CN116825288A - Autism rehabilitation course recording method and device, electronic equipment and storage medium - Google Patents
Autism rehabilitation course recording method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116825288A CN116825288A CN202310774309.5A CN202310774309A CN116825288A CN 116825288 A CN116825288 A CN 116825288A CN 202310774309 A CN202310774309 A CN 202310774309A CN 116825288 A CN116825288 A CN 116825288A
- Authority
- CN
- China
- Prior art keywords
- data
- text
- question
- answer
- student
- 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
- 206010003805 Autism Diseases 0.000 title claims abstract description 46
- 208000020706 Autistic disease Diseases 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 230000036651 mood Effects 0.000 claims abstract description 9
- 230000001815 facial effect Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013518 transcription Methods 0.000 claims description 9
- 230000035897 transcription Effects 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000005236 sound signal Effects 0.000 claims description 6
- 230000033764 rhythmic process Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000008451 emotion Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 206010011469 Crying Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The application relates to an artificial intelligence technology and discloses an autism rehabilitation course recording method, device, equipment and medium. The method comprises the following steps: teacher voice data and student voice data are identified from audio and video data of a rehabilitation classroom, and intonation identification is carried out on the student voice data; respectively converting teacher voice data and student voice data into first text data and second text data; analyzing matching data between the teacher's question in the first text data and the student's corresponding answer in the second text data; extracting a face image of a student from the audio and video data, and performing microexpressive recognition operation on the face image to obtain a microexpressive label of the student; and according to the mood intonation, the first text data, the second text data, the matching data and the micro-expression label, and a classroom record text of the rehabilitation classroom is obtained. The application can improve the objectivity and accuracy of the rehabilitation course record of the autism.
Description
Technical Field
The application relates to an artificial intelligence technology, which is suitable for the field of medical health, in particular to an autism rehabilitation course recording method, device, equipment and medium based on multi-mode data acquisition and analysis.
Background
In the autism rehabilitation classroom, when a teacher performs rehabilitation training on a student suffering from autism, the teacher needs to manually record the lesson presentation of the student, such as whether the student answers correctly or not, whether crying or not, whether the student is listening to the lesson or not, and the like, and evaluate the overall state of the student according to the record. But in practice, especially for autism students, whether to express interests, express concerns about people, express willingness to interact with people, stability of emotion, etc. under different scenes and interaction conditions is quite important for assessing the overall status of the autism students. For autism students generally do not have the advantage of expressing emotion, and the problems of subjectivity, inaccuracy and the like exist in manual evaluation records.
Disclosure of Invention
The application provides an autism rehabilitation course recording method, an autism rehabilitation course recording device, electronic equipment and a storage medium, and aims to improve the objectivity and accuracy of the autism rehabilitation course recording.
In order to achieve the above object, the present application provides a method for recording an autism rehabilitation session, comprising:
collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, carrying out speaker recognition on the voice dialogue data, recognizing teacher voice data and student voice data, and carrying out intonation recognition on the student voice data;
performing text transcription on the teacher voice data and the student voice data, and respectively converting the teacher voice data and the student voice data into first text data and second text data;
analyzing matching data between the teacher's question in the first text data and the corresponding answer of the student in the second text data;
recording the mood intonation, the first text data, the second text data and the matching data in a first template;
extracting video data from the audio and video data, extracting facial images of students from the video data, and performing microexpressive recognition operation on the facial images to obtain microexpressive labels of the students;
and recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of the rehabilitation classroom.
Optionally, the speaker recognition of the voice dialogue data, recognizing teacher voice data and student voice data, includes:
collecting sound signal characteristics in the voice dialogue data through a voiceprint recognition technology, wherein the sound signal characteristics comprise frequency, amplitude, tone, speech speed and voice rhythm characteristics;
performing voice clustering according to the voice signal characteristics;
and according to the voice clustering, recognizing teacher voice data and student voice data from the audio and video data by utilizing a pre-trained classifier.
Optionally, the performing the intonation recognition on the student voice data includes:
extracting frequency, energy and time domain characteristics of the student voice data;
and judging the intonation of the student voice data by using the frequency, energy and time domain features through a pre-constructed classifier.
