CN110221684A

CN110221684A - Apparatus control method, system, electronic device and computer readable storage medium

Info

Publication number: CN110221684A
Application number: CN201910156093.XA
Authority: CN
Inventors: 陈刚
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2019-03-01
Filing date: 2019-03-01
Publication date: 2019-09-10

Abstract

The embodiment of the present application provides a kind of apparatus control method, system, electronic device and computer readable storage medium, is related to field of communication technology, wherein method includes that the type of the bioelectrical signals of user to be collected is determined according to current application scenarios；By acquiring biological electric signals device, determining at least one bioelectrical signals are acquired, and extract characteristic from least one bioelectrical signals of acquisition；The characteristic of extraction is inputted into classifier, to identify the intention of the user；The data that the classifier exports are converted into corresponding apparatus control instruction, and executes the apparatus control and instructs corresponding operation.The application can realize the human-computer interaction based on the fusion of multi-mode bioelectrical signals.

Description

Device control method, system, electronic device, and computer-readable storage medium

Technical Field

The present application relates to the field of communications technologies, and in particular, to a device control method, a system, an electronic device, and a computer-readable storage medium.

Background

In the traditional human-computer interaction mode in the mainstream market at present, information of a human brain is transmitted to four limbs and then to a mobile terminal, and then the information presented by the mobile terminal is fed back to the human brain to realize the human-computer interaction mode. However, on the one hand, it takes a certain time for the human consciousness to be transferred to the trunk and the limbs, and on the other hand, for some users with physical disabilities, the consciousness cannot be transferred to the mobile terminal through the trunk and the limbs, so that the mobile terminal cannot respond. Therefore, how to more efficiently transmit the awareness of people to the mobile terminal and control the mobile terminal is a big problem in the industry at present.

Disclosure of Invention

The embodiment of the application provides a device control method, a system, an electronic device and a computer readable storage medium, which can be used for realizing man-machine interaction based on multi-mode bioelectricity signal fusion.

An embodiment of the present application provides a device control method, including: determining the type of the bioelectricity signal of the user to be acquired according to the current application scene; acquiring at least one determined bioelectric signal through a bioelectric signal acquisition device, and extracting characteristic data from the acquired at least one bioelectric signal; inputting the extracted feature data into a classifier to identify the user's intent; and converting the data output by the classifier into a corresponding machine control instruction, and executing the operation corresponding to the machine control instruction.

An aspect of the embodiments of the present application further provides a device control method, where the method includes: the controlled device determines the type of the bioelectricity signal of the user to be acquired according to the current application scene and sends the determined type to the control device; the control device collects at least one bioelectricity signal according to the determined type through a bioelectricity signal collector, extracts characteristic data from the collected at least one bioelectricity signal, inputs the extracted characteristic data into a classifier to identify the intention of the user, converts the data output by the classifier into a corresponding machine control instruction, and sends the machine control instruction to the controlled device; and the controlled device responds to the machine control instruction and executes corresponding operation.

An aspect of an embodiment of the present application further provides an electronic apparatus, including: the determining module is used for determining the type of the bioelectricity signal of the user to be acquired according to the current application scene; the acquisition module is used for acquiring the determined at least one bioelectricity signal through the bioelectricity signal acquisition device and extracting characteristic data from the acquired at least one bioelectricity signal; an identification module for inputting the extracted feature data into a classifier to identify a user's intention; the conversion module is used for converting the data output by the classifier into a corresponding machine control instruction; and the execution module is used for executing the operation corresponding to the machine control instruction.

An aspect of an embodiment of the present application further provides an electronic apparatus, including: the device control method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the device control method provided by the embodiment is realized.

An aspect of the embodiments of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the apparatus control method provided in the above embodiments is implemented.

An aspect of an embodiment of the present application further provides a device control system, where the system includes: an electronic device and a signal acquisition device; the signal acquisition device includes: the device comprises a collector, a micro-processing unit, a data transmission unit and a fixing belt; the micro-processing unit is used for controlling the collector to collect at least one bioelectricity signal according to the type information of the at least one bioelectricity signal of the user to be collected, which is sent by the electronic device, and sending the collected bioelectricity signal to the electronic device through the data transmission unit after being preprocessed; the electronic device is used for determining the category information according to the current application scene and sending the category information to the signal acquisition device; and extracting feature data from the preprocessed bioelectricity signal, inputting the extracted feature data into a classifier to identify the intention of the user, converting data output by the classifier into a corresponding machine control instruction, and executing an operation corresponding to the machine control instruction.

In the embodiments, at least one bioelectricity signal matched with the current application scene is acquired according to the current application scene, the feature data is extracted from the acquired at least one bioelectricity signal, the intention of the user is identified according to the extracted feature data through the classifier and converted into the corresponding machine control instruction, so that the electronic device is controlled, and the intention identification is more targeted relative to the current application scene while the man-machine interaction based on the multi-mode bioelectricity signal fusion is realized.

Drawings

Fig. 1 is a schematic flow chart illustrating an implementation of a device control method according to an embodiment of the present application;

FIG. 2 is a schematic illustration of ERS or ERD phenomena triggered by an awareness task;

fig. 3 is a schematic diagram of a bioelectrical signal acquisition position and manner in the device control method according to the embodiment of the present application;

fig. 4 is a schematic flow chart illustrating an implementation of a device control method according to another embodiment of the present application;

fig. 5 is a schematic diagram illustrating a feature data selection method in a device control method according to an embodiment of the present application;

fig. 6 is a schematic diagram illustrating training of a classifier in the device control method according to the embodiment of the present application;

fig. 7 is a schematic timing flow chart of a device control method according to another embodiment of the present application;

fig. 8 is an interaction diagram of a device control method according to another embodiment of the present application;

fig. 9 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application;

fig. 10 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application;

FIG. 11 is a diagram of a hardware configuration of an electronic device;

fig. 12 is a schematic structural diagram of a device control system according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a signal acquisition device in a device control system according to an embodiment of the present application.

