21 results about "Hand mouthing" patented technology

The invention relates to the field of artificial intelligence, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a method, a device, equipment and a medium for detecting other person pickup behaviors, and the method comprises the steps: obtaining to-be-detected face examination video data, and carrying out the detection of a speaking segment, and obtaining a corresponding speaking video segment; identifying speaking content in the speaking video clip and matching the speaking content with a preset verbal skill to obtain a matched to-be-detected clip; performing mouth movement detection on the to-be-detected segments, and marking the segments which do not meet a preset mouth movement condition as suspected pickup segments; performing multi-dimensional false alarm detection on the suspected pickup fragments to obtain detection results of a plurality of false alarm factors; and according to the detection results of the plurality of false alarm factors, determining whether the suspected pickup fragment is misreported, if so, determining that the suspected pickup fragment is a normal answering behavior, and otherwise, determining that the suspected pickup fragment is a others pickup behavior. The accuracy of pickup detection is improved through multi-dimensional false alarm detection and filtering, and the increase of manual auditing cost due to false alarm is avoided.

The utility model provides a mouth moving device and relates to the technical field of toys. The utility model relates to a cam structure, which comprises a shell, an upper lip component, a lower lip component, a cam structure, a driving component and a resetting component, the front end of the upper lip component and the front end of the lower lip component are movably connected with the shell, and the front end of the upper lip component is positioned above the front end of the lower lip component; the middle of the upper lip assembly and the middle of the lower lip assembly are movably connected and both movably connected with the shell, the rear end of the upper lip assembly is located below the rear end of the lower lip assembly and both make contact with the cam structure, the cam structure is in transmission connection with the driving assembly, and the driving assembly is connected to the shell. The reset assembly is connected with the upper lip assembly and the lower lip assembly. The upper lip assembly and the lower lip assembly can be combined to form a scissor-shaped structural form, and can move simultaneously in the mouth opening process in cooperation with the lever principle, so that the mouth opening amplitude is greatly improved, the working current of the driving assembly can be reduced, and more electricity is saved.

The utility model discloses an electric dog mouth cover capable of preventing personal injury, and relates to the technical field of protective appliances, the electric dog mouth cover comprises a wearing element, a limiting element, a driving element and a clamping element, the wearing element is used for sleeving the neck of a pet dog, and the limiting element is used for covering the upper part of the nose and the upper part of the mouth of the pet dog; the two sides of the limiting element are connected with the two sides of the wearing element, the clamping element is used for sleeving the lower portion of the mouth of the pet dog, the two sides of the clamping element are rotationally connected to the two sides of the limiting element respectively, an output shaft of the driving element is connected with the clamping element and can drive the clamping element to rotate, and the clamping element can rotate to the throat of the pet dog. Or rotating to the jaw of the pet dog and matching with the limiting element to clamp the mouth of the pet dog. According to the invention, pet dog attack accidents can be effectively prevented, and the life quality of pet dogs can be ensured.

The application discloses a rodent mouth opener and a use method thereof, and the mouth opener comprises a sleeve, a sleeve rod, a locking nut, a U-shaped spring, a tooth buckle and a jaw pad. The sleeve, the sleeve rod and the locking nut constitute an oval mouth opener of the rodent mouth opener, the sleeve and the sleeve rod are connected into a whole through the locking nut, and the sleeve rod is convenient to adjust the mouth opener through expansion and contraction in the sleeve. The tooth buckle is connected to the middle part of the sleeve, the tooth buckle is matched with upper and lower front teeth of the rodent, and the tooth buckle is used for sleeving the front teeth of the rodent. The tooth buckle is provided with the jaw pad, the jaw pad prevents the mouth of the rodent from being hurt by being pressed, the middle part of the sleeve rod is connected with the U-shaped spring, the U-shaped spring provides elastic force to open the corners of the mouth of the rodent, and the U-shaped spring can assist in adjusting the opening degree. The application adopts a symmetrical structure design, is fixed firmly, avoids multiple adjustment of fixation and opening degrees of experimental animals caused by loosening or left-right shaking, and can adjust multiple structures to match rodent animals with different opening degrees for experiments.