Optionally, the analyzing the matching data between the question of the teacher in the first text data and the corresponding answer of the student in the second text data includes:
extracting a question text from the first text data, extracting an answer text from the second text data, and forming a plurality of question-answer text pairs from the question text and the answer text according to a timestamp;
selecting one of the question-answer text pairs, segmenting the question text and the answer text in the selected question-answer text pair, splicing the segmented question text into a question sequence, and splicing the corresponding segmented answer text into an answer sequence;
respectively inputting the question sequence and the answer sequence into a pre-trained BERT model, and obtaining the hidden state output by the last layer of the BERT model to obtain the hidden state of the question sequence and the hidden state of the answer sequence;
carrying out cosine similarity calculation on the hidden states of the question sequence and the hidden states of the answer sequence to obtain a similarity calculation result;
determine if there are question-answer text pairs that are not selected?
If the question-answer text pairs which are not selected exist, returning to the step of selecting one of the question-answer text pairs;
and if the question-answer text pairs which are not selected do not exist, generating question-answer matching data between the first text data and the second text data according to the similarity calculation result.
Optionally, the generating, according to the similarity calculation result, question-answer matching data between the first text data and the second text data includes:
when the similarity calculation result is greater than or equal to a preset threshold value, judging that the question text and the answer text in the question-answer text pair are matched;
when the similarity calculation result is smaller than a preset threshold value, judging that the question text and the answer text in the question-answer text pair are not matched;
and summarizing the matching results of all the question-answer text pairs to obtain question-answer matching data between the first text data and the second text data.
Optionally, the performing a microexpressive recognition operation on the facial image includes:
extracting a key frame from the facial image, and detecting a face area from the key frame;
inputting the face region into the Se_ResNet network for end-to-end micro-expression recognition, and outputting the micro-expression label of the student.
Optionally, the first template includes a timestamp, a question mark and a data item of a tone of a word when the answer is matched with the question mark or not, and the second template includes a micro-expression tag of a student and a data item of the timestamp, and the aligning and integrating operations are performed on the second template and the first template to obtain a classroom record text of a rehabilitation classroom, including:
and aligning and integrating the micro-expression labels of the students in the second template with the data of whether the answers of the students in the first template are matched or not according to the time stamp to obtain a classroom record text of the rehabilitation classroom.
In order to solve the above problems, the present application also provides an autism rehabilitation session recording device, the device comprising:
the voice and tone recognition module is used for collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, recognizing a speaker for the voice dialogue data, recognizing teacher voice data and student voice data, and performing voice and tone recognition for the student voice data;
the question matching analysis module is used for carrying out text transcription on the teacher voice data and the student voice data, respectively converting the teacher voice data and the student voice data into first text data and second text data, and analyzing matching data between questions of the teacher in the first text data and corresponding answers of the students in the second text data;
the recording module is used for recording the intonation, the first text data, the second text data and the matching data in a first template;
the micro-expression recognition module is used for extracting video data from the audio and video data, extracting facial images of students from the video data, and carrying out micro-expression recognition operation on the facial images to obtain micro-expression labels of the students;
the recording module is further used for recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of a rehabilitation classroom.
In order to solve the above-mentioned problems, the present application also provides an electronic apparatus including:
a memory storing at least one computer program; and
And the processor executes the computer program stored in the memory to realize the method for recording the autism rehabilitation courses.
In order to solve the above-mentioned problems, the present application also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned method of recording an autism rehabilitation session.
The method for recording the autism rehabilitation courses provided by the embodiment of the application uses a multi-mode data acquisition and analysis technology to obtain the emotion, the mood and other changes of students in real time, reduces the subjectivity and information omission problems of teachers when performing course recording, and provides more objective and more accurate recording and evaluation results. Therefore, the embodiment of the application improves the objectivity and accuracy of the rehabilitation course record of the autism.
