CN117153163A - Hand rehabilitation method, system, storage medium and terminal based on voice interaction - Google Patents
Hand rehabilitation method, system, storage medium and terminal based on voice interaction Download PDFInfo
- Publication number
- CN117153163A CN117153163A CN202311295231.5A CN202311295231A CN117153163A CN 117153163 A CN117153163 A CN 117153163A CN 202311295231 A CN202311295231 A CN 202311295231A CN 117153163 A CN117153163 A CN 117153163A
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- training
- hand rehabilitation
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000003993 interaction Effects 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 91
- 230000006870 function Effects 0.000 claims description 35
- 238000001914 filtration Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 11
- 238000009432 framing Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005314 correlation function Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 230000009471 action Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 206010008190 Cerebrovascular accident Diseases 0.000 description 2
- 208000006011 Stroke Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000002490 cerebral effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 208000011092 Hand injury Diseases 0.000 description 1
- 206010019196 Head injury Diseases 0.000 description 1
- 208000030886 Traumatic Brain injury Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/04—Training, enrolment or model building
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
- G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention discloses a hand rehabilitation method, a hand rehabilitation system, a storage medium and a hand rehabilitation terminal based on voice interaction, which belong to the technical field of intelligent voice interaction and comprise the following steps: acquiring a user voice command; extracting voice command information and judging whether to open the hand rehabilitation equipment according to the voice command information; prompting the user whether to lock the training or not by voice, and judging whether to lock the training or not according to the voice reply of the user; if the training is locked, recording the personal identity information of the user by a voiceprint recognition method; the user sends out a training voice instruction, and whether the training voice instruction is the voice sent by the locked user is judged through voiceprint comparison; and controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user. The invention realizes the current training locking of the user by utilizing the voiceprint recognition technology, is not influenced by other users, does not cause misoperation, and improves the reliability and accuracy of the training of the hand rehabilitation equipment of the user.
Description
Technical Field
The invention relates to the technical field of intelligent voice interaction, in particular to a hand rehabilitation method, a hand rehabilitation system, a hand rehabilitation storage medium and a hand rehabilitation terminal based on voice interaction.
Background
The factors caused by hand dysfunction are very many, and are mainly manifested by cerebral apoplexy, craniocerebral injury, hand injury and the like, wherein at present, about 1500 ten thousand of patients with cerebral apoplexy exist in China, and up to 60% of patients can have hand dysfunction. At present, some medical instruments for treating hand disorders appear in the market, but the hand rehabilitation instruments change training modes or functional parameters in a touch mode, and patients or other auxiliary staff are required to touch keys to adjust the hand rehabilitation instruments, so that the use experience of the hand rehabilitation instruments is reduced. Particularly, for patients lying on chairs or sickbeds, the use is extremely inconvenient, and the requirements of the patients cannot be met.
The voice recognition technology can convert natural voice into character strings, and the character strings are analyzed in a semantic level to obtain the actual meaning of the voice. The voice semantic recognition analysis technology is reasonably utilized, so that autonomous operation of the hand rehabilitation device by a patient can be realized, non-contact rehabilitation training and adjustment can be realized, however, when the hand rehabilitation device is in use, if other people change the same or similar voice of the function, the system can be triggered to make misoperation, and the treatment accident is caused, which is undesirable for the user. Therefore, due to factors such as low voice recognition accuracy and misoperation caused by other voices, the voice interaction product is greatly hindered from being used and popularized in the aspect of hand rehabilitation.
In addition, after the patient finishes the current treatment by using the hand rehabilitation device, the patient or other personnel cannot view important information of the previous treatment and cannot clearly compare the previous treatment data; the memory of the individual or the simple record is easy to confuse or miss, reliable data can not be provided for the subsequent treatment accurately, and the data support is lacked.
Disclosure of Invention
The invention aims to overcome the defects of a voice interaction method in the existing hand rehabilitation equipment and provides a hand rehabilitation method, a hand rehabilitation system, a storage medium and a terminal based on voice interaction.
