current condition data meets the set control trigger condition, the training model obtained by training according to the historical condition data and the device data when the first household device is operated is called, the historical condition data comprises personal data, environment data and state data of the second household device of a user, the device data comprises a control instruction for the first household device, then the current condition data is input into the training model to obtain the control instruction for the first household device, and the first household device is controlled according to the control instruction, so that the operation instruction for the household device is predicted according to the historical operation of the user on the household device, the automatic control on the household device is realized, the intelligent degree of the control of the household device is improved, the relevance with the user is high, the user requirement is met, and the user experience is improved.

Referring to fig. 7, a block diagram of a server according to an embodiment of the present application is shown. The server 100 in this application may include one or more of the following components: a processor 110, a memory 120, and one or more application programs, wherein the one or more application programs may be stored in the memory 120 and configured to be executed by the one or more processors 110, the one or more program(s) configured to perform the method as described in the foregoing method embodiments.

Processor 110 may include one or more processing cores. The processor 110 connects various portions of the overall server 100 using various interfaces and lines, performs various functions of the server 100 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and invoking data stored in the memory 120. Alternatively, the processor 110 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 110 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 110 and may be implemented solely by a single communication chip.

The Memory 120 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Memory 120 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 120 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc. The storage data area may also store data created by the terminal 100 in use (such as phonebook, audio-video data, chat-record data), etc.

Referring to fig. 8, a block diagram of a computer readable storage medium according to an embodiment of the present application is shown. The computer readable medium 800 has stored therein program code which can be invoked by a processor to perform the methods described in the method embodiments described above.

The computer readable storage medium 800 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 800 comprises a non-volatile computer readable medium (non-transitory computer-readable storage medium). The computer readable storage medium 800 has storage space for program code 810 that performs any of the method steps described above. The program code can be read from or written to one or more computer program products. Program code 810 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, one of ordinary skill in the art will appreciate that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of controlling a device, the method comprising:

acquiring current condition data, wherein the current condition data is used for controlling first household equipment;

when the current condition data meets a set triggering condition, a trained training model is called, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the condition data at least comprise personal data, environment data and state data of second household equipment of a user, the equipment data at least comprise control instructions for the first household equipment, and the environment data at least comprise time data, position data and weather data;

Inputting the current condition data into the training model to obtain a control instruction for the first household equipment;

acquiring the number of times of control operation of a user on the first household equipment in a set time period before the current time, wherein the current time is the time when the control instruction is obtained;

if the number of times is greater than the set number of times, sending prompt content to a mobile terminal of a user, wherein the prompt content is used for prompting whether to perform operation corresponding to the control instruction on the first household equipment;

when a determining instruction sent by the mobile terminal is received, controlling the first household equipment according to the control instruction;

the set triggering conditions comprise:

the time data is at least one of set time data, the position data is set position data, the weather data is set weather data, the second home equipment is set state, and the current condition data comprises a trigger instruction input by a user.

2. The method of claim 1, wherein before invoking the trained training model when the current condition data meets a set trigger condition, the method further comprises:

Acquiring historical condition data and equipment data when the first household equipment is operated, wherein the historical condition data corresponds to the equipment data;

and inputting the historical condition data and the equipment data into an initial model, and training the initial model to obtain the trained training model.

3. The method of claim 2, wherein prior to said entering said historical condition data and said device data into an initial model, said method further comprises:

screening the historical condition data and the equipment data;

classifying the screened historical condition data and the device data.

4. The method of claim 2, wherein the obtaining historical condition data and device data of the first home device when operated comprises:

and acquiring historical condition data and equipment data when the first household equipment is operated from the mobile terminal, the environment acquisition device, the first household equipment, the second household equipment and the server of the third party platform.

5. The method according to claim 1, wherein controlling the first home device according to the control instruction comprises:

The control instruction is sent to gateway equipment in a network where the first home equipment is located, the gateway equipment is used for sending the control instruction to the first home equipment, and the control instruction is used for indicating the first home equipment to perform operation corresponding to the control instruction.

6. The method of claim 5, wherein the sending the control instruction to a gateway device in a network in which the first home device is located comprises:

and sending the control instruction to a manufacturer server corresponding to the first household equipment, wherein the manufacturer server is used for sending the control instruction to gateway equipment in a network where the first household equipment is located.

7. The method according to claim 1, wherein the method further comprises:

after the first household equipment is controlled according to the control instruction, judging whether the control instruction is wrong or not;

and if the error exists, correcting the training model.

8. The method of claim 7, wherein said determining whether said control instruction is erroneous comprises:

detecting whether the control operation of a user on the first household equipment is acquired within a set time length after the first household equipment is controlled;

And if the control operation of the user on the first household equipment is obtained, determining that the control instruction is wrong.

9. The method of claim 8, wherein said correcting said training model comprises:

acquiring a control instruction corresponding to the control operation and condition data when the control operation is performed;

and inputting a control instruction corresponding to the control operation and condition data during the control operation into the training model, and training the training model.

10. The method according to any one of claims 1-9, wherein prior to said obtaining current condition data, the method further comprises:

receiving an automatic control request sent by a mobile terminal;

and responding to the automatic control request, and controlling the first household equipment to be in an automatic control mode.

11. A device control apparatus, characterized in that the apparatus comprises: the system comprises a data acquisition module, a model acquisition module, an instruction acquisition module and a control execution module, wherein,

the data acquisition module is used for acquiring current condition data, and the current condition data is used for controlling the first household equipment;

The model acquisition module is used for calling a trained training model when the current condition data meets a set trigger condition, the training model is obtained by training according to historical condition data and equipment data when the first household equipment is operated, the condition data at least comprise personal data of a user, environment data and state data of second household equipment, the equipment data at least comprise control instructions for the first household equipment, and the environment data at least comprise time data, position data and weather data;

the instruction acquisition module is used for inputting the current condition data into the training model to obtain a control instruction for the first household equipment;

the control execution module is used for obtaining the times of control operation of the user on the first household equipment in a set time period before the current time, wherein the current time is the time when the control instruction is obtained; if the number of times is greater than the set number of times, sending prompt content to a mobile terminal of a user, wherein the prompt content is used for prompting whether to perform operation corresponding to the control instruction on the first household equipment; when a determining instruction sent by the mobile terminal is received, controlling the first household equipment according to the control instruction;

The set triggering conditions comprise:

12. The apparatus of claim 11, wherein the apparatus further comprises: a model training module for:

when the current condition data meets a set trigger condition, before a trained training model is obtained, historical condition data and equipment data when the first household equipment is operated are obtained, wherein the historical condition data corresponds to the equipment data;

13. The apparatus of claim 12, wherein the apparatus further comprises: the data screening module and the data classifying module, wherein,

the data screening module is used for screening the historical condition data and the equipment data before inputting the historical condition data and the equipment data into an initial model;

The data classification module is used for classifying the screened historical condition data and the device data.

14. The apparatus of claim 12, wherein the model training module obtains historical condition data and device data for the first household device when it was operated, comprising:

15. A server, comprising:

one or more processors;

a memory;

one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to perform the method of any of claims 1-10.

16. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code, which is callable by a processor for executing the method according to any one of claims 1-10.