Drawings
Fig. 1 is a flow chart of an autism rehabilitation session recording method according to an embodiment of the present application;
fig. 2 is a detailed flowchart of one step in the method for recording an autism rehabilitation session according to an embodiment of the present application;
fig. 3 is a schematic block diagram of an autism rehabilitation session recording device according to an embodiment of the present application;
fig. 4 is a schematic diagram of an internal structure of an electronic device for implementing an autism rehabilitation session recording method according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a method for recording an autism rehabilitation course. The execution subject of the autism rehabilitation course recording method includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the method provided by the embodiment of the application. In other words, the autism rehabilitation lesson recording method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: the server can be an independent server, or can be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDNs), basic cloud computing services such as big data and artificial intelligent platforms, and the like.
Referring to fig. 1, an embodiment of the present application provides a flowchart of an autism rehabilitation session recording method, where in the embodiment of the present application, the method includes:
s1, collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, carrying out speaker recognition on the voice dialogue data, recognizing teacher voice data and student voice data, and carrying out intonation recognition on the student voice data.
In the embodiment of the application, the audio and video data of the teacher in the course of the autism rehabilitation can be automatically collected in the course of the teacher giving the students, and the audio and video data can comprise the contents of asking questions by the teacher and answering the questions by the students, or the teacher carries out the recognition, the prize-winning, the stroking and the like on the students. In the embodiment of the application, the video equipment arranged at the preset position can be adopted, and when the preset triggering condition is met, the audio and video data can be automatically acquired. The preset triggering condition may be that a preset time arrives, and a preset event occurs, for example, when a person is detected in a preset area.
Further, in an embodiment of the present application, the speaker recognition for the voice dialogue data, recognizing teacher voice data and student voice data includes:
collecting sound signal characteristics in the voice dialogue data through a voiceprint recognition technology, wherein the sound signal characteristics comprise frequency, amplitude, tone, speech speed and voice rhythm characteristics;
performing voice clustering according to the voice signal characteristics;
and according to the voice clustering, recognizing teacher voice data and student voice data from the audio and video data by using a first classifier trained in advance.
A classifier is a machine learning algorithm that can classify new data by training and learning the input data. In the embodiment of the application, firstly, voice dialogue data are subjected to voice clustering according to voice signal characteristics to obtain voice data of different speakers, and then the teacher voice data are separated from the voice data of different speakers by utilizing a first classifier trained in advance according to the speech characteristics of the teacher, and the rest voice data are student voice data.
Further, according to the embodiment of the application, the voice data of the students are subjected to intonation recognition, so that whether the students cry, scream, low intonation and the like can be recognized.
In detail, the performing the intonation recognition on the student voice data includes:
extracting frequency, energy and time domain characteristics of the student voice data;
and judging the intonation of the student voice data by using the frequency, energy and time domain features through a pre-constructed second classifier.
In the embodiment of the application, the second classifier judges the intonation by utilizing the characteristics of frequency, energy, time domain and the like. For example, when the frequency of the voice data is higher, the energy is higher, and the time domain waveform is smoother, it is often indicated that the speaker is more excited or excited; when the frequency of the voice signal is lower, the energy is smaller, the time domain waveform is more jittered, the speaker's emotion is generally calm, etc.
S2, performing text transcription on the teacher voice data and the student voice data, and converting the teacher voice data and the student voice data into first text data and second text data respectively.
In detail, the embodiment of the application can perform text transcription on the teacher voice data and the student voice data through voice recognition (Automatic Speech Recognition, ASR) software or Natural Language Processing (NLP) technology, and convert the teacher voice data and the student voice data into first text data and second text data.
S3, analyzing matching data between the questions of the teacher in the first text data and the corresponding answers of the students in the second text data.
As described above, the teacher voice data is voice data about a question posed by the teacher, and the student voice data is voice data for a student to answer the question. In the embodiment of the application, the first text data corresponding to the voice data of the teacher and the second text data corresponding to the voice data of the student are respectively input into a pre-trained language model, such as BERT (Bidirectional Encoder Representation from Transformers) model, LLM (Large Language Model ) and the like, and whether the answer made by the student to the question posed by the teacher is correct or not is analyzed.
The language model is trained through text data, learns rich language knowledge and semantic relations, has very strong semantic understanding capability, and can understand the meaning, calculation logic, context correlation and the like of sentences.