Detailed Description

In order to make the objects, features, and advantages of the present invention more apparent and understandable, the embodiments of the present invention will be described in detail and fully with reference to the accompanying drawings, in which the embodiments are described in detail. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Please refer to fig. 1, which is a schematic flow chart illustrating an implementation of a device control method according to an embodiment of the present application. The method can be applied to electronic devices, such as: the mobile terminal comprises an electronic device which can perform data processing in the moving process, such as a mobile phone, a tablet computer, an intelligent wearable device and an intelligent camera, or an electronic device which can not perform data processing in the moving process, such as an intelligent television and a desktop computer. The electronic device establishes a data transmission channel with the bioelectric signal collector in a wireless network or data line connection mode, the bioelectric signal collector is used for collecting bioelectric signals of people, and the bioelectric signal collector can be but is not limited to include: electroencephalogram, electrocardio, myoelectricity, and electrooculogram signals. As shown in fig. 1, the method mainly includes:

s101, determining the type of a bioelectrical signal of a user to be acquired according to a current application scene;

the bioelectric signal can be of various types, and in the embodiment, the bioelectric signal can specifically include, but is not limited to: brain electricity, muscle electricity, eye electricity, electrocardio, and the like. The bioelectric signal records the index of biological physiological activity with a very weak voltage signal, which is explained from the physiological mechanism level, is the electric potential formed after the synaptation of a large number of neurons, is a physical reflection that the central nervous system can be detected to the outside, and is essentially the transmembrane movement of ions, the signals are generated by hundreds of millions of neurons together, the functions of different regions are different, the generated electric potential and the characteristics are different, the electric charge is generated by the neurons, the electrodes on the scalp are conducted by electrolyte to pull or push metal electrons on the electrodes, the weak voltage difference between the electrodes is amplified by a high-precision high-performance amplifier, and the voltage which changes along with the time change is the collected bioelectric signal. Some physiological or psychological weak changes of living beings can be reflected on the bioelectric signals, for example, conscious activity, emotional changes, conscious blinking and the like of the human brain can be judged through the extracted bioelectric signal characteristics.

Taking electroencephalograms (EEG) as an example, electroencephalograms with different frequencies contain different physiological information, spontaneous electroencephalograms are bioelectricity activities which are spontaneously generated by thinking activities of cerebral cortex, specific areas of the cortex have continuous rhythmic potential changes, the brain spontaneously generates different rhythms in different consciousness states, the EEG is generally classified according to frequency bands and can be divided into delta waves, theta waves, α waves, mu waves and β waves, and specific characteristics of the five electroencephalograms are shown in table 1.

TABLE 1 EEG signals and characteristics in different frequency bands

Different bioelectricity signals can be induced by the human body when consciousness imagery is performed, the power spectrum energy of mu and beta rhythm signals of a motion functional area, an auxiliary motion area and a somatosensory area on the top of the brain can be changed by the actual limb movement of the human body or the process of imagining the limb movement of the human body, the phenomenon of the reduction of the function spectrum energy is called generation of Event-Related Desynchronization (ERD), and the phenomenon of the increase of the power spectrum energy is called generation of Event-Related Desynchronization (ERS). When the brain imagines unilateral limb movement, the primary sensory-motor cortex on the contralateral side of the brain is active, and the rhythmic activity of mu and beta is represented by the reduction of amplitude, namely the ERD phenomenon occurs, whereas, the primary sensory-motor cortex on the ipsilateral side of the brain is inhibited, and the rhythmic activity of mu and beta is represented by the increase of amplitude, which is called the ERS phenomenon. ERS or ERD belongs to spontaneous electroencephalogram, external stimulation is not needed, and spatial domain and frequency domain features are obvious. As shown in fig. 2, when a person performs an conscious task imagery, an ERS or ERD phenomenon is generated, and the main energy of a bio-signal is distributed in a specific region.

In this embodiment, the application scene may correspond to a function of an application program running in the foreground or a currently executed task. According to different application scenes, some control operations can be completed only by electroencephalogram signals, such as: unlocking the scene of the screen, and determining whether the intention of the user is left or right according to the electroencephalogram signal; some may need electroencephalogram signals and electromyogram signals to complete control operations, such as: under the scene of executing the task of monitoring whether the user is asleep, the electroencephalogram signal and the electro-oculogram signal need to be fused to determine whether the user is asleep. Therefore, under different application scenes preset in the device, the corresponding relation between the control instruction for controlling the device to execute different operations and the corresponding type of the bioelectrical signal. When the control operation is triggered, at least one bioelectric signal to be acquired is determined according to the current application scenario.

S102, collecting the determined at least one bioelectric signal through a bioelectric signal collector, and extracting characteristic data from the collected at least one bioelectric signal;

the bioelectric signals are collected by a plurality of high-sensitivity sensors, the positions of the bioelectric signals can be attached to the scalp, the eye socket, the ear and the like of a user, as shown in fig. 3, the electroencephalogram signals under the skull ③ can be collected by an electroencephalogram sensor ① placed above the scalp ②, the collected bioelectric signals are processed, characteristic data in the bioelectric signals are extracted, and the extracted characteristic data can include, but is not limited to, consciousness imagination event combination data (electroencephalogram signals), consciousness facial expression characteristic data (electromyogram signals) and consciousness blink frequency and strength data (electrooculogram signals) according to the types of the processed bioelectric signals.

S103, inputting the extracted feature data into a classifier to identify the intention of the user;

classification is the learning of a classification function or the construction of a classification model (i.e., classifier) based on existing data. The function or model can map data recorded in the database to one of the given categories and thus can be applied to data prediction. The conventional task of a classifier is to learn classification rules and classifiers using a given class, known training data, and then classify (or predict) unknown data. In this embodiment, the classifier classifies the feature data extracted from the bioelectrical signal, and the intention or behavior of the user can be recognized.

Optionally, the classifier may be obtained by training or learning according to various pre-collected bioelectrical signal samples, and the training or learning process may be completed online by the server. In practical applications, the classifier may be constructed based on Support Vector Machine (SVM) or neural network training, and in this embodiment, the specific construction manner is not limited.

And S104, converting the data output by the classifier into a corresponding machine control instruction, and executing an operation corresponding to the machine control instruction.

The data output by the classifier corresponds to the user's intent or behavior, such as: 0 represents left and 1 represents right. The device is provided with a corresponding relation between the data output by the classifier and the machine control command, and the corresponding machine control command can be determined according to the corresponding relation.

In the embodiment, at least one bioelectricity signal matched with the current application scene is acquired according to the current application scene, the feature data is extracted from the acquired at least one bioelectricity signal, the intention of the user is identified according to the extracted feature data through the classifier, and the intention is converted into the corresponding machine control instruction, so that the electronic device is controlled, and the intention identification is more targeted relative to the current application scene while the man-machine interaction based on the multi-mode bioelectricity signal fusion is realized.

Please refer to fig. 4, which is a schematic flow chart illustrating an implementation of a device control method according to another embodiment of the present application. The method can be applied to electronic devices, such as: the mobile terminal comprises an electronic device which can perform data processing in the moving process, such as a mobile phone, a tablet computer, an intelligent wearable device and an intelligent camera, or an electronic device which can not perform data processing in the moving process, such as an intelligent television and a desktop computer. The electronic device establishes a data transmission channel with the bioelectric signal collector in a wireless network or data line connection mode, the bioelectric signal collector is used for collecting bioelectric signals of people, and the bioelectric signal collector can be but is not limited to include: brain electrical, muscle electrical, and eye electrical signals. As shown in fig. 4, the method mainly includes:

s201, determining the type of a bioelectrical signal of a user to be acquired according to a current application scene;

s202, collecting at least one determined bioelectric signal through a bioelectric signal collector;

step S201 and step S202 are the same as step S101 and step S102, and reference may be specifically made to the description related to step S101 and step S102, which is not repeated herein.