An interactive stuffed toy device is disclosed, which is an interactive plush toy with AI-driven interactive capabilities. The interactive stuffed toy device comprises a body component that is configured in an animal shape with plush fur and twinkling lights. The body component includes voice recognition technology which is used to adapt stories based on a child's responses. The body component also lights up to show features of the toy, including tail, ears, eyes, mouth, etc. The body component also includes gesture recognition sensors to enable the device to respond to physical interactions, such as hugs or pats. Further, the device is battery-powered and made from hypoallergenic materials.

1. The name of the design product: oral rehabilitation exercise graphical user interface for electronic device. 2. The use of the design product: for an electronic device. 3. The design features of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design features: front view. 5. The electronic device is of conventional design, and other views are omitted. 6. The use of the graphical user interface: for oral rehabilitation exercise by recognizing the user's mouth opening and closing activity through facial recognition; the user's face image is in the upper right corner of the interface, the food image is in the middle, and the doll's mouth at the bottom of the interface will change accordingly according to the recognized user's mouth opening and closing. The front view shows the change state diagram 1 as the food falls, the user opens his mouth, and the change state diagram 2 as the user eats the falling food.

The utility model discloses a profiling whistle toy which comprises a toy shell, an ear structure is movably installed at the position of an upper port of the toy shell, a mouth structure is movably installed at the position of a lower port of the toy shell, and a trigger is movably installed at the position, located on one side of the mouth structure, of the surface of the toy shell. A mounting seat is fixedly mounted in the toy shell, a built-in whistle is fixedly mounted in the toy shell, and a trigger rotating shaft is fixedly mounted in the toy shell and located below the built-in whistle. According to the profiling whistle toy, when the built-in whistle is blown, opening and closing of a dog mouth, swinging of dog ears and the sound length, high pitch and low pitch of the built-in whistle can be controlled at the same time through the trigger, so that the profiling whistle toy is more interesting when being played, and the vividness of the toy is improved; in addition, the air blowing coordination of the hands and the mouths of the children can be exercised.

This invention discloses a mouse control method, medium, and device based on head posture recognition. It acquires a facial image and collects key feature points of the zygomatic arch, eyebrows, nose tip, and mouth. Based on the geometric relationship of these key feature points, it determines the head posture movement data in the horizontal and vertical directions. Based on the vector relationship of this movement data in a pre-established Cartesian coordinate system of the facial image, it calculates the mouse offset and controls the cursor movement accordingly. Based on the key feature point of the mouth, within a continuous fixed frame cycle, a mouse click event is triggered when the distance difference between the two corners of the mouth remains consistently greater than a set distance threshold. Advantages: Applicable to a contactless scenario, especially in the field of accessibility applications, it strengthens the solution to the problem of inconvenience for disabled users and has a certain degree of fun, with a broad market potential.

The utility model discloses an adhesive tape for breathing in a closed mouth. The adhesive tape comprises an adhesive tape roll. The adhesive tape roll (1) is formed by rolling the adhesive tape body (2). A first gluing area (3) and a second gluing area (4) are arranged on the two sides of the adhesive tape body (2) in the length direction respectively, and a non-glue area (5) is arranged in the middle of the adhesive tape body (2). When the adhesive tape roll (1) is used, a section of the adhesive tape body (2) is torn off according to the required length and is adhered to the upper part and the lower part of a lip. And the width of the non-glue area (5) is between 13mm and 24mm. And the adhesive tape roll is formed by preparing micropores from a PE film, coating medical adhesive and winding. The first gluing area and the second gluing area are respectively adhered to the upper part of the upper lip and the lower part of the lower lip of a user in use, and the non-glue area is in close contact with the lips of the user in a use state. According to the utility model, the adhesive tape bodies with different lengths can be torn off to be adhered to the mouth according to the requirements of users. Therefore, the manufacturing cost and the use cost are lower, the air permeability is good, the comfort is high, and the use is more convenient.

The utility model relates to a kind of mouth scar restricted mouth opening training device, including bite mouth body, the bottom end of the bite mouth body is detachably connected with water collecting cup;Two sides of the bite mouth body are respectively equipped with support arm one end, the other end of the support arm is equipped with V-shaped mouth corner support ware;The V-shaped mouth corner support ware includes V-shaped support and the outer wrapping layer being set on the outer wall of V-shaped support;The support arm is adjustable length arm.Relative to self-opening training, the present application carries out mouth opening support training to mouth scar restricted mouth corner by training device, improves mouth scar restricted mouth corner training efficiency, and does not need to carry out surgical operation, reduces risk such as wound infection;The size of mouth can be adjusted support arm length according to mouth scar restricted mouth, to realize the spacing adjustment between the two V-shaped mouth corner support wares, to adapt to different population or different period of mouth scar mouth corner training, and strong adaptability.

