CN117672026B - Educational service question-answering dialogue system with privacy protection - Google Patents
Educational service question-answering dialogue system with privacy protection Download PDFInfo
- Publication number
- CN117672026B CN117672026B CN202410133167.9A CN202410133167A CN117672026B CN 117672026 B CN117672026 B CN 117672026B CN 202410133167 A CN202410133167 A CN 202410133167A CN 117672026 B CN117672026 B CN 117672026B
- Authority
- CN
- China
- Prior art keywords
- dialogue
- module
- fixedly connected
- lip
- ring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 29
- 238000004088 simulation Methods 0.000 claims description 18
- 230000009471 action Effects 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 235000017166 Bambusa arundinacea Nutrition 0.000 claims 8
- 235000017491 Bambusa tulda Nutrition 0.000 claims 8
- 241001330002 Bambuseae Species 0.000 claims 8
- 235000015334 Phyllostachys viridis Nutrition 0.000 claims 8
- 239000011425 bamboo Substances 0.000 claims 8
- 230000005611 electricity Effects 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 6
- 208000027418 Wounds and injury Diseases 0.000 abstract description 4
- 230000006378 damage Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 208000014674 injury Diseases 0.000 abstract description 4
- 230000009323 psychological health Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 7
- 230000004064 dysfunction Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 239000013589 supplement Substances 0.000 description 4
- 206010011878 Deafness Diseases 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 206010071368 Psychological trauma Diseases 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000016354 hearing loss disease Diseases 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Educational Technology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Educational Administration (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to an educational service question-answering dialogue system with privacy protection, which is applied to the field of online education, wherein language handicapped people can smoothly input dialogue contents through the combination of lip language identification and text input modes, then the dialogue contents are converted into virtual voice type audio dialogue contents for other people to play, unified dialogue processing of all users is realized, the special characters among the users are not easy to find, good hiding effect is achieved on special people, privacy of the language handicapped people is effectively protected, the content which causes psychological injury to the special people can be effectively blocked by detecting sensitive words before the dialogue contents are sent out, psychological health of the special people in the online learning process is further maintained, in addition, the lip language identification area size can be effectively controlled by adopting a face hiding identifier, and the face privacy safety of the users is further protected.
Description
Technical Field
The invention relates to a question-answering dialogue system, in particular to an educational service question-answering dialogue system with privacy protection, which is applied to the field of online education.
Background
The remote on-line education is an education mode of mainly adopting a multimedia mode to carry out system teaching between students and teachers and between students and education organizations, is a novel education mode generated along with the development of modern information technology, is flexible, can greatly save commute cost, can freely select class listening time, and is popular with vast learners.
The teaching characteristic of the remote online education is that the learning content video is displayed through the learning terminal, and learning education processes such as teaching, solving, discussion and the like can be carried out on the learning content through the question-answer dialogue among users.
However, for the special crowd in society, such as the crowd with voice dysfunction, because of lacking the speech ability, there is great obstacle in the use of online education, and the privacy of current online education is relatively poor, and the self condition of special crowd is known by other person or other learners easily in the learning process, thereby causes special crowd to receive the unconscious treatment of other personnel, influences its study and psychological state.
Disclosure of Invention
Aiming at the prior art, the technical problem to be solved by the invention is that the existing online education mode has a large obstacle for special people with voice dysfunction, and the special people are easily subjected to the non-civilization treatment of other people due to poor privacy, so that the learning and psychological state of the special people are influenced.
In order to solve the problems, the invention provides an educational service question-answering dialogue system with privacy protection, which comprises an educational terminal, wherein the educational terminal comprises a dialogue input module, a multi-element data overall module, a sensitive word extraction module, a sound simulation playing module, an audio conversion module and a reminding and refusing module, the dialogue input module comprises a lip language identification unit, a text correction unit and a recording unit, the lip language identification unit is used for acquiring and identifying lip actions of characters and converting the lip actions into text information through a camera, the text correction unit is used for inputting the text information, the recording unit is used for acquiring human voice and forming audio information, the multi-element data overall module is used for transmitting one of the text information and the audio information to the sensitive word extraction module, the sensitive word extraction module is connected with a sensitive word library, the sound simulation playing module is used for playing the data information identified by the sensitive word extraction module in a virtual human voice mode, and the reminding and refusing module is used for transmitting the data information identified by the sensitive word extraction module back to the dialogue input module and giving unqualified reminding.
