CN112672120B - Projector with voice analysis function and personal health data generation method - Google Patents
Projector with voice analysis function and personal health data generation method Download PDFInfo
- Publication number
- CN112672120B CN112672120B CN201910979936.6A CN201910979936A CN112672120B CN 112672120 B CN112672120 B CN 112672120B CN 201910979936 A CN201910979936 A CN 201910979936A CN 112672120 B CN112672120 B CN 112672120B
- Authority
- CN
- China
- Prior art keywords
- module
- voice
- unit
- information
- voiceprint
- 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
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to the field of projectors, in particular to a projector with a voice analysis function and a personal health data generation method, wherein the projector comprises: the circuit comprises a central control module, an optical projection module, an audio output module, a power supply module, a voice analysis module and an edge calculation voice processing module; the voice analysis module comprises a recording unit, an A/D conversion unit, a denoising unit and a voiceprint detection and extraction unit which are sequentially and electrically connected, the personal health data generation method comprises voice recording, signal conversion, denoising processing, voiceprint recognition and extraction and edge calculation, and the projector can collect information of daily life information, voiceprint characteristics and the like of the user and provide data support for health diagnosis of the user.
Description
Technical Field
The invention relates to the technical field of projectors, in particular to a projector with a voice analysis function and a personal health data generation method.
Background
A projector, which is a device capable of projecting images or videos onto a curtain, is widely used in homes, multimedia conferences, schools and entertainment places at present; the current projector has single function, cannot collect the daily life information and other physical, physiological and psychological information of a user, and provides data support for health diagnosis of the user.
In the prior art, a single human health detector is provided, for example, patent No. CN109859843A can only detect physiological data of a user, such as blood sugar, blood fat, and the like, and does not involve collection and analysis of psychological and emotional changes, and also does not collect data of daily diet, medicines, and the like of the user to assist health diagnosis. In fact, if a doctor diagnoses a patient, misdiagnosis is easy to occur without combining the long-term psychological, emotional, diet, medicines and the like of the patient.
Disclosure of Invention
The invention aims to provide a projector with a voice analysis function, which can realize the acquisition and processing of voice information and voiceprints and provide data support for the body health analysis of a user; another object is to provide a personal health data generation method based on the projector with voice analysis function.
To achieve the above object, the present invention provides a projector with a voice analysis function, comprising: the circuit comprises a central control module, an optical projection module, an audio output module, a power supply module, a voice analysis module and an edge calculation voice processing module; the central control module is respectively and electrically connected with the optical projection module, the audio output module, the power supply module, the voice analysis module and the edge calculation voice processing module; the voice analysis module comprises a recording unit, an A/D conversion unit, a denoising unit and a voiceprint detection and extraction unit which are sequentially and electrically connected, wherein the recording unit is used for recording voice information of a user and sending the voice information to the A/D conversion unit to be converted into a digital voice signal, and the denoising unit is used for denoising the digital voice signal and then transmitting the digital voice signal to the voiceprint detection and extraction unit; the voiceprint detection and extraction unit receives the digital voice signal, extracts the voiceprint, compares the voiceprint with a user voiceprint stored in advance, and sends the voiceprint and the digital voice signal to the edge calculation voice processing module if the comparison is successful; the edge calculation voice processing module is used for analyzing and processing the received voiceprint and the digital voice signal to generate personal health data.
Furthermore, the voice analysis module also comprises a voice instruction control unit, the voice instruction control unit is used for generating an instruction control signal according to a voice instruction of a user and sending the instruction control signal to the central control module, and the central control module controls the on-off of the projector and the operation of an internal system of the projector according to the instruction control signal; the voice command control unit is electrically connected with the denoising unit and the voiceprint detection and extraction unit.