S203, performing voltage amplification on the acquired at least one bioelectrical signal through a high-precision amplifier;

s204, performing frequency domain filtering on the voltage amplified bioelectricity signal;

noise interference in the bioelectrical signal can be eliminated by frequency domain filtering.

Optionally, the frequency-domain filtering is performed on the acquired bioelectrical signal, and specifically includes: eliminating industrial noise in the bioelectricity signal after voltage amplification through a wave trap; and filtering the bioelectrical signal subjected to industrial noise elimination by using a band-pass filter, wherein the band-pass filter is a finite long impulse response filter with a linear phase and is matched with the frequency characteristic of the bioelectrical signal to be filtered.

It can be understood that, the industrial frequency interference of the industrial noise to the bioelectric signal is eliminated through the wave trap, and because the bioelectric signal data can be seriously interfered by the industrial frequency noise, if the 50Hz (hertz) industrial frequency interference of the industrial noise is not eliminated, the frequency domain information of the useful signal can be completely lost.

In this embodiment, it is necessary to design different FIR (finite long impulse response) band pass filters with linear phases according to the frequency characteristics of different bioelectrical signals, such as: the frequency band of the ERD or ERS signal of the event imagination is mainly concentrated in 10 Hz-15 Hz, and in order to ensure that useful information is not lost, a band-pass filter with the frequency band slightly larger than 10 Hz-15 Hz can be selected, and the design frequency band of the band-pass filter is 5 Hz-25 Hz.

S205, performing spatial filtering on the bioelectricity signal subjected to frequency domain filtering;

the spatial filtering aims at eliminating random noise widely distributed in human bodies, highlighting useful signals of current useful leads and improving the signal-to-noise ratio.

Optionally, the average value of all transient signals of the leads is used as a reference signal, and spatial filtering is performed on the bioelectricity signal after frequency domain filtering, wherein an adopted formula is as follows:

wherein,for spatial-domain filtered signals, X_iIs the original signal before spatial filtering.

S206, evaluating whether the intensity of the bioelectricity signal after spatial filtering reaches a preset intensity;

s207, if the preset intensity is not reached, acquiring the bioelectrical signals with the intensity smaller than the preset intensity again;

s208, if the preset intensity is reached, extracting characteristic data from the bioelectricity signals subjected to spatial filtering;

it is understood that the bioelectric signal has various combination patterns according to application scenarios. In practical application, different feature forms can be selected according to different requirements of application scenes, and the basic principle of selection is that the features are obvious. Taking fig. 5 as an example, before extracting the feature data, spatial filtering and frequency filtering are performed on various bioelectric signals respectively to improve the signal-to-noise ratio of the data signal, and then the strength of the filtered bioelectric signals is evaluated. If the intensity of the bioelectric signal reaches the preset intensity, the bioelectric signal is effective, and the bioelectric signal is output to the feature extraction module so as to extract feature data from the bioelectric signal. If the intensity of the bioelectric signal does not reach the preset intensity, the bioelectric signal is invalid, and effective features cannot be extracted from the bioelectric signal, so that similar bioelectric signals are collected again.

S209, inputting the extracted feature data into a classifier to identify the intention of the user;

and inputting the feature data extracted from the acquired bioelectricity signals into a classifier, comparing the similarity of the feature data with the feature data in the sample library by the classifier, judging the user intention or behavior corresponding to the feature data to be consistent with the previously learned user intention or behavior by the classifier when the similarity of the feature data and the feature data reaches a preset similarity value, and outputting corresponding data for identifying the corresponding user intention or behavior.

And S210, converting the data output by the classifier into a corresponding machine control instruction, and executing an operation corresponding to the machine control instruction.

Step S210 is the same as step S104, and reference may be specifically made to the description related to step S104 in the embodiment shown in fig. 1, which is not repeated herein.

Optionally, in order to improve the recognition rate, the classifier may be optimally trained to obtain an optimal classifier. The specific training method comprises the following steps: collecting at least one bioelectrical signal corresponding to different intentions of a user in different application scenes as samples; extracting characteristic data from the acquired at least one bioelectrical signal; inputting the extracted feature data into a classifier for supervised classification, and judging whether the classification precision reaches a preset threshold value or not; if the classification precision reaches a threshold value, outputting an optimal classifier for user intention identification; and if the classification precision does not reach the preset value, adding the extracted feature data into a sample database, and updating the classifier. In the above-mentioned optimization training of the classifier, reference may be made to the description of step S203 to step S208 for a specific process of extracting feature data from at least one collected bioelectric signal, which is not repeated herein.

Taking fig. 6 as an example, the user may be guided to perform a special consciousness task by using a predetermined guide, the bioelectric signal of the user is collected by a sensor worn by the user, then the collected bioelectric signal is used as a sample to extract sample feature data, the extracted sample feature data is input into an existing classifier to perform supervised classification, and meanwhile, according to an output classification result, it is determined whether the classification accuracy reaches a preset threshold value, if the classification accuracy does not reach the threshold value, the classifier is updated and the sample feature data is added into a sample database, and if the accuracy reaches the threshold value, an optimal classifier is output for use when the device is used for identifying the intention of the user.

Wherein, supervised classification means that all samples used for training the classifier are labeled manually or in other ways. The classification accuracy refers to the classification accuracy, and if the classification accuracy is required to reach 95%, the learning can be stopped. And if the classification precision does not reach the threshold value, adding the characteristic data into a sample database, wherein the aim is to increase training data samples, so that the training data comprises various scenes, and a classifier learns certain boundary data.

Optionally, in order to further optimize the classifier and improve the recognition rate, feedback information input by the user when the operation is inconsistent with the intention of the user may be acquired; and updating the classifier according to the feedback information, for example, modifying the label of the characteristic data corresponding to the operation in the classifier.

Alternatively, in another embodiment of the present application, the bioelectric signal may be used for unlocking. Specifically, when a machine control instruction corresponding to data output by the classifier is used for triggering unlocking password setting operation, the electronic device outputs prompt information of a target intention for unlocking, and acquires any two first bioelectric signals of an electrooculogram, an electroencephalogram, an electrocardio and a muscle point of a user according to selection operation of the user through the bioelectric signal acquisition device; first characteristic data is extracted from the first bioelectrical signal and stored in the electronic device. The control instruction triggered by the selection operation of the user can be determined according to the data output by the classifier in the schemes from step S201 to step S209. The user can select any two bioelectric signals of the electrooculogram, the electroencephalogram, the electrocardio and the muscle point for unlocking.

Under the unblock scene, when the unblock task was triggered, through biological electricity signal collector, gather user's second biological electricity signal, the kind of second biological electricity signal is the same with first biological electricity signal, if: if the signals of the eye electricity and the brain electricity are collected when the unlocking password is set, the signals of the eye electricity and the brain electricity are also collected when the unlocking password is set. And then, extracting second characteristic data from the acquired second bioelectrical signal, matching the second characteristic data with the stored first characteristic data, and executing unlocking operation when the matching degree of the second characteristic data and the first characteristic data is greater than a preset matching degree. The unlocking operation may include, but is not limited to, unlocking a screen, unlocking a file, unlocking other functions of the electronic device, and the like. In this embodiment, the trigger condition of the unlocking task is not specifically limited, and the case where the machine control instruction obtained through steps S201 to S209 is a trigger unlocking instruction may also be included.

The device control method provided by the embodiment is independent of a human spine or peripheral nerve and muscle tissue system, does not depend on a normal four-limb access of a human, but simulates a human nerve center working system, responds to consciousness or idea of the human instead of four limbs of the human by acquiring multi-mode bioelectricity signals and translating and decoding the signals into machine control instructions, establishes a direct access between various bioelectricity signals generated by a brain and a terminal, and realizes man-machine interaction by acquiring a bioelectricity signal control device.

For details of this embodiment, reference may be made to the description of other embodiments.

Please refer to fig. 7, which is a timing flow diagram illustrating a device control method according to another embodiment of the present application. The method can be realized through interaction between a controlled device and a control device, wherein the controlled device and the control device can be electronic devices, such as: the mobile phone, the tablet computer, the intelligent wearable device, the intelligent camera and other electronic devices capable of performing data processing in the mobile, or the intelligent television, the desktop computer and other electronic devices not capable of performing data processing in the mobile. The control device establishes a data transmission channel with the bioelectric signal collector in a wireless network or data line connection mode, the bioelectric signal collector is used for collecting bioelectric signals of people, and the control device can be but is not limited to comprise: brain electrical, muscle electrical, and eye electrical signals. Alternatively, the control device may be integrated in the bioelectrical signal collector. As shown in fig. 7, the method mainly includes:

s301, the controlled device determines the type of the bioelectrical signal of the user to be acquired according to the current application scene;

s302, the controlled device sends the determined type to the control device;

s303, the control device collects at least one bioelectricity signal according to the determined type through the bioelectricity signal collector, extracts characteristic data from the collected at least one bioelectricity signal, inputs the extracted characteristic data into the classifier so as to identify the intention of the user, and converts the data output by the classifier into a corresponding machine control instruction;

step S303 may specifically refer to the related steps in the embodiment shown in fig. 4, and is not described herein again.

S304, the control device sends a machine control instruction to the controlled device;

optionally, the control device may send the machine control instruction to the controlled device through a wireless channel or a data line according to a connection manner between the control device and the controlled device.

And S305, the controlled device responds to the machine control command and executes corresponding operation.

Optionally, the classifier may be obtained by a server online learning method, and optimized training is performed. Specifically, the controlled device instruction control device acquires at least one bioelectric signal corresponding to different intentions of the user in different application scenes as samples through the bioelectric signal collector, and sends the acquired at least one bioelectric signal to the server. The server extracts feature data from at least one collected bioelectricity signal, inputs the extracted feature data into a classifier for supervised classification, judges whether the classification precision reaches a preset threshold value or not, outputs an optimal classifier if the classification precision reaches the threshold value, and sends the optimal classifier to a control device for user intention identification, and if the classification precision does not reach the threshold value, adds the extracted feature data into a sample database and updates the classifier.

Optionally, the controlled device obtains feedback information input by the user when the operation executed by the controlled device is inconsistent with the intention of the user, and sends the feedback information to the server, and the server updates the classifier according to the feedback information and sends the updated classifier to the control device for user intention identification. It is understood that the controlled device provides the user with an information feedback interface through which the user can input feedback information into the controlled device when the operation performed by the controlled device does not conform to the user's intention. Wherein the feedback information may include, but is not limited to: the real intention of the user or the real operation corresponding to the intention of the user.

To further explain the embodiment, a bioelectric signal collector integrated with a control device and a mobile terminal as a controlled device are taken as examples, as shown in fig. 8. The bioelectricity signal collector collects at least one bioelectricity signal of a user, then carries out feature extraction on the collected bioelectricity signal, inputs the extracted feature data into the optimal classifier, thereby recognizing the intention of the user, converts the intention into a machine control instruction, and then sends the machine control instruction to the mobile terminal through a wireless channel, so that the mobile terminal can execute corresponding operation and carry out visual and auditory feedback to the user. Whole process does not have traditional four limbs route to participate in, and this application is direct to translate user's bioelectricity signal into machine instruction, then transmits for mobile terminal through wireless access to accomplish the interaction, and then realize interacting with mobile terminal under the prerequisite that does not rely on normal four limbs route.

It can be understood that some special people, such as the disabled, may not be able to use the mobile terminal according to their own will, with the aid of the device control method provided by this embodiment, such vulnerable groups can be helped to regain the ability to interact with the mobile terminal, and the method can also be applied to the application scenario of the intelligent internet of things, a user can realize idea control of a home, such as a lamp, an air conditioner, etc., with the aid of the method, the user only needs to wear a bioelectricity signal acquisition device, realizes idea control of the home by decoding a bioelectricity signal mentally excited by the user idea, and does not need to control a mobile phone by four limbs to perform remote control.

Optionally, in another embodiment of the present application, the bioelectric signal may be applied to unlocking, specifically, when a machine control instruction corresponding to data output by the classifier is used to trigger an unlocking password setting operation, the controlled device outputs prompt information of a target intention for unlocking, and sends, according to a selection operation of a user, first description information of any two first bioelectric signals of an eye current, an brain current, an electrocardiogram current and a muscle point of the user to be acquired to the control device. Then, the control device collects any two first bioelectrical signals through the bioelectrical signal collector according to the first description information, extracts first characteristic data from the first bioelectrical signals, and sends the first characteristic data to the controlled device for storage, so as to be used for later unlocking.

In an unlocking scene, when an unlocking task is triggered, the controlled device sends second description information of a second bioelectric signal to the control device, wherein the type of the second bioelectric signal is the same as that of the first bioelectric signal. The control device acquires the second bioelectric signal according to the second description information through the bioelectric signal acquisition device, extracts second characteristic data from the second bioelectric signal, matches the second characteristic data with the first characteristic data, and sends an unlocking instruction to the controlled device when the matching degree of the second characteristic data and the first characteristic data is greater than a preset matching degree. The controlled device responds to the unlocking instruction and executes unlocking operation. It is understood that the first descriptive information and the second descriptive information may be identification information of a bioelectrical signal, such as: and (4) presetting codes. The above-mentioned manner of extracting the first feature data and the second feature data may specifically refer to the related description in step S203 to step S208, and is not repeated herein.

It will be appreciated that in a non-unlocking scenario, feature data extracted from the bioelectrical signal needs to be input into the classifier to identify the user's intent. Under the unlocking scene, the extracted feature data can be directly matched with the preset feature data without a classifier, so that different operations can be executed aiming at different application scenes, and the pertinence and the efficiency of data processing are improved.

It can be understood that, in practical applications, the extraction of the feature data may also be completed by the controlled device, and the specific extraction manner is similar to that of the control device, and is not described herein again.

For details of the embodiment, such as the manner of extracting the feature data, reference may be made to the related descriptions of other embodiments.

Please refer to fig. 9, which is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application. The electronic device may be used to implement the device control method shown in fig. 1 described above. As shown in fig. 9, the electronic device mainly includes: a determination module 401, an acquisition module 402, a recognition module 403, a conversion module 404, and an execution module 405.

A determining module 401, configured to determine, according to a current application scenario, a type of a bioelectrical signal of a user to be acquired;

an acquisition module 402, configured to acquire, by a bioelectrical signal acquisition device, the determined at least one bioelectrical signal, and extract feature data from the acquired at least one bioelectrical signal;

an identification module 403 for inputting the extracted feature data into a classifier to identify the intention of the user;

a conversion module 404, configured to convert the data output by the classifier into a corresponding machine control instruction;

and the execution module 405 is configured to execute an operation corresponding to the machine control instruction.

Further, the collecting module 402 is further configured to collect at least one bioelectrical signal corresponding to different intentions of the user in different application scenarios as samples, and extract feature data from the collected at least one bioelectrical signal;

the device also includes:

the classification module is used for inputting the extracted feature data into the classifier for supervised classification and judging whether the classification precision reaches a preset threshold value or not;

the output module is used for outputting an optimal classifier for user intention identification if the classification precision reaches the threshold;

and the updating module is used for adding the extracted feature data into the sample database and updating the classifier if the classification precision does not reach the threshold.

Further, the acquisition module 402 includes:

the amplifying module is used for carrying out voltage amplification on the acquired at least one bioelectricity signal through a high-precision amplifier;

the frequency domain filtering module is used for carrying out frequency domain filtering on the bioelectricity signal after the voltage amplification;

the spatial filtering module is used for carrying out spatial filtering on the bioelectricity signals after the frequency domain filtering;

and the evaluation module is used for evaluating whether the intensity of the spatial-domain filtered bioelectricity signals reaches a preset intensity, if not, re-collecting the bioelectricity signals of which the intensity is smaller than the preset intensity, and if so, extracting the characteristic data from the spatial-domain filtered bioelectricity signals.

Further, the frequency domain filtering module is specifically configured to eliminate, by a wave trap, industrial noise in the voltage-amplified bioelectrical signal; it is also particularly useful for filtering the bioelectric signal after removal of the industrial noise by means of a band-pass filter, which is a finite long impulse response filter with a linear phase and which is matched to the frequency characteristics of the bioelectric signal to be filtered.

Further, the spatial filtering module is specifically configured to perform spatial filtering on the frequency-domain filtered bioelectric signal by using an average of all lead transient signals as a reference signal, where an adopted formula is as follows:

Further, the apparatus further comprises:

the acquisition module is used for acquiring feedback information input by the user when the operation is inconsistent with the intention of the user;

the updating module is further configured to update the classifier according to the feedback information.

The specific process of each module for implementing its function may refer to the specific contents in the embodiments shown in fig. 1 to fig. 7, and is not described herein again.

Referring to fig. 10, fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

The electronic apparatus described in this embodiment includes:

a memory 501, a processor 502 and a computer program stored on the memory 501 and capable of running on the processor 502, wherein the processor 502 executes the computer program to implement the device control method described in the embodiments of fig. 1 to 6.

At least one input device 503 and at least one output device 504.

The memory 501, the processor 502, the input device 503, and the output device 504 are connected by a bus 505.

The input device 503 may be a camera, a touch panel, a physical button, or the like. The output device 504 may specifically be a touch screen.

The Memory 501 may be a high-speed Random Access Memory (RAM) Memory or a non-volatile Memory (non-volatile Memory), such as a disk Memory. The memory 501 is used for storing a set of executable program code, and the processor 502 is coupled to the memory 501.

The electronic device is externally connected with a bioelectricity signal collector.

Further, the electronic device further includes:

the high-precision amplifier is used for carrying out voltage amplification on the bioelectricity signals collected by the bioelectricity signal collector;

the wave trap is used for eliminating industrial noise in the bioelectricity signal;

the band-pass filter is used for filtering the bioelectricity signal subjected to industrial noise elimination, is a finite long impulse response filter with a linear phase, and is matched with the frequency characteristics of the bioelectricity signal to be filtered; and

and the spatial filter is used for performing spatial filtering on the bioelectricity signals after the frequency domain filtering.

Further, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium may be an electronic device configured in the foregoing embodiments, and the computer-readable storage medium may be a storage unit configured in the main control chip and the data acquisition chip in the foregoing embodiments. The computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the device control method described in the foregoing embodiments shown in fig. 1 to 6.

For example, the electronic device may be any of various types of computer system apparatuses that are mobile or portable with a flexible capacitive touch screen and perform wireless communication. In particular, the electronic apparatus may be a mobile phone or a smart phone (e.g., iPhone (TM) -based phone), a Portable game device (e.g., Nintendo (TM), PlayStation Portable (TM), Gameboy Advance (TM), iPhone (TM)), a laptop, a PDA, a Portable internet appliance, a music player, and a data storage device, other handheld devices, and a head-mounted device (HMD) such as a watch, a headset, a pendant, a headset, and the like, and may also be other wearable devices (e.g., a head-mounted device (HMD) such as electronic glasses, electronic clothing, an electronic bracelet, an electronic necklace, an electronic tattoo, an electronic device, or a smart watch).

The electronic apparatus may also be any of a number of electronic devices including, but not limited to, cellular phones, smart phones, other wireless communication devices, personal digital assistants, audio players, other media players, music recorders, video recorders, cameras, other media recorders, radios, medical devices, vehicle transportation equipment, calculators, programmable remote controllers, pagers, laptop computers, desktop computers, printers, netbook computers, Personal Digital Assistants (PDAs), Portable Multimedia Players (PMPs), moving picture experts group (MPEG-1 or MPEG-2) audio layer 3(MP3) players, portable medical devices, and digital cameras and combinations thereof.

In some cases, the electronic device may perform a variety of functions (e.g., playing music, displaying video, storing pictures, and receiving and sending telephone calls). If desired, the electronic apparatus may be a portable device such as a cellular telephone, media player, other handheld device, wristwatch device, pendant device, earpiece device, or other compact portable device.

As shown in fig. 11, the electronic device 10 may include control circuitry, which may include storage and processing circuitry 30. The storage and processing circuitry 30 may include memory, such as hard drive memory, non-volatile memory (e.g., flash memory or other electronically programmable erase limit memory used to form solid state drives, etc.), volatile memory (e.g., static or dynamic random access memory, etc.), and so forth, although the embodiments of the present application are not limited thereto. Processing circuitry in the storage and processing circuitry 30 may be used to control the operation of the electronic device 10. The processing circuitry may be implemented based on one or more microprocessors, microcontrollers, digital signal processors, baseband processors, power management units, audio codec chips, application specific integrated circuits, display driver integrated circuits, and the like.

The storage and processing circuitry 30 may be used to run software within the electronic device 10 such as, for example, an Internet browsing application, a Voice Over Internet Protocol (VOIP) telephone call application, an email application, a media playing application, operating system functions, etc. Such software may be used to perform control operations such as, for example, camera-based image capture, ambient light measurement based on an ambient light sensor, proximity sensor measurement based on a proximity sensor, information display functionality based on status indicators such as status indicator lights of light emitting diodes, touch event detection based on a touch sensor, functionality associated with displaying information on multiple (e.g., layered) displays, operations associated with performing wireless communication functions, operations associated with collecting and generating audio signals, control operations associated with collecting and processing button press event data, and other functions in the electronic device 10, and the like, without limitation of the embodiments of the present application.

The electronic device 10 may also include input-output circuitry 42. The input-output circuitry 42 may be used to enable the electronic device 10 to enable input and output of data, i.e., to allow the electronic device 10 to receive data from external devices and also to allow the electronic device 10 to output data from the electronic device 10 to external devices. The input-output circuitry 42 may further include the sensor 32. The sensors 32 may include ambient light sensors, optical and capacitive based proximity sensors, touch sensors (e.g., optical based touch sensors and/or capacitive touch sensors, where the touch sensors may be part of a touch display screen or may be used independently as a touch sensor structure), acceleration sensors, and other sensors, among others.

The input-output circuitry 42 may also include one or more displays, such as display 14. The display 14 may include one or a combination of liquid crystal displays, organic light emitting diode displays, electronic ink displays, plasma displays, displays using other display technologies. The display 14 may include an array of touch sensors (i.e., the display 14 may be a touch display screen). The touch sensor may be a capacitive touch sensor formed by a transparent touch sensor electrode (e.g., an Indium Tin Oxide (ITO) electrode) array, or may be a touch sensor formed using other touch technologies, such as acoustic wave touch, pressure sensitive touch, resistive touch, optical touch, and the like, and the embodiments of the present application are not limited thereto.

The electronic device 10 may also include an audio component 36. The audio component 36 may be used to provide audio input and output functionality for the electronic device 10. Audio components 36 in electronic device 10 may include speakers, microphones, buzzers, tone generators, and other components for generating and detecting sound.

The communication circuitry 38 may be used to provide the electronic device 10 with the ability to communicate with external devices. The communication circuit 38 may include analog and digital input-output interface circuits, and wireless communication circuits based on radio frequency signals and/or optical signals. The wireless communication circuitry in communication circuitry 38 may include radio-frequency transceiver circuitry, power amplifier circuitry, low noise amplifiers, switches, filters, and antennas. For example, the wireless Communication circuitry in Communication circuitry 38 may include circuitry to support Near Field Communication (NFC) by transmitting and receiving Near Field coupled electromagnetic signals. For example, the communication circuitry 38 may include a near field communication antenna and a near field communication transceiver. The communications circuitry 38 may also include a cellular telephone transceiver and antenna, a wireless local area network transceiver circuit and antenna, and the like.

The electronic device 10 may further include a battery, power management circuitry, and other input-output units 40. The input and output unit 40 may include buttons, joysticks, click wheels, scroll wheels, touch pads, keypads, keyboards, cameras, light emitting diodes and other status indicators, etc.

A user may input commands through the input-output circuitry 42 to control operation of the electronic device 10, and may use output data of the input-output circuitry 42 to enable receipt of status information and other outputs from the electronic device 10.

Please refer to fig. 12, which is a schematic structural diagram of a device control system according to an embodiment of the present application. As shown in fig. 12, the system includes: electronics 60 and signal acquisition device 70. The electronic device 60 may be, for example: for convenience of understanding, fig. 12 illustrates a mobile terminal as an example, where the mobile terminal is a mobile terminal capable of performing data processing in motion, such as a mobile phone, a tablet computer, a smart wearable device, and a smart camera, or other computer devices which are not capable of performing data processing in motion, such as a smart television and a desktop computer. The electronic device 60 and the signal acquisition device 70 may perform data interaction through wireless channels such as WI-FI (wireless fidelity), bluetooth, NFC (Near field communication), and the like, or may perform data interaction through data lines.

As shown in fig. 13, the signal acquisition device 70 includes: a collector 71, a Micro Control Unit (MCU) 72, a data transmission unit 73, and a fixing band 74. Optionally, the collector 71 includes: the device comprises a bioelectrical signal acquisition sensor, a high-precision amplifier, a frequency domain filter and a digital-to-analog converter. The data transmission unit 73 is a wireless transmission module, or a USB (Universal Serial Bus) module.

The collector 71 is used for collecting a bioelectrical signal of a user, and may include, but is not limited to: electro-oculogram, myoelectricity, electrocardio-electricity, electroencephalogram, etc. The fixing band 74 is used to fix the signal collecting device 70 on a portion of the human body where signal collection is required. The data transmission unit 73 is used to transmit the bioelectric signal to the electronic device 60.

And the micro-processing unit 72 is configured to control the collector 71 to collect at least one bioelectric signal according to the type information of the at least one bioelectric signal of the user to be collected, which is sent by the electronic device 60, and send the collected bioelectric signal to the electronic device 60 through the data transmission unit 93 after preprocessing. Wherein the pre-treatment may include, but is not limited to: voltage amplification, frequency domain, spatial filtering, digital-to-analog conversion, and the like. For a specific preprocessing process, reference may be made to the related descriptions from step S204 to step S206 in the embodiment shown in fig. 4, which are not described herein again.

The structure of the electronic device 60 can specifically refer to the embodiment shown in fig. 10, and is not described herein again. The electronic device 60 is used for determining the category information according to the current application scene and sending the category information to the signal acquisition device 70; and extracting feature data from the preprocessed bioelectrical signal, inputting the extracted feature data into a classifier to recognize the intention of the user, converting data output by the classifier into a corresponding machine control instruction, and executing an operation corresponding to the machine control instruction.

Further, the system may be applied to unlocking, and specifically, when the machine control instruction is used to trigger an unlocking password setting operation, the electronic device 60 is further configured to output prompt information of a target intention for unlocking, and send, according to a selection operation of the user, first description information of any two first bioelectric signals of an electrooculogram, an electroencephalogram, an electrocardiograph, and a muscle point of the user to be acquired to the signal acquisition device 70.

The micro-processing unit 72 is further configured to control the collector 71 to collect and pre-process the two arbitrary first bioelectrical signals according to the first description information, and send the pre-processed first bioelectrical signals to the electronic device 60 through the data transmission unit 93.

The electronic device 60 is further configured to extract and store first feature data from the preprocessed first bioelectrical signal.

When the current application scenario is an unlocking scenario and the unlocking task is triggered, the electronic device 60 is further configured to send second description information of a second bioelectric signal to the signal acquisition device 70, where the type of the second bioelectric signal is the same as that of the first bioelectric signal.

The micro-processing unit 72 is further configured to control the collector 71 to collect and pre-process the second bioelectric signal according to the second description information, and send the pre-processed second bioelectric signal to the electronic device 60 through the data transmission unit 93.

The electronic device 60 is further configured to extract second feature data from the second bioelectrical signal, match the second feature data with the first feature data, and perform an unlocking operation when a matching degree of the second feature data with the first feature data is greater than a preset matching degree.

It will be appreciated that the user needs to save the user's bioelectrical signal template at the first use. Taking a smart phone as an example, specifically, after the user wears the signal acquisition device, the user is prompted to perform an awareness task (i.e., a target intention) on the screen of the smart phone for a period of time to induce a specific bio-electrical signal, and the awareness task includes, but is not limited to, according to the user's customized selection: at least two of the operations of consciousness imagination, consciousness blink, consciousness facial expression, consciousness heartbeat and the like. Meanwhile, the smart phone instruction signal acquisition device acquires at least two bioelectricity signals selected by a user, the signal acquisition device acquires bioelectricity signals (analog signals) of the user through a bioelectricity signal acquisition sensor, then voltage amplification is carried out on the acquired bioelectricity signals through a high-precision amplifier, the amplified voltages are filtered in a frequency domain and a space domain to filter noise waves so as to improve the signal-to-noise ratio of the signals, and then the analog signals are converted into digital signals through a digital-analog converter and then transmitted to the smart phone through a wireless transmission module. And the smart phone extracts multi-dimensional signal characteristics from the bioelectricity signals sent by the signal acquisition device and stores the multi-dimensional signal characteristics in a template. After the user wears the signal acquisition device for the second time, the same biological electric signal can be induced by performing the same consciousness task as the first time, the multi-dimensional features extracted after the signal is processed are matched with the first template, and the user is considered as the same user and unlocks the mobile phone after the similarity reaches a certain threshold value.

Further, the system also comprises a server which is used for constructing the classifier and carrying out optimization training and updating on the classifier.

Specifically, the classifier can be obtained by a server online learning method and optimized training is performed. The electronic device 60 instructs the signal acquisition device 70 to acquire at least one bioelectric signal corresponding to different intentions of the user in different application scenes as samples, and transmits the acquired at least one bioelectric signal to the server. The server extracts feature data from at least one bioelectric signal sent by at least one electronic device 60, inputs the extracted feature data into a classifier for supervised classification, judges whether the classification accuracy reaches a preset threshold value, outputs an optimal classifier if the classification accuracy reaches the threshold value, and sends the optimal classifier to the control device for user intention identification, and if the classification accuracy does not reach the threshold value, adds the extracted feature data into a sample database and updates the classifier.

Optionally, the electronic device 60 obtains feedback information input by the user when the operation performed by the electronic device 60 does not conform to the intention of the user, and sends the feedback information to the server, and the server updates the classifier according to the feedback information and sends the updated classifier to the electronic device 60 for user intention identification. It will be appreciated that the electronic device 60 provides the user with an information feedback interface through which the user can input feedback information into the electronic device 60 when the operation performed by the electronic device 60 does not correspond to the user's intent. Wherein the feedback information may include, but is not limited to: the real intention of the user or the real operation corresponding to the intention of the user.

Optionally, the above-mentioned construction, optimization training and updating of the classifier can also be completed by the electronic device 60.

In the embodiment, at least one bioelectricity signal matched with the current application scene is acquired according to the current application scene, the feature data is extracted from the acquired at least one bioelectricity signal, the intention of the user is identified according to the extracted feature data through the classifier, and the intention is converted into the corresponding machine control instruction, so that the electronic device is controlled, and the intention identification is more targeted relative to the current application scene while the man-machine interaction based on the multi-mode bioelectricity signal fusion is realized. Further, when the device control system is applied to unlocking, due to the fact that the electronic device can be unlocked rapidly through the bioelectricity signal, the process can be completely independent of two hands, and conscious task content during unlocking cannot be observed by other people, and therefore the device control system has high safety.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules or components may be combined or integrated into another system, or some feature data may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a readable storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned readable storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In view of the above description of the device control method, system, electronic device and computer-readable storage medium provided by the present application, those skilled in the art will recognize that there may be variations in the embodiments and applications of the method and system provided by the present application.

Claims

1. A device control method applied to an electronic device is characterized by comprising the following steps:

determining the type of the bioelectricity signal of the user to be acquired according to the current application scene;

acquiring at least one determined bioelectric signal through a bioelectric signal acquisition device, and extracting characteristic data from the acquired at least one bioelectric signal;

inputting the extracted feature data into a classifier to identify the user's intent;

and converting the data output by the classifier into a corresponding machine control instruction, and executing the operation corresponding to the machine control instruction.

2. The method of claim 1, wherein the method further comprises:

acquiring at least one bioelectrical signal corresponding to different intentions of the user in different application scenes as samples;

extracting characteristic data from the acquired at least one bioelectrical signal;

inputting the extracted feature data into the classifier to perform supervised classification, and judging whether the classification precision reaches a preset threshold value;

if the classification precision reaches the threshold value, outputting an optimal classifier for user intention identification;

and if the classification precision does not reach the threshold value, adding the extracted feature data into a sample database, and updating the classifier.

3. The method according to claim 2, wherein said extracting characteristic data from the acquired at least one bioelectrical signal comprises:

performing voltage amplification on the acquired at least one bioelectrical signal through a high-precision amplifier;

carrying out frequency domain filtering on the bioelectricity signal after voltage amplification;

performing spatial filtering on the bioelectricity signal after the frequency domain filtering;

evaluating whether the intensity of the bioelectrical signal after spatial filtering reaches a preset intensity;

if the preset intensity is not reached, acquiring the bioelectrical signals with the intensity smaller than the preset intensity again;

and if the preset intensity is reached, extracting the characteristic data from the bioelectricity signals after spatial filtering.

4. The method according to claim 3, wherein the frequency-domain filtering of the voltage-amplified bioelectrical signal comprises:

eliminating industrial noise in the voltage amplified bioelectricity signal through a wave trap;

and filtering the bioelectrical signal subjected to industrial noise elimination through a band-pass filter, wherein the band-pass filter is a finite long impulse response filter with a linear phase, and the band-pass filter is matched with the frequency characteristics of the bioelectrical signal to be filtered.