An educational service question-answering dialogue system with privacy protection, the dialogue method comprises the following steps:
s1, a user A automatically selects a speaking, text or lip recognition mode according to the condition of physical conditions, dialogue contents are input into an education terminal, and the multi-data overall module transmits the dialogue contents to the sensitive word extraction module;
S2, a sensitive word extraction module detects sensitive words of dialogue content, and when handicapped sensitive words are not found, step S3 is carried out; when the handicapped sensitive words are found, performing a step S4;
s3, the sensitive word extraction module transmits the detected dialogue content to the sound simulation playing module, and the sound simulation playing module transmits the dialogue content to the education terminal of the user B by adopting simulated voice;
after receiving the dialogue content, the user B can selectively adopt the sound simulation playing module to directly play the dialogue content according to the condition of the user B or adopt the audio conversion module to convert the dialogue content into text content for viewing;
S4, the sensitive word extraction module transmits the detected unqualified dialogue content to the reminding and refusing module, the reminding and refusing module transmits the unqualified dialogue content back to the dialogue input module, and gives an unqualified reminding to remind the user A to input the dialogue content again.
As still another improvement of the present application, in step S1, when the user a inputs the dialogue content in a manner of selecting the lip recognition, the lip recognition may be performed using the face-hidden recognizer.
In addition to the improvement of the application, the face hiding identifier comprises a single-mouth barrel and a cylinder, wherein one ends of the single-mouth barrel and the cylinder, which are close to each other, are fixedly connected with round soft sleeves, an elastic rope ring is fixedly connected between a pair of round soft sleeves, one end of the single-mouth barrel, which is far away from the cylinder, is fixedly connected with a wire, one end of the wire, which is far away from the single-mouth barrel, is electrically connected with a connector, the connector is matched with an interface on an education terminal, and a camera is fixedly arranged on the inner wall of the single-mouth barrel, which is far away from the cylinder.
As a further improvement supplement of the application, one end of the single-port cylinder and one end of the cylinder, which are close to each other, are respectively provided with an annular groove, the annular grooves are positioned at the inner sides of the ports of the round soft sleeve, the inner parts of the annular grooves are connected with the annular cylinder in a sliding manner, and a pair of cylinders are fixedly connected between the end parts of the annular cylinder and the inner walls of the annular grooves.
As a further improvement supplement of the application, the lower ends of the single-port cylinder and the cylinder are respectively fixedly connected with a main base and an auxiliary base, and a telescopic plate is fixedly connected between the main base and the auxiliary base.
In addition to the further improvement of the application, the expansion plate comprises an outer plate frame and an inner plate, wherein one ends of the outer plate frame and the inner plate, which are far away from each other, are respectively fixedly connected with the auxiliary base and the main base, one end of the inner plate is slidably connected to the inside of the outer plate frame, and a pair of compression springs are fixedly connected between the two ends.
As a further improvement supplement of the application, one end of the auxiliary base far away from the expansion plate is fixedly connected with a bottom plate, the upper side of the bottom plate is provided with a base plate, an electric push rod is fixedly connected between the two, and the upper end of the base plate is fixedly connected with a soft cushion.
In addition to the improvement of the application, the side end of the auxiliary base is fixedly connected with a controller, the camera, the air cylinder and the electric push rod are electrically connected with the controller, and the controller is electrically connected with the education terminal through wires.
As a supplement to a further development of the application, the elastic cord loop is initially of annular configuration and has an inner diameter smaller than the diameter of the inner ring of the cylinder.
In summary, the application combines the three input modes of lip language identification, characters and spoken language recording, so that the language handicapped can smoothly input dialogue content, then the dialogue content is converted into the virtual voice type audio dialogue content by adopting the voice simulation playing module for playing by others, unified dialogue processing of all users is realized, the special characters among the users are not easy to find, good hiding effect is achieved for special crowds, privacy of the special crowds is effectively protected, and the content which is easy to cause psychological injury to the special crowds can be effectively blocked by detecting sensitive words of the dialogue content before the dialogue content is sent out, so that psychological health of the special crowds in the on-line learning process is further maintained.