Furthermore, the circuit also comprises a remote fingerprint switch module, the remote fingerprint switch module is electrically connected with the central control module or wirelessly connected with the central control module, a user controls the projector to start through the remote fingerprint switch module, and meanwhile, the optical projection module appears a white screen; or, the user inputs a startup voice instruction through the voice analysis module to control the projector to start up, and meanwhile, the optical projection module appears a white screen.
Furthermore, the circuit further comprises a heat dissipation module which is electrically connected with the central control module and used for dissipating heat of the running projector.
Furthermore, the power module comprises a power control circuit, a lithium battery and an external power supply adaptive interface, and the lithium battery and the external power supply adaptive interface switch and input the power supply through the power control circuit.
Further, the audio output module comprises a built-in loudspeaker and an audio output interface.
Furthermore, the circuit also comprises a wireless module which is electrically connected with the central control module.
Furthermore, the circuit also comprises a storage module which is electrically connected with the central control module and the edge calculation voice analysis module.
Further, the edge computing voice analysis module comprises an efficient cache unit, a neural network acceleration unit, a data visualization unit and an abnormal network information feedback unit, wherein: the neural network acceleration unit is used for analyzing and processing the digital voice signals and the voiceprints transmitted by the voice analysis module to generate personal health data and sending the personal health data to the high-efficiency cache unit for caching; the data visualization unit is used for performing data visualization processing on the personal health data generated by the neural network acceleration unit, the digital voice signals and the voiceprints which cannot be processed by the neural network acceleration unit and transmitting the data visualization processing to the abnormal network information feedback unit for feedback.
The invention also provides a health data generation method based on the projector with the voice analysis function, which comprises the following steps:
s101: the projector is started up through voice or is started up through a switch;
s102: the voice analysis module starts to input the voice information of the user;
s103: converting the user voice information recorded in the step S103 into a digital voice signal and extracting a voiceprint;
s104: judging whether the extracted voiceprint is matched with a prestored voiceprint, if so, executing the step S105, otherwise, ending;
s105: sending the digital voice signal and the voiceprint to an edge computing voice processing module;
s106: the edge calculation voice processing module carries out semantic recognition on the received digital voice signals and divides the received digital voice signals into diet information, medication information, emotion information and life speech information according to a semantic recognition result;
s107: the edge calculation voice processing module analyzes and processes the diet information, the medication information, the emotion information, the life speech information and the voiceprint information respectively to generate personal health data.
The invention has the following beneficial effects:
1. the projector with the voice analysis function provided by the invention is additionally provided with the voice analysis module and the edge calculation voice processing module, can acquire the diet information, the medicine use information, the emotion information and the life speech information of the user through the voice analysis module, extracts the voiceprint characteristics, performs edge calculation on the data, analyzes the emotion and psychological changes and the daily diet and medicine use conditions of the user, provides data support for the subsequent health diagnosis of the user, and reduces the misdiagnosis rate of doctors.
2. The voice analysis module has a voice control function and can recognize a user instruction, so that the voice control of the projector is realized.
Drawings
Fig. 1 is a schematic diagram of an internal circuit structure of a projector according to an embodiment of the invention;
FIG. 2 is a schematic circuit diagram of a voice analysis module according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal circuit structure of a projector according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of a power module according to an embodiment of the present invention;
FIG. 5 is a schematic circuit diagram of an audio output module according to an embodiment of the present invention;
FIG. 6 is a schematic circuit diagram of an edge computing speech processing module according to an embodiment of the present invention;
FIG. 7 is a flow chart of a method for generating personal health data in accordance with an embodiment of the present invention;
1-a central control module, 2-an optical projection module, 3-an audio output module, 4-a power supply module, 5-an edge calculation voice processing module, 6-a voice analysis module, 7-a remote fingerprint switch module, 8-a heat dissipation module, 9-a wireless module, 10-a storage module, 301-an audio output interface, 302-a built-in loudspeaker, 401-a power supply control circuit, 402-a lithium battery, 403-an external power supply adaptive interface, 501-a high-efficiency cache unit, 502-a neural network acceleration unit, 503-a data visualization unit, 504-an abnormal network information feedback unit, 601-a recording unit, 602-A/D conversion unit, 603-a de-noising unit, 604-a voiceprint detection and extraction unit, a voice processing module, 6-a voice analysis module, 7-a remote fingerprint switch module, 8-a heat dissipation module, 9-a wireless module, 10-a storage module, 301-an audio output interface, 302-a built-in loudspeaker, 401-a power supply control circuit, 402-a lithium battery, 403-an external power supply adaptive interface, 501-an efficient cache unit, 502-a neural network acceleration unit, 503-a data visualization unit, 504-an abnormal network information feedback unit, a voice recording unit, a central control module, a central control unit, a central control module, a central control unit, a central control module, 605-voice command control unit.