5. The method according to claim 3, wherein the spatial filtering of the frequency domain filtered bioelectrical signal comprises:

taking the mean value of all the transient signals of the leads as a reference signal, and carrying out spatial filtering on the bioelectricity signals after frequency domain filtering, wherein the adopted formula is as follows:

6. The method of claim 1, wherein the method further comprises:

acquiring feedback information input by the user when the operation is inconsistent with the intention of the user;

and updating the classifier according to the feedback information.

7. The method according to any one of claims 1 to 6, wherein when the machine control instruction is used to trigger an unlock password setting operation, the executing an operation corresponding to the machine control instruction specifically includes:

outputting prompt information of target intention for unlocking, and acquiring any two first bioelectricity signals of the eye, brain, electrocardio and muscle points of the user according to the selection operation of the user through the bioelectricity signal acquisition device;

extracting first characteristic data from the first bioelectrical signal and storing the first characteristic data in the electronic device;

when the current application scene is an unlocking scene, the method further comprises:

when an unlocking task is triggered, acquiring a second bioelectric signal of the user through the bioelectric signal collector, wherein the type of the second bioelectric signal is the same as that of the first bioelectric signal;

and extracting second characteristic data from the second bioelectrical signal, and executing unlocking operation when the matching degree of the second characteristic data and the first characteristic data is greater than a preset matching degree.

8. A device control method, characterized in that the method comprises:

the controlled device determines the type of the bioelectricity signal of the user to be acquired according to the current application scene and sends the determined type information to the control device;

the control device collects at least one bioelectricity signal according to the determined type information through a bioelectricity signal collector, extracts characteristic data from the collected at least one bioelectricity signal, inputs the extracted characteristic data into a classifier to identify the intention of the user, converts the data output by the classifier into a corresponding machine control instruction, and sends the machine control instruction to the controlled device;

and the controlled device responds to the machine control instruction and executes corresponding operation.

9. The method of claim 8, wherein the method further comprises:

the controlled device instructs the control device to collect at least one bioelectric signal corresponding to different intentions of the user in different application scenes as samples through a bioelectric signal collector and send the collected at least one bioelectric signal to a server;

the server extracts feature data from the acquired at least one bioelectricity signal, inputs the extracted feature data into the classifier for supervised classification, judges whether the classification precision reaches a preset threshold value, outputs an optimal classifier if the classification precision reaches the threshold value, and sends the optimal classifier to the control device for user intention identification, and adds the extracted feature data into a sample database if the classification precision does not reach the threshold value, and updates the classifier.

10. The method of claim 9, wherein the method further comprises:

the controlled device acquires feedback information input by the user when the operation is inconsistent with the intention of the user, and sends the feedback information to the server;

and the server updates the classifier according to the feedback information and sends the updated classifier to the control device.

11. The method of claim 8, wherein when the machine control instruction is used to trigger an unlock password setting operation, the controlled device, in response to the machine control instruction, performs a corresponding operation, specifically including:

the controlled device outputs prompt information of target intention for unlocking, and sends first description information of any two first bioelectric signals of the user to be acquired, namely the electrooculogram, the electroencephalogram, the electrocardio and the muscle point to the control device according to the selection operation of the user;

the control device acquires any two first bioelectrical signals through the bioelectrical signal collector according to the first description information, extracts first characteristic data from the first bioelectrical signals, and sends the first characteristic data to the controlled device for storage;

when the unlocking task is triggered, the controlled device sends second description information of a second bioelectric signal to the control device, wherein the type of the second bioelectric signal is the same as that of the first bioelectric signal;

the control device acquires a second bioelectric signal according to the second description information through the bioelectric signal collector, extracts second characteristic data from the second bioelectric signal, matches the second characteristic data with the first characteristic data, and sends an unlocking instruction to the controlled device when the matching degree of the second characteristic data and the first characteristic data is greater than a preset matching degree;

and the controlled device responds to the unlocking instruction and executes unlocking operation.

12. An electronic device, the device comprising:

the determining module is used for determining the type of the bioelectricity signal of the user to be acquired according to the current application scene;

the acquisition module is used for acquiring the determined at least one bioelectricity signal through the bioelectricity signal acquisition device and extracting characteristic data from the acquired at least one bioelectricity signal;

an identification module for inputting the extracted feature data into a classifier to identify a user's intention;

the conversion module is used for converting the data output by the classifier into a corresponding machine control instruction;

and the execution module is used for executing the operation corresponding to the machine control instruction.

13. An electronic device having a touch screen, the electronic device comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the device control method according to any one of claims 1 to 7 when executing the computer program.

14. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing the apparatus control method according to any one of claims 1 to 7.

15. A device control system, the system comprising: an electronic device and a signal acquisition device;

the signal acquisition device includes: the device comprises a collector, a micro-processing unit, a data transmission unit and a fixing belt;

the micro-processing unit is used for controlling the collector to collect at least one bioelectricity signal according to the type information of the at least one bioelectricity signal of the user to be collected, which is sent by the electronic device, and sending the collected bioelectricity signal to the electronic device through the data transmission unit after being preprocessed;

the electronic device is used for determining the category information according to the current application scene and sending the category information to the signal acquisition device; and extracting feature data from the preprocessed bioelectricity signal, inputting the extracted feature data into a classifier to identify the intention of the user, converting data output by the classifier into a corresponding machine control instruction, and executing an operation corresponding to the machine control instruction.

16. The system of claim 15,

when the machine control instruction is used for triggering unlocking password setting operation, the electronic device is further used for outputting prompt information of a target intention for unlocking, and sending first description information of any two first bioelectric signals of the eye, brain, heart and muscle points of the user to be acquired to the signal acquisition device according to the selection operation of the user;

the micro-processing unit is further used for controlling the collector to collect any two first bioelectrical signals according to the first description information, preprocessing the collected two first bioelectrical signals and sending the preprocessed first bioelectrical signals to the electronic device through the data transmission unit;

the electronic device is also used for extracting and storing first characteristic data from the preprocessed first bioelectrical signal;

when the current application scene is an unlocking scene and an unlocking task is triggered, the electronic device is further used for sending second description information of a second bioelectric signal to the signal acquisition device, wherein the type of the second bioelectric signal is the same as that of the first bioelectric signal;

the micro-processing unit is further used for controlling the collector to collect and pre-process the second bioelectric signal according to the second description information, and sending the pre-processed second bioelectric signal to the electronic device through the data transmission unit;

the electronic device is further used for extracting second feature data from the second bioelectrical signal, matching the second feature data with the first feature data, and executing unlocking operation when the matching degree of the second feature data with the first feature data is larger than a preset matching degree.