CN213211277U - Old man nurses equipment based on degree of depth study - Google Patents

Abstract

The utility model discloses an old man nurses equipment based on degree of depth study, including controller, microphone, speech recognition module, super wide angle camera, power module, GSM module, WIFI module, storage module and the speaker that has degree of depth study module. The nursing equipment is connected with the cloud database through the WIFI module, and a local music library is established through an external TF card. The utility model discloses possess functions such as pronunciation interchange, speech control, gesture detection, can realize accompanying the old man and chat under the condition that does not need old man operation intelligence machine, for old man broadcast music, whether automated inspection old man gesture is abnormal state simultaneously, realize adding the interest of old man's life and to the nurse of old man.

Description

Old man nurses equipment based on degree of depth study

Technical Field

The utility model relates to an intelligence house equipment field specifically is an old man nurses equipment based on degree of depth study.

Background

The 21 st century is a century that artificial intelligence is rapidly developing continuously, and with the continuous improvement of computer science and technology and electronic science technology, various intelligent devices are developed endlessly, and are applied and served in the aspect of people's life, so that people's life is better helped and the burden of people's life is relieved. Along with the improvement of living standard of people, the aging of population is a not negligible problem, the phenomenon of 'empty nest old people' is frequently seen in a population country like China, but a plurality of young people are independent children at present, and the work of accompanying the old people and caring for the old people for 24 hours is not easy to be completed. The old man alone is at nobody and accompanies very alone, and if the old man alone was at home the situation that falls down, disease and twitch appears, if nobody in time provides help to the old man, causes the consequence that can't retrieve easily.

SUMMERY OF THE UTILITY MODEL

Aiming at the defects of the prior art, the utility model provides an old people nursing device based on deep learning, which has the advantages of an intelligent voice communication system and an abnormal behavior monitoring system, and has the functions of chatting for the aged, playing appointed music for the old, and not needing the old to operate any electronic equipment; when the old people falls down or twitch, the controller with the deep learning module in the equipment can detect the situation and send the information that the old people have abnormal conditions to the mobile phone number bound by the equipment; the problem of old man's operation smart mobile phone difficulty, can not easily enjoy music and accompany, when the unusual circumstances appears in the old man simultaneously, can not in time inform the nurse is solved.

The utility model discloses a following technical scheme realizes: an old people nursing device based on deep learning comprises a device shell, a microphone, a loudspeaker, a camera, a memory, a voice recognition module, a camera driving module, a WiFi module, a GSM module, a TF (TransFlash) card slot, a MicroUSB (Universal Serial bus) power interface and a mainboard controller with a built-in deep learning module; the front of equipment is installed the super wide angle camera, and the left lower extreme fixed mounting of equipment has speech recognition module, and the speaker is installed to the right lower extreme of equipment, and the sound hole draw-in groove has all been seted up to the microphone identification mouth and the speaker of equipment broadcast mouth, and TF draw-in groove and power interface groove have been seted up to the back of equipment.

Preferably, the utility model discloses well mainboard controller passes through the wiFi module and is connected with mobile terminal and high in the clouds database server, has contained online music storehouse in the high in the clouds database server to and the dialogue storehouse commonly used.

Preferably, the utility model discloses a microphone gathers outside voice to convey the voice to speech recognition module and fall the noise treatment, thereby make the speech information who conveys in the mainboard controller more accurate reliable.

Preferably, the utility model discloses local music is obtained to the mode of the external TF card of accessible to the old man can hear the music equally under the not good or disconnected circumstances of net of network connection.

Preferably, the utility model discloses a speech recognition module gathers outside voice to with data transfer to the chinese speech analysis who has the degree of depth study and handle, trun into control command with the speech of gathering, thereby make local music of speaker broadcast or broadcast the music after searching for high in the clouds music library.

Preferably, the utility model discloses a speaker broadcast music and to the answer to the problem that the old man proposed, to the instruction of "broadcast music", the utility model discloses with the priority acquire music data and broadcast from online music storehouse, and to the instruction of "broadcast local music", the utility model discloses will follow and acquire music data and broadcast in the local external TF card.

Preferably, the utility model discloses an old man's image data in the room is gathered in real time to super wide-angle camera to with image data cache earlier in storage module, then convey to have the controller of degree of depth learning module in with existing training model carry out the comparison analysis, when unusual gesture predictive value has reached or exceeded the threshold value, will trigger the alarm program in the equipment, start the GSM module, send the SMS of unusual notice to binding in people's the cell-phone, make the speaker broadcast the alarm ring simultaneously.

Preferably, the controller in the present apparatus is a GPU or an ASIC for deep learning calculation. The control chip is a mainstream device used in the market at present and can be selectively purchased according to a specific application environment.

Preferably, the power supply interface of the equipment is of a MicroUSB type, the interface type is a common and easily available type, and when the power supply interface is required to be used outdoors, the power supply requirement can be easily met.

Preferably, the side wall of the shell of the equipment, which is close to the camera driving module, is provided with a heat dissipation hole.

Preferably, the shell of the equipment is provided with the symmetrical C-shaped handle, so that the equipment is convenient to move and install, and the attractiveness is improved.

Compared with the prior art, the beneficial effects of the utility model are that: the utility model discloses application degree of depth learning technique through the model file that the loading has trained, will gather and carry out the contrastive analysis through the audio frequency or the image data of preliminary treatment, judges current old man's demand or state. When the elderly want to talk, the device chats with the elderly. When the old people want to listen to music, the music is played. When the body gesture of old man is monitored to be unusual, will trigger the GSM module and send alarm information to let the caregiver know and give help.

Drawings

Fig. 1 is a schematic structural diagram of the present invention.

Fig. 2 is a front structural view of the present invention.

Fig. 3 is a sectional view of the present invention.

Figure 4 is the back structure view of the utility model

Fig. 5 is a schematic view of the working principle of the present invention.

In the figure: the mobile phone comprises a shell, a 2-super wide-angle camera, a 3-C-shaped symmetrical handle, a 4-camera driving module, a 5-controller with a deep learning module, a 6-GSM module, a 7-voice recognition module, an 8-interference isolation layer, a 9-power supply module, a 10-loudspeaker, a 11-storage module, a 12-through hole, a 13-microphone, a 14-WIFI module, a 15-power switch, a 16-operation indicator lamp, a 17-loudspeaker sound outlet, a 18-camera heat dissipation hole, a 19-microphone sound receiving hole, a 20-power supply interface, a 21-TF card slot and a 22-SIM card slot.

Detailed Description

The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention. It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and/or process steps that are closely related to the solution according to the invention are shown in the drawings, while other details that are not relevant to the invention are omitted.

Referring to fig. 1-5, the present invention provides a technical solution: the ultra-wide-angle camera comprises a shell 1, wherein an ultra-wide-angle camera 2 and a camera driving module 4 are installed on the upper part of an inner cavity of the shell 1, and a controller 5 with a deep learning module, a GSM module 6, a voice recognition module 7, an interference isolation layer 8, a power supply module 9, a loudspeaker 10, a storage module 11, a microphone 13 and a WIFI module 14 are installed in the inner cavity of the shell; the side surface of the outer part of the shell 1 is provided with a C-shaped symmetrical handle 3, and the side wall is provided with a through hole 12, a speaker sound outlet hole 17, a camera heat dissipation hole 18 and a microphone sound receiving hole 19; the front surface of the equipment is provided with a power switch 15 and an operation indicator light 16; the back of the equipment is provided with a power interface 20, a TF card slot 21 and a SIM card slot 22.

The controller is respectively electrically connected with the camera driving module 4, the storage module 11, the voice recognition module 7, the GSM module 6, the operation indicator lamp 16, the loudspeaker 10 and the WIFI module 14.

The controller is provided with a deep learning module, and can carry out deep learning on human voice by means of a deep learning technology so as to better realize interactive communication between people and equipment. The controller can analyze and process data, performs model matching analysis by reading data acquired by the ultra-wide-angle camera 2 in the storage module 11, and triggers the GSM module to send alarm information and enables the loudspeaker 10 to play alarm ring when detecting that the predicted value of the abnormal posture of the old people reaches or exceeds a threshold value.

The voice recognition module 7 performs pre-processing of denoising and blank elimination on the collected voice, and then transmits voice data to the controller, the controller 5 recognizes whether the voice content is a chat instruction or a music playing instruction, and performs chat if the voice content is the chat instruction, and controls the loudspeaker 10 to play music if the voice content is the music playing instruction. The radiating holes 18 and the through holes 12 are beneficial to radiating, and the directions of the through holes 12 and the radiating holes 18 are both designed obliquely inwards, so that dust is prevented from entering the radiating holes, and the service life of the equipment is prolonged. The interference isolation layer 8 is arranged between the microphone 13 and the loudspeaker 17, so that the influence on microphone reception when the equipment plays music is reduced, the accuracy of voice recognition is improved, and the high-efficiency and stable operation of the equipment is ensured. The C-shaped symmetrical handle 3 is fixedly arranged on the shell 1, so that the equipment is convenient for people to move, and the ornamental value is improved.

When the device is used, when a person communicates with a nursing device, the microphone receives sound firstly, then the voice module preprocesses audio data, the preprocessed data are transmitted to the main controller for analysis and processing, and if a user needs to chat, the user obtains a conversation text from the cloud database server for chatting; and if the music playing requirement is met, acquiring the music from the cloud database server or the local TF card for playing.

To sum up, this old man nurses equipment based on deep study possesses and can carry out the pronunciation chat, and the audio media broadcast uses the advantage of deep learning technique detection old man's health gesture, has solved the inconvenient problem of a lot of old man operation smart mobile phone, has strengthened the nurse to the old man simultaneously, has increased the interest of old man's life of late year, has alleviateed caregiver's burden.

It is obvious to a person skilled in the art that the invention is not restricted to details of the above-described exemplary embodiments, but that it can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention 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 sign in a claim should not be construed as limiting the claim concerned.

Claims (9)

1. The utility model provides an old man nurses equipment based on deep study which characterized in that: the device comprises a shell, wherein a through hole is formed in the upper side wall of the shell, a camera driving module, a controller with a deep learning module, a GSM module, a WIFI module, a microphone, a voice recognition module, a loudspeaker, a storage module and an indicator light are fixedly mounted in the shell respectively; the equipment realizes power supply through a power interface on the back, and is connected with the expanded TF card through the TF card slot on the back; the power module is electrically connected with each device and module in the equipment through wires.

2. The advanced learning based geriatric care device of claim 1, wherein: the shell is provided with a symmetrical C-shaped grip.

3. The advanced learning based geriatric care device of claim 1, wherein: the camera driving module is arranged on the back of the equipment, heat dissipation holes are formed in the camera driving module, and through holes with openings facing the upper portion of the center of the equipment are formed in the side walls of the camera driving module.

4. The advanced learning based geriatric care device of claim 1, wherein: in the internal structure of the equipment, a layer of interference isolation material is fixedly arranged on the microphone and the loudspeaker.

5. The advanced learning based geriatric care device of claim 1, wherein: the front of the equipment is provided with a loudspeaker sound outlet, and the back of the equipment is provided with a microphone sound receiving hole.

6. The advanced learning based geriatric care device of claim 1, wherein: the controller with the deep learning module is a GPU or ASIC for deep learning calculations.

7. The advanced learning based geriatric care device of claim 1, wherein: the camera is for installing the super wide angle camera in the shell upper end, provides data file for whether the controller detects the old man and falls down or twitch.

8. The advanced learning based geriatric care device of claim 1, wherein: the deep learning module of the controller is provided with a common dialog library which is trained and can be continuously updated through a cloud database.

9. The advanced learning based geriatric care device of claim 1, wherein: the loudspeaker can play music in the cloud database and music in the local TF card at the same time in a networking state, and can play local music in a disconnected state.

Images