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 present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a projector with a voice analysis function, which comprises a shell and a circuit arranged in the shell, wherein the schematic diagram of the internal circuit structure of one embodiment of the projector is shown in fig. 1, and the circuit structure in the shell comprises a central control module 1, an optical projection module 2, an audio output module 3, a power supply module 4, an edge calculation voice processing module 5 and a voice analysis module 6. The central control module 1 is electrically connected with the optical projection module 2, the audio output module 3, the power supply module 4, the edge calculation voice processing module 5 and the voice analysis module 6 respectively, and controls normal operation of the modules, such as controlling the on/off of the projector and the on/off operation system, and mainly undertakes system control, data transfer and the like. The analysis processing of the voice information is mainly completed by the edge computing voice analysis module 5. The power module 4 is respectively electrically connected with the central control module 1, the optical projection module 2, the audio output module 3, the voice analysis module 6 and the edge calculation voice processing module 5, and supplies power to each module to ensure the normal work of each module.
Specifically, as shown in fig. 2, the speech analysis module 6 includes a recording unit 601, an a/D conversion unit 602, a denoising unit 603, and a voiceprint detection and extraction unit 604.
The recording unit 601 is configured to collect voice of the user, the recording unit 601 is electrically connected to the a/D conversion unit 602, optionally, the recording unit 601 may be a microphone and a commercially available recording chip, such as a voice chip with a model of WTR050 or WT2000, and is configured to collect or record voice information of the user, record a situation of oral personal diet, taking medicine, and speech information in daily life, and output the collected voice information of the user to the a/D conversion unit 602. The a/D conversion unit 602 is an analog-to-digital converter, optionally, a dual eight-bit high-speed ADC converter MXT2002 may be used to convert the voice analog signal into a digital voice signal that can be subsequently processed by the projector, the a/D conversion unit 602 is electrically connected to the denoising unit 603, the converted digital voice signal is output to the denoising unit 603 for denoising, and the denoised digital voice signal is respectively transmitted to the voiceprint detection and extraction unit 604 after denoising is completed. Noise in the digital voice signal can be effectively eliminated after the noise is removed by the noise removing unit 603, so that a more accurate digital voice signal is obtained, the voiceprint detection and extraction unit 604 which is convenient to carry out voiceprint detection and extraction and the edge calculation voice processing module 5 carries out analysis and calculation, the difficulty of voiceprint detection and extraction and analysis and calculation is reduced, the accuracy of voiceprint detection and extraction and analysis and calculation is improved, and the sound effect of recording is ensured. Optionally, the denoising unit 603 may be a commercially available filter.
The voiceprint detection and extraction unit 604 is electrically connected to the edge calculation and speech processing module 5, and performs voiceprint and speech detection on the input digital signal, extracts voiceprint features, and compares the voiceprint features with the voiceprint of the projector user, which is stored in the voiceprint detection and extraction unit 604 in advance. Alternatively, the voiceprint detection and extraction unit 604 can also use a commercially available voiceprint recognition chip, such as a voiceprint recognition chip of SpeakIn. The voiceprint detection and extraction unit 604 stores the voiceprint of the user in advance, when the voiceprint detection and extraction unit 604 detects the voiceprint, the current voiceprint is compared with the prestored voiceprint to judge whether the current user is the user of the projector, and if the voiceprint of the current user is successfully matched with the voiceprint of the preset user, the voiceprint detection and extraction unit 604 sends the extracted voiceprint feature and the received digital voice signal to the edge calculation voice processing module 5 for processing and calculation.