Drawings
FIG. 1 is a system diagram of embodiments 1 and 2 of the present application;
FIG. 2 is a perspective view of the device according to embodiments 1 and 2 of the present application;
FIG. 3 is a partial perspective view of the device according to embodiments 1 and 2 of the present application;
FIG. 4 is a schematic side view of a portion of the apparatus according to embodiments 1 and 2 of the present application;
FIG. 5 is a schematic side view of a portion of the apparatus according to embodiments 1 and 2 of the present application in use;
FIG. 6 is a schematic diagram showing a partial side structure of the device according to embodiments 1 and 2 of the present application;
FIG. 7 is a diagram showing a structural change of the device according to embodiments 1 and 2 of the present application;
fig. 8 is a schematic diagram of a partial side structure of the device according to embodiments 1 and 2 of the present application in use.
The reference numerals in the figures illustrate:
The education terminal 1, the lead 2, the single-port cylinder 3, the cylinder 4, the soft sleeve 5, the elastic rope loop 6, the main base 7, the auxiliary base 8, the expansion plate 9, the outer plate frame 91, the inner plate 92, the compression spring 93, the ring cylinder 10, the cylinder 11, the bottom plate 12, the electric push rod 13, the backing plate 14, the soft cushion 15 and the controller 16.
Detailed Description
2 Embodiments of the present application will be described in detail with reference to the accompanying drawings.
Embodiment 1:
The invention provides an educational service question-answer dialogue system with privacy protection, referring to fig. 1 and 2, comprising an educational terminal 1, wherein the educational terminal 1 comprises a dialogue input module, a multi-element data overall module, a sensitive word extraction module, a sound simulation playing module, an audio conversion module and a reminding and refusing module, the dialogue input module comprises a lip recognition unit, a word correction unit and a recording unit, the lip recognition unit is used for collecting and recognizing lip actions of characters through a camera and converting the lip actions into word information, the word correction unit is used for inputting the word information, the recording unit is used for collecting voice and forming audio information, the multi-element data overall module is used for transmitting one of the word information and the audio information to the sensitive word extraction module, the sound simulation playing module is used for playing data information recognized by the sensitive word extraction module in a virtual voice mode, and the refusing module is used for transmitting the data information recognized by the sensitive word extraction module back to the dialogue input module and giving disqualification reminding.
The sensitive word extraction module is connected with a sensitive word library, sensitive words related to disabilities, such as dumb, deaf and dumb, disabled and the like, are stored in the sensitive word library, and the disability sensitive words are easy to cause psychological trauma to special people and are irrelevant to learning education contents, so that the sensitive word extraction module is used for detecting the dialogue contents to confirm whether the dialogue contents are qualified or not, and qualified dialogue contents without the sensitive words can be remotely transmitted to education terminals 1 of other learning users.
An educational service question-answering dialogue system with privacy protection, the dialogue method comprises the following steps:
S1, a user A automatically selects a speaking, text or lip recognition mode according to the condition of physical conditions, dialogue contents are input into an education terminal 1, and a multivariate data overall module transmits the dialogue contents to a sensitive word extraction module;
S2, a sensitive word extraction module detects sensitive words of dialogue content, and when handicapped sensitive words are not found, step S3 is carried out; when the handicapped sensitive words are found, performing a step S4;
S3, the sensitive word extraction module transmits the detected dialogue content to the sound simulation playing module, and the sound simulation playing module transmits the dialogue content to the education terminal 1 of the user B by adopting simulated voice;
after receiving the dialogue content, the user B can selectively adopt the sound simulation playing module to directly play the dialogue content according to the condition of the user B or adopt the audio conversion module to convert the dialogue content into text content for viewing;
S4, the sensitive word extraction module transmits the detected unqualified dialogue content to the reminding and refusing module, the reminding and refusing module transmits the unqualified dialogue content back to the dialogue input module, and gives an unqualified reminding to remind the user A to input the dialogue content again.
First, three dialogue input modes are set in the application: the language handicapped can recognize the lip action of the user through the lip recognition unit, then the lip action is converted into text information, and when the text information obtained through conversion has local recognition errors, the text information can be locally regulated through the text correction unit to obtain final dialogue content; the normal user can directly express dialogue content by using spoken language, and the dialogue content is recorded by a recording module and forms audio information; in addition, the normal user and the language handicapped can directly adopt the text correction unit to input the dialogue content in text form, and the three dialogue input modes enable the language handicapped to smoothly input the dialogue content to perform online education learning and perform a question-answer learning process with other people;
Secondly, the voice simulation playing module is adopted to convert text type dialogue contents or audio type dialogue contents into virtual voice type audio dialogue contents, and then the virtual voice type audio dialogue contents are transmitted to the education terminal 1 of other users, so that unified dialogue processing of all users is realized, the special features of the users are not easy to find each other, good hiding effect is achieved for special crowds, privacy of language dysfunction people is effectively protected, and the voice simulation playing module can be used for safely and generally receiving online education with normal people, and is not easy to be damaged by speech of other users on line;
and the sensitive word extraction module is arranged to detect the sensitive words of the text type dialogue content or the audio type dialogue content input by the user, and detect whether the handicapped sensitive words exist in the dialogue content, if so, the dialogue content is not in accordance with the playing rules, and psychological injury is easily generated to the user belonging to the special crowd, so that the reminding and refusing module transmits the unqualified dialogue content back to the dialogue input module to remind the user to re-edit, the users can be effectively blocked from exchanging some content which is irrelevant to learning education and is easy to cause psychological injury to the special crowd, and the dignity and psychological health of the special crowd in the on-line learning process are further maintained.
In addition, if the person with language dysfunction has hearing impairment at the same time, after receiving the dialogue content of other people, the person with language dysfunction can adopt the audio conversion module to convert the dialogue content into text content for viewing, so that the deaf-mute can smoothly conduct on-line question-answering dialogue education.
Embodiment 2:
in the present embodiment, on the basis of ensuring that the structure of embodiment 1 is unchanged, a face hiding identifier is added, and in step S1, when the user a selects the manner of lip language recognition to input the dialogue content, the face hiding identifier may be used to perform lip language recognition, so that privacy protection for the person with language dysfunction may be further improved.
As shown in fig. 2-4, the face hiding identifier comprises a single-port barrel 3 and a barrel 4, wherein the ends of the single-port barrel 3 and the barrel 4, which are close to each other, are fixedly connected with a round soft sleeve 5, an elastic rope ring 6 is fixedly connected between a pair of round soft sleeves 5, the elastic rope ring 6 is of a circular ring-shaped structure in an initial state, the inner diameter of the elastic rope ring is smaller than the diameter of the inner ring of the barrel 4, one end of the single-port barrel 3, which is far away from the barrel 4, is fixedly connected with a wire 2, one end of the wire 2, which is far away from the single-port barrel 3, is electrically connected with a joint, the joint is matched with an interface on the education terminal 1, a camera is fixedly installed on the inner wall of the single-port barrel 3, which is far away from the barrel 4, and in use, the joint on the wire 2 is inserted into the interface of the education terminal 1, so that the face hiding identifier and the education terminal 1 can be connected and data transmission can be realized, the ends of the single-port barrel 3 and the barrel 4, which are close to each other, are all provided with annular grooves, are positioned on the inner sides of the ports of the round soft sleeve 5, the annular grooves are slidably connected with the annular barrel 10, a pair of rings 11, the ends of the annular barrels 10 and the inner walls of the cylinder 10 are fixedly connected with the inner walls of the annular ring 11, the annular rings 10, the inner walls of the annular ring 11, and the inner walls of the annular ring 10, the annular ring are controlled by the inner ring, and the annular ring of the annular ring 6, and the annular ring diameter of the annular ring 6, and the ring 6, which is the diameter of the ring-shaped ring moving ring and the ring-shaped ring moving ring.