In detail, referring to fig. 2, the analyzing the matching data between the question of the teacher in the first text data and the corresponding answer of the student in the second text data includes:
s30, extracting a question text from the first text data, extracting an answer text from the second text data, and forming a plurality of question-answer text pairs by the question text and the answer text according to a time stamp;
s31, selecting one of the question-answer text pairs, segmenting the question text and the answer text in the selected question-answer text pair, splicing the segmented question text into a question sequence, and splicing the corresponding segmented answer text into an answer sequence;
s32, respectively inputting the question sequence and the answer sequence into a pre-trained BERT model, and obtaining the hidden state output by the last layer of the BERT model to obtain the hidden state of the question sequence and the hidden state of the answer sequence;
s33, performing cosine similarity calculation on the hidden state of the question sequence and the hidden state of the answer sequence to obtain a similarity calculation result;
s34, judging whether a question-answer text pair which is not selected exists?
If the question-answer text pairs which are not selected exist, returning to the step S31;
if the question-answer text pairs which are not selected do not exist, S35, according to the similarity calculation result, question-answer matching data between the first text data and the second text data are generated.
In the embodiment of the application, when the similarity calculation result is greater than or equal to the preset threshold value, judging that the question text and the answer text in the question-answer text pair are matched, namely the answer is correct; when the similarity calculation result is smaller than a preset threshold value, judging that the question text and the answer text in the question-answer text pair are not matched, namely the answer is incorrect; and summarizing the matching results of all the question-answer text pairs to obtain question-answer matching data between the first text data and the second text data.
S4, recording the mood intonation, the first text data, the second text data and the matching data in a first template.
In the embodiment of the application, the first template comprises data items such as a time stamp, whether the question mark and the answer are matched or not, a intonation when the question is answered, and the like.
In the embodiment of the present application, the content output in the above step S2, for example, the question of the teacher in the first text data is a "completely identical item pairing question" (teaching children to put identical items together), and the record of "student placement correct" according to the answer of the student in the second text data or the feedback of the teacher to the student answer or action in the first text data is recorded in the template according to the timestamp, the question mark and the data items such as whether the answer matches or not, the intonation when answering the question, and the like.
S5, extracting video data from the audio and video data, extracting facial images of students from the video data, and performing microexpressive recognition operation on the facial images to obtain microexpressive labels of the students;
in the embodiment of the application, the faces of a teacher and a student are possibly collected simultaneously in the interaction process, so that the face image of the student is required to be identified from the video data, and the face image of the student is obtained by image processing such as background removal and distortion correction of the face image.
Further, the embodiment of the application can use a pre-trained third classifier to identify the face image of the student from the video data.
In an embodiment of the present application, the performing a microexpressive recognition operation on the facial image includes:
extracting a key frame from the facial image, and detecting a face area from the key frame;
inputting the face region into the Se_ResNet network for end-to-end micro-expression recognition, and outputting the micro-expression label of the student.
In the embodiment of the application, key frame extraction is performed from face images in a continuous video stream form by a traditional video processing method such as maximum inter-frame differential intensity or a neural network method such as 3D-CNN.
The Se_ResNet is a network formed by embedding SE (Squeeze and Excitation) Block into ResNet, the network introduces an Attention mechanism, and the SE Block module adaptively learns the relation among channels of an input image and performs weighted adjustment on a feature map, so that the network can better capture details and key features in the image and improve the accuracy of image classification. The neural network is a multi-label multi-classification network, and can output various micro-expression labels expressed by students, such as resistance, anxiety, straying, fatigue, anger, distraction and the like.
And S6, recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of the rehabilitation classroom.
In the embodiment of the application, the contents such as the micro-expression label and the time stamp of the student are recorded in the second template, the micro-expression label of the student in the second template is aligned and integrated with the answer matching data of the student in the first template according to the time stamp, the classroom record text of the rehabilitation classroom is obtained, and the emotion such as resistance, boring, liking, hesitation and the like can be shown when the student performs the task training can be recorded.