The aim of the invention is realized by the following technical scheme:
in a first aspect, a hand rehabilitation method based on voice interaction is provided, including the following steps:
s1, acquiring a user voice command;
s2, extracting the voice command information, judging whether to open the hand rehabilitation equipment according to the voice command information, if yes, performing a step S3, otherwise, ending;
s3, prompting the user whether to lock the training or not by voice, and judging whether to lock the training or not according to the voice reply of the user; if the training is locked, recording the personal identity information of the user by a voiceprint recognition method and performing step S4, otherwise, performing step S5;
s4, a user sends out a training voice instruction, whether the training voice instruction is the voice sent out by the user locked in the step S3 is judged through voiceprint comparison, if yes, the step S5 is carried out, and otherwise, the step is ended;
s5, controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
In some possible embodiments, the hand rehabilitation method based on voice interaction includes a switching function, a training time, a training frequency, and a training intensity.
In some possible embodiments of the present invention, the method for hand rehabilitation based on voice interaction, which determines whether to lock the training according to the voice reply of the user, includes:
if the voice reply of the user is not received within a certain time after the voice prompt is sent, the training is not locked.
In some possible embodiments of the present invention, a method for hand rehabilitation based on voice interaction, the recording, by a voiceprint recognition method, personal identity information of a user includes:
the voice of the user is subjected to pretreatment, fast Fourier transformation, filtering, logarithmic taking and inverse discrete cosine transformation in sequence.
In some possible embodiments, the preprocessing includes pre-emphasis, framing and windowing, where the windowing function expression is:
wherein N is more than 0 and less than N-1, lambda is an adjustment coefficient, lambda is more than 0 and less than 1, and F (N) is a correlation function of N.
In some possible embodiments, the filtering includes:
firstly converting the original frequency into a representation form of Mel frequency, then constructing Mel filter for filtering, and converting the functional relation as follows:
f mel ＝2595×lg(1+f Hz /700)
wherein f mel Is the mel frequency; f (f) Hz Frequency is expressed in Hz; the filter function expression is:
wherein k is the kth triangular filter, f (M) is the corresponding mth center frequency, and the value of M is 0 < M < M (the number of the filters corresponding to M).
In some possible embodiments of the present invention, the function expression of the inverse discrete cosine transform is:
where X (m) is a logarithmic function of the energy spectrum taken by the Mel filter output.
In a second aspect, a hand rehabilitation system based on voice interaction is provided, including:
the voice acquisition module is used for acquiring voice information of a user;
the hand rehabilitation device opening module is used for extracting the voice command information and judging whether to open the hand rehabilitation device according to the voice command information;
the voice prompt module is used for prompting a user whether to lock the training or not in voice;
the locking module is used for judging whether to lock the training according to the voice reply of the user, and recording the personal identity information of the user through a voiceprint recognition method when the user locks the training;
the information storage module is used for storing the user personal identity information recorded by the locking module;
the training voice instruction judging module is used for judging whether the current training voice instruction is the voice sent by the locked user or not through voiceprint comparison;
and the output control module is used for controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
In a third aspect, a computer storage medium having stored thereon computer instructions that, when executed, perform the relevant steps of any of the embodiments of a voice interaction based hand rehabilitation method is provided.
In a fourth aspect, a terminal is provided, including a memory and a processor, where the memory stores computer instructions executable on the processor, where the processor executes the computer instructions to perform the steps associated with a hand rehabilitation method based on voice interaction according to any of the embodiments.
It should be further noted that the technical features corresponding to the above embodiments of the options may be combined with each other or replaced to form a new technical solution without collision.
Compared with the prior art, the invention has the beneficial effects that:
(1) The voice recognition method can realize the function of locking the voice effectiveness of the current patient only when the voice recognition technology is used, after the instruction for locking the personal identity is selected, the personal identity characteristics are identified and compared, and only the voice instruction sent by the patient who is confirmed to be treated is effective, so that misoperation caused by the fact that other people send the same or similar voice for changing functions or parameters can be avoided, the intention of the patient is obtained through the voice recognition technology, the voice interaction between the patient and the hand rehabilitation system can be accurately realized, and the reliability and the accuracy of the training of the hand rehabilitation equipment of the user are improved.
(2) The method records the personal identity information of the user by using an optimized voiceprint recognition method, and carries out pretreatment, fast Fourier transformation, filtering, logarithmic transformation and inverse discrete cosine transformation on the voice of the user in sequence, thereby improving the voice recognition accuracy.
(3) When the method is not used for locking training, voice interaction demonstration can be provided for a first user or an unskilled user of the equipment, so that the effective voice can be sent by both a demonstrator and the user in the teaching process, and the extensibility of the equipment is ensured.
(4) The system controls the hand rehabilitation equipment in a voice mode, performs rehabilitation training on the hands of the patient, can perform function switching without contact, changes parameter values under various function menus, and is convenient for the patient to use.
(5) The system provided by the invention is provided with an information storage module for storing the information of patients, is convenient for checking the treatment records of different patients, different time periods and different treatment functions and parameters, and can provide effective basis for the next treatment according to the information.
In addition, the storage medium and the terminal of the invention can realize the same effects as the method and the system.
Drawings
FIG. 1 is a flow chart of a hand rehabilitation method based on voice interaction according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating performing a training lock in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a control flow of a hand rehabilitation system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a hand rehabilitation device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully understood from the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
Referring to fig. 1, in an exemplary embodiment, a hand rehabilitation method based on voice interaction is provided, including the steps of:
s1, acquiring a user (or patient) voice command;
s2, extracting the voice command information, judging whether to open the hand rehabilitation equipment according to the voice command information, if yes, performing a step S3, otherwise, ending;
s3, prompting the user whether to lock the training or not by voice, and judging whether to lock the training or not according to the voice reply of the user; if the training is locked, recording the personal identity information of the user by a voiceprint recognition method and performing step S4, otherwise, performing step S5;
s4, a user sends out a training voice instruction, whether the training voice instruction is the voice sent out by the user locked in the step S3 is judged through voiceprint comparison, if yes, the step S5 is carried out, and otherwise, the step is ended;
s5, controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
Specifically, when the method is realized, the hand rehabilitation device receives a user voice command in real time, extracts voice command information (such as terms of opening, equipment opening and the like), judges whether the voice needs to be opened by utilizing a voice recognition technology, and sends out a voice prompt after confirming that the voice information needs to be opened: whether to lock the training only allows the own voice to be valid.
Further, referring to fig. 2, if the voice response of the user is unlocked or the voice response of the user is not received within a certain time after the voice prompt is sent, the training is unlocked. Then the voice of other people is allowed to be valid in addition to the user (either the user or the other can send out the voice control system to change the function or parameter); if the voice reply of the user is locked, the personal identity information of the user is recorded through a voiceprint recognition technology and used as the basis for voice interaction between the patient and the hand rehabilitation system, and only the voice of the user is allowed to be effective in the process of the training (in the training, other people except the user can not control the system to change functions or parameters).
Further, referring to fig. 3, the user sends out an effective training voice command (such as switching to the x function, changing the training time to x minutes, changing the training frequency to the x-th gear, changing the training intensity to the x-th gear, etc.), receives such voice, and if the locking is not performed in step S3, the corresponding function or parameter is changed according to the voice intention through voice recognition; if the user is locked in the step S3, voiceprint comparison is needed, whether the user is locked in the step S3 is judged, whether the current voice accords with personal identity information is judged, if the current voice does not accord with personal identity, invalid processing is carried out, and when the current voice is confirmed to be the voice sent by the user, the function or the parameter is modified through voice recognition according to voice intention. Specifically, the voiceprint comparison process is to perform voiceprint recognition on the voice sent by the current user to obtain the personal identity information of the user, and compare the personal identity information of the user with the personal identity information of the user which is recorded and locked in step S3. The user personal identity information is unique voiceprint characteristics of each person obtained by voiceprint recognition, the voiceprint characteristics are converted into a code format of data, and then the data code is recorded and stored as the unique information of the personal identity. When the lock is performed in step S3, the unique data code of the lock user is saved. And when the voice is received each time, extracting the characteristics of the current voice information, obtaining a data code corresponding to the current voice, calling the unique data code stored by the locking user obtained in the step S3, and comparing the two data codes, thereby judging whether the locking user is matched with the current voice.
Further, since the same person may have a difference in voice at different times, under different states or under noise influence, when comparing voiceprint features, a threshold of similarity, denoted Th, needs to be set to avoid erroneous judgment. If the similarity of the two data codes is larger than the threshold Th during comparison, judging that the two data codes are the same person, namely the voice is valid; if the similarity of the two data codes is smaller than the threshold Th during comparison, judging that the two data codes are not identical, namely voice invalidation, wherein the similarity is calculated in a conventional similarity calculation mode, and details are omitted.
Further, whether locking is performed or not, an effective training voice instruction of the user (only the voice of the user is effective when locking is performed, and other voices are ineffective) is processed, and a processing result is fed back, and corresponding reply voices (such as that the function is switched to x, the training time is changed to x minutes, the training frequency is changed to x-th gear, the training intensity is changed to x-th gear, and the like) are sent out, so that the user knows that the equipment has processed the voice instruction; at the same time, the function or parameter for which the modification has been made is displayed.
Each subsequent training session goes through the loop of steps S3, S4 and S5, and the system saves some important information about the patient' S treatment during the training session. Including recording information of the current training treatment (time, frequency of action, force of action of patient treatment, and changes in any function and parameter during the current treatment, when it changes, etc.).
Further, the recording the personal identity information of the user through the voiceprint recognition method comprises the following steps:
the voice of the user is sequentially subjected to voice signal recording, preprocessing, fast Fourier transformation, filtering, logarithm taking, inverse discrete cosine transformation, static Mel frequency cepstrum coefficient extraction and dynamic characteristic coefficient extraction. The preprocessing comprises pre-emphasis, framing and windowing, the windowing can enable voice signals to be more uniform and smooth, continuity is enhanced, and the windowing function expression is as follows:
wherein N is more than 0 and less than N-1, lambda is an adjustment coefficient, lambda is more than 0 and less than 1, and F (N) is a correlation function of N.
Further, after the pre-emphasis, framing and windowing, the voice signal is not obvious in the time domain, and the signal is subjected to fast Fourier transform and is converted from the time domain to the frequency domain, so that the signal characteristics are further extracted.
Further, to better conform to the auditory characteristics of the human ear, the original frequency is converted into a representation of mel frequency, and the conversion function relation is as follows:
f mel ＝2595×lg(1+f Hz /700)
wherein f mel Is the mel frequency; f (f) Hz Frequency is expressed in Hz; then, a Mel filter is constructed for filtering, harmonic content is reduced, noise is filtered, signal identification accuracy is improved, and a filter function expression is:
wherein k is the kth triangular filter, f (M) is the corresponding mth center frequency, and the value of M is 0 < M < M (the number of the filters corresponding to M).
Further, after filtering and logarithming, the voice signal is subjected to inverse discrete cosine transform, so as to obtain mel frequency cepstrum coefficient, wherein the function expression of the inverse discrete cosine transform is as follows:
where X (m) is a logarithmic function of the energy spectrum taken by the Mel filter output.
Further, because the mel frequency cepstrum coefficient is a characteristic of the voice under static state, and the voice signal also has dynamic characteristic, the dynamic characteristic coefficient is obtained, and the dynamic and static characteristics of the voice are combined to obtain the voiceprint recognition with higher precision. The optimized voiceprint recognition method is used for recording personal identity information of the user, and voice of the user is subjected to pretreatment, fast Fourier transformation, filtering, logarithm taking and inverse discrete cosine transformation in sequence, so that the voice recognition accuracy is improved.
In another exemplary embodiment, a hand rehabilitation system based on voice interaction is provided, comprising:
the voice acquisition module is used for acquiring voice information of a user;
the hand rehabilitation device opening module is used for extracting the voice command information and judging whether to open the hand rehabilitation device according to the voice command information;
the voice prompt module is used for prompting a user whether to lock the training or not in voice;
the locking module is used for judging whether to lock the training according to the voice reply of the user, and recording the personal identity information of the user through a voiceprint recognition method when the user locks the training;
the information storage module is used for storing the user personal identity information recorded by the locking module;
the training voice instruction judging module is used for judging whether the current training voice instruction is the voice sent by the locked user or not through voiceprint comparison;
and the output control module is used for controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
The hand rehabilitation device comprises a hand rehabilitation device opening module, a voice prompt module, a locking module, a training voice instruction judging module and an output control module, wherein the hand rehabilitation device opening module, the voice prompt module, the locking module, the training voice instruction judging module and the output control module can be integrated into an MCU main control module, the voice acquisition module acquires voice information of a patient and comprises the steps of acquiring voices in different steps mentioned in the method, the acquired information is transmitted to the MCU main control module, the acquired information is processed and then is reversely transmitted to the voice module, voice response is sent out through a voice output part in the module, and normal voice interaction between the patient and a hand rehabilitation system is achieved.
The MCU main control module receives the voice information transmitted by the voice module and extracts voice information characteristics, wherein the hand rehabilitation equipment starting module judges whether to start the hand rehabilitation equipment according to voice command information; the voice prompt module is used for prompting a user whether to lock the training or not in voice; the locking module is used for judging whether to lock the training according to the voice reply of the user, and recording the personal identity information of the user through a voiceprint recognition method when the user locks the training; the training voice instruction judging module is used for judging whether the current training voice instruction is the voice sent by the locked user or not through voiceprint comparison; then, according to the personal voiceprint characteristics extracted from the voice signals and the personal identity information in the information storage module, judging whether the voice is sent by a patient or not; and simultaneously, the extracted voice information is utilized to make voice recognition, and the intention of the patient is judged to make a reaction again.
Further, the reaction of the MCU master control module comprises: firstly, the voice information is reversely fed back to the voice module to send voice response to the patient, secondly, the voice information is sent to the output control module to carry out corresponding actions, and after the output control module receives the instructions sent by the MCU main control module, the hand actions required by the patient are made, so that the voice interaction function is realized.
Further, the information storage module is used for storing the personal identity characteristic information of the patient extracted by the MCU main control module, and providing data of voice information for the MCU main control module to make judgment basis when needed, so that erroneous judgment is avoided; the voice information storage module can also store some relevant historical data of each treatment of the patient, so that the later inquiry and analysis are convenient.
Specifically, the user personal identity information is a voiceprint feature unique to each person obtained by voiceprint recognition, the voiceprint feature is converted into a code format of data, and then the data code is recorded in the information storage module as the unique information of the personal identity. When the locking is performed, the unique data code of the locking user is stored in the information storage module. And when the voice is received each time, extracting the characteristics of the current voice information, acquiring a data code corresponding to the current voice, calling the data code stored in the information storage module by the locking user before, and comparing the two data codes to judge whether the locking user is matched with the current voice or not.
Further, the system also comprises a display module for displaying the training function of the hand rehabilitation system and various parameters in each function menu, and displaying the result after following the voice control.
In one example, referring to fig. 4, a hand rehabilitation device is provided, where the device includes a host, an air tube and a glove, and each functional module corresponding to the above system is integrated in the host, when a patient sends out voice, the host receives the voice information and processes the voice information, and controls the glove to perform stretching or holding actions (including changes of treatment time, action frequency, action force, etc.) through the air tube, and simultaneously displays effective information on a display screen.
After the host computer of the hand rehabilitation device is started, when the patient sends out voice, the system extracts the characteristics of the voice information, after voice recognition, the voice is sent out from the voice prompt module according to the voice intention sent by the patient, and the patient is reminded whether to only allow the voice to be effective (other voices or noise are invalid) when the use is performed, if the voice reply is not received, the voice reply is invalid after a period of time; if the personal identity information of the current patient is confirmed, the personal identity information is stored in an information storage module and is used as the basis for voice interaction between the patient and hand rehabilitation equipment.
After the personal identity information is stored, the hand rehabilitation system firstly performs voice information feature extraction every time when voice information is received, and judges whether the personal identity stored in the treatment is met or not through voiceprint recognition, if the personal identity is not met, invalid processing is performed; if the patient is in line with the personal identity, the voice feedback is carried out on the patient, the glove is controlled to make the voice intention action of the patient, the changed functions and parameters are displayed on the display screen, and meanwhile, the treatment information (the treatment time, the action frequency, the action force and the like of the patient, including the change of any functions and parameters in the treatment process, the time of the change and the like) is recorded.
In another exemplary embodiment, the invention provides a computer storage medium having stored thereon computer instructions that, when executed, perform the relevant steps of the one hand rehabilitation method based on voice interaction.
Based on such understanding, the technical solution of the present embodiment may be essentially or a part contributing to the prior art or a part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another exemplary embodiment, the invention provides a terminal comprising a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes relevant steps in the hand rehabilitation method based on voice interaction when executing the computer instructions.
The processor may be a single or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the invention.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and structural equivalents thereof, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on a manually-generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by data processing apparatus.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Processors suitable for the execution of a computer program include, by way of example, general and/or special purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read only memory and/or a random access memory. The essential elements of a computer include a central processing unit for carrying out or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks, etc. However, a computer does not have to have such a device. Furthermore, the computer may be embedded in another device, such as a mobile phone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features of specific embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. On the other hand, the various features described in the individual embodiments may also be implemented separately in the various embodiments or in any suitable subcombination. Furthermore, although features may be acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
The foregoing detailed description of the invention is provided for illustration, and it is not to be construed that the detailed description of the invention is limited to only those illustration, but that several simple deductions and substitutions can be made by those skilled in the art without departing from the spirit of the invention, and are to be considered as falling within the scope of the invention.
Claims (10)
1. The hand rehabilitation method based on voice interaction is characterized by comprising the following steps of:
s1, acquiring a user voice command;
s2, extracting the voice command information, judging whether to open the hand rehabilitation equipment according to the voice command information, if yes, performing a step S3, otherwise, ending;
s3, prompting the user whether to lock the training or not by voice, and judging whether to lock the training or not according to the voice reply of the user; if the training is locked, recording the personal identity information of the user by a voiceprint recognition method and performing step S4, otherwise, performing step S5;
s4, a user sends out a training voice instruction, whether the training voice instruction is the voice sent out by the user locked in the step S3 is judged through voiceprint comparison, if yes, the step S5 is carried out, and otherwise, the step is ended;
s5, controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
2. The method of claim 1, wherein the training voice instructions comprise a switching function, a training time, a training frequency, and a training intensity.
3. The hand rehabilitation method based on voice interaction according to claim 1, wherein the determining whether to lock the training according to the voice reply of the user comprises:
if the voice reply of the user is not received within a certain time after the voice prompt is sent, the training is not locked.
4. The hand rehabilitation method based on voice interaction according to claim 1, wherein the recording of the personal identity information of the user by the voiceprint recognition method comprises:
the voice of the user is subjected to pretreatment, fast Fourier transformation, filtering, logarithmic taking and inverse discrete cosine transformation in sequence.
5. The voice interaction based hand rehabilitation method according to claim 4, wherein the preprocessing comprises pre-emphasis, framing and windowing, wherein the windowing function expression is:
wherein N is more than 0 and less than N-1, lambda is an adjustment coefficient, lambda is more than 0 and less than 1, and F (N) is a correlation function of N.
6. The voice interaction based hand rehabilitation method according to claim 4, wherein the filtering comprises:
firstly converting the original frequency into a representation form of Mel frequency, then constructing Mel filter for filtering, and converting the functional relation as follows:
f mel ＝2595×lg(1+f Hz /700)
wherein f mel Is the mel frequency; f (f) Hz Frequency is expressed in Hz; the filter function expression is:
wherein k is the kth triangular filter, f (M) is the corresponding mth center frequency, and the value of M is 0 < M < M (the number of the filters corresponding to M).
7. The method for hand rehabilitation based on voice interaction according to claim 4, wherein the function expression of the inverse discrete cosine transform is:
where X (m) is a logarithmic function of the energy spectrum taken by the Mel filter output.
8. A hand rehabilitation system based on voice interaction, comprising:
the voice acquisition module is used for acquiring voice information of a user;
the hand rehabilitation device opening module is used for extracting the voice command information and judging whether to open the hand rehabilitation device according to the voice command information;
the voice prompt module is used for prompting a user whether to lock the training or not in voice;
the locking module is used for judging whether to lock the training according to the voice reply of the user, and recording the personal identity information of the user through a voiceprint recognition method when the user locks the training;
the information storage module is used for storing the user personal identity information recorded by the locking module;
the training voice instruction judging module is used for judging whether the current training voice instruction is the voice sent by the locked user or not through voiceprint comparison;
and the output control module is used for controlling the hand rehabilitation equipment to execute the training according to the training voice instruction sent by the user.
9. A computer storage medium having stored thereon computer instructions which, when executed, perform the relevant steps of a voice interaction based hand rehabilitation method according to any of claims 1-7.
10. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps associated with a voice interaction based hand rehabilitation method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295231.5A CN117153163A (en) | 2023-10-08 | 2023-10-08 | Hand rehabilitation method, system, storage medium and terminal based on voice interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311295231.5A CN117153163A (en) | 2023-10-08 | 2023-10-08 | Hand rehabilitation method, system, storage medium and terminal based on voice interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117153163A true CN117153163A (en) | 2023-12-01 |
Family
ID=88910132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311295231.5A Pending CN117153163A (en) | 2023-10-08 | 2023-10-08 | Hand rehabilitation method, system, storage medium and terminal based on voice interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117153163A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252464A (en) * | 2013-06-26 | 2014-12-31 | 联想(北京)有限公司 | Information processing method and information processing device |
| CN104834849A (en) * | 2015-04-14 | 2015-08-12 | 时代亿宝(北京)科技有限公司 | Dual-factor identity authentication method and system based on voiceprint recognition and face recognition |
| CN105244031A (en) * | 2015-10-26 | 2016-01-13 | 北京锐安科技有限公司 | Speaker identification method and device |
| KR20190048394A (en) * | 2017-10-31 | 2019-05-09 | 임태향 | A healthcare, beatycare and dietcare digital massage chair for digital massage chair system operated by artificial intelligence and big data |
| CN111759658A (en) * | 2020-07-09 | 2020-10-13 | 江西台德智慧科技有限公司 | Massage chair control method and artificial intelligence massage chair |
| CN112084483A (en) * | 2019-06-14 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Application locking and unlocking method, device, equipment and storage medium |
| CN112558911A (en) * | 2020-12-04 | 2021-03-26 | 苏州思必驰信息科技有限公司 | Voice interaction method and device for massage chair |
| CN112818316A (en) * | 2021-03-08 | 2021-05-18 | 南京大正智能科技有限公司 | Voiceprint-based identity recognition and application method, device and equipment |
| CN113093980A (en) * | 2021-05-08 | 2021-07-09 | 北京字节跳动网络技术有限公司 | Terminal control method and device, terminal and storage medium |
| CN114081771A (en) * | 2021-10-27 | 2022-02-25 | 豪中豪健康科技有限公司 | Massage system with biological recognition function |
| CN115862638A (en) * | 2023-03-01 | 2023-03-28 | 北京海上升科技有限公司 | Financial transaction operation and big data secure storage method and system based on block chain |
| CN116645969A (en) * | 2023-06-06 | 2023-08-25 | 北京云行在线软件开发有限责任公司 | Voiceprint recognition method based on network-based car interior scene |
-
2023
- 2023-10-08 CN CN202311295231.5A patent/CN117153163A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252464A (en) * | 2013-06-26 | 2014-12-31 | 联想(北京)有限公司 | Information processing method and information processing device |
| CN104834849A (en) * | 2015-04-14 | 2015-08-12 | 时代亿宝(北京)科技有限公司 | Dual-factor identity authentication method and system based on voiceprint recognition and face recognition |
| CN105244031A (en) * | 2015-10-26 | 2016-01-13 | 北京锐安科技有限公司 | Speaker identification method and device |
| KR20190048394A (en) * | 2017-10-31 | 2019-05-09 | 임태향 | A healthcare, beatycare and dietcare digital massage chair for digital massage chair system operated by artificial intelligence and big data |
| CN112084483A (en) * | 2019-06-14 | 2020-12-15 | 腾讯科技（深圳）有限公司 | Application locking and unlocking method, device, equipment and storage medium |
| CN111759658A (en) * | 2020-07-09 | 2020-10-13 | 江西台德智慧科技有限公司 | Massage chair control method and artificial intelligence massage chair |
| CN112558911A (en) * | 2020-12-04 | 2021-03-26 | 苏州思必驰信息科技有限公司 | Voice interaction method and device for massage chair |
| CN112818316A (en) * | 2021-03-08 | 2021-05-18 | 南京大正智能科技有限公司 | Voiceprint-based identity recognition and application method, device and equipment |
| CN113093980A (en) * | 2021-05-08 | 2021-07-09 | 北京字节跳动网络技术有限公司 | Terminal control method and device, terminal and storage medium |
| CN114081771A (en) * | 2021-10-27 | 2022-02-25 | 豪中豪健康科技有限公司 | Massage system with biological recognition function |
| CN115862638A (en) * | 2023-03-01 | 2023-03-28 | 北京海上升科技有限公司 | Financial transaction operation and big data secure storage method and system based on block chain |
| CN116645969A (en) * | 2023-06-06 | 2023-08-25 | 北京云行在线软件开发有限责任公司 | Voiceprint recognition method based on network-based car interior scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106653021B (en) | Voice wake-up control method and device and terminal | |
| US10476872B2 (en) | Joint speaker authentication and key phrase identification | |
| CA1097817A (en) | Speech recognition apparatus | |
| EP2810277B1 (en) | Speaker verification in a health monitoring system | |
| CN102568478B (en) | Video play control method and system based on voice recognition | |
| EP3998557A1 (en) | Audio signal processing method, model training method, and related apparatus | |
| WO2022078146A1 (en) | Speech recognition method and apparatus, device, and storage medium | |
| CN107623614A (en) | Method and apparatus for pushed information | |
| CN108010526B (en) | Voice processing method and device | |
| CN102647521B (en) | Method for removing lock of mobile phone screen based on short voice command and voice-print technology | |
| CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
| CN113129897B (en) | Voiceprint recognition method based on attention mechanism cyclic neural network | |
| CN113077798B (en) | Old man calls for help equipment at home | |
| CN105913842A (en) | Method for waking up mobile phone by custom voice | |
| CN109544745A (en) | A kind of intelligent door lock control method, apparatus and system | |
| CN117153163A (en) | Hand rehabilitation method, system, storage medium and terminal based on voice interaction | |
| CN109686365A (en) | A kind of audio recognition method and speech recognition system | |
| WO2019041871A1 (en) | Voice object recognition method and device | |
| CN117037820A (en) | Voice conversion method based on diffusion content and style decoupling | |
| Chit et al. | Myanmar continuous speech recognition system using fuzzy logic classification in speech segmentation | |
| CN111916074A (en) | Cross-device voice control method, system, terminal and storage medium | |
| Semary et al. | Using voice technologies to support disabled people | |
| Iswanto et al. | The Power-Normalized Cepstral Coefficient (PNCC) for convolutional neural networks-based robust speech command recognition | |
| CN115132204B (en) | Voice processing method, equipment, storage medium and computer program product | |
| CN116741193B (en) | Training method and device for voice enhancement network, storage medium and computer equipment |
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 |