Optionally, the voiceprint detection and extraction unit 604 in the projector provided by the present invention may store a plurality of user information in advance, including voiceprint information, and the edge computing speech processing module 5 may also establish a plurality of user-independent personal information databases for temporarily caching personal data. When there are a plurality of pre-stored user information of the projector, the voiceprint detection and extraction unit 604 detects which user the voiceprint feature belongs to when performing detection and extraction, and sends the user identity information along with the voiceprint and the digital voice signal to the edge computing voice processing module 5, so that the edge computing voice processing module 5 can know which specific user the voice information such as the voiceprint and the digital voice signal analyzed and calculated at present is, and the voice information and the result of the analysis and calculation are stored in the personal information database of the user.
The edge calculation voice processing module 5 can extract the information of the voice speed and the voice frequency, recognize the semantics, analyze the expression of the user, analyze the change of the vocal print characteristics and the like, because the emotion of a person can generate certain influence on the vocal print, the voice speed, the voice frequency and the like, the vocal print, the voice speed and the voice frequency of the sound generated when the user is angry and happy are different, the edge calculation voice processing module 5 can determine the emotion and the psychological state of the current user through the analysis, carry out comprehensive analysis in a certain time period, and can also analyze the fluctuation condition of the current emotion and the psychological state of the user. And the edge calculation voice processing module 5 can recognize semantics, so that the diet information and the medication information of the user can be analyzed and converted into characters to be analyzed and calculated to obtain the diet condition and the medication condition of the user. The emotion, psychology, diet, medication information and other information obtained by the edge calculation voice processing module 5 through analysis and calculation can be used as personal health data, health data support is provided for doctors during health diagnosis, and misdiagnosis rate of the doctors is reduced.
In this embodiment, the projector with the voice analysis function is added with an edge calculation voice processing module 5, and optionally, the edge calculation voice processing module 5 may be an xforece edge AI computing platform of the geodesic corporation, Google's TPU, the DianNao series of the cambrian, the NPU of the eyeris, and an intel to strong D-2100 processor. The edge computing voice processing module 5 may also be a GPU with an edge computing function, the GPU is a graphics processor, the current GPU is not limited to 3D graphics processing, the development of the GPU general computing technology has attracted much attention in the industry, and the fact proves that the GPU can provide tens of times or hundreds of times of the performance of the CPU in the aspects of partial computing such as floating point operation and parallel computing, and the addition of a chip with an edge computing function to the current GPU can quickly implement processing of large data.
The edge computing voice processing module 5 can realize short-term storage of voice information such as voiceprint, diet and medicine, and therefore short-term computing analysis of the voice information can be realized on a local projector with a voice analysis function, and the voice information does not need to be transmitted to a cloud terminal for analysis. The addition of the edge computing speech processing module 5 can produce the following beneficial effects: 1. a large number of calculation tasks can be processed at a data acquisition end without being transmitted to a cloud end, so that the transmission pressure of a network is greatly relieved, and the pressure of a data center is reduced; 2. the edge calculation distribution and the characteristic of the device end close to the edge calculation distribution have the advantages of real-time processing, so that the edge calculation distribution can better support the real-time processing and execution of local services, and the task is processed at the edge, so that the time for transmitting data in a network is reduced sharply, and the time for a user to obtain response is quicker; 3. because the voiceprint features of the user extracted by the projector are quite private data, if the personal private data are uploaded to a cloud center for calculation processing, certain safety risks exist, and the edge calculation voice processing module 5 is added to the projector to better protect the private data.
In another embodiment of the present invention, optionally, as shown in fig. 2, the voice analysis module further includes a voice instruction control unit 605, where the voice instruction control unit 605 is configured to generate an instruction control signal according to a voice instruction of a user and send the instruction control signal to the central control module 1, and the central control module 1 controls the on/off of the projector and the operation of an internal system of the projector according to the instruction control signal; the voice instruction control unit 605 is electrically connected to the denoising unit 603 and the voiceprint detection and extraction unit 604, when the voiceprint detection and extraction unit 604 detects that the currently extracted voiceprint is consistent with the voiceprint of the pre-stored user, it is proved that the current user is the user of the projector, and the subsequent operation can be performed, the voice instruction control unit 605 can generate a corresponding instruction control signal according to a power on/off command or a system operation command identified from the digital voice signal received from the denoising unit 603, and send the instruction control signal to the central control module 1, and the central control module 1 controls the power on/off of the projector or the system operation according to the instruction control signal.
In another embodiment of the present invention, as shown in fig. 3, the circuit further includes a remote fingerprint switch module 7, the remote fingerprint switch module 7 is electrically connected to the central control module 1 or the remote fingerprint switch module 7 is wirelessly connected to the central control module, and the user controls the projector to turn on through the remote fingerprint switch module 7, and at the same time, the optical projection module appears white. Specifically, the remote fingerprint switch module 7 is mainly used for controlling the startup of a projector with a voice analysis function, turning on a power supply by pressing a switch, inputting fingerprint information of a user by pressing, and starting up the projector after the fingerprint information is successfully matched; optionally, for convenience of use, a user may input a power-on voice command through the voice analysis module to control the projector to be powered on, and at the same time, the optical projection module appears white. The specific principle of voice control has been mentioned above, and will not be described in detail herein.
In another embodiment of the present invention, as shown in fig. 3, the circuit further includes a heat dissipation module 8, and the heat dissipation module 8 is electrically connected to the central control module 1 for dissipating heat of the operating projector. Specifically, when the projector is in operation, especially when a large amount of data is transmitted and calculated, the projector inevitably causes a rapid rise in the temperature of the machine due to high-speed operation, and in order to better protect each component of the projector from being burned out and ensure the high-speed operation of the projector, the heat dissipation module 8 is required to be arranged to dissipate heat of the operating projector or main components. The heat dissipation module 8 may be an existing relatively mature heat dissipation plate, and the present invention is not limited specifically.
In another embodiment, as shown in fig. 4, the power module 4 includes a power control circuit 401, a lithium battery 402 and an external power adapter 403, wherein the lithium battery 402 and the external power adapter 403 perform power switching and input through the power control circuit 401. After the projector is started, each voltage stabilizing chip in the power control circuit 401 provides required power supply voltage for each module in the projector, each functional module and each driving circuit start to work normally, if an external power supply is used, the power control circuit 401 determines whether to execute charging operation according to the electric quantity of the lithium battery 402 while the process is completed, and when the external power supply is not used, the lithium battery 402 discharges to supply power for each module in the projector.
In a further embodiment, as shown in fig. 5, the audio output module 3 comprises an audio output interface 301 and a built-in speaker 302. The built-in speaker 302 plays sound through a speaker located on the lower surface of the housing, and the audio output interface 301 is electrically connected to external devices such as a speaker box and an earphone.
In another embodiment, as shown in fig. 3, the circuit in the housing further includes a wireless module 9, the wireless module 9 is electrically connected to the central control module 1, optionally, the wireless module 9 includes a wireless router, an infrared remote control signal receiver and a bluetooth device, the projector can perform information interaction with other intelligent devices through the wireless module 9, for example, can perform information interaction with other health detection devices, collect physiological data information of the human body measured by these health detection devices, and send the physiological data information to the edge computing voice processing module 5 through the central control module 1 for processing and calculation. The wireless module 9 can also output the result of the calculation and analysis of the edge calculation voice processing module to other intelligent devices of the user, so that the user can check the analysis result conveniently.
In another embodiment of the present invention, as shown in fig. 3, the circuit further includes a memory module 10, and the memory module 10 is electrically connected to the central control module 1 and the edge calculation voice analysis module 5. The storage module 10 has a large-capacity memory, and can store the personal health data generated by the edge-computing speech processing module 5 for a long time, and although the edge-computing speech processing module 5 can also temporarily buffer the personal health data, the edge-computing speech processing module 5 can only store data within a certain time period because the personal health data is large in amount and the edge-computing speech processing module 5 cannot store the data for a long time, so that only short-term analysis can be performed during analysis processing, and after the storage module 10 is added, long-term monitoring and tracking of the personal health data can be realized, and support is provided for the edge-computing speech processing module 5 to perform long-term comprehensive calculation analysis of the data. The result of the analysis and calculation performed by the edge calculation voice processing module 5 is stored in the storage module 10 for storage, so that the storage pressure of the edge calculation voice processing module 5 is reduced. Along with the increase of the use times and time of the user, the amount of personal health data stored by the storage module 10 is larger and larger, and then sufficient data support is provided for subsequent edge calculation and the like. In addition, the storage module 10 of the projector of the present invention may store the personal health data in a classified manner according to the type of the personal health data actually stored, such as a mood change library, a psychological state change library, a medication situation change library, a diet situation change library, and the like.
Further, on the basis of the above-mentioned embodiment of the present invention, as shown in fig. 6, the edge-computing speech processing module 5 includes an efficient cache unit 501, a neural network acceleration unit 502, a data visualization unit 503, and an abnormal network information feedback unit 504, where:
the neural network acceleration unit 502 is used for analyzing and processing the voice information transmitted by the voice analysis module 6 in real time to generate personal health data, and sending the personal health data to the high-efficiency cache unit 501 and the storage module 10 for caching. Specifically, the neural network acceleration unit 502 firstly compares the voice information received within a certain time: the voiceprint, the diet information, the medication information, the living language information and the like are analyzed and calculated to obtain data of emotion, psychology, diet, medication conditions and the like of the user, the data are sent to the data visualization unit 503 to be visually processed to generate a textual conclusion or a graphical conclusion and the like which can be viewed by the user, and the generated textual conclusion or the graphical conclusion is stored in the storage module 10; meanwhile, the neural network accelerating unit 502 sends the obtained data of emotion, psychology, diet, medication and the like to the high-efficiency cache unit 501 and the storage module 10 for storage.
At intervals, the neural network acceleration unit 502 extracts the emotion, psychology, diet, medication and other data stored in the efficient cache unit 501, and then performs comprehensive analysis to generate fluctuation of the emotion, psychology, diet, medication and other data of the user at the interval, and after extraction, the data stored in the efficient cache unit 501 is removed, so that the efficient cache unit 501 can continue to store newly generated data. The generated fluctuation conditions of emotion, psychology, diet, medication and the like are sent to the high-efficiency cache unit 501 and the storage module 10 again for storage. The time may be set to perform a comprehensive processing analysis every 5 days, 10 days, half a month, etc., and the specific time setting may be determined according to actual conditions, which is not limited in the present invention.
The data visualization unit 503 is configured to perform data visualization processing on the personal health data (including data such as emotion, psychology, diet, and medication situation, and fluctuation situation of emotion, psychology, diet, and medication) generated by the neural network acceleration unit 502, and transmit the data to the abnormal network information feedback unit 504 for feedback and transmit the data to the storage module 10 for storage. Meanwhile, if the neural network acceleration unit 502 has speech information that cannot be analyzed and processed, the speech information may also be sent to the data visualization unit 503 for visualization and transmitted to