The utility model discloses an animal head fixing device, including head fixed frame, the front side of head fixed frame is provided with the flared medicine pouring subassembly, head fixed frame includes the U-shaped handle, the servo motor of fixed in the U-shaped handle rear end face to the guide rod of traversing U-shaped handle front end. Compared with the past hand fixing mode, the present fixing device avoids the direct contact between the personnel and the animal, the operator does not need to close contact with the potentially aggressive animal, and the risk of being bitten by the animal is effectively reduced. Moreover, the present fixing device adopts the side plate and the mouth opener design, which can realize stable fixation without causing harm to the animal's oral cavity, avoid the damage of the animal's oral mucosa and the loosening of the teeth, and is beneficial to the maintenance of the animal's health, the accuracy and reliability of the experimental data, and the animal welfare principle.

To provide a beverage container that enhances recyclability while suppressing the rise in beverage temperature, resulting in a pleasant mouthfeel. [Solution] A beverage container according to one embodiment is a beverage container 1 for holding a beverage. The beverage container 1 comprises a body portion 2, which is the part that a drinker touches with their fingers to hold the beverage container 1, and a mouth portion 3, which is the part that the drinker puts their mouth to when drinking the beverage. The beverage container 1 is made of pulp mold, and the density of the pulp mold paper is 0.3 (g / cm³). 3 ) greater than and 1.0 (g / cm³) 3 It is less than ).

The invention relates to the technical field of auxiliary diagnosis, in particular to a children twitch disorder auxiliary diagnosis method, which comprises the following steps of: shooting a video of 1-5 minutes for a doctor seeing child, the frame number of the video being greater than or equal to 67 frames; acquiring head information of a doctor seeing child through the video; establishing a time axis for the video; performing blink identification, mouth opening identification and head shaking identification on the head information; judging whether a mouth is opened within 15-35ms after each blink on the time axis, if so, judging whether head shaking exists within 30-75ms after the first node, and if so, recording as complete twitch; according to the method, the eyes, the mouth and the head are independently identified by adopting an algorithm, and the complete twitch is defined in cooperation with the time axis and the nerve conduction velocity, so that normal blinking, normal mouth opening and normal head shaking can be prevented from being listed as abnormal conditions, the diagnosis efficiency is improved, and the diagnosis objectivity and accuracy are enhanced.

Easily detachable medical suction device for a mouth opening, comprising an opening part (1) which is inserted into a mouth of a user, wherein teeth are thereafter held on the opening part (1) and the opening part (1) can thus maintain an open state of the mouth, and within which a hole is formed so that it sucks a liquid within the mouth therefrom; and a suction part (2) which is provided with a guide portion (410) whose one end is detachably attachable to another end of the opening part (1) and to whose other end a pipe (T) is connected, and which also has an extractor for exerting an extraction force; wherein the opening part (1) comprises: a first body (100) provided with first concave portions (120) and (120a) to which an occlusal surface is attached, and a first gap (110) through which the liquid is sucked; and a second body (200) formed extending from another end of the first body (100), and which is provided with holding portions (230) and (230a) on which the teeth are held, first support portions (231) and (231a) each formed projecting from the respective sides of the holding portions (230) and (230a) and located between a row of teeth and an oral mucosa; characterized in that the opening part (1) also comprises: Handles (240) and (240a) each formed extending from the respective holding portions (230) and (230a); and a third body (300) provided with a connecting groove (310) to which the suction part (2) is attached or from which the suction part (2) is separated.

The invention provides a wearable manual control simulation cattle. The wearable manual control simulation cattle comprises a cattle body assembly, a cattle head assembly and a cattle eye assembly. The cattle body assembly is fixed to the back of an operator through a bandage, bracket frameworks on the two sides of the cattle body assembly are connected with the two legs of the operator in a staggered mode through bracket pull wires, and brackets are driven to simulate actions when the cattle body assembly walks. The head assembly is hung on the neck framework through a ball head and a ball groove structure and can deflect flexibly. An operator manipulates the eye handle and the operation handle on the head skeleton with one hand, and controls the two eyes to blink synchronously through the stay wire; and the other hand operates a mouth operation handle on the neck skeleton, and the mouth is controlled to be opened and closed through a pull wire to simulate chewing. The device is flexible in structure, capable of vividly simulating walking, blinking and chewing actions of the cattle, convenient to operate and high in performance ornamental value.