The method for recording the autism rehabilitation courses, which is provided by the application, uses a multi-mode data acquisition and analysis technology to obtain changes of emotion, mood and the like of students in real time, reduces the subjectivity and information omission problems of teachers during course recording, and provides more objective and accurate recording and evaluation results.
Fig. 3 is a functional block diagram of the recording device for rehabilitation courses for autism according to the present application.
The autism rehabilitation program recording device 100 of the present application may be installed in an electronic apparatus. Depending on the functions implemented, the autism rehabilitation program recording device may include a intonation recognition module 101, a question matching analysis module 102, a recording module 103, and a micro-expression recognition module 104, where the modules may also be referred to as units, and refer to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and are stored in a memory of the electronic device.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the intonation recognition module 101 is configured to collect audio and video data of a rehabilitation classroom, extract voice dialogue data from the audio and video data, perform speaker recognition on the voice dialogue data, recognize teacher voice data and student voice data, and perform intonation recognition on the student voice data;
the question matching analysis module 102 is configured to perform text transcription on the teacher voice data and the student voice data, respectively convert the teacher voice data and the student voice data into first text data and second text data, and analyze matching data between a question of the teacher in the first text data and a corresponding answer of the student in the second text data;
the recording module 103 is configured to record the intonation, the first text data, the second text data, and the matching data in a first template;
the micro-expression recognition module 104 is configured to extract video data from the audio and video data, extract a facial image of a student from the video data, and perform micro-expression recognition operation on the facial image to obtain a micro-expression label of the student;
the recording module 103 is further configured to record the micro-expression label in a second template, and perform alignment and integration operations on the second template and the first template, so as to obtain a classroom record text of the rehabilitation classroom.
In detail, each module in the autism rehabilitation course recording device 100 in the embodiment of the present application adopts the same technical means as the method for recording the autism rehabilitation course described in fig. 1 and 2, and can produce the same technical effects, which are not described herein.
Fig. 4 is a schematic structural diagram of an electronic device for implementing the method for recording an autism rehabilitation session according to the present application.
The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as an autism rehabilitation program.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of an autism rehabilitation program, etc., but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing Unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., an autism rehabilitation program, etc.) stored in the memory 11, and calling data stored in the memory 11.
The communication bus 12 may be a peripheral component interconnect standard (PerIPheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
Fig. 4 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 4 is not limiting of the electronic device and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure classification circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
Optionally, the communication interface 13 may comprise a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The autism rehabilitation program stored in the memory 11 of the electronic device is a combination of a plurality of computer programs, which when run in the processor 10, can realize:
collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, carrying out speaker recognition on the voice dialogue data, recognizing teacher voice data and student voice data, and carrying out intonation recognition on the student voice data;
performing text transcription on the teacher voice data and the student voice data, and respectively converting the teacher voice data and the student voice data into first text data and second text data;
analyzing matching data between the teacher's question in the first text data and the corresponding answer of the student in the second text data;
recording the mood intonation, the first text data, the second text data and the matching data in a first template;
extracting video data from the audio and video data, extracting facial images of students from the video data, and performing microexpressive recognition operation on the facial images to obtain microexpressive labels of the students;
and recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of the rehabilitation classroom.
In particular, the specific implementation method of the processor 10 on the computer program may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Embodiments of the present application may also provide a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, may implement:
collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, carrying out speaker recognition on the voice dialogue data, recognizing teacher voice data and student voice data, and carrying out intonation recognition on the student voice data;
performing text transcription on the teacher voice data and the student voice data, and respectively converting the teacher voice data and the student voice data into first text data and second text data;
analyzing matching data between the teacher's question in the first text data and the corresponding answer of the student in the second text data;
recording the mood intonation, the first text data, the second text data and the matching data in a first template;
extracting video data from the audio and video data, extracting facial images of students from the video data, and performing microexpressive recognition operation on the facial images to obtain microexpressive labels of the students;
and recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of the rehabilitation classroom.
Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
In addition, each functional module in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.
Claims (10)
1. A method of rehabilitation session recording for autism, the method comprising:
collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, carrying out speaker recognition on the voice dialogue data, recognizing teacher voice data and student voice data, and carrying out intonation recognition on the student voice data;
performing text transcription on the teacher voice data and the student voice data, and respectively converting the teacher voice data and the student voice data into first text data and second text data;
analyzing matching data between the teacher's question in the first text data and the corresponding answer of the student in the second text data;
recording the mood intonation, the first text data, the second text data and the matching data in a first template;
extracting video data from the audio and video data, extracting facial images of students from the video data, and performing microexpressive recognition operation on the facial images to obtain microexpressive labels of the students;
and recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of the rehabilitation classroom.
2. The method of claim 1, wherein said speaker recognition of said voice session data, recognizing teacher voice data and student voice data, comprises:
collecting sound signal characteristics in the voice dialogue data through a voiceprint recognition technology, wherein the sound signal characteristics comprise frequency, amplitude, tone, speech speed and voice rhythm characteristics;
performing voice clustering according to the voice signal characteristics;
and according to the voice clustering, recognizing teacher voice data and student voice data from the audio and video data by utilizing a pre-trained classifier.
3. The method for recording autism recovery courses according to claim 1, wherein the performing of intonation recognition on the student voice data includes:
extracting frequency, energy and time domain characteristics of the student voice data;
and judging the intonation of the student voice data by using the frequency, energy and time domain features through a pre-constructed classifier.
4. The method of claim 1, wherein said analyzing match data between a teacher's question in said first text data and a student's corresponding answer in a second text data comprises:
extracting a question text from the first text data, extracting an answer text from the second text data, and forming a plurality of question-answer text pairs from the question text and the answer text according to a timestamp;
selecting one of the question-answer text pairs, segmenting the question text and the answer text in the selected question-answer text pair, splicing the segmented question text into a question sequence, and splicing the corresponding segmented answer text into an answer sequence;
respectively inputting the question sequence and the answer sequence into a pre-trained BERT model, and obtaining the hidden state output by the last layer of the BERT model to obtain the hidden state of the question sequence and the hidden state of the answer sequence;
carrying out cosine similarity calculation on the hidden states of the question sequence and the hidden states of the answer sequence to obtain a similarity calculation result;
determine if there are question-answer text pairs that are not selected?
If the question-answer text pairs which are not selected exist, returning to the step of selecting one of the question-answer text pairs;
and if the question-answer text pairs which are not selected do not exist, generating question-answer matching data between the first text data and the second text data according to the similarity calculation result.
5. The method for recording an autism rehabilitation session according to claim 4, wherein generating question-answer matching data between the first text data and the second text data according to the similarity calculation result includes:
when the similarity calculation result is greater than or equal to a preset threshold value, judging that the question text and the answer text in the question-answer text pair are matched;
when the similarity calculation result is smaller than a preset threshold value, judging that the question text and the answer text in the question-answer text pair are not matched;
and summarizing the matching results of all the question-answer text pairs to obtain question-answer matching data between the first text data and the second text data.
6. The method for recording an autism rehabilitation session according to claim 1, wherein the performing a microexpressive recognition operation on the face image includes:
extracting a key frame from the facial image, and detecting a face area from the key frame;
inputting the face region into the Se_ResNet network for end-to-end micro-expression recognition, and outputting the micro-expression label of the student.
7. The method for recording an autism rehabilitation lesson according to claim 1, wherein the first template includes a timestamp, a question mark and answer matching or not, a data item of a mood tone when answering a question, and the second template includes a micro-expression tag of a student and a data item of a timestamp, and the aligning and integrating the second template with the first template to obtain a classroom record text of a rehabilitation classroom includes:
and aligning and integrating the micro-expression labels of the students in the second template with the data of whether the answers of the students in the first template are matched or not according to the time stamp to obtain a classroom record text of the rehabilitation classroom.
8. An autism rehabilitation program recording device, characterized by comprising:
the voice and tone recognition module is used for collecting audio and video data of a rehabilitation classroom, extracting voice dialogue data from the audio and video data, recognizing a speaker for the voice dialogue data, recognizing teacher voice data and student voice data, and performing voice and tone recognition for the student voice data;
the question matching analysis module is used for carrying out text transcription on the teacher voice data and the student voice data, respectively converting the teacher voice data and the student voice data into first text data and second text data, and analyzing matching data between questions of the teacher in the first text data and corresponding answers of the students in the second text data;
the recording module is used for recording the intonation, the first text data, the second text data and the matching data in a first template;
the micro-expression recognition module is used for extracting video data from the audio and video data, extracting facial images of students from the video data, and carrying out micro-expression recognition operation on the facial images to obtain micro-expression labels of the students;
the recording module is further used for recording the micro-expression label in a second template, and performing alignment and integration operation on the second template and the first template to obtain a classroom record text of a rehabilitation classroom.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of rehabilitation program according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for recording an autism rehabilitation session according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774309.5A CN116825288A (en) | 2023-06-27 | 2023-06-27 | Autism rehabilitation course recording method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774309.5A CN116825288A (en) | 2023-06-27 | 2023-06-27 | Autism rehabilitation course recording method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116825288A true CN116825288A (en) | 2023-09-29 |
Family
ID=88117951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310774309.5A Pending CN116825288A (en) | 2023-06-27 | 2023-06-27 | Autism rehabilitation course recording method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116825288A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473304A (en) * | 2023-12-28 | 2024-01-30 | 天津大学 | Multi-mode image labeling method and device, electronic equipment and storage medium |
| CN118197363A (en) * | 2024-01-05 | 2024-06-14 | 山东同其万疆科技创新有限公司 | Education quality supervision method based on voice processing |
-
2023
- 2023-06-27 CN CN202310774309.5A patent/CN116825288A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117473304A (en) * | 2023-12-28 | 2024-01-30 | 天津大学 | Multi-mode image labeling method and device, electronic equipment and storage medium |
| CN118197363A (en) * | 2024-01-05 | 2024-06-14 | 山东同其万疆科技创新有限公司 | Education quality supervision method based on voice processing |
| CN118197363B (en) * | 2024-01-05 | 2024-10-18 | 山东同其万疆科技创新有限公司 | Education quality supervision method based on voice processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991381B (en) | Real-time classroom student status analysis and indication reminding system and method based on behavior and voice intelligent recognition | |
| CN110782921B (en) | Voice evaluation method and device, storage medium and electronic device | |
| CN111144191B (en) | Font identification method, font identification device, electronic equipment and storage medium | |
| CN109359215A (en) | Video intelligent method for pushing and system | |
| CN107918821A (en) | Teachers ' classroom teaching process analysis method and system based on artificial intelligence technology | |
| CN116825288A (en) | Autism rehabilitation course recording method and device, electronic equipment and storage medium | |
| CN110825867B (en) | Similar text recommendation method and device, electronic equipment and storage medium | |
| CN111833861B (en) | Event evaluation report generation based on artificial intelligence | |
| CN109545218A (en) | Voice recognition method and system | |
| CN108520662B (en) | Teaching feedback system based on knowledge point analysis | |
| CN107609736A (en) | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology | |
| CN111833853A (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
| CN108734379A (en) | It is a kind of that Training Methodology on the line of differentiation is realized to contact staff | |
| CN108898115A (en) | data processing method, storage medium and electronic equipment | |
| CN110956142A (en) | Intelligent interactive training system | |
| CN113888757A (en) | Examination paper intelligent analysis method, examination paper intelligent analysis system and storage medium based on benchmarking evaluation | |
| CN117252259A (en) | Deep learning-based natural language understanding method and AI teaching aid system | |
| CN116010569A (en) | Online answering method, system, electronic equipment and storage medium | |
| CN111985282A (en) | Learning ability training and evaluating system | |
| Krishnamoorthy et al. | E-Learning Platform for Hearing Impaired Students | |
| CN112966518A (en) | High-quality answer identification method for large-scale online learning platform | |
| CN116226410B (en) | Teaching evaluation and feedback method and system for knowledge element connection learner state | |
| CN111563697A (en) | Online classroom student emotion analysis method and system | |
| CN116883208A (en) | Classroom quality assessment system based on images | |
| CN115527404A (en) | Artificial intelligence self-adaptation interactive teaching system |
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 |