CN115153985B - Control method, device and terminal of intelligent artificial limb and computer readable storage medium - Google Patents
Control method, device and terminal of intelligent artificial limb and computer readable storage medium Download PDFInfo
- Publication number
- CN115153985B CN115153985B CN202211095379.XA CN202211095379A CN115153985B CN 115153985 B CN115153985 B CN 115153985B CN 202211095379 A CN202211095379 A CN 202211095379A CN 115153985 B CN115153985 B CN 115153985B
- Authority
- CN
- China
- Prior art keywords
- action
- electromyographic signal
- standard
- duration
- target
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/50—Prostheses not implantable in the body
- A61F2/68—Operating or control means
- A61F2/70—Operating or control means electrical
- A61F2/72—Bioelectric control, e.g. myoelectric
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/251—Means for maintaining electrode contact with the body
- A61B5/256—Wearable electrodes, e.g. having straps or bands
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/296—Bioelectric electrodes therefor specially adapted for particular uses for electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
Abstract
The invention provides a control method, a control device, a control terminal and a computer readable storage medium of an intelligent artificial limb, wherein the method comprises the steps of acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal; acquiring a first action time length corresponding to a first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold; when the first action duration is greater than a first duration threshold, executing and locking the first action; and acquiring a second electromyographic signal and a preset second duration threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second duration threshold, and executing a second action corresponding to the second electromyographic signal. When the intelligent artificial limb executes the action with longer action time, the action is locked, the electromyographic signals are continuously analyzed, and the intelligent artificial limb can be unlocked when the duration of the next electromyographic signal is longer, so that the control stability of the intelligent artificial limb is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a control method, a control device, a control terminal and a computer readable storage medium of an intelligent artificial limb.
Background
Surface electromyographic signals are a complex combination of sub-epidermal electromyographic activity at the skin surface, which can be collected by surface electrodes. The intelligent artificial limb can be controlled through the electromyographic signals of the wearer, the movement intention of the wearer is identified through extracting the electromyographic signals of the wearer, and the movement intention is converted into the movement of the intelligent artificial limb.
Because the electromyographic signals are generated based on the brain activity of a wearer, when a user controls the intelligent artificial limb through the electromyographic signals, the electromyographic signals fluctuate due to inattention or other factors, so that the attention of the user is hard to keep special attention of the specific electromyographic signals for a long time, once the user is distracted, other control signals are possibly detected, the electromyographic signals generated by muscles are disconnected, misoperation is caused, and the control stability of the intelligent artificial limb is poor.
Therefore, the prior art has defects and needs to be improved and developed.
Disclosure of Invention
The present invention provides a method, an apparatus, a terminal and a computer readable storage medium for controlling an intelligent prosthesis, aiming to solve the problem of poor control stability of the intelligent prosthesis in the prior art.
The technical scheme adopted by the invention for solving the technical problem is as follows:
in a first aspect, an embodiment of the present invention provides a control method for an intelligent prosthesis, where the method includes:
acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal;
acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold;
when the first action duration is greater than the first duration threshold, executing and locking the first action;
and acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal.
In one embodiment, the control method of the intelligent prosthesis further comprises:
a standard action database is stored in advance, and the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals.
In one embodiment, acquiring a first electromyographic signal, determining a first action from the first electromyographic signal, comprises:
acquiring a first electromyographic signal, and searching the standard action database;
matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
and obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation, and taking the first target standard action as a first action.
In one embodiment, the standard action database further includes: the action duration and a second corresponding relation between the standard action and the action duration;
acquiring a first action duration corresponding to the first action and a preset first duration threshold, and comparing the first action duration with the first duration threshold, including:
searching the second corresponding relation according to the first target standard action to obtain a target action duration corresponding to the first target standard action, and taking the target action duration as a first action duration;
comparing the first action duration to the first duration threshold.
In one embodiment, the acquiring the second electromyographic signal and a preset second time threshold, unlocking the first action and executing a second action corresponding to the second electromyographic signal when the duration of the second electromyographic signal is greater than the second time threshold, includes:
acquiring a second electromyographic signal and a preset second time length threshold;
when the duration time of the second electromyographic signal is greater than the second duration threshold, searching the standard action database;
matching the second electromyographic signal with the standard electromyographic signal, and taking the successfully matched standard electromyographic signal as a second target electromyographic signal;
obtaining a second target standard action corresponding to the second target electromyographic signal according to the first corresponding relation, and taking the second target standard action as a second action;
and unlocking the first action and executing the second action.