The application relates to the technical field of financial technology, and discloses a method and device for detecting a behavior of answering on behalf of others, equipment and a medium. The method comprises the following steps: obtaining voice text content corresponding to a target video segment and a time stamp of each character in the voice text content by using a voice recognition technology; if the voice text content matches a preset dialogue template, performing mouth movement detection on the target video segment according to the time stamp and generating a mouth movement detection result; if the mouth movement detection result is mouth movement, storing voiceprint data corresponding to the voice text content in a voiceprint library corresponding to a target event; and if the mouth movement detection result is no mouth movement, obtaining historical voiceprint data corresponding to the target event from the voiceprint library, detecting target voiceprint data of the target video segment according to the historical voiceprint data, and obtaining a result of detecting a behavior of answering on behalf of others by an outsider. The embodiment of the application can improve the accuracy of detecting the behavior of answering on behalf of others by the outsider.

Disclosed in embodiments of the present disclosure are a data processing method and apparatus, a device, a medium, and a product. The method comprises: upon acquiring a reference video and a driving audio, such as an i-th audio frame in a certain audio segment, first obtaining speech characteristic representation data of the reference video on the basis of expression change representation data of the reference video, so that the speech characteristic representation data can represent speech characteristics, such as exaggerated mouth opening during speaking, presented in the reference video; and then, on the basis of the speech characteristic representation data, audio features of the driving audio, and distinctive facial representation data of the reference video, predicting expression state representation data corresponding to the driving audio, so that the expression state representation data can represent the expression state of a subject in the reference video under the driving audio, such as a lip shape state.

The utility model relates to the technical field of gastroscopy, and discloses a mouthpiece for gastroscopy, which comprises a pipe sleeve, a telescopic pipe is movably sleeved in the front end of the pipe sleeve, a movable groove is arranged at the lower part of the front end of the pipe sleeve, a threaded sleeve is mounted in the pipe sleeve in a threaded manner, a connecting plate is movably sleeved outside the threaded sleeve, and the connecting plate is connected with the telescopic pipe in a threaded manner. The lower end of the telescopic pipe is fixedly connected with a blocking groove, the lower end of the blocking groove is fixedly connected with a connecting pipe, and a first one-way valve and a second one-way valve are installed in the connecting pipe. According to the mouthpiece for gastroscopy, a connecting pipe is arranged in a telescopic pipe, a pressing pump is pressed and loosened, and a first one-way valve and a second one-way valve assist in driving the interior of the connecting pipe to form negative pressure, so that secretion is discharged by a blocking groove, the power for discharging the secretion is improved, and the secretion is prevented from accumulating in the mouth; the comfort and the safety are influenced.

The invention discloses a sound and lip synchronous detection method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining an audio frame sequence and a video frame sequence of a to-be-detected audio and video, and obtaining a probability sequence that each frame of the audio has human speaking sound and a probability sequence that each frame of the video has mouth movement; performing offset traversal on the probability sequence of the speaking sound and the probability sequence of the mouth movement of the person, and calculating the similarity of the two sequences under different offsets so as to determine the offset with the maximum similarity; and adjusting the audio frame sequence or the video frame sequence to generate an adjusted audio frame sequence and an adjusted video frame sequence, and obtaining an audio and lip synchronization detection result according to the adjusted audio frame sequence and the adjusted video frame sequence. According to the method, false alarms caused by network transmission can be effectively recognized and filtered out, the false alarm rate caused by the network transmission problem is reduced, the accuracy of sound and lip synchronous detection is improved, and the technical scheme can be applied to the fields of finance and medical health.

The invention discloses a data processing method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a reference video and a driving audio, for example, after the ith frame of audio in a certain audio segment is obtained, obtaining the speaking feature representation data of the reference video according to the expression change representation data of the reference video, the speaking characteristic representation data can represent the speaking characteristics presented in the reference video, such as the characteristics of relatively large mouth opening amplitude during speaking and the like; and according to the speaking characteristic representation data, the audio characteristics of the driving audio and the identification face representation data of the reference video, predicting expression state representation data corresponding to the driving audio, so that the expression state representation data can accurately represent the expression state of an object in the reference video under the driving audio. Therefore, the expression determination effect can be improved.