Working mode determination method, system, device, storage medium

Abstract

The present application discloses a method, system, device, and storage medium for determining a working mode. The method includes: obtaining at least one first status data of an intelligent household appliance; the first acquisition times corresponding to the at least one first status data are different; obtaining first environment data corresponding to each of the first acquisition times; inputting each of the first status data and the corresponding first environment data into a trained neural network model to obtain a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using a plurality of historical working modes of the intelligent household appliance and historical status data and historical environment data corresponding to each of the historical working modes; and outputting the first working mode.

Description

Technical Field

[0001] This application relates to the technology of smart home appliances, including but not limited to a method, system, device, and storage medium for determining a working mode. Background Art

[0002] Currently, the popularity of smart home appliances is increasing, and their functions are also becoming more and more diverse. Users often need to spend more energy and time to select the desired functions.

[0003] In the related art, a default setting is provided to the user when the smart home appliance is started, such as the menu function of a rice cooker or the wind type gear of an electric fan, and the user adjusts it to the mode required for this use automatically; however, if the default setting is unreasonable, it will result in additional adjustment operations for the user every time they start, which is counterproductive. Summary of the Invention

[0004] In view of this, this application provides a method, system, device, and storage medium for determining a working mode.

[0005] In a first aspect, an embodiment of this application provides a method for determining a working mode. The method includes: obtaining at least one first state data of a smart home appliance; the first acquisition times corresponding to the at least one first state data are different; obtaining first environment data corresponding to each of the first acquisition times; inputting each of the first state data and the corresponding first environment data into a trained neural network model to obtain a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and historical state data and historical environment data corresponding to each of the historical working modes; outputting the first working mode.

[0006] In a second aspect, an embodiment of this application provides a method for determining a working mode. The method includes: the smart home appliance in the system sends at least one first state data to the working mode determination device in the system; the working mode determination device obtains the at least one first state data of the smart home appliance; the first acquisition times corresponding to the at least one first state data are different; the working mode determination device obtains first environment data corresponding to each of the first acquisition times; the working mode determination device inputs each of the first state data and the corresponding first environment data into a trained neural network model; the working mode determination device obtains a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and historical state data and historical environment data corresponding to each of the historical working modes; the working mode determination device outputs the first working mode.

[0007] In a third aspect, an embodiment of the present application provides a working mode determination device, including: a first acquisition module, configured to acquire at least one first status data of an intelligent household appliance; the at least one first status data corresponds to different first acquisition times; a second acquisition module, configured to acquire first environment data corresponding to each of the first acquisition times; an input module, configured to input each of the first status data and the corresponding first environment data into a trained neural network model to obtain a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model by using a plurality of historical working modes of the intelligent household appliance and historical status data and historical environment data corresponding to each of the historical working modes; and an output module, configured to output the first working mode.

[0008] In a fourth aspect, an embodiment of the present application provides a working mode determination system, including: an intelligent household appliance and a working mode determination device, where: the intelligent household appliance is configured to send at least one first status data to the working mode determination device; the working mode determination device is configured to acquire the at least one first status data of the intelligent household appliance; the at least one first status data corresponds to different first acquisition times; acquire first environment data corresponding to each of the first acquisition times; input each of the first status data and the corresponding first environment data into a trained neural network model; obtain a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model by using a plurality of historical working modes of the intelligent household appliance and historical status data and historical environment data corresponding to each of the historical working modes; and the working mode determination device is configured to output the first working mode.

[0009] In a fifth aspect, an embodiment of the present application provides a working mode determination device, including a memory and a processor, where the memory stores a computer program that can run on the processor, and when the processor executes the program, the steps in the working mode determination method described in the first aspect of the embodiments of the present application are implemented.

[0010] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the working mode determination method described in the first aspect of the embodiments of the present application are implemented.

[0011] In the embodiments of the present application, by inputting the obtained first state data of the smart home appliance and the corresponding first environmental data into a neural network model trained with multiple historical working modes of the smart home appliance and their corresponding historical state data and historical environmental data, to obtain the first working mode output by the neural network model and output the first working mode, it is possible to combine the state data of the smart home appliance and the surrounding environmental data to more intelligently determine the working mode of the smart home appliance; in addition, since the neural network model is trained with the historical working modes of the smart home appliance and their corresponding historical state data and historical environmental data, therefore, it is possible to more accurately predict the working mode of the smart home appliance according to the user's usage habits and the current environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a schematic flowchart of a method for determining a working mode according to an embodiment of the present application;

[0013] Figure 2 is a schematic flowchart of another method for determining a working mode according to an embodiment of the present application;

[0014] Figure 3 is a schematic diagram of an application scenario of a working mode determination system according to an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of the composition structure of a working mode determination device according to an embodiment of the present application;

[0016] Figure 5 is a schematic diagram of the composition structure of a working mode determination system according to an embodiment of the present application;

[0017] Figure 6 is a schematic diagram of a hardware entity of a working mode determination device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The technical solutions of the present application will be further described in detail below with reference to the drawings and embodiments.

[0019] Figure 1 is a schematic flowchart of the implementation process of a method for determining a working mode provided by an embodiment of the present application. The method can be applied to a working mode determination device, such as Figure 1 as shown, the method includes:

[0020] Step 102: Obtain at least one first state data of the smart home appliance; the first acquisition moments corresponding to the at least one first state data are different;

[0021] Among them, the smart home appliance can be a home appliance product formed by introducing microprocessor, sensor technology, and network communication technology into home appliance devices. The smart home appliance can be interconnected with other home appliances or facilities to form a system; the smart home appliance can be a smart electric fan, a smart rice cooker, etc.; the first state data can be the performance parameters of the smart home appliance in a certain working mode. The at least one first state data can be one first state data or multiple first state data. When the smart home appliance is a smart electric fan, the first state data can include the rotation speed, shaking angle, efficiency, and torque of the smart electric fan, etc.; the first acquisition moment can be the moment when the first state data is acquired. The first acquisition moment can be 10:00, 12:00, 21:00, etc.; the working mode determination device can be a cloud server or a user terminal. The user terminal can be a terminal device used by the user. The terminal device can be a mobile phone, a tablet computer, a laptop computer, etc.

[0022] Step 104: Obtain the first environmental data corresponding to each of the first acquisition moments;

[0023] Among them, the first environmental data can be data obtained by observing and processing various natural factors that can directly or indirectly affect human life and development in the space where humans live. The first environmental data can include measurement data such as the temperature and humidity of the environment, and can also include data such as wind direction, wind speed, sunlight, air pressure, rainfall level, snow, fog warning level, and lightning warning level; the first environmental data can be a temperature of 38°C, a wind speed of 0 (calm), an illuminance of 1.2 lux, or can also be a temperature of 10°C, a wind speed of 4, and an illuminance of 0.2 lux.

[0024] Step 106: Input each of the first state data and the corresponding first environmental data into the trained neural network model to obtain the first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and the historical state data and historical environmental data corresponding to each historical working mode.

[0025] Among them, the trained neural network model can be a neural network model trained with a large amount of historical state data, corresponding historical environmental data, and corresponding historical working modes. The trained neural network model has the ability of self-learning; when the smart home appliance is an electric fan, the first working mode can be a combination of the type of wind (normal wind with constant wind speed or sleep wind with changing wind speed), the shaking range, and the wind force.

[0026] In one embodiment, assume that the smart home appliance is a smart electric fan. The first state data includes the rotation speed and the shaking range. The greater the rotation speed, the greater the wind speed. The wind speed gradually increases from gear 1 to gear 8. The first environmental data includes the temperature and the illuminance of light. Then, when the rotation speed of the smart electric fan is relatively high, the shaking range is 0 degrees (i.e., it does not shake), the temperature is 38 °C, and the illuminance of light is 1.2 lux, the first state data and the corresponding first environmental data are input into the trained neural network model, and the first working mode output by the neural network model can be normal wind, shaking 0 degrees, and gear 8 wind force; when the rotation speed of the smart electric fan is relatively low, the shaking range is 90 degrees, the temperature is 12 °C, and the illuminance of light is 0.2 lux, the first state data and the corresponding first environmental data are input into the trained neural network model, and the first working mode output by the neural network model can be sleep wind, shaking 90 degrees, and gear 2 wind force.

[0027] Step 108: Output the first working mode.

[0028] In the embodiment of the present application, the working mode determination device inputs the obtained first state data of the smart home appliance and the corresponding first environmental data into a neural network model trained by multiple historical working modes of the smart home appliance and their corresponding historical state data and historical environmental data, so as to obtain the first working mode output by the neural network model and output the first working mode, thereby being able to combine the state data of the smart home appliance and the surrounding environmental data to more intelligently determine the working mode of the smart home appliance; in addition, since the neural network model is trained by the historical working modes of the smart home appliance and their corresponding historical state data and historical environmental data, therefore, it can more accurately predict the working mode of the smart home appliance according to the user's usage habits and the current environment.

[0029] The embodiment of the present application also provides a working mode determination method, which can be applied to a working mode determination device. The method includes steps S202 to S214:

[0030] Step S202: Obtain multiple historical working modes of the smart home appliance and the historical state data corresponding to each historical working mode; the second collection times corresponding to the multiple historical working modes are different;

[0031] Among them, the second collection time can be earlier than the first collection time, and it can be considered that the second collection time is a historical time, that is, the historical working mode and the corresponding historical state data are data collected at a historical time.

[0032] Step S204: Obtain the historical environmental data corresponding to each second collection time;

[0033] Among them, the historical environmental data may be environmental data collected at a historical moment.

[0034] Step S206: Use each of the historical working modes, the corresponding historical state data, and the corresponding historical environmental data to train the initial neural network model to obtain a trained neural network model;

[0035] Among them, the trained neural network model may be a neural network model trained using each historical working mode, the corresponding historical state data, and the corresponding historical environmental data.

[0036] In one embodiment, the trained neural network model may also be a neural network model trained using each historical working mode, the corresponding user operation instruction, the corresponding historical state data, and the corresponding historical environmental data.

[0037] Step S208: Obtain at least one first state data of the smart home appliance; the first acquisition moments corresponding to the at least one first state data are different;

[0038] Step S210: Obtain the first environmental data corresponding to each of the first acquisition moments;

[0039] Step S212: Input each of the first state data and the corresponding first environmental data into the trained neural network model to obtain the first working mode output by the neural network model;

[0040] In one embodiment, when the trained neural network model may also be a neural network model trained using each historical working mode, the corresponding user operation instruction, the corresponding historical state data, and the corresponding historical environmental data, each of the first state data, the corresponding user operation instruction, and the corresponding first environmental data may be input into the trained neural network model to obtain the first working mode output by the neural network model.

[0041] Step S214: Send the first working mode to the smart home appliance.

[0042] Among them, when the working mode determination device is a cloud server, the cloud server may send the first working mode to the smart home appliance, and the smart home appliance may work according to the first working mode after receiving the first working mode.

[0043] In the embodiments of the present application, by using the historical working mode, corresponding historical state data, and historical environment data at a historical moment to train the initial neural network model, the obtained neural network model can more accurately predict the working mode of the smart home appliance when inputting state data and environment data. In addition, by directly sending the first working mode to the smart home appliance, the smart home appliance can work according to the first working mode, and the smart home appliance can be controlled more conveniently.

[0044] The embodiments of the present application further provide a method for determining a working mode. The method can be applied to a device for determining a working mode, and the method includes steps S302 to S320:

[0045] Step S302: Obtain at least one first state data of the smart home appliance; the first collection moments corresponding to the at least one first state data are different;

[0046] Step S304: Perform a verification process and a conversion process on the at least one first state data to obtain at least one third state data; at least one of the validity, integrity, and accuracy of the third state data is higher than that of the first state data;

[0047] Data verification is a verification operation performed to ensure data integrity. Usually, a check value calculated from the original data can be obtained using a specified algorithm. The receiving party calculates a check value using the same algorithm. If the two calculated check values are the same, it means the data is complete. The verification process can include parity check, CRC check (Cyclic Redundancy Check), LRC check (Longitudinal Redundancy Check), and Gray code check, etc. The data conversion process can be to convert or merge the data to form a description form suitable for data processing. The conversion process can include smoothing process, summation process, data generalization process, normalization process, and attribute construction process, etc.

[0048] Step S306: Obtain the first environment data corresponding to each of the first collection moments;

[0049] Step S308: Input each of the third state data and the corresponding first environment data into the trained neural network model to obtain the first working mode output by the neural network model;

[0050] Step S310: Display the first working mode;

[0051] Wherein, when the working mode determining device is a user terminal, an application APP (Application) matching the smart home appliance can be installed on the user terminal, and the first working mode can be displayed on the control page of the APP.

[0052] Step S312: Determine a second working mode according to the received working mode determination instruction;

[0053] Wherein, the working mode determination instruction can be that the user clicks on a certain control on the control page of the APP, triggering an instruction corresponding to the control. The second working mode can be the same as the first working mode or different from the first working mode. Assume that the control page includes a control corresponding to the first working mode and controls corresponding to other working modes. In the case where the user clicks on the control corresponding to the first working mode, the user terminal determines that the working mode to be sent to the smart home appliance is the first working mode. In the case where the user clicks on the control corresponding to other working modes, the user terminal determines that the working mode to be sent to the smart home appliance is other working modes.

[0054] Step S314: Send the second working mode to the smart home appliance;

[0055] Step S316: Obtain second state data of the smart home appliance in the second working mode, where the second working mode is collected at a third collection moment;

[0056] Step S318: Obtain second environmental data corresponding to the third collection moment;

[0057] Step S320: Use the second working mode, the second state data, and the second environmental data to optimize the trained neural network model to obtain an optimized neural network model, so as to determine the working mode of the smart home appliance based on the optimized neural network model.

[0058] In the embodiments of the present application, by performing verification processing and conversion processing on the first state data, the effectiveness, integrity, and accuracy of the data can be ensured. In addition, when the user is not satisfied with the first working mode output by the working mode determining device, the working mode can be determined or adjusted through the working mode determination instruction, thereby improving the flexibility, adjustability, and diversity of working mode determination. Furthermore, by using the adjusted working mode and the state data and environmental data in this working mode to optimize the neural network model, the optimized neural network model can more accurately meet customer needs.

[0059] An embodiment of this application further provides a method for determining a working mode. The method can be applied to a cloud server and includes steps S402 to S416:

[0060] Step S402: The cloud server obtains at least one first status data of the smart home appliance; the first collection times corresponding to the at least one first status data are different;

[0061] Step S404: The cloud server performs verification processing and conversion processing on the at least one first status data to obtain at least one third status data; at least one of the validity, integrity, and accuracy of the third status data is higher than that of the first status data;

[0062] Step S406: The cloud server obtains first environment data corresponding to each of the first collection times;

[0063] Step S408: The cloud server inputs each of the third status data and the corresponding first environment data into the trained neural network model to obtain a first working mode output by the neural network model;

[0064] Step S410: The cloud server sends the first working mode to the user terminal;

[0065] Wherein, after receiving the first working mode, the user terminal can display the first working mode on the control page of the APP of the smart home appliance. The user can click on a certain control on the control page of the APP to trigger a working mode determination instruction corresponding to the control. The user terminal determines a second working mode according to the received working mode determination instruction; the second working mode may be the same as the first working mode or different from the first working mode.

[0066] Assume that the control page includes a control corresponding to the first working mode and controls corresponding to other working modes. In the case where the user clicks on the control corresponding to the first working mode, the user terminal determines that the working mode to be sent to the smart home appliance is the first working mode and sends the first working mode to the smart home appliance. In the case where the user clicks on a control corresponding to another working mode, the user terminal determines that the working mode to be sent to the smart home appliance is another working mode and sends another working mode to the smart home appliance.

[0067] When the smart home appliance works according to the corresponding working mode, it can generate corresponding second status data and upload the second working mode and the corresponding second status data to the cloud server.

[0068] Step S412: The cloud server obtains the second working mode of the smart home appliance and the second status data corresponding to the second working mode, where the second working mode is collected at the third collection moment;

[0069] Step S414: The cloud server obtains the second environmental data corresponding to the third collection moment;

[0070] Step S416: The cloud server uses the second working mode, the second status data, and the second environmental data to optimize the trained neural network model to obtain an optimized neural network model, so as to determine the working mode of the smart home appliance based on the optimized neural network model.

[0071] In the embodiments of the present application, by performing verification processing and conversion processing on the first status data, the validity, integrity, and accuracy of the data can be ensured; in addition, when the user is not satisfied with the first working mode output by the working mode determination device, the working mode can be determined or adjusted through the working mode determination instruction, thereby improving the flexibility, adjustability, and diversity of working mode determination; furthermore, by using the adjusted working mode and the status data and environmental data in this working mode to optimize the neural network model, the optimized neural network model can more accurately meet customer needs.

[0072] Figure 2 It is a schematic implementation flow diagram of a working mode determination method provided by an embodiment of the present application. The method can be applied to Figure 5 the working mode determination system shown in the figure. The method includes:

[0073] Step 202: The smart home appliance in the system sends at least one first status data to the working mode determination device in the system;

[0074] Step 204: The working mode determination device obtains the at least one first status data of the smart home appliance; the first collection moments corresponding to the at least one first status data are different;

[0075] Step 206: The working mode determination device obtains the first environmental data corresponding to each first collection moment;

[0076] Step 208: The working mode determination device inputs each first status data and the corresponding first environmental data into the trained neural network model;

[0077] Step 210: The working mode determination device obtains a first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model by using a plurality of historical working modes of the smart home appliance and historical state data and historical environment data corresponding to each historical working mode.

[0078] Step 212: The working mode determination device outputs the first working mode.

[0079] In the embodiment of the present application, through the cooperation between the smart home appliance and the working mode determination device in the working mode determination system, by inputting the first state data of the smart home appliance and the first environment data corresponding to the first acquisition moment of the first state data into the trained neural network model, the neural network model can output the first working mode of the smart home appliance. Since the neural network model is based on a plurality of historical working modes of the smart home appliance and the corresponding historical state data and historical environment data, it can more intelligently and accurately predict the working mode of the smart home appliance according to the user's usage habits and preferences for the smart home appliance.

[0080] The embodiment of the present application further provides a working mode determination method, which can be applied to a working mode determination system as Figure 5 shown. The method includes:

[0081] Step S502: The working mode determination device obtains a plurality of historical working modes of the smart home appliance and historical state data corresponding to each historical working mode; the second acquisition moments corresponding to the plurality of historical working modes are different;

[0082] Among them, the second acquisition moment may be earlier than the first acquisition moment, and it can be considered that the second acquisition moment is a historical moment, that is, the historical working mode and the corresponding historical state data are data collected at a historical moment.

[0083] Step S504: The working mode determination device obtains historical environment data corresponding to each second acquisition moment;

[0084] Among them, the historical environment data may be environment data collected at a historical moment.

[0085] Step S506: The working mode determination device uses each historical working mode, the corresponding historical state data, and the corresponding historical environment data to train an initial neural network model to obtain the trained neural network model.

[0086] Step S508: The smart home appliance in the system sends at least one first state data to the working mode determination device in the system;

[0087] Step S510: The working mode determination device acquires the at least one first status data of the smart home appliance; the first acquisition times corresponding to the at least one first status data are different;

[0088] Step S512: The working mode determination device acquires the first environmental data corresponding to each of the first acquisition times;

[0089] Step S514: The working mode determination device inputs each of the first status data and the corresponding first environmental data into the trained neural network model;

[0090] Step S516: The working mode determination device acquires the first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model by using multiple historical working modes of the smart home appliance and the historical status data and historical environmental data corresponding to each of the historical working modes;

[0091] Step S518: The working mode determination device displays the first working mode;

[0092] Step S520: The working mode determination device sends the second working mode to the smart home appliance according to the received working mode determination instruction;

[0093] Step S522: The smart home appliance acquires the second working mode sent by the working mode determination device.

[0094] In the embodiment of the present application, by training the initial neural network model by using the historical working modes and the corresponding historical status data and historical environmental data at historical times, the obtained neural network model can more accurately predict the working mode of the smart home appliance when inputting status data and environmental data; in addition, when the user is not satisfied with the first working mode output by the working mode determination device, the working mode can be determined or adjusted through the working mode determination instruction, so as to improve the flexibility, adjustability and diversity of working mode determination.

[0095] The embodiment of the present application further provides a working mode determination method, which can be applied to a working mode determination system. The working mode determination system can include a smart home appliance, a cloud server and a user terminal. The method includes:

[0096] Step S602: The smart home appliance in the system sends at least one first status data to the cloud server in the system;

[0097] Among them, the smart home appliances can be home appliance products formed by introducing microprocessors, sensor technologies, and network communication technologies into home appliance devices. The smart home appliances can be interconnected with the cloud server and the user terminal to form the system; the smart home appliances can be smart electric fans, smart rice cookers, etc.; the first state data can be the performance parameters of the smart home appliances in a certain working mode. When the smart home appliance is a smart electric fan, the first state data can include the rotation speed, shaking angle, efficiency, torque, etc. of the smart electric fan.

[0098] Step S604: The cloud server obtains the at least one first state data of the smart home appliance; the first collection times corresponding to the at least one first state data are different;

[0099] Among them, the first collection time can be the time when the first state data is collected, and the first collection time can be 10:00, 12:00, 21:00, etc.

[0100] Step S606: The cloud server obtains the first environmental data corresponding to each first collection time;

[0101] Among them, the first environmental data can be data obtained by observing and processing various natural factors that can directly or indirectly affect human life and development in the space where humans live at the first collection time. The first environmental data can include measurement data such as the temperature and humidity of the environment, and can also include data such as wind direction, wind speed, sunlight, air pressure, rainfall level, snow, fog warning level, and lightning warning level; the first environmental data can be a temperature of 38°C, a wind speed of 0 (calm), an illuminance of 1.2 lux, or can also be a temperature of 10°C, a wind speed of 4, and an illuminance of 0.2 lux.

[0102] Step S608: The cloud server inputs each first state data and the corresponding first environmental data into the trained neural network model; to obtain the first working mode output by the neural network model; the neural network model is obtained by training the initial neural network model using multiple historical working modes of the smart home appliance and the historical state data and historical environmental data corresponding to each historical working mode.

[0103] Among them, the trained neural network model can be a neural network model trained with a large amount of historical state data, corresponding historical environmental data, and corresponding historical working modes. The trained neural network model has the ability of self-learning; when the smart home appliance is an electric fan, the first working mode can be a combination of the type of wind (normal wind with constant wind speed or sleep wind with variable wind speed), shaking range, and wind force.

[0104] Step S610: The cloud server sends the first working mode to the user terminal of the system;

[0105] Among them, the user terminal may be a terminal device used by the user, and the terminal device may be a mobile phone, a tablet computer, a laptop computer, etc.

[0106] Step S612: The user terminal displays the first working mode;

[0107] Among them, an APP matching the smart home appliance may be installed on the user terminal, and the first working mode may be displayed on the control page of the APP.

[0108] Step S614: The user terminal determines an instruction according to the received working mode and sends the second working mode to the smart home appliance;

[0109] Among them, the working mode determination instruction may be an instruction corresponding to a click operation on a certain control on the control page of the APP; the control includes a control corresponding to the first working mode and controls corresponding to other working modes; the second working mode may be the first working mode or one of the other working modes. When the user clicks the control corresponding to the first working mode, the user terminal determines that the working mode to be sent to the smart home appliance is the first working mode and sends the first working mode to the smart home appliance. When the user clicks the control corresponding to the other working mode, the user terminal determines that the working mode to be sent to the smart home appliance is the other working mode and sends the other working mode to the smart home appliance.

[0110] Step S616: The smart home appliance obtains the second working mode sent by the user terminal.

[0111] Among them, after receiving the second working mode, the smart home appliance controls itself to work in the second working mode and can obtain second state data of the smart home appliance in the second working mode.

[0112] In the embodiments of the present application, through the cooperation of the three terminals of the smart home appliance, the cloud server and the user terminal in the working mode determination system, the first state data of the smart home appliance and the first environmental data corresponding to the first acquisition moment of the first state data can be input into the trained neural network model, so that the neural network model outputs the first working mode of the smart home appliance. Since the neural network model is based on multiple historical working modes of the smart home appliance and the corresponding historical state data and historical environmental data, it can more intelligently and accurately predict the working mode of the smart home appliance according to the user's usage habits and preferences for the smart home appliance.

[0113] An embodiment of the present application further provides a method for determining a working mode. The method can be applied to a working mode determination system, which may include intelligent household appliances, a cloud server, and a user terminal. The method includes:

[0114] Step S702: The cloud server obtains multiple historical working modes of the intelligent household appliance and historical status data corresponding to each historical working mode; the second collection times corresponding to the multiple historical working modes are different;

[0115] Among them, the second collection time may be earlier than the first collection time, and it can be considered that the second collection time is a historical time, that is, the historical working mode and the corresponding historical status data are data collected at a historical time.

[0116] Step S704: The cloud server obtains historical environment data corresponding to each second collection time;

[0117] Among them, the historical environment data may be environment data collected at a historical time.

[0118] Step S706: The cloud server uses each historical working mode, the corresponding historical status data, and the corresponding historical environment data to train an initial neural network model to obtain the trained neural network model.

[0119] Step S708: The intelligent household appliance in the system sends multiple first status data to the cloud server in the system;

[0120] Step S710: The cloud server obtains the multiple first status data of the intelligent household appliance; the first collection times corresponding to the multiple first status data are different;

[0121] Step S712: The cloud server obtains first environment data corresponding to each first collection time;

[0122] Step S714: The cloud server inputs each first status data and the corresponding first environment data into the trained neural network model; to obtain the first working mode output by the neural network model; the neural network model is trained from an initial neural network model using multiple historical working modes of the intelligent household appliance and historical status data and historical environment data corresponding to each historical working mode.

[0123] Step S716: The cloud server sends the first working mode to the user terminal of the system;

[0124] Step S718: The user terminal displays the first working mode;

[0125] Step S720: the user terminal sends the second working mode to the smart home appliance according to the received working mode determination instruction;

[0126] Step S722: The smart home appliance obtains the second working mode sent by the user terminal.

[0127] In an embodiment of the present application, the initial neural network model is trained by utilizing the historical working modes at historical moments and the corresponding historical status data and historical environmental data, so that the obtained neural network model can more accurately predict the working mode of the smart home appliance when the status data and environmental data are input.

[0128] At present, the popularity of smart home appliances is increasing, and their functions are also increasing. The problem that comes with it is that users often need to spend more energy and time to select the functions they want. At present, the common solution of major smart home appliance manufacturers is to provide users with a default setting when starting the smart home appliance, such as the menu function of the rice cooker, the wind gear of the electric fan, etc., and the user can adjust it to the working mode required for this use. This method does reduce the user's decision-making cost in some cases, but if the default setting is unreasonable, it will cause the user to need to make additional adjustments every time it starts, which is counterproductive.

[0129] In addition, some products are equipped with a "power-off memory" function, that is, the default settings when the smart home appliance is started next time are the settings when the smart home appliance was last turned off; however, this method simply assumes that the user's next usage habits will be continuous, and such an assumption is often inaccurate.

[0130] In order to solve the above problems, the present application proposes a control method and device for the adaptive startup mode of smart home appliances. According to the user's historical behavior records, environmental parameters and other information, the startup mode (or working mode) most likely to be selected by the user at different time nodes is calculated and sent to the home appliance, thereby reducing or even completely avoiding the user's manual adjustment of the startup mode after turning on the device.

[0131] Figure 3 This is a schematic diagram of an application scenario of a working mode determination system according to an embodiment of the present application, see Figure 3 In order to realize the adaptive startup mode on the smart home appliance, the entire smart home appliance adaptive startup system (also called the working mode determination system) includes three modules: the user end 301, the data exchange layer 302 and the cloud data service (or cloud server) 303:

[0132] Users need to use smart home appliances equipped with an adaptive startup mode. The smart home appliances can be controlled directly through their own control panels, buttons, knobs, etc., or by using the supporting APP on the mobile terminal. The mobile terminal can be a user terminal such as a mobile phone, a tablet computer, a laptop computer, etc., and can even be controlled by third-party means such as voice and gestures. When the smart home appliances are used for the first time (this situation also includes a period of time at the beginning of use), since there is no historical data yet, the smart home appliances can use the default startup mode 307 instead of the adaptive startup mode 308. In the case of not using the smart home appliances for the first time, the adaptive startup mode 308 can be used. During the use process, the user's operation instructions and the device's status data are reported through the mobile network via the data exchange layer 302.

[0133] After the data exchange layer 302 performs simple verification processing and conversion processing on the reported operation instructions and status data, it will push the processed reported data 304 to the cloud data service 303 for storage by the latter. The reported data includes user data and device data. The user data can be the data obtained by performing verification processing and conversion processing on the operation instructions, and the device data can be the data obtained by performing verification processing and conversion processing on the status data. In addition, for assisting in decision-making, the cloud simultaneously accesses various types of third-party data 305, including but not limited to environmental data 3051, meteorological data 3052, etc. The environmental data 3051 can include measurement data such as the temperature and humidity of the environment, and the meteorological data 3052 can include data such as wind direction, wind speed, sunshine, air pressure, rainfall level, snow, fog warning level, and lightning warning level. A set of preset algorithm models 306 are deployed in the background of the cloud data service 303, which can take the reported data 304 of the smart home appliance device and the third-party data 305 as inputs and calculate the most likely working mode to be used when each user starts the smart home appliance device 3011 next time; then the cloud data service 303 will send the calculation result to the user side 301 regularly or in real time. The user side 301 generally includes the smart home appliance device itself 3011 and the supporting APP 3012 on the mobile side. Therefore, in this sending process, in addition to pushing the calculated working mode to the smart home appliance device 3011, it will also be reflected on the interaction interface of the APP 3012; by sending the calculation result to the user side regularly or in real time, the user can experience the working mode modified according to their own usage habits in real time, improving the user's personalized experience; in addition, through the multi-terminal collaboration of the user side 301, the data exchange layer 302, and the cloud data service 303, not only can the working mode obtained according to the user's usage habits be pushed to the smart home appliance device 3011 to make the smart home appliance device work according to the working mode, but also the working mode obtained according to the user's usage habits can be displayed on the interface of the APP for the user to confirm or change the working mode, thereby enhancing the adaptive ability of the smart home appliance device.

[0134] The above is the control method for the adaptive start mode of the smart home appliance device; in addition, there is also a device that can apply this control method, that is, the smart home appliance device on the user side. This device should at least have the following characteristics: some or all functions will have default settings after the device is started; the default settings can be remotely modified through an electronic control program (or electronic control instruction); in the case of networking, the default settings pushed by the cloud data service to the smart home appliance device will overwrite the previously saved value, that is, the start mode can be switched through the electronic control instruction, and the saved start mode after switching (i.e., the result is saved) can be achieved.

[0135] In one embodiment, the embodiment of the present application provides an electric fan with an adaptive startup mode. If a user starts the device at a specific time node for a continuous period of time and basically uses the same working mode, the working mode can be normal wind, 90-degree oscillation, and 8-speed wind power; the state data generated by the working mode is reported to the cloud data service 303 through the electric control program and calculated by a preset algorithm model 306 to obtain the working mode most likely to be used by the user when starting the electric fan next time, and then sent to the electric fan for storage. When the user starts the electric fan next time, its default mode will become this working mode.

[0136] In one embodiment, if the user controls the smart home appliance 3011 through the mobile phone APP 3012, the calculation result of the cloud data service 303 will be synchronously sent to the interface of the APP 3012. That is, when the user starts the APP 3012 and enters the corresponding control page, the displayed default working mode will be replaced by the calculation result of the cloud data service 303; after the user clicks the startup control on the control page, the smart home appliance 3011 will also operate according to the working mode corresponding to the calculation result; in addition, the user can also click the startup control corresponding to other startup modes on the control page to modify the calculation result to other startup modes.

[0137] In one embodiment, the state data of the smart home appliance 3011 can be reported to the cloud data service 303 via the mobile network, so the background of the remote data service 303 can obtain the user's usage information; combined with the time when the status data is reported, it can be known when and how the user operates the device 3011. Before the target product (i.e., the product that realizes the adaptive startup mode function) is launched, the state data of existing similar products online can be used as a training set to train the preset algorithm model 306 and deploy it to the cloud data service 303. After the target product is launched, when the user's usage data accumulates to a certain extent, the algorithm model 306 can predict the next startup mode more accurately; at the same time, if the user is not satisfied with the pushed startup mode, the user can intervene manually, modify the startup mode to a satisfactory startup mode, and report the state data of the smart home appliance 3011 in this startup mode to the cloud data service 303 via the mobile network. The cloud data service 303 can optimize the algorithm model 306 through the new state data and the corresponding third-party data, and achieve the purpose of result correction through user feedback, which can also play a role in feedback adjustment and iterative optimization of the algorithm model 306, and promote the improvement of the prediction accuracy of the algorithm model 306 for the startup mode.

[0138] Based on the foregoing embodiments, an embodiment of the present application provides a working mode determination device. The device includes each unit included therein, as well as each module included in each unit, and can be implemented by a processor in a computer device; of course, it can also be implemented by specific logic circuits; during implementation, the processor can be a central processing unit (CPU), a microprocessor unit (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0139] Figure 4 It is a schematic structural diagram of the working mode determination device according to an embodiment of the present application. As Figure 4 shown, the working mode determination device 400 includes a first acquisition module 401, a second acquisition module 402, an input module 403, and an output module 404, where:

[0140] The first acquisition module 401 is configured to acquire at least one first status data of the smart home appliance; the first acquisition times corresponding to the at least one first status data are different;

[0141] The second acquisition module 402 is configured to acquire the first environmental data corresponding to each of the first acquisition times;

[0142] The input module 403 is configured to input each of the first status data and the corresponding first environmental data into the trained neural network model to obtain the first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and the historical status data and historical environmental data corresponding to each of the historical working modes;

[0143] The output module 404 is configured to output the first working mode.

[0144] In one embodiment, the working mode determination device further includes: a training module, configured to acquire multiple historical working modes of the smart home appliance and the historical status data corresponding to each of the historical working modes; the second acquisition times corresponding to the multiple historical working modes are different; acquire the historical environmental data corresponding to each of the second acquisition times; and use each of the historical working modes, the corresponding historical status data, and the corresponding historical environmental data to train the initial neural network model to obtain the trained neural network model.

[0145] In one embodiment, the output module 404 is configured to send the first working mode to the smart home appliance.

[0146] In one embodiment, the output module 404 is configured to display the first working mode.

[0147] In one embodiment, the working mode determination device further includes: an optimization module, configured to determine a second working mode according to a received working mode determination instruction; send the second working mode to the smart home appliance; obtain second state data of the smart home appliance in the second working mode, where the second working mode is collected at a third collection moment; obtain second environment data corresponding to the third collection moment; use the second working mode, the second state data, and the second environment data to optimize the trained neural network model to obtain an optimized neural network model, so as to determine the working mode of the smart home appliance based on the optimized neural network model.

[0148] In one embodiment, the cloud server further includes: a processing module, configured to perform verification processing and conversion processing on the at least one first state data to obtain at least one third state data; at least one of the validity, integrity, and accuracy of the third state data is higher than that of the first state data;

[0149] Correspondingly, the input module 403 is configured to input each of the third state data and the corresponding first environment data into the trained neural network model to obtain the first working mode output by the neural network model.

[0150] Figure 5 The figure is a schematic structural diagram of a working mode determination system according to an embodiment of the present application. As Figure 5 shown, the working mode determination system 500 includes a smart home appliance 501 and a working mode determination device 502, where:

[0151] The smart home appliance 501 is configured to send at least one first state data to the working mode determination device 502; obtain the second working mode sent by the working mode determination device 502;

[0152] The working mode determination device 502 is configured to obtain the at least one first state data of the smart home appliance 501; the first collection moments corresponding to the at least one first state data are different; obtain first environment data corresponding to each of the first collection moments; input each of the first state data and the corresponding first environment data into the trained neural network model; obtain the first working mode output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance 501 and historical state data and historical environment data corresponding to each of the historical working modes.

[0153] The working mode determination device 502 is configured to output the first working mode.

[0154] The description of the working mode determination device embodiments above is similar to the description of the method embodiments of the first aspect above, and has beneficial effects similar to those of the method embodiments of the first aspect. For technical details not disclosed in the working mode determination device embodiments of this application, please refer to the description of the method embodiments of the first aspect of this application for understanding.

[0155] It should be noted that in the embodiments of this application, if the above-mentioned working mode determination method is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a cloud server to execute all or part of the methods described in the first aspect of the various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of this application are not limited to any specific combination of hardware and software.

[0156] Correspondingly, the embodiments of this application provide a working mode determination device Figure 6 FIG. is a schematic diagram of a hardware entity of the working mode determination device in the embodiments of this application. As Figure 6 shown, the hardware entity of the working mode determination device 600 includes: a memory 601 and a processor 602. The memory 601 stores a computer program that can run on the processor 602. When the processor 602 executes the program, it implements the steps in the working mode determination method provided in the first aspect in the above embodiments.

[0157] The memory 601 is configured to store instructions and applications executable by the processor 602, and can also cache data to be processed or already processed by the processor 602 and each module in the computer device 600 (for example, image data, audio data, voice communication data, and video communication data), and can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0158] Correspondingly, the embodiments of this application provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps in the working mode determination method provided in the first aspect in the above embodiments.

[0159] It should be noted that the descriptions of the above storage medium and device embodiments are similar to those of the above method embodiments and have similar beneficial effects to the method embodiments. For the technical details not disclosed in the storage medium and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0160] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures, or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not mean the order of execution is prior or posterior. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The sequence numbers of the embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0161] It should be noted that in this text, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including such element.

[0162] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0163] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Additionally, in each embodiment of this application, each functional unit can be fully integrated into one processing unit, or each unit can be separately regarded as a unit on its own, or two or more units can be integrated into one unit; the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0164] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments; and the aforementioned storage medium includes: removable storage devices, read-only memory (ROM), magnetic disks, or optical discs and other various media that can store program codes. Alternatively, if the above-mentioned integrated units of this application are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of this application, in essence or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a cloud server to execute all or part of the methods described in the first aspect of each embodiment of this application. And the aforementioned storage medium includes: removable storage devices, ROM, magnetic disks, or optical discs and other various media that can store program codes.

[0165] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments. The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments. The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0166] The above is only the implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for determining a working mode, characterized in that Applied to a working mode determination device, the method includes: Obtaining at least one first status data of an intelligent household appliance; the first acquisition times corresponding to the at least one first status data are different; Obtaining first environment data corresponding to each of the first acquisition times; Inputting each of the first status data and the corresponding first environment data into a trained neural network model to obtain a first working mode of the intelligent household appliance corresponding to the first status data output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the intelligent household appliance and historical status data and historical environment data corresponding to each of the historical working modes; Outputting the first working mode; The method further includes: Determining a second working mode according to a received working mode determination instruction; Sending the second working mode to the intelligent household appliance; The method further includes: Obtaining second status data of the intelligent household appliance in the second working mode, where the second working mode is collected at a third acquisition time; Obtaining second environment data corresponding to the third acquisition time; Optimizing the trained neural network model using the second working mode, the second status data, and the second environment data to obtain an optimized neural network model for determining the working mode of the intelligent household appliance based on the optimized neural network model.

2. The method according to claim 1, wherein The method further includes: Obtaining multiple historical working modes of the intelligent household appliance and historical status data corresponding to each of the historical working modes; the second acquisition times corresponding to the multiple historical working modes are different; Obtaining historical environment data corresponding to each of the second acquisition times; Training the initial neural network model using each of the historical working modes, the corresponding historical status data, and the corresponding historical environment data to obtain the trained neural network model.

3. The method according to any one of claims 1 to 2, characterized in that, After obtaining at least one first status data of the intelligent household appliance, the method further includes: Performing verification processing and conversion processing on the at least one first status data to obtain at least one third status data; at least one of the validity, integrity, and accuracy of the third status data is higher than that of the first status data; Correspondingly, the step of inputting each of the first status data and the corresponding first environment data into the trained neural network model to obtain the first working mode output by the neural network model includes: Inputting each of the third status data and the corresponding first environment data into the trained neural network model to obtain the first working mode output by the neural network model.

4. A method for determining a working mode, which is applied to a working mode determination system, is characterized in that The method includes: The intelligent household appliance in the system sends at least one first status data to the working mode determination device in the system; The working mode determination device obtains the at least one first status data of one of the intelligent household appliances; the first acquisition times corresponding to the at least one first status data are different; The working mode determination device obtains first environment data corresponding to each of the first acquisition times; The working mode determination device inputs each of the first state data and the corresponding first environmental data into the trained neural network model; The working mode determination device obtains the first working mode of the smart home appliance corresponding to the first state data output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and the historical state data and historical environmental data corresponding to each historical working mode; The working mode determination device outputs the first working mode; The method further includes: Determining a second working mode according to a received working mode determination instruction; Sending the second working mode to the smart home appliance; The working mode determination device obtains second state data of the smart home appliance in the second working mode, and the second working mode is collected at a third collection moment; Obtaining second environmental data corresponding to the third collection moment; Using the second working mode, the second state data, and the second environmental data to optimize the trained neural network model to obtain an optimized neural network model for determining the working mode of the smart home appliance based on the optimized neural network model.

5. The method according to claim 4, characterized in that, The method further includes: The working mode determination device obtains multiple historical working modes of the smart home appliance and the historical state data corresponding to each historical working mode; the second collection moments corresponding to the multiple historical working modes are different; The working mode determination device obtains the historical environmental data corresponding to each second collection moment; The working mode determination device uses each historical working mode, the corresponding historical state data, and the corresponding historical environmental data to train the initial neural network model to obtain the trained neural network model.

6. A working mode determination device, characterized in that, The working mode determination device includes: A first acquisition module for acquiring at least one first state data of a smart home appliance; the first collection moments corresponding to the at least one first state data are different; A second acquisition module for acquiring the first environmental data corresponding to each first collection moment; An input module for inputting each of the first state data and the corresponding first environmental data into the trained neural network model to obtain the first working mode of the smart home appliance corresponding to the first state data output by the neural network model; the neural network model is obtained by training an initial neural network model using multiple historical working modes of the smart home appliance and the historical state data and historical environmental data corresponding to each historical working mode; An output module for outputting the first working mode; An optimization module for determining a second working mode according to a received working mode determination instruction; and sending the second working mode to the smart home appliance; The optimization module is further configured to obtain second state data of the smart home appliance in the second working mode, where the second working mode is collected at a third collection moment; obtain second environmental data corresponding to the third collection moment; use the second working mode, the second state data, and the second environmental data to optimize the trained neural network model to obtain an optimized neural network model, so as to determine the working mode of the smart home appliance based on the optimized neural network model.

7. A working mode determination system, characterized in that, The system includes: a smart home appliance and a working mode determination device, where: The smart home appliance is configured to send at least one first state data to the working mode determination device; and is further configured to obtain the second working mode sent by the working mode determination device. The working mode determination device is configured to obtain the at least one first state data of one smart home appliance; the first collection moments corresponding to the at least one first state data are different; obtain first environmental data corresponding to each of the first collection moments; input each of the first state data and the corresponding first environmental data into a trained neural network model; obtain a first working mode of the smart home appliance corresponding to the first state data output by the neural network model; the neural network model is obtained by training an initial neural network model by using multiple historical working modes of the smart home appliance and historical state data and historical environmental data corresponding to each of the historical working modes. The working mode determination device is configured to output the first working mode. The working mode determination device is further configured to obtain second state data of the smart home appliance in the second working mode, where the second working mode is collected at a third collection moment; obtain second environmental data corresponding to the third collection moment; use the second working mode, the second state data, and the second environmental data to optimize the trained neural network model to obtain an optimized neural network model, so as to determine the working mode of the smart home appliance based on the optimized neural network model.

8. A working mode determination device, comprising a memory and a processor, where the memory stores a computer program that can run on the processor, and is characterized in that, When the processor executes the program, the steps in the working mode determination method according to any one of claims 1 to 3 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps in the working mode determination method according to any one of claims 1 to 3 are implemented.

Images