In one embodiment, matching the second electromyographic signal with the standard electromyographic signal, and using the successfully matched standard electromyographic signal as a second target electromyographic signal includes:
matching the second electromyographic signal with the standard electromyographic signal;
acquiring a similarity result between the second electromyographic signal and the successfully matched standard electromyographic signal;
and acquiring a preset similarity threshold, and when the similarity result is greater than the similarity threshold, taking the successfully matched standard electromyographic signal as a second target electromyographic signal.
In one embodiment, when the first action duration is greater than the first duration threshold, after the first action is executed and locked, the method further includes:
controlling an IMU to detect motion data, and analyzing according to the motion data to obtain the attitude action of the intelligent artificial limb in a three-dimensional space;
acquiring a preset unlocking action, and matching the gesture action with the unlocking action;
when the gesture action is successfully matched with the unlocking action, a unlocking instruction is generated;
and unlocking the first action according to the unlocking instruction.
In a second aspect, an embodiment of the present invention further provides a control device for an intelligent prosthesis, including:
the acquisition module is used for acquiring a first electromyographic signal and determining a first action according to the first electromyographic signal;
the comparison module is used for acquiring a first action time length corresponding to the first action and a preset first time length threshold value, and comparing the first action time length with the first time length threshold value;
the locking module is used for executing and locking the first action when the first action duration is greater than the first duration threshold;
the unlocking module is used for acquiring a second electromyographic signal and a preset second duration threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second duration threshold, and executing a second action corresponding to the second electromyographic signal.
In a third aspect, an embodiment of the present invention further provides a terminal, including: the intelligent artificial limb control method comprises a memory, a processor and a control program of the intelligent artificial limb, wherein the control program of the intelligent artificial limb is stored on the memory and can run on the processor, and the steps of the control method of the intelligent artificial limb are realized when the control program of the intelligent artificial limb is executed by the processor.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, which stores a computer program, where the computer program can be executed to implement the steps of the control method for an intelligent prosthesis described above.
The invention has the beneficial effects that: according to the embodiment of the invention, a first action is determined according to a first electromyographic signal by acquiring the first electromyographic signal; acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold; when the first action duration is greater than the first duration threshold, executing and locking the first action; and acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal. When the intelligent artificial limb performs the action with long action time, the action is locked, the electromyographic signals are continuously analyzed, and the intelligent artificial limb can be unlocked when the next electromyographic signal lasts for a long time, so that misjudgment caused by fluctuation of the electromyographic signals due to inational attention of a wearer of the intelligent artificial limb is avoided, and the control stability of the intelligent artificial limb is improved.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the control method of the intelligent artificial limb of the invention.
Fig. 2 is a functional block diagram of a preferred embodiment of the control device for an intelligent prosthesis according to the present invention.
Fig. 3 is a functional block diagram of a preferred embodiment of the terminal of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Because the electromyographic signals are generated based on the brain activity of a wearer, when a user controls the intelligent artificial limb through the electromyographic signals, the electromyographic signals fluctuate due to inattention or other factors, so that the attention of the user is hard to keep special attention of the specific electromyographic signals for a long time, once the user is distracted, other control signals are possibly detected, the electromyographic signals generated by muscles are disconnected, misoperation is caused, and the control stability of the intelligent artificial limb is poor.
In view of the above-mentioned drawbacks of the prior art, the present invention provides a method for controlling an intelligent prosthesis, which determines a first action according to a first electromyographic signal by acquiring the first electromyographic signal; acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold; when the first action duration is greater than the first duration threshold, executing and locking the first action; and acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal. When the intelligent artificial limb performs the action with longer action time, the action is locked, the electromyographic signals are continuously analyzed, and the intelligent artificial limb can be unlocked when the next electromyographic signal lasts for longer time, so that misjudgment caused by fluctuation of the electromyographic signals due to inational force inattention of a wearer of the intelligent artificial limb is avoided, and the control stability of the intelligent artificial limb is improved.
Referring to fig. 1, a control method of an intelligent prosthesis according to an embodiment of the present invention includes the following steps:
step S100, acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal.
Specifically, the first electromyographic signal may be any electromyographic signal acquired by an intelligent prosthesis. When the user wears the intelligent artificial limb and the brain generates movement intention, the peripheral nervous system is excited, and the muscle action potential is induced through nerves. Myoelectric induction sensors on the intelligent artificial limbs can detect myoelectric signals generated by muscles of users, so that different actions can be performed according to different myoelectric signals, namely corresponding actions can be performed according to different movement intentions.
In one implementation, the control method of the intelligent prosthesis further includes: a standard action database is stored in advance, and the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals.
Specifically, in order to improve the efficiency of acquiring the execution action, the present embodiment establishes a standard action database in advance, where the standard action database includes a first corresponding relationship between a standard action and a standard electromyographic signal. When the myoelectric induction sensor on the intelligent artificial limb collects any myoelectric signal, the first corresponding relation in the standard action database can be searched, so that the standard action corresponding to the myoelectric signal is obtained, and the intelligent artificial limb can execute the standard action. According to the embodiment, the corresponding standard action can be directly searched after the electromyographic signals are collected, so that the standard action is executed without a complex calculation process, the action execution efficiency is improved, and the action delay time is effectively shortened.
In one implementation, the step S100 specifically includes:
step S110, acquiring a first electromyographic signal, and searching the standard action database;
step S120, matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
step S130, obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation, and taking the first target standard action as a first action.
Specifically, in this embodiment, when the intelligent prosthesis acquires the first electromyographic signal acquired by the electromyographic induction sensor, the first electromyographic signal needs to be matched with the standard electromyographic signal in the standard action database, the matching rule may be to calculate the signal feature similarity between the first electromyographic signal and the standard electromyographic signal, and the criterion of successful matching is that the signal feature similarity is the highest. That is, the standard electromyographic signal with the highest signal characteristic similarity is used as the first target electromyographic signal matched with the first electromyographic signal, so that the first target standard action corresponding to the first target electromyographic signal is found, and the first target standard action is executed as the first action. According to the embodiment, the successfully matched standard electromyographic signal is used as the first target electromyographic signal, so that the first target standard action corresponding to the first target electromyographic signal is found, the accuracy of electromyographic signal identification is improved, and the action which the user wants to execute can be executed.
As shown in fig. 1, the control method of the intelligent prosthesis further includes the following steps:
step S200, obtaining a first action time length corresponding to the first action and a preset first time length threshold value, and comparing the first action time length with the first time length threshold value.
Specifically, when the intelligent prosthesis completes actions, the corresponding action duration of each action in the operation process is also different. For example, when a user uses the intelligent artificial limb to take up a cup to drink water, the intelligent artificial limb is required to complete the action of gripping the cup, and a long time is required to complete the whole water drinking action. However, the user's concentration may not be maintained all the time, and the myoelectric signal corresponding to the action may be disconnected, resulting in an operation error. In order to avoid misoperation, the first time threshold is preset in the embodiment and is used for judging whether the action time required by the current action is too long, if so, the intelligent artificial limb locks the action, and the effect of continuously keeping the action can be achieved without the need of keeping the attention of the user for a long time, so that convenience is brought to the user.
In one implementation, the standard action database further includes: an action duration, and a second correspondence between the standard action and the action duration. The step S200 specifically includes:
step S210, searching the second corresponding relation according to the first target standard action to obtain a target action duration corresponding to the first target standard action, and taking the target action duration as a first action duration;
step S220, comparing the first action duration with the first duration threshold.
Specifically, the standard motion database is constructed at the stage of the wearer registering to use the intelligent prosthesis. In the registration stage, electromyographic signals induced when the brain of a wearer generates movement intentions corresponding to various actions are collected, the duration time of each electromyographic signal is detected, and action duration corresponding to standard actions is generated according to the duration time of the electromyographic signals. Therefore, when the intelligent artificial limb obtains the first electromyographic signal, the first corresponding relation is searched for firstly to obtain the first action corresponding to the first electromyographic signal, and then the second corresponding relation is searched for to obtain the corresponding action duration, so that the action duration obtaining efficiency is improved, and the reaction time of the intelligent artificial limb can be shortened.
As shown in fig. 1, the control method of the intelligent prosthesis further includes the following steps:
and step S300, when the first action duration is greater than the first duration threshold, executing and locking the first action.
Specifically, when the first action duration is greater than the first duration threshold, the action cannot be completed in a short time, and at this time, the intelligent prosthesis performs the action and locks the action. For example, the first time threshold value is preset to be 5s, when the electromyographic signals collected by the intelligent artificial limb correspond to the action of gripping the water cup, the action time of the action of gripping the water cup is found to be 7s, at the moment, the intelligent artificial limb performs the action of gripping the water cup and locks the action of gripping the water cup, and therefore, in the process of drinking water by a user, even if the user does not keep the concentration, the action of gripping the water cup can be still kept, and action errors can not be caused. The embodiment enables the user to achieve the effect of continuously keeping the action without keeping the attention for a long time through the locking action, brings convenience to the user and improves the control stability of the intelligent artificial limb.
It is understood that if the first action duration is less than or equal to the first duration threshold, the action may be completed in a short time, and thus, the action is performed but not locked.
As shown in fig. 1, the control method of the intelligent prosthesis further includes the following steps:
step S400, a second electromyographic signal and a preset second duration threshold are obtained, when the duration time of the second electromyographic signal is longer than the second duration threshold, the first action is unlocked, and a second action corresponding to the second electromyographic signal is executed.
Specifically, during the locking of the first action, the electromyographic signals are continuously detected, and if other electromyographic signals, namely the second electromyographic signal, are detected, the embodiment needs to be judged to determine whether to execute the second action corresponding to the second electromyographic signal. Since the intelligent artificial limb locks the first action, if other electromyographic signals appear in the period, the electromyographic signals may fluctuate due to insufficient attention of the user, and the user may want to perform the next action. In this embodiment, a second duration threshold is preset, and when the duration of the second electromyographic signal is less than or equal to the second duration threshold, it indicates that the second electromyographic signal is short-time, and may be fluctuation of the electromyographic signal caused by insufficient attention of the user, and at this time, the intelligent artificial limb is not unlocked; when the duration of the second electromyogram signal is greater than the second duration threshold, it may be determined that this is an action that the user wants to perform very much, not an electromyogram signal fluctuation caused by insufficient concentration, and thus, the lock is released and the second action is performed.
In one implementation, the step S400 specifically includes:
step S410, acquiring a second electromyographic signal and a preset second time length threshold;
step S420, when the duration time of the second electromyographic signal is greater than the second duration threshold, searching the standard action database;
step S430, matching the second electromyographic signal with the standard electromyographic signal, and taking the successfully matched standard electromyographic signal as a second target electromyographic signal;
step S440, obtaining a second target standard action corresponding to the second target electromyographic signal according to the first corresponding relation, and taking the second target standard action as a second action;
and S450, unlocking the first action and executing the second action.
Specifically, when the duration of the second electromyographic signal is greater than a second duration threshold, it may be determined that the second electromyographic signal is an electromyographic signal generated by the movement intention of the user, and the duration of the second electromyographic signal is an expression of confirmation by the user. That is, when the user wants to unlock and perform the next action, the user only needs to last for a time greater than the second duration threshold. And matching the second electromyographic signal with the standard electromyographic signal, wherein the matching rule still can be that the signal characteristic similarity between the second electromyographic signal and the standard electromyographic signal is calculated, the standard of successful matching is that the signal characteristic similarity is highest, the electromyographic signal with the highest signal characteristic similarity is taken as a second target electromyographic signal matched with the second electromyographic signal, so that a second target standard action corresponding to the second target electromyographic signal is searched, and the second target standard action is taken as a second action. And after the second action is obtained, unlocking the first action and executing the second action. According to the embodiment, the user actively confirms the next electromyographic signal, namely, the electromyographic signal with the duration is generated, the successfully matched standard electromyographic signal is used as the second target electromyographic signal, and the second target standard action corresponding to the second target electromyographic signal is searched, so that the accuracy of electromyographic signal identification is improved, and the next action which the user wants to execute can be executed.
In an implementation manner, the step S430 specifically includes:
step S431, matching the second electromyographic signal with the standard electromyographic signal;
step S432, obtaining a similarity result between the second electromyographic signal and the successfully matched standard electromyographic signal;
and S433, acquiring a preset similarity threshold, and when the similarity result is greater than the similarity threshold, taking the successfully matched standard electromyographic signal as a second target electromyographic signal.
Specifically, in order to further prevent the second electromyographic signal from fluctuating due to inattention of the user, a similarity threshold is preset in this embodiment, that is, the successfully matched standard electromyographic signal is only the electromyographic signal with the highest similarity among all the standard electromyographic signals, the embodiment may obtain a similarity result between the standard electromyographic signal with the highest similarity and the second electromyographic signal, compare the similarity result with the similarity threshold, and if the similarity result is greater than the similarity threshold, it indicates that the similarity between the second electromyographic signal and the standard electromyographic signal is extremely high, and use the standard electromyographic signal as the second target electromyographic signal; if the similarity result is smaller than or equal to the similarity threshold, it indicates that the similarity between the second electromyographic signal and the standard electromyographic signal is low, and it indicates that the second electromyographic signal is still possible to be the electromyographic signal fluctuation caused by the inattention of the user, and the unlocking is not performed at this time. In the embodiment, the standard electromyographic signal of which the similarity result is greater than the similarity threshold is used as the second target electromyographic signal by acquiring the preset similarity threshold, so that the first action can be unlocked and the next action can be executed by focusing attention of the user to generate the electromyographic signal with extremely high similarity to the standard electromyographic signal in the locking process, and the unlocking accuracy is improved.
In one implementation, the step S300 is followed by:
s10, controlling an IMU to detect motion data, and analyzing according to the motion data to obtain the posture action of the intelligent artificial limb in a three-dimensional space;
s20, acquiring a preset unlocking action, and matching the gesture action with the unlocking action;
s30, when the gesture action is successfully matched with the unlocking action, generating an unlocking instruction;
and S40, unlocking the first action according to the unlocking instruction.
Specifically, an IMU (Inertial Measurement Unit), i.e., an Inertial Measurement Unit, is used to measure three-axis attitude angles (or angular rates) and acceleration of an object, and a gyroscope and an accelerometer are main elements of the IMU. In this embodiment, if the user does not have any next action, active unlocking may be performed, which requires presetting of an unlocking action, where the unlocking action may be writing "O" or "C" in the air, and when the user wants to unlock, the user may drive the intelligent prosthesis to perform the unlocking action in the air. Therefore, when the IMU detects the motion data of the intelligent artificial limb in the three-dimensional space and analyzes the corresponding posture action, the motion data is matched with the unlocking action, and if the matching is successful, the intelligent artificial limb can be unlocked. According to the unlocking method and the unlocking device, the unlocking action is set, so that the user can unlock the device under the condition that the user does not have the next movement intention, the unlocking mode is simple and efficient, and convenience is further brought to the user.
In an embodiment, as shown in fig. 2, based on the above-mentioned control method of the intelligent prosthesis, the present invention further provides a control device of the intelligent prosthesis, including:
the acquisition module 100 is configured to acquire a first electromyographic signal, and determine a first action according to the first electromyographic signal;
a comparison module 200, configured to obtain a first action duration corresponding to the first action and a preset first duration threshold, and compare the first action duration with the first duration threshold;
a locking module 300, configured to execute and lock the first action when the first action duration is greater than the first duration threshold;
the unlocking module 400 is configured to acquire a second electromyographic signal and a preset second duration threshold, unlock the first action when the duration of the second electromyographic signal is greater than the second duration threshold, and execute a second action corresponding to the second electromyographic signal.
In one implementation, the control device of the intelligent prosthesis further comprises:
the storage module is used for pre-storing a standard action database, wherein the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals.
In an implementation manner, the obtaining module 100 specifically includes:
the first acquisition unit is used for acquiring a first electromyographic signal and searching the standard action database;
the first matching unit is used for matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
and the first determining unit is used for obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation and taking the first target standard action as a first action.
In one implementation, the standard action database further includes: the action duration and a second corresponding relation between the standard action and the action duration; the comparing module 200 specifically includes:
the first searching unit is used for searching the second corresponding relation according to the first target standard action to obtain target action duration corresponding to the first target standard action, and the target action duration is used as first action duration;
a comparison unit, configured to compare the first action duration with the first duration threshold.
In one implementation, the unlocking module 400 specifically includes:
the second acquisition unit is used for acquiring a second electromyographic signal and a preset second time length threshold;
the second searching unit is used for searching the standard action database when the duration time of the second electromyographic signal is greater than the second duration threshold;
the second matching unit is used for matching the second electromyographic signal with the standard electromyographic signal and taking the successfully matched standard electromyographic signal as a second target electromyographic signal;
a second determining unit, configured to obtain a second target standard action corresponding to the second target electromyographic signal according to the first corresponding relationship, and use the second target standard action as a second action;
and the unlocking unit is used for unlocking the first action and executing the second action.
In one implementation, the second matching unit specifically includes:
the signal matching subunit is used for matching the second electromyographic signal with the standard electromyographic signal;
the result acquiring subunit is used for acquiring a similarity result between the second electromyographic signal and the successfully matched standard electromyographic signal;
and the signal determining subunit is used for acquiring a preset similarity threshold value, and when the similarity result is greater than the similarity threshold value, taking the successfully matched standard electromyographic signal as a second target electromyographic signal.
In one implementation, the control device of the intelligent prosthesis further comprises:
the IMU detection module is used for controlling the IMU to detect motion data and analyzing the motion data to obtain the gesture action of the intelligent artificial limb in a three-dimensional space;
the action matching module is used for acquiring a preset unlocking action and matching the gesture action with the unlocking action;
the instruction generating module is used for generating an unlocking instruction when the gesture action is successfully matched with the unlocking action;
and the instruction control module is used for unlocking the first action according to the unlocking instruction.
In an embodiment, as shown in fig. 3, based on the above control method of the intelligent prosthesis, the present invention further provides a terminal, which includes a processor 10 and a memory 20. Fig. 3 shows only some of the components of the terminal, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The memory 20 may in some embodiments be an internal storage unit of the terminal, such as a hard disk or a memory of the terminal. The memory 20 may also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the memory 20 may also include both an internal storage unit and an external storage device of the terminal. The memory 20 is used for storing application software installed in the terminal and various types of data, such as program codes for installing the terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores a control program 30 of the intelligent prosthesis, and the control program 30 of the intelligent prosthesis can be executed by the processor 10, so as to realize the control method of the intelligent prosthesis in the application.
The processor 10 may be a Central Processing Unit (CPU), a microprocessor or other data Processing chip in some embodiments, and is used for running program codes stored in the memory 20 or Processing data, such as executing a control method of the intelligent prosthesis, and the like.
In one embodiment, when the processor 10 executes the control program 30 for the smart prosthesis in the memory 20, the following steps are implemented:
acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal;
acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold;
when the first action duration is greater than the first duration threshold, executing and locking the first action;
and acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal.
A standard action database is stored in advance, and the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals.
Acquiring a first electromyographic signal, determining a first action according to the first electromyographic signal, and comprising the following steps of:
acquiring a first electromyographic signal, and searching the standard action database;
matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
and obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation, and taking the first target standard action as a first action.
The standard action database further comprises: the action duration and a second corresponding relation between the standard action and the action duration;
acquiring a first action duration corresponding to the first action and a preset first duration threshold, and comparing the first action duration with the first duration threshold, including:
searching the second corresponding relation according to the first target standard action to obtain a target action duration corresponding to the first target standard action, and taking the target action duration as a first action duration;
comparing the first action duration to the first duration threshold.
The acquiring a second electromyographic signal and a preset second duration threshold, unlocking the first action and executing a second action corresponding to the second electromyographic signal when the duration of the second electromyographic signal is greater than the second duration threshold, and the method includes:
acquiring a second electromyographic signal and a preset second time length threshold;
when the duration time of the second electromyographic signal is greater than the second duration threshold, searching the standard action database;
matching the second electromyographic signal with the standard electromyographic signal, and taking the successfully matched standard electromyographic signal as a second target electromyographic signal;
obtaining a second target standard action corresponding to the second target electromyographic signal according to the first corresponding relation, and taking the second target standard action as a second action;
and unlocking the first action and executing the second action.
Matching the second electromyographic signal with the standard electromyographic signal, and taking the successfully matched standard electromyographic signal as a second target electromyographic signal, wherein the method comprises the following steps:
matching the second electromyographic signal with the standard electromyographic signal;
acquiring a similarity result between the second electromyographic signal and the successfully matched standard electromyographic signal;
and acquiring a preset similarity threshold, and when the similarity result is greater than the similarity threshold, taking the successfully matched standard electromyographic signal as a second target electromyographic signal.
When the first action duration is greater than the first duration threshold, after the first action is executed and locked, the method further includes:
controlling an IMU to detect motion data, and analyzing according to the motion data to obtain the attitude action of the intelligent artificial limb in a three-dimensional space;
acquiring a preset unlocking action, and matching the gesture action with the unlocking action;
when the gesture action is successfully matched with the unlocking action, a unlocking instruction is generated;
and unlocking the first action according to the unlocking instruction.
The present invention also provides a computer readable storage medium storing a computer program executable for implementing the steps of the control method of an intelligent prosthesis as described above.
In summary, the method, the apparatus, the terminal and the computer-readable storage medium for controlling the intelligent prosthesis disclosed in the present invention include: acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal; acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold; when the first action duration is greater than the first duration threshold, executing and locking the first action; and acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal. When the intelligent artificial limb performs the action with longer action time, the action is locked, the electromyographic signals are continuously analyzed, and the intelligent artificial limb can be unlocked when the next electromyographic signal lasts for longer time, so that misjudgment caused by fluctuation of the electromyographic signals due to inational force inattention of a wearer of the intelligent artificial limb is avoided, and the control stability of the intelligent artificial limb is improved.
It will be understood that the invention is not limited to the examples described above, but that modifications and variations will occur to those skilled in the art in light of the above teachings, and that all such modifications and variations are considered to be within the scope of the invention as defined by the appended claims.
Claims (6)
1. A method of controlling an intelligent prosthesis, the method comprising:
acquiring a first electromyographic signal, and determining a first action according to the first electromyographic signal;
acquiring a first action time length corresponding to the first action and a preset first time length threshold, and comparing the first action time length with the first time length threshold;
when the first action duration is greater than the first duration threshold, executing and locking the first action;
acquiring a second electromyographic signal and a preset second time threshold, unlocking the first action when the duration of the second electromyographic signal is greater than the second time threshold, and executing a second action corresponding to the second electromyographic signal;
when the first action duration is greater than the first duration threshold, after the first action is executed and locked, the method further includes:
controlling an IMU to detect motion data, and analyzing according to the motion data to obtain the attitude action of the intelligent artificial limb in a three-dimensional space;
acquiring a preset unlocking action, and matching the gesture action with the unlocking action;
when the gesture action is successfully matched with the unlocking action, a unlocking instruction is generated;
unlocking the first action according to the unlocking instruction;
pre-storing a standard action database, wherein the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals;
acquiring a first electromyographic signal, determining a first action according to the first electromyographic signal, comprising:
acquiring a first electromyographic signal, and searching the standard action database;
matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation, and taking the first target standard action as a first action;
the standard action database further comprises: the action duration and a second corresponding relation between the standard action and the action duration;
acquiring a first action duration corresponding to the first action and a preset first duration threshold, and comparing the first action duration with the first duration threshold, including:
searching the second corresponding relation according to the first target standard action to obtain target action duration corresponding to the first target standard action, and taking the target action duration as first action duration;
comparing the first action duration to the first duration threshold.
2. A control method of an intelligent artificial limb according to claim 1, wherein the obtaining of the second electromyographic signal and a preset second time threshold, unlocking the first action and executing a second action corresponding to the second electromyographic signal when the duration of the second electromyographic signal is greater than the second time threshold comprises:
acquiring a second electromyographic signal and a preset second time length threshold;
when the duration time of the second electromyographic signal is greater than the second duration threshold, searching the standard action database;
matching the second electromyographic signal with the standard electromyographic signal, and taking the successfully matched standard electromyographic signal as a second target electromyographic signal;
obtaining a second target standard action corresponding to the second target electromyographic signal according to the first corresponding relation, and taking the second target standard action as a second action;
and unlocking the first action and executing the second action.
3. A control method of an intelligent prosthesis according to claim 2, wherein matching the second electromyographic signal with the standard electromyographic signal, taking the successfully matched standard electromyographic signal as a second target electromyographic signal, comprises:
matching the second electromyographic signal with the standard electromyographic signal;
acquiring a similarity result between the second electromyographic signal and the successfully matched standard electromyographic signal;
and acquiring a preset similarity threshold, and when the similarity result is greater than the similarity threshold, taking the successfully matched standard electromyographic signal as a second target electromyographic signal.
4. A control device for an intelligent artificial limb, comprising:
the acquisition module is used for acquiring a first electromyographic signal and determining a first action according to the first electromyographic signal;
the comparison module is used for acquiring a first action time length corresponding to the first action and a preset first time length threshold value and comparing the first action time length with the first time length threshold value;
the locking module is used for executing and locking the first action when the first action duration is greater than the first duration threshold;
the unlocking module is used for acquiring a second electromyographic signal and a preset second duration threshold, unlocking the first action when the duration time of the second electromyographic signal is greater than the second duration threshold, and executing a second action corresponding to the second electromyographic signal;
when the first action duration is greater than the first duration threshold, after the first action is executed and locked, the method further includes:
controlling an IMU to detect motion data, and analyzing according to the motion data to obtain the attitude action of the intelligent artificial limb in a three-dimensional space;
acquiring a preset unlocking action, and matching the gesture action with the unlocking action;
when the gesture action is successfully matched with the unlocking action, a unlocking instruction is generated;
unlocking the first action according to the unlocking instruction;
pre-storing a standard action database, wherein the standard action database comprises standard actions, standard electromyographic signals and a first corresponding relation between the standard actions and the standard electromyographic signals;
acquiring a first electromyographic signal, determining a first action according to the first electromyographic signal, comprising:
acquiring a first electromyographic signal, and searching the standard action database;
matching the first electromyographic signal with a standard electromyographic signal in the standard action database, and taking the successfully matched standard electromyographic signal as a first target electromyographic signal;
obtaining a first target standard action corresponding to the first target electromyographic signal according to the first corresponding relation, and taking the first target standard action as a first action;
the standard action database further comprises: the action duration and a second corresponding relation between the standard action and the action duration;
acquiring a first action duration corresponding to the first action and a preset first duration threshold, and comparing the first action duration with the first duration threshold, including:
searching the second corresponding relation according to the first target standard action to obtain a target action duration corresponding to the first target standard action, and taking the target action duration as a first action duration;
comparing the first action duration to the first duration threshold.
5. A terminal, comprising: a memory, a processor and a control program of the intelligent artificial limb stored on the memory and capable of running on the processor, wherein the control program of the intelligent artificial limb realizes the steps of the control method of the intelligent artificial limb according to any one of claims 1 to 3 when being executed by the processor.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which can be executed for implementing the steps of the control method of an intelligent prosthesis according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095379.XA CN115153985B (en) | 2022-09-08 | 2022-09-08 | Control method, device and terminal of intelligent artificial limb and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095379.XA CN115153985B (en) | 2022-09-08 | 2022-09-08 | Control method, device and terminal of intelligent artificial limb and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115153985A CN115153985A (en) | 2022-10-11 |
| CN115153985B true CN115153985B (en) | 2022-12-09 |
Family
ID=83482490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211095379.XA Active CN115153985B (en) | 2022-09-08 | 2022-09-08 | Control method, device and terminal of intelligent artificial limb and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115153985B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116030536B (en) * | 2023-03-27 | 2023-06-09 | 国家康复辅具研究中心 | Data collection and evaluation system for use state of upper limb prosthesis |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111743667A (en) * | 2020-06-29 | 2020-10-09 | 北京海益同展信息科技有限公司 | Artificial limb control method, device, system and storage medium |
| JP6996722B1 (en) * | 2020-10-08 | 2022-01-17 | 株式会社スキノス | Detection device and detection method |
| CN113946225B (en) * | 2021-12-20 | 2022-04-26 | 深圳市心流科技有限公司 | Gesture locking method, intelligent bionic hand, terminal and storage medium |
| CN114167995B (en) * | 2022-02-14 | 2022-05-17 | 浙江强脑科技有限公司 | Gesture locking method and device for bionic hand, terminal and storage medium |
| CN114625257B (en) * | 2022-05-16 | 2022-08-16 | 浙江强脑科技有限公司 | Action recognition method and device based on electromyographic signals |
| CN114652493B (en) * | 2022-05-25 | 2022-08-30 | 深圳市心流科技有限公司 | Electromyographic signal control method and device, electromyographic equipment and storage medium |
| CN114707562B (en) * | 2022-06-01 | 2022-09-02 | 深圳市心流科技有限公司 | Electromyographic signal sampling frequency control method and device and storage medium |
-
2022
- 2022-09-08 CN CN202211095379.XA patent/CN115153985B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115153985A (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115153985B (en) | Control method, device and terminal of intelligent artificial limb and computer readable storage medium | |
| KR102466995B1 (en) | Method and device for authenticating user | |
| US20160272214A1 (en) | Method for recognizing vehicle driver and determining whether driver can start vehicle | |
| KR20120023083A (en) | Biometric authentication device, biometric authentication method and computer program for biometric authentication | |
| Hoang et al. | On the instability of sensor orientation in gait verification on mobile phone | |
| JP2008134786A (en) | Authentication system, authentication device and authentication method | |
| JP2019117579A (en) | Biometric authentication system | |
| Pires et al. | Identification of activities of daily living using sensors available in off-the-shelf mobile devices: Research and hypothesis | |
| CN110248025B (en) | Identity recognition method, device and storage medium for multi-fingerprint and palm print information | |
| CN111581625A (en) | User identity identification method and device and electronic equipment | |
| Fernandez-Lopez et al. | Optimizing resources on smartphone gait recognition | |
| JP2014038513A (en) | Input unit, device, input method and program | |
| US20070147667A1 (en) | Biometrics information processing device and method | |
| CN112231033A (en) | Software interface element matching method and device combining RPA and AI | |
| JP2005258801A (en) | Personal identification system | |
| JP6468823B2 (en) | Biological identification system and electronic device | |
| CN104036245A (en) | Biometric feature recognition method based on on-line feature point matching | |
| CN113785558A (en) | Wearable device for detecting events using camera module and wireless communication device | |
| US7415141B2 (en) | Signature authentication device, signature authentication method, and computer program product | |
| CN110795985A (en) | Information processing method and information processing system | |
| JP6794687B2 (en) | Authentication device, authentication system, authentication method and program | |
| CN108664956B (en) | Living body identification method and device in human vein biological characteristic information acquisition process | |
| Mecca | Impact of gait stabilization: A study on how to exploit it for user recognition | |
| JP7384157B2 (en) | Information processing devices, wearable devices, information processing methods and programs | |
| CN114190886A (en) | Noise waveform removal device and method, model training device and method, generation model, and wearable device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |