CN110554612A - Information protection method, server and computer readable storage medium - Google Patents
Information protection method, server and computer readable storage medium Download PDFInfo
- Publication number
- CN110554612A CN110554612A CN201810565063.XA CN201810565063A CN110554612A CN 110554612 A CN110554612 A CN 110554612A CN 201810565063 A CN201810565063 A CN 201810565063A CN 110554612 A CN110554612 A CN 110554612A
- Authority
- CN
- China
- Prior art keywords
- data
- preset
- model
- equipment
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Telephonic Communication Services (AREA)
Abstract
the embodiment of the invention discloses an information protection method, which comprises the following steps: receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data; generating a first model based on a preset algorithm and the first data; and if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment. The embodiment of the invention also discloses a server and a computer readable storage medium, which reduce the risk of malicious start of the household appliances of the Internet of things and ensure the normal work of the household appliances of the Internet of things.
Description
Technical Field
the present invention relates to protection technologies in the field of home appliance control, and in particular, to an information protection method, a server, and a computer-readable storage medium.
Background
with the continuous development of the internet of things technology, in order to meet the remote control of a user on household appliances and further realize the idea of smart home, household appliance manufacturers have provided internet of things household appliances, namely household appliances are in communication link with the internet; therefore, the user can adopt the intelligent terminal such as a mobile phone to remotely control the Internet of things household appliance through the Internet, the user can control the Internet of things household appliance to work before arriving at the place where the Internet of things household appliance is located, and for example, the user can control the Internet of things electric cooker to cook rice and the like when the user is in an office.
However, with the increasing demand of remote control, there is an attack behavior such as network malicious attack due to competition between industry opponents. The remote control system is easy to crack by the attack behaviors, so that the household appliances of the internet of things are maliciously started and enter an abnormal working state.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide an information protection method, a server, and a computer-readable storage medium, so as to solve the problem that in the prior art, an attack behavior such as a network malicious attack is easy to crack a remote control system, to find abnormal operations of an internet of things home appliance in time, and to prompt a user whether to allow execution of the abnormal operations of the internet of things home appliance, to reduce a risk that an internet of things home appliance is maliciously started, and to ensure normal operation of the internet of things home appliance.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
A method of information protection, the method comprising:
Receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
Generating a first model based on a preset algorithm and the first data;
And if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
optionally, before sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the method includes:
Acquiring a characteristic coefficient of the preset algorithm;
Acquiring target sample data when the first equipment is in a preset working mode;
determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first device based on the target sample data;
and training the target sample data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training set to obtain the second model.
Optionally, after sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the method includes:
and receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
optionally, the obtaining target sample data of the first device in the preset working mode includes:
receiving data sent within a second preset time period when the first equipment is in a preset working mode to obtain second data;
Sampling the second data to obtain first sample sub-data;
acquiring the first data stored in the server in the first preset time period to obtain second sample subdata; wherein the target sample data comprises the first sample sub-data and the second sample sub-data.
optionally, the generating a first model based on a preset algorithm and the first data includes:
Determining a number of second training samples and a number of second training sets for the first device based on the first data;
And training the first data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain the first model.
optionally, the first data includes: the first device is in the working time point, the working duration, the working power and the working interval duration when the preset working mode works, the IP address of the first device, the identification information of the preset working mode, the user identification of the first device and/or the IP address of the second device.
Optionally, the preset algorithm includes a long-time and short-time memory neural network algorithm;
the characteristic coefficients comprise input layer weight coefficients, output layer weight coefficients and bias of the long-time memory neural network algorithm.
A server, the server comprising: a processor, a memory, and a communication bus;
The communication bus is used for realizing connection communication between the processor and the memory;
The processor is configured to execute a protection program stored in the memory to implement the steps of:
receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
Generating a first model based on a preset algorithm and the first data;
And if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
Optionally, before the step of sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the processor is further configured to execute the following steps:
acquiring a characteristic coefficient of the preset algorithm;
acquiring target sample data when the first equipment is in a preset working mode;
determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first device based on the target sample data;
And training the target sample data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training set to obtain the second model.
Optionally, after the step of sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the processor is further configured to execute the following steps:
and receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
optionally, the processor is further configured to perform the following steps:
receiving data sent within a second preset time period when the first equipment is in a preset working mode to obtain second data;
sampling the second data to obtain first sample sub-data;
acquiring the first data stored in the server in the first preset time period to obtain second sample subdata; wherein the target sample data comprises the first sample sub-data and the second sample sub-data.
Optionally, the processor is further configured to perform the following steps:
Determining a number of second training samples and a number of second training sets for the first device based on the first data;
And training the first data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain the first model.
A computer-readable storage medium having a protection program stored thereon, the protection program, when executed by a processor, implementing the steps of the information protection method described above.
the information protection method, the server and the computer-readable storage medium provided by the embodiment of the invention receive data sent in a first preset time period when the first device is in a preset working mode to obtain first data, generate a first model based on a preset algorithm and the first data, and send a prompt message for determining whether the first device continues to work to the second device if the first model is not matched with a preset second model. Therefore, when the server receives data sent by the first equipment when the first equipment is in the preset working mode, the first data are analyzed to generate a first model, the first model and the preset second model are matched, if the first model is not matched with the second model, the server generates prompt information and sends the prompt information to the second equipment of the user, the user can control the first equipment to continue working through the second equipment, the problem that the remote control system is easy to crack by attack behaviors such as network malicious attack and the like in the prior art is solved, the abnormal operation of the household appliance of the internet of things can be timely discovered, the user is prompted whether to allow the abnormal operation of the household appliance of the internet of things to be executed, the risk that the household appliance of the internet of things is maliciously started is reduced, and the normal work of the household appliance of the internet of things is guaranteed.
Drawings
fig. 1 is a schematic flowchart of an information protection method according to an embodiment of the present invention;
Fig. 2 is a schematic flowchart of another information protection method according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of another information protection method according to an embodiment of the present invention;
Fig. 4 is a schematic view of an application scenario of an information protection method according to an embodiment of the present invention;
Fig. 5 is a schematic flowchart of another information protection method according to an embodiment of the present invention;
fig. 6 is a flowchart illustrating an information protection method according to another embodiment of the present invention;
Fig. 7 is a flowchart illustrating another information protection method according to another embodiment of the present invention;
fig. 8 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
in the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
An embodiment of the present invention provides an information protection method, which is shown in fig. 1 and includes the following steps:
Step 101, receiving data sent in a first preset time period when a first device is in a preset working mode, and obtaining first data.
Specifically, the step 101 of receiving data sent in a first preset time period when the first device is in the preset working mode to obtain the first data may be implemented by the server. The first device can be an intelligent household appliance with an internet access function, such as an electric cooker, an air conditioner, a refrigerator, an induction cooker and other household appliances with the internet access function. The preset working mode is a working mode corresponding to the first device, for example, the preset working mode of the electric rice cooker may be a firewood rice mode, a clay pot rice mode, or the like. The first data may be time for which the first device operates in the preset operating mode, operating power of the first device, an Internet Protocol (IP) address for interconnection between networks connected to the first device in the preset operating mode, and the like, and further includes a network IP address connected to a second device having a communication link with the first device, and the like. The first preset time period may be a preset time period, for example, a time period starting from a time when the first device is purchased home by the user to be used for the first time, or a time period starting from the first time to a time when the first device is used for a preset time period.
and 102, generating a first model based on a preset algorithm and the first data.
Specifically, the step 102 "generating the first model based on the preset algorithm and the first data" may be implemented by the server. The preset algorithm may be a Long Short Term Memory Network (LSTM) algorithm. And performing learning training on the first data by adopting a preset algorithm to obtain a first model corresponding to the first data currently sent by the first equipment.
And 103, if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
Specifically, step 103 "sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model" may be implemented by the server. The second model is a reference model which can be used as a standard and is obtained by learning and training data of the first device obtained by the server for a long time by adopting a preset algorithm. The second device may be a terminal device having a network access function and capable of installing an application program for remotely controlling the first device, and may be, for example, a smart phone, a tablet computer, a computer, and the like.
the information protection method provided by the embodiment of the invention receives data sent in a first preset time period when the first device is in a preset working mode, obtains first data, generates a first model based on a preset algorithm and the first data, and sends a prompt message for determining whether the first device continues to work to the second device if the first model is not matched with a preset second model. Therefore, when the server receives data sent by the first equipment when the first equipment is in the preset working mode, the first data are analyzed to generate a first model, the first model and the preset second model are matched, if the first model is not matched with the second model, the server generates prompt information and sends the prompt information to the second equipment of the user, the user can control the first equipment to continue working through the second equipment, the problem that the remote control system is easy to crack by attack behaviors such as network malicious attack and the like in the prior art is solved, the abnormal operation of the household appliance of the internet of things can be timely discovered, the user is prompted whether to allow the abnormal operation of the household appliance of the internet of things to be executed, the risk that the household appliance of the internet of things is maliciously started is reduced, and the normal work of the household appliance of the internet of things is guaranteed.
Based on the foregoing embodiments, an embodiment of the present invention provides an information protection method, which is shown in fig. 4 and includes the following steps:
Step 201, a server receives data sent in a first preset time period when a first device is in a preset working mode, and first data are obtained.
Wherein the first data includes: the method comprises the steps of working time point, working duration, working power and/or working interval duration when the first equipment works in a preset working mode, an IP address of the first equipment, identification information of the preset working mode, a user identification of the first equipment and/or an IP address of the second equipment.
Specifically, taking the first device as a home appliance with a cooking function as an example for explanation, when the first device is already in the cooking mode, the first device obtains a working time point when entering the cooking mode, a working time length from the beginning of cooking to the current time, a working power when cooking is performed, a working interval length between two adjacent cooking operations when multiple cooking operations are performed, an IP address of a data network connected to the first device, identification information set by a manufacturer for the cooking mode of the first device, identification information of the first device, namely identification information of a user who can use the first device and is set after the user purchases the first device, and an IP address of a data network connected to the second device to obtain first data, it should be explained that the user uses the second device to send a remote control instruction to the first device when the first device performs the cooking mode, the first device can acquire the IP address of the second device.
Step 202, the server obtains the characteristic coefficient of the preset algorithm.
The preset algorithm comprises a long-time memory neural network algorithm and a short-time memory neural network algorithm; the characteristic coefficients comprise input layer weight coefficients, output layer weight coefficients and bias of the long-time and short-time memory neural network algorithm.
specifically, the preset algorithm may be a neural network algorithm other than the LSMT algorithm. The characteristic coefficient may be an empirical value obtained by the server obtaining stored first data of other first devices, which are the same as the first device model and stored in the same preset working mode, from the server and performing statistical analysis on the first data of the other devices. When the preset algorithm is the LSMT algorithm, the feature coefficients are the input layer weight coefficient, the output layer weight coefficient, and the offset.
step 203, the server acquires target sample data when the first device is in a preset working mode.
Specifically, the target sample data is sample data obtained by sampling historical data sent by the server when the locally stored first device is in the preset working mode.
Step 204, the server determines the number of first training samples, the number of first training sets, the time interval and the learning rate of the first device based on the target sample data.
Specifically, the server analyzes the target sample data, determines the number of first training samples based on a method for determining the number of training samples, determines the number of first training sets based on a method for determining the number of training sets, and performs statistical analysis on the target sample data to obtain a time interval and a learning rate corresponding to the first device.
Step 205, the server trains the target sample data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training sets to obtain a second model.
specifically, the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training sets are parameters of a preset algorithm, so that the server brings the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training sets into the preset algorithm, and then performs learning training on target sample data to obtain a second model. The second model is a reference model, and can be continuously corrected according to the received first data, and is a user model, an intelligent household appliance model or a user and intelligent household appliance model.
step 206, the server generates a first model based on a preset algorithm and the first data.
wherein step 206 can be implemented by the following steps:
Step 206a, the server determines the number of second training samples and the number of second training sets of the first device based on the first data.
and step 206b, the server trains the first data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain a first model.
And step 207, if the first model is not matched with the preset second model, the server sends a prompt message for determining whether the first equipment continues to work to the second equipment.
Specifically, if the first model is matched with a second model of the pre-equipment, the server stores the first data and defaults that the first equipment continues to work.
And step 208, the server receives a control instruction which is sent by the second device and used for indicating the first device to continue working, and stores the first data.
Specifically, after seeing the prompt message sent by the server to the second device, the prompt message displayed by the second device of the user confirms whether the current work of the first device in the preset work mode is that the user controls the first device to work, if the user confirms that the current work of the first device is not that the user controls the first device to work, the user sends a control instruction which does not agree with the continuous work of the first device to the second device and forbids the continuous work of the first device, the second device sends the control instruction which forbids the continuous work of the first device to the server after receiving the control instruction which forbids the continuous work of the first device and is sent by the user, the server sends the control instruction which forbids the continuous work of the first device to the first device, the first device responds to the control instruction which forbids the continuous work of the first device, stops working, and the server discards the first data; and if the user confirms that the user controls the first equipment to work, the user sends a control instruction value server for indicating the first equipment to continue working to the second equipment, and the server stores the first data and takes the first data as target sample data so as to continuously correct the second model.
based on the foregoing embodiment, in another embodiment of the present invention, as shown in fig. 3, step 203 may be implemented by the following steps:
step 203a, the server receives data sent within a second preset time period when the first device is in the preset working mode, and obtains second data.
Specifically, the second preset time period may be a time period during which the user purchases the first device home to start using the first device, and since the first device is just bought back to use and is less likely to be attacked, the second preset time period may be an empirical value obtained by performing statistics on the time from the beginning to the beginning of attacking the intelligent appliance, that is, the second preset time period is a time period set when the first device is used by the user for the first time, for example, the second preset time period is a month when the first device starts to be used for the first time, and the corresponding first preset time period is a time period started after the first device starts to be used for the first time and the second preset time period is counted up, that is, the service life of the first device is a time period excluding the second preset time period. And in a second preset time period, the first equipment can send the data obtained when the first equipment works in the preset working mode to the server in real time or at regular time, and the server stores the data sent by the first equipment to obtain second data.
And step 203b, the server performs sampling processing on the second data to obtain first sample sub-data.
specifically, the server may sample the second data in a preset manner, for example, 6: the sampling rate of the second data between 00-8:00, 11:30-12:30 and 5:00-7:00 is higher, such as the sampling frequency is once every 30 seconds, and the sampling rate of the other time of the day except the above time is lower, such as the sampling frequency is once every 10 minutes.
step 203c, the server obtains first data stored by the server in a first preset time period to obtain second sample subdata.
The target sample data comprises first sample sub data and second sample sub data.
It should be noted that, for the explanation of the same steps or concepts in the present embodiment as in the other embodiments, reference may be made to the description in the other embodiments, and details are not described here.
The information protection method provided by the embodiment of the invention receives data, which is sent by first equipment and is in a preset working mode by the first equipment, in a first preset time period to obtain first data, generates a first model based on a preset algorithm and the first data, and sends a prompt message for determining whether the first equipment continues to work to second equipment if the first model is not matched with a preset second model. Therefore, when the server receives data sent by the first equipment when the first equipment is in the preset working mode, the first data are analyzed to generate a first model, the first model and the preset second model are matched, if the first model is not matched with the second model, the server generates prompt information and sends the prompt information to the second equipment of the user, the user can control the first equipment to continue working through the second equipment, the problem that the remote control system is easy to crack by attack behaviors such as network malicious attack and the like in the prior art is solved, the abnormal operation of the household appliance of the internet of things can be timely discovered, the user is prompted whether to allow the abnormal operation of the household appliance of the internet of things to be executed, the risk that the household appliance of the internet of things is maliciously started is reduced, and the normal work of the household appliance of the internet of things is guaranteed.
Based on the foregoing embodiments, the present invention provides an application scenario diagram of an information protection method, which is applied to a home appliance device, a deep learning server, and a terminal device such as a mobile phone that can be connected to the internet, and is described by taking the terminal device as a mobile terminal device, as shown in fig. 4, a communication link relationship between the home appliance device (a1, a2, a3, a4 … …), the deep learning server b, and the mobile terminal device c, and two-way communication between the home appliance device (a1, a2, a3, a4 … …) and the deep learning server b is possible, that is, the home appliance device (a1, a2, a3, a4 … …) may send a message to the deep learning server b, and may also receive a message sent by the deep learning server b to the home appliance device (a1, a2, a3, a4 … …); the mobile terminal device c may transmit a message to the deep learning server b, or may receive a message transmitted by the deep learning server b to the home devices (a1, a2, a3, a4 … …). Note that, the message sent by the deep learning server b by the home appliances (a1, a2, a3, and a4 … …) may be that after the deep learning server b receives the relevant control instruction about the home appliance (a1, a2, a3, or a4 … …) sent by the mobile terminal device c, the deep learning server b forwards the relevant control instruction to the home appliance (a1, a2, a3, or a4 … …).
based on the embodiment shown in fig. 4, an embodiment of the present invention provides an information protection method, including the following steps:
step 301, the deep learning server records data reported by the intelligent household appliance in detail, and obtains original data: the method comprises the steps of using a time point, cooking time duration, cooking power, an IP address of the intelligent household appliance, an Identity (ID) of a function menu, user relationship data of the intelligent household appliance, cooking interval time duration and an IP address of an application program user.
specifically, intelligent household electrical appliances are household electrical appliances with the function of cooking, and thus, the original data reported by the intelligent household electrical appliances include: the method comprises the steps that a user uses the intelligent household appliance at a time point, cooking time, cooking power, an IP address of the intelligent household appliance, an Identity (ID) of a function menu, user relation data of the intelligent household appliance, cooking interval time, an IP address of an application program user and the like. The IP address of the intelligent household appliance is the IP address of the internet connected with the intelligent household appliance, the function menu ID is an identification corresponding to a certain cooking function of the intelligent household appliance used by a user, the IP address of an application program user is the IP address of the internet connected with the application program of the user capable of remotely controlling the intelligent household appliance, the user relation data of the intelligent household appliance can be the user capable of using the intelligent household appliance, and can be the preset relation among the users capable of using the intelligent household appliance at home, for example, when one household has three persons, the users having the intelligent household appliance using the household are user 1, user 2 and user 3, and the user relation data corresponding to the intelligent household appliance can be dad, mom and me. Deep learning server pair
Step 302, the deep learning server samples the original data to form training data.
Specifically, the number of training samples (batch _ size), time interval (time _ step), and number of training sets (train _ begin, train _ end) are set, and deep learning training is performed by adjusting a specific learning rate (learn _ rate).
and step 303, forming a user and/or household appliance operation data model temp _ module by the deep learning server through deep learning and training.
it should be noted that, before the training is started, the step deep learning server needs to define the weights and biases of the input layer and the output layer, and the algorithm for performing deep learning and training may be an LSTM algorithm, or may be other neural network algorithms, which is not limited.
Specifically, the user and/or appliance operation model temp _ module is the first model.
And step 304, the deep learning server performs feedback optimization based on the time memory of the LSMT algorithm.
And 305, finally forming a user and/or household appliance behavior data model module by the deep learning server.
Specifically, the user and/or home device behavior data model is a second model. It should be noted that, when the first model is the user operation model temp _ module, the corresponding second model is the user behavior data model module; when the first model is a household appliance operation model temp _ module, the corresponding second model is a household appliance behavior data model module; and when the first model is a user and household appliance operation model temp _ module, the corresponding second model is a user and household appliance behavior data model module.
a process of obtaining a preset second model based on receiving second data in a second preset time period is shown in fig. 6, and specifically includes the following steps:
step 401, the intelligent household electrical appliance and the deep learning server start to run the information protection program.
and step 402, when the intelligent household appliance receives a control instruction for starting working within a second preset time period, the intelligent household appliance starts to operate.
step 403, the intelligent household appliance obtains third data of the use time point, the cooking time length, the cooking power, the IP address of the household appliance, the ID of the function menu, the user relationship data of the household appliance, the cooking interval time length, the IP address of the application program user, and the like of the user on the household appliance, and reports the third data to the deep learning server.
And step 404, the deep learning server accumulates third data sent by the intelligent household appliance to obtain second data, samples the second data to obtain a sample, and fills the sample into the sample data.
And 405, performing deep learning and training on the obtained sample data by the deep learning server by adopting an LSMT algorithm, and forming a user and household appliance operation model module.
And step 406, in a first preset time period, the deep learning server continues to receive the first data, continuously optimizes, adjusts and feeds back the first user and the household appliance operation model, and judges whether the first data enables the first user and the household appliance operation model to approach the optimal state.
and 407, if the first data enables the first user and the household appliance operation model not to be close to the optimal, the deep learning server removes the first data as invalid data.
and 408, if the first data enables the first user and the household appliance operation model to approach the optimal state, the deep learning server stores the first data as second data, continues to receive third data sent by the intelligent household appliance device, optimizes, adjusts and feeds back the first user and the household appliance operation model, and repeatedly executes the steps 407 and 408.
And step 409, the deep learning server finally forms a user and household appliance behavior data model.
and step 411, the intelligent household appliance and the deep learning server finish running the information protection program.
In a first preset time period, an operation process of obtaining, based on fig. 6, that a user and home appliance behavior data model module matches with a home appliance operation model temp _ module corresponding to received first data sent by an intelligent home appliance is shown in fig. 7, and specifically includes the following steps:
Step 501, the intelligent household appliance and the deep learning server start to run the information protection program.
Step 502, when the intelligent household appliance receives a control instruction for starting cooking work, reporting the operation data of the intelligent household appliance to a deep learning server in real time.
And 503, combining the data into sample data by the deep learning server, and training by adopting an LSMT algorithm to form a user and household appliance operation model temp _ module.
Step 504, the deep learning server compares the temp _ module with the module to determine whether the temp _ module is consistent with the module.
And 505, if the temp _ module does not conform to the module, the deep learning server sends active warning information to the mobile terminal equipment of the user, and prompts the user whether to allow the intelligent household appliance equipment to continue cooking to prompt the mobile terminal equipment.
step 506, the deep learning server judges the received control instruction sent by the mobile terminal device.
And 507, if the user sends a control instruction for allowing the intelligent household appliance to continue cooking to the deep learning server through the mobile terminal device, the deep learning server does not send any control instruction to the intelligent household appliance, so that the intelligent household appliance continues cooking.
And step 508, if the user sends a control instruction which does not allow the intelligent household appliance to continue cooking to the deep learning server through the mobile terminal device, the deep learning server sends a control instruction for stopping cooking to the intelligent household appliance, so that the intelligent household appliance stops cooking.
and 509, if the temp _ module conforms to the module, the deep learning server does not perform any operation, so that the household appliance continues to cook.
and step 510, the intelligent household appliance and the deep learning server finish running the information protection program.
It should be noted that, for the explanation of the same steps or concepts in the present embodiment as in the other embodiments, reference may be made to the description in the other embodiments, and details are not described here.
the information protection method provided by the embodiment of the invention receives data sent in a first preset time period when the first device is in a preset working mode, obtains first data, generates a first model based on a preset algorithm and the first data, and sends a prompt message for determining whether the first device continues to work to the second device if the first model is not matched with a preset second model. Therefore, when the server receives data sent by the first equipment when the first equipment is in the preset working mode, the first data are analyzed to generate a first model, the first model and the preset second model are matched, if the first model is not matched with the second model, the server generates prompt information and sends the prompt information to the second equipment of the user, the user can control the first equipment to continue working through the second equipment, the problem that the remote control system is easy to crack by attack behaviors such as network malicious attack and the like in the prior art is solved, the abnormal operation of the household appliance of the internet of things can be timely discovered, the user is prompted whether to allow the abnormal operation of the household appliance of the internet of things to be executed, the risk that the household appliance of the internet of things is maliciously started is reduced, and the normal work of the household appliance of the internet of things is guaranteed.
based on the foregoing embodiments, an embodiment of the present invention provides a server 6, which may be applied to an information protection method provided in the embodiments corresponding to fig. 1 to 3 and 5 to 7, and as shown in fig. 8, the server may include: a processor 61, a memory 62, and a communication bus 63, wherein:
the communication bus 63 is used for realizing connection communication between the processor and the memory;
The processor 61 is configured to execute the protection program stored in the memory 62 to implement the following steps:
Receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
generating a first model based on a preset algorithm and the first data;
And if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
in other embodiments of the present invention, before the step of sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the processor 61 is further configured to perform the following steps:
acquiring a characteristic coefficient of a preset algorithm;
Acquiring target sample data when the first equipment is in a preset working mode;
Determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first equipment based on the target sample data;
And training target sample data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training sets to obtain a second model.
In other embodiments of the present invention, after the step of sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the processor 61 is further configured to execute the following steps:
and receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
In other embodiments of the present invention, the processor 61 is further configured to perform the following steps:
receiving data sent within a second preset time period when the first equipment is in a preset working mode to obtain second data;
sampling the second data to obtain first sample sub-data;
Acquiring first data stored in a first preset time period by a server to obtain second sample subdata; the target sample data comprises first sample sub data and second sample sub data.
In other embodiments of the present invention, the processor 61 is further configured to perform the following steps:
determining a number of second training samples and a number of second training sets for the first device based on the first data;
And training the first data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain a first model.
In other embodiments of the present invention, the first data includes: the method comprises the steps of working time point, working duration, working power and working interval duration when the first equipment works in a preset working mode, an IP address of the first equipment, identification information of the preset working mode, a user identification of the first equipment and/or an IP address of the second equipment.
In other embodiments of the present invention, the predetermined algorithm comprises a long-term and short-term memory neural network algorithm;
the characteristic coefficients comprise input layer weight coefficients, output layer weight coefficients and bias of the long-time and short-time memory neural network algorithm.
It should be noted that, in the interaction process between the steps implemented by the processor in this embodiment, reference may be made to the interaction process in the information protection method provided in the embodiments corresponding to fig. 1 to 3 and 5 to 7, which is not described herein again.
the server provided by the embodiment of the invention receives data sent in a first preset time period when the first device is in a preset working mode, obtains the first data, generates the first model based on a preset algorithm and the first data, and sends a prompt message for determining whether the first device continues to work to the second device if the first model is not matched with a preset second model. Therefore, when the server receives data sent by the first equipment when the first equipment is in the preset working mode, the first data are analyzed to generate a first model, the first model and the preset second model are matched, if the first model is not matched with the second model, the server generates prompt information and sends the prompt information to the second equipment of the user, the user can control whether the first equipment continues to work or not through the second equipment, the problems that a remote control system is easy to control by a hacker and household appliances of the internet of things are easy to control by the hacker in the prior art are solved, hacker behaviors can be timely found, and when abnormal operation of household appliances of the internet of things is found, the user is prompted whether to allow the abnormal operation of the household appliances of the internet of things to be executed, and the risk that the household appliances of the internet of things are maliciously started is reduced.
Based on the foregoing embodiments, embodiments of the present invention provide a computer-readable storage medium storing one or more protection programs, the one or more protection programs being executable by one or more processors to implement the steps of:
receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
generating a first model based on a preset algorithm and the first data;
And if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
In other embodiments of the present invention, if the first model does not match the preset second model, before sending a prompt message for determining whether the first device continues to operate to the second device, the method includes:
Acquiring a characteristic coefficient of a preset algorithm;
Acquiring target sample data when the first equipment is in a preset working mode;
determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first equipment based on the target sample data;
And training target sample data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training sets to obtain a second model.
In other embodiments of the present invention, after sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the method includes:
and receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
In other embodiments of the present invention, obtaining target sample data when the first device is in the preset operating mode includes:
Receiving data sent within a first preset time period when first equipment is in a preset working mode to obtain second data;
Sampling the second data to obtain first sample sub-data;
Acquiring first data stored in a first preset time period by a server to obtain second sample subdata; the target sample data comprises first sample sub data and second sample sub data.
in other embodiments of the present invention, generating the first model based on the preset algorithm and the first data includes:
determining a number of second training samples and a number of second training sets for the first device based on the first data;
And training the first data by adopting a preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain a first model.
In other embodiments of the present invention, the first data includes: the method comprises the steps of working time point, working duration, working power and working interval duration when the first equipment works in a preset working mode, an IP address of the first equipment, identification information of the preset working mode, a user identification of the first equipment and/or an IP address of the second equipment.
In other embodiments of the present invention, the predetermined algorithm comprises a long-term and short-term memory neural network algorithm;
the characteristic coefficients comprise input layer weight coefficients, output layer weight coefficients and bias of the long-time and short-time memory neural network algorithm.
It should be noted that, in the interaction process between the steps implemented by the processor in this embodiment, reference may be made to the interaction process in the information protection method provided in the embodiments corresponding to fig. 1 to 3 and 5 to 7, which is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
the above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods described in the embodiments of the present invention.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (13)
1. An information protection method, characterized in that the method comprises:
Receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
Generating a first model based on a preset algorithm and the first data;
And if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
2. The method of claim 1, wherein before sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the method comprises:
Acquiring a characteristic coefficient of the preset algorithm;
Acquiring target sample data when the first equipment is in a preset working mode;
determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first device based on the target sample data;
and training the target sample data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training set to obtain the second model.
3. the method according to claim 1 or 2, wherein after sending a prompt message for determining whether the first device continues to operate to the second device if the first model does not match the preset second model, the method comprises:
And receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
4. The method according to claim 3, wherein the obtaining target sample data of the first device in a preset operating mode comprises:
Receiving data sent within a second preset time period when the first equipment is in a preset working mode to obtain second data;
Sampling the second data to obtain first sample sub-data;
Acquiring the first data stored in the first preset time period by the server to obtain second sample subdata; wherein the target sample data comprises the first sample sub-data and the second sample sub-data.
5. The method of claim 2, wherein generating a first model based on a predetermined algorithm and the first data comprises:
determining a number of second training samples and a number of second training sets for the first device based on the first data;
and training the first data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain the first model.
6. the method of claim 1,
The first data includes: the first device is in the working time point, the working duration, the working power and the working interval duration when the preset working mode works, the IP address of the first device, the identification information of the preset working mode, the user identification of the first device and/or the IP address of the second device.
7. The method of claim 1, 2 or 5,
The preset algorithm comprises a long-time memory neural network algorithm;
the characteristic coefficients comprise input layer weight coefficients, output layer weight coefficients and bias of the long-time memory neural network algorithm.
8. A server, characterized in that the server comprises: a processor, a memory, and a communication bus;
the communication bus is used for realizing connection communication between the processor and the memory;
The processor is configured to execute a protection program stored in the memory to implement the steps of:
receiving data sent in a first preset time period when first equipment is in a preset working mode to obtain first data;
Generating a first model based on a preset algorithm and the first data;
and if the first model is not matched with the preset second model, sending a prompt message for determining whether the first equipment continues to work to the second equipment.
9. The server according to claim 8, wherein before the step of sending a prompt message to the second device for determining whether the first device continues to operate if the first model does not match the preset second model, the processor is further configured to perform the following steps:
Acquiring a characteristic coefficient of the preset algorithm;
acquiring target sample data when the first equipment is in a preset working mode;
Determining the number of first training samples, the number of first training sets, a time interval and a learning rate of the first device based on the target sample data;
and training the target sample data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the first training samples and the number of the first training set to obtain the second model.
10. the server according to claim 8 or 9, wherein after the step of sending a prompt message to the second device for determining whether the first device continues to operate if the first model does not match the preset second model, the processor is further configured to perform the following steps:
and receiving a control instruction which is sent by the second equipment and used for indicating the first equipment to continue working, and storing the first data.
11. the server of claim 10, wherein the processor is further configured to perform the steps of:
receiving data sent within a second preset time period when the first equipment is in a preset working mode to obtain second data;
sampling the second data to obtain first sample sub-data;
acquiring the first data stored in the server in the first preset time period to obtain second sample subdata; wherein the target sample data comprises the first sample sub-data and the second sample sub-data.
12. The server of claim 9, wherein the processor is further configured to perform the steps of:
determining a number of second training samples and a number of second training sets for the first device based on the first data;
And training the first data by adopting the preset algorithm based on the characteristic coefficient, the time interval, the learning rate, the number of the second training samples and the number of the second training sets to obtain the first model.
13. A computer-readable storage medium, characterized in that a protection program is stored thereon, which, when being executed by a processor, implements the steps of the information protection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810565063.XA CN110554612A (en) | 2018-06-04 | 2018-06-04 | Information protection method, server and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810565063.XA CN110554612A (en) | 2018-06-04 | 2018-06-04 | Information protection method, server and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110554612A true CN110554612A (en) | 2019-12-10 |
Family
ID=68736063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810565063.XA Pending CN110554612A (en) | 2018-06-04 | 2018-06-04 | Information protection method, server and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110554612A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112415981A (en) * | 2020-11-10 | 2021-02-26 | 珠海格力电器股份有限公司 | Abnormal state detection method of intelligent household appliance, storage medium and computer equipment |
| CN116795066A (en) * | 2023-08-16 | 2023-09-22 | 南京德克威尔自动化有限公司 | Communication data processing method, system, server and media of remote IO module |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160205123A1 (en) * | 2015-01-08 | 2016-07-14 | Abdullah Saeed ALMURAYH | System, apparatus, and method for detecting home anomalies |
| US20160261621A1 (en) * | 2015-03-02 | 2016-09-08 | Verizon Patent And Licensing Inc. | Network threat detection and management system based on user behavior information |
| CN106230849A (en) * | 2016-08-22 | 2016-12-14 | 中国科学院信息工程研究所 | A kind of smart machine machine learning safety monitoring system based on user behavior |
| WO2017113677A1 (en) * | 2015-12-28 | 2017-07-06 | 乐视控股（北京）有限公司 | User behavior data processing method and system |
| CN106980055A (en) * | 2017-03-13 | 2017-07-25 | 东华大学 | A kind of student dormitory based on data mining electrical equipment violating the regulations uses monitoring system |
-
2018
- 2018-06-04 CN CN201810565063.XA patent/CN110554612A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160205123A1 (en) * | 2015-01-08 | 2016-07-14 | Abdullah Saeed ALMURAYH | System, apparatus, and method for detecting home anomalies |
| US20160261621A1 (en) * | 2015-03-02 | 2016-09-08 | Verizon Patent And Licensing Inc. | Network threat detection and management system based on user behavior information |
| WO2017113677A1 (en) * | 2015-12-28 | 2017-07-06 | 乐视控股（北京）有限公司 | User behavior data processing method and system |
| CN106230849A (en) * | 2016-08-22 | 2016-12-14 | 中国科学院信息工程研究所 | A kind of smart machine machine learning safety monitoring system based on user behavior |
| CN106980055A (en) * | 2017-03-13 | 2017-07-25 | 东华大学 | A kind of student dormitory based on data mining electrical equipment violating the regulations uses monitoring system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112415981A (en) * | 2020-11-10 | 2021-02-26 | 珠海格力电器股份有限公司 | Abnormal state detection method of intelligent household appliance, storage medium and computer equipment |
| CN116795066A (en) * | 2023-08-16 | 2023-09-22 | 南京德克威尔自动化有限公司 | Communication data processing method, system, server and media of remote IO module |
| CN116795066B (en) * | 2023-08-16 | 2023-10-27 | 南京德克威尔自动化有限公司 | Communication data processing method, system, server and media of remote IO module |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105871671B (en) | Method and device for controlling and acquiring uploading data of intelligent household equipment | |
| CN107991891B (en) | Method and system for adjusting environmental parameters and user equipment | |
| CN103941686B (en) | Sound control method and system | |
| CN110784906B (en) | Wireless network distribution method and device, storage medium and processor | |
| CN109947031A (en) | A kind of intelligent home equipment control method, medium, mobile terminal and device | |
| CN104991539A (en) | Smart home automated system | |
| WO2016173189A1 (en) | Smart household control method, device and system | |
| CN104009898A (en) | Household appliance and control method and device thereof | |
| CN108986807B (en) | Device control method and apparatus, storage medium, and electronic apparatus | |
| US10117258B2 (en) | Wireless channel redistribution method and apparatus | |
| CN107148072B (en) | Method and system for acquiring target resource parameters of intelligent terminal application | |
| CN103944983A (en) | Error correction method and system for voice control instruction | |
| US20160029214A1 (en) | Home control gateway and home control network connection method thereof | |
| CN110554612A (en) | Information protection method, server and computer readable storage medium | |
| CN105630456A (en) | Instruction processing method and device | |
| CN110149622B (en) | Intelligent household appliance control method and device | |
| CN108646577A (en) | A kind of client operation management method and client | |
| US9923769B2 (en) | Methods and systems for verifying installation of a device | |
| CN104317205B (en) | terminal control method and system | |
| CN112468538B (en) | Operation method and system of Internet of things equipment | |
| CN103676705A (en) | Remote power control method, system thereof and remote control platform | |
| CN105698396A (en) | Water heater, control method and device thereof and mobile communication terminal | |
| CN106060033A (en) | Intelligent home appliance control method, intelligent home appliance control system, mobile terminal and server | |
| CN107942701A (en) | appliance control system and method based on internet of things | |
| CN107560065A (en) | A kind of intelligent air-conditioner control method and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191210 |
|
| RJ01 | Rejection of invention patent application after publication |