Referring to fig. 2 and 4, the lower ends of the single-port cylinder 3 and the cylinder 4 are fixedly connected with the main base 7 and the auxiliary base 8 respectively, a telescopic plate 9 is fixedly connected between the main base 7 and the auxiliary base 8, the telescopic plate 9 comprises an outer plate frame 91 and an inner plate 92, one ends of the outer plate frame 91 and the inner plate 92, which are far away from each other, are fixedly connected with the auxiliary base 8 and the main base 7 respectively, one ends of the inner plate 92 are slidably connected with the inner part of the outer plate frame 91, a pair of compression springs 93 are fixedly connected between the two ends, the telescopic plate 9 has a connection stabilizing effect on the single-port cylinder 3 and the cylinder 4, and meanwhile, the single-port cylinder 3 and the cylinder 4 can be stably close to or far away from each other through the elastic telescopic effect of the telescopic plate 9, so that the round soft sleeve 5 between the single-port cylinder 3 and the cylinder 4 can be in a straightened state, and the elastic rope ring 6 is positioned in a central position under the straightening of the pair of round soft sleeves 5.
The side end of the auxiliary base 8 is fixedly connected with a controller 16, the camera and the air cylinder 11 are electrically connected with the controller 16, the controller 16 is electrically connected with the education terminal 1 through a lead 2, and the controller 16 is used for realizing the operation control of the face hiding identifier.
As shown in fig. 5 to 7, the privacy protection mode of the face hiding identifier for the voice dysfunctional person is specifically as follows:
Fig. 5 is a face-hidden identifier initial state: the compression spring 93 is in a compressed state, the annular tube 10 extends out of the annular groove for a certain distance, the elastic rope ring 6 is in a slightly elastic stretching state, the inner diameter is smaller, the round soft sleeve 5 is in a tightening state under the elastic action of the elastic rope ring 6, the elastic coefficient of the compression spring 93 is smaller than that of the elastic rope ring 6, and therefore the elastic recovery action of the compression spring 93 does not keep the single-port tube 3 and the cylinder 4 away under the elastic action of the elastic rope ring 6;
When the lip recognition is carried out in the initial state, a user places the face at the mouth of the cylinder 4, the round soft sleeve 5 and the elastic rope loop 6 can greatly shield the sight of the camera, and only the shooting sight passing through the space inside the elastic rope loop 6 can reach the face of the mouth of the cylinder 4 to recognize the lip, so that the shooting recognition area of the camera is limited to the lip and the periphery thereof, other information of the face of the user is effectively protected, the face information of the person is not easy to leak, and the privacy safety of the user is further protected.
In addition, as shown in fig. 6 and 7, when the face hidden identifier in the initial state has poor accuracy in recognizing the lip language, the user can control the cylinder 11 to extend through the controller 16, so that the ring tube 10 continues to extend outwards, the contracted round soft sleeve 5 is supported outwards, the free part of the round soft sleeve 5 is reduced, the elastic rope ring 6 is forced to elastically deform and expand the inner diameter outwards in a nearly circular shape under the tensile force of the round soft sleeve 5, meanwhile, in combination with fig. 8, under the elastic recovery of the compression spring 93, the single-mouth tube 3 and the cylinder 4 have a mutual apart trend, so that the free part of the round soft sleeve 5 which is not supported by the ring tube 10 is kept in a tight state, the expanded elastic rope ring 6 is kept at the central position of the pair of round soft sleeves 5 under the tensile force of the round soft sleeve 5, the central area where the camera shoots the sight is kept unchanged, and the area where the camera shoots the sight is expanded, and the recognition area of the camera on the peripheral area of the lip is increased, thereby improving the accuracy in recognizing the lip language.
Referring to fig. 6 and 7, one end of the sub-base 8 far away from the expansion plate 9 is fixedly connected with a bottom plate 12, a base plate 14 is arranged on the upper side of the bottom plate 12, an electric push rod 13 is fixedly connected between the two, a soft pad 15 is fixedly connected to the upper end of the base plate 14, the electric push rod 13 is electrically connected with a controller 16, a user can adjust the height position of the soft pad 15 according to the face size of the user when carrying out lip language identification, the chin part is conveniently placed on the soft pad 15 and faces the pipe orifice direction of the cylinder 4 to carry out lip language identification, on one hand, the lip position is kept in the center area of the pipe orifice of the cylinder 4, the camera is conveniently identified, and on the other hand, the user head is supported, and the use comfort is improved.
The present application is not limited to the above-described embodiments, which are adopted in connection with the actual demands, and various changes made by the person skilled in the art without departing from the spirit of the present application are still within the scope of the present application.
Claims (6)
1. An educational service question-answering dialogue system with privacy protection, characterized in that: the system comprises an education terminal (1), wherein the education terminal (1) comprises a dialogue input module, a multi-element data overall module, a sensitive word extraction module, a sound simulation playing module, an audio conversion module and a reminding and playing rejection module, the dialogue input module comprises a lip recognition unit, a word correction unit and a recording unit, the lip recognition unit is used for collecting and recognizing lip actions of characters through a camera and converting the lip actions into word information, the word correction unit is used for inputting the word information, the recording unit is used for collecting voice and forming audio information, the multi-element data overall module is used for transmitting one of the word information and the audio information to the sensitive word extraction module, the sensitive word extraction module is connected with a sensitive word library, the sound simulation playing module is used for playing data information recognized by the sensitive word extraction module in a virtual voice mode, and the reminding and playing rejection module is used for transmitting the data information recognized by the sensitive word extraction module back to the dialogue input module and giving unqualified reminding;
The dialogue method of the educational service question-answer dialogue system with privacy protection comprises the following steps:
s1, a user A automatically selects a speaking, text or lip recognition mode according to the condition of physical conditions, dialogue contents are input into an education terminal (1), and a multivariate data overall module transmits the dialogue contents to a sensitive word extraction module;
S2, a sensitive word extraction module detects sensitive words of dialogue content, and when handicapped sensitive words are not found, step S3 is carried out; when the handicapped sensitive words are found, performing a step S4;
s3, the sensitive word extraction module transmits the detected dialogue content to the sound simulation playing module, and the sound simulation playing module transmits the dialogue content to the education terminal (1) of the user B by adopting simulated voice;
after receiving the dialogue content, the user B can selectively adopt the sound simulation playing module to directly play the dialogue content according to the condition of the user B or adopt the audio conversion module to convert the dialogue content into text content for viewing;
S4, the sensitive word extraction module transmits the detected unqualified dialogue content to the reminding and refusing module, the reminding and refusing module transmits the unqualified dialogue content back to the dialogue input module, and gives an unqualified reminder to remind the user A to input the dialogue content again;
In step S1, when user A selects the mode of lip language discernment to input dialogue content, can adopt face to hide the recognizer and carry out the lip language discernment, face to hide the recognizer and include single mouth section of thick bamboo (3) and drum (4), the one end that single mouth section of thick bamboo (3) and drum (4) are close to each other all fixedly connected with soft cover of circle (5), a pair of fixedly connected with elastic rope ring (6) between soft cover of circle (5), the one end fixedly connected with wire (2) that single mouth section of thick bamboo (3) kept away from drum (4), the one end electric connection that single mouth section of thick bamboo (3) was kept away from to wire (2) has the joint, joint and education terminal (1) interface phase-match, camera fixed mounting is kept away from on the inner wall of drum (4) at single mouth section of thick bamboo (3), the ring channel has all been seted up to the one end that single mouth section of thick bamboo (3) and drum (4) are close to each other, and the ring channel is located the port inboard of soft cover of circle (5), inside sliding connection have ring section of thick bamboo (10), the one end that ring section of thick bamboo (10) was kept away from drum (11) is kept away from to ring channel.
2. An educational service question-answer dialog system with privacy protection of claim 1, wherein: the lower ends of the single-port cylinder (3) and the cylinder (4) are respectively fixedly connected with a main base (7) and an auxiliary base (8), and a telescopic plate (9) is fixedly connected between the main base (7) and the auxiliary base (8).
3. An educational service question-answer dialog system with privacy protection, according to claim 2, characterized in that: the expansion plate (9) comprises an outer plate frame (91) and an inner plate (92), wherein one ends of the outer plate frame (91) and the inner plate (92) which are far away from each other are fixedly connected with the auxiliary base (8) and the main base (7) respectively, one end of the inner plate (92) is slidably connected to the inside of the outer plate frame (91), and a pair of compression springs (93) are fixedly connected between the two ends.
4. An educational service question-answer dialog system with privacy protection, according to claim 2, characterized in that: one end of the auxiliary base (8) far away from the expansion plate (9) is fixedly connected with a bottom plate (12), a base plate (14) is arranged on the upper side of the bottom plate (12), an electric push rod (13) is fixedly connected between the base plate and the base plate, and a soft cushion (15) is fixedly connected to the upper end of the base plate (14).
5. An educational service question-answer dialog system with privacy protection of claim 4, wherein: the side end fixedly connected with controller (16) of vice base (8), camera, cylinder (11) and electric putter (13) all are connected with controller (16) electricity, controller (16) are connected with education terminal (1) electricity through wire (2).
6. An educational service question-answer dialog system with privacy protection of claim 1, wherein: the elastic rope ring (6) is of a circular ring structure in an initial state, and the inner diameter of the elastic rope ring is smaller than the diameter of the inner ring of the cylinder (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410133167.9A CN117672026B (en) | 2024-01-31 | 2024-01-31 | Educational service question-answering dialogue system with privacy protection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410133167.9A CN117672026B (en) | 2024-01-31 | 2024-01-31 | Educational service question-answering dialogue system with privacy protection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117672026A CN117672026A (en) | 2024-03-08 |
| CN117672026B true CN117672026B (en) | 2024-04-19 |
Family
ID=90064512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410133167.9A Active CN117672026B (en) | 2024-01-31 | 2024-01-31 | Educational service question-answering dialogue system with privacy protection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117672026B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007330343A (en) * | 2006-06-12 | 2007-12-27 | Astec Corp:Kk | Blood collection supporting system adaptable to handicapped person |
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| CA2689026A1 (en) * | 2009-07-17 | 2011-01-17 | Andre Gene Douen | Systems, methods and articles for managing presentation of information |
| CN101950498A (en) * | 2010-08-25 | 2011-01-19 | 赵洪鑫 | Spoken Chinese encryption method for privacy protection |
| CN201732432U (en) * | 2009-05-26 | 2011-02-02 | 南充市商业银行股份有限公司 | Client dialogue-free server |
| WO2012046907A1 (en) * | 2010-10-05 | 2012-04-12 | 한국인터넷진흥원 | Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor |
| CN106056994A (en) * | 2016-08-16 | 2016-10-26 | 安徽渔之蓝教育软件技术有限公司 | Assisted learning system for gesture language vocational education |
| CN106514665A (en) * | 2016-11-24 | 2017-03-22 | 上海澜苍信息科技有限公司 | Education robot and control method thereof |
| CN111355924A (en) * | 2019-11-18 | 2020-06-30 | 杭州亿圣信息技术有限公司 | Method for detecting face scrambling code of special person based on video intelligent analysis |
| EP3716207A1 (en) * | 2019-03-26 | 2020-09-30 | Can Ince | Method and apparatus for diagnostic analysis of the function and morphology of microcirculation alterations |
| CN214541131U (en) * | 2021-05-18 | 2021-10-29 | 江西环境工程职业学院 | A face-to-face formula show shelf for psychology education |
| CN115439291A (en) * | 2022-08-11 | 2022-12-06 | 川北医学院 | Intelligent disabled assisting system |
| CN115482583A (en) * | 2022-09-20 | 2022-12-16 | 珠海市魅族科技有限公司 | Vehicle-mounted sign language translation method |
| CN116828258A (en) * | 2023-06-30 | 2023-09-29 | 湖南科技学院 | Personal data privacy protection method based on intelligent education |
| CN117037571A (en) * | 2023-08-28 | 2023-11-10 | 南京华设云信息技术有限公司 | AI-based artificial intelligence auxiliary communication system |
| CN117059102A (en) * | 2023-10-12 | 2023-11-14 | 广州市零脉信息科技有限公司 | Intelligent children toy dialogue system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160042654A1 (en) * | 2013-03-15 | 2016-02-11 | Ethan Fieldman | Methods for online education |
-
2024
- 2024-01-31 CN CN202410133167.9A patent/CN117672026B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007330343A (en) * | 2006-06-12 | 2007-12-27 | Astec Corp:Kk | Blood collection supporting system adaptable to handicapped person |
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| CN201732432U (en) * | 2009-05-26 | 2011-02-02 | 南充市商业银行股份有限公司 | Client dialogue-free server |
| CA2689026A1 (en) * | 2009-07-17 | 2011-01-17 | Andre Gene Douen | Systems, methods and articles for managing presentation of information |
| CN101950498A (en) * | 2010-08-25 | 2011-01-19 | 赵洪鑫 | Spoken Chinese encryption method for privacy protection |
| WO2012046907A1 (en) * | 2010-10-05 | 2012-04-12 | 한국인터넷진흥원 | Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor |
| CN106056994A (en) * | 2016-08-16 | 2016-10-26 | 安徽渔之蓝教育软件技术有限公司 | Assisted learning system for gesture language vocational education |
| CN106514665A (en) * | 2016-11-24 | 2017-03-22 | 上海澜苍信息科技有限公司 | Education robot and control method thereof |
| EP3716207A1 (en) * | 2019-03-26 | 2020-09-30 | Can Ince | Method and apparatus for diagnostic analysis of the function and morphology of microcirculation alterations |
| CN111355924A (en) * | 2019-11-18 | 2020-06-30 | 杭州亿圣信息技术有限公司 | Method for detecting face scrambling code of special person based on video intelligent analysis |
| CN214541131U (en) * | 2021-05-18 | 2021-10-29 | 江西环境工程职业学院 | A face-to-face formula show shelf for psychology education |
| CN115439291A (en) * | 2022-08-11 | 2022-12-06 | 川北医学院 | Intelligent disabled assisting system |
| CN115482583A (en) * | 2022-09-20 | 2022-12-16 | 珠海市魅族科技有限公司 | Vehicle-mounted sign language translation method |
| CN116828258A (en) * | 2023-06-30 | 2023-09-29 | 湖南科技学院 | Personal data privacy protection method based on intelligent education |
| CN117037571A (en) * | 2023-08-28 | 2023-11-10 | 南京华设云信息技术有限公司 | AI-based artificial intelligence auxiliary communication system |
| CN117059102A (en) * | 2023-10-12 | 2023-11-14 | 广州市零脉信息科技有限公司 | Intelligent children toy dialogue system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117672026A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4439740B2 (en) | Voice conversion apparatus and method | |
| Zhao et al. | Coding tactile symbols for phonemic communication | |
| US9858924B2 (en) | Voice processing apparatus and voice processing method | |
| CN1679371B (en) | Microphone and communication interface system | |
| US20170243582A1 (en) | Hearing assistance with automated speech transcription | |
| US20170303052A1 (en) | Wearable auditory feedback device | |
| US20140171036A1 (en) | Method of communication | |
| JP6291303B2 (en) | Communication support robot system | |
| US9028255B2 (en) | Method and system for acquisition of literacy | |
| Dhanjal et al. | Tools and techniques of assistive technology for hearing impaired people | |
| US20020158816A1 (en) | Translating eyeglasses | |
| CN117672026B (en) | Educational service question-answering dialogue system with privacy protection | |
| JP2003108362A (en) | Communication supporting device and system thereof | |
| CN111128180A (en) | Auxiliary dialogue system for hearing-impaired people | |
| US20180197564A1 (en) | Information processing apparatus, information processing method, and program | |
| KR100393122B1 (en) | System and Method for learning languages by using bone-path hearing function of a deaf person and storage media | |
| KR20160122869A (en) | Apparatus for being possible language converting using robot arm | |
| Freitas et al. | Multimodal silent speech interface based on video, depth, surface electromyography and ultrasonic doppler: Data collection and first recognition results | |
| JP6889597B2 (en) | robot | |
| KR102126388B1 (en) | Language rehabilitation system and method for the deaf | |
| KR102325506B1 (en) | Virtual reality-based communication improvement system and method | |
| US11100814B2 (en) | Haptic and visual communication system for the hearing impaired | |
| US20170018281A1 (en) | Method and device for helping to understand an auditory sensory message by transforming it into a visual message | |
| Zekveld et al. | User evaluation of a communication system that automatically generates captions to improve telephone communication | |
| KR102487847B1 (en) | System and method for providing call service for the hearing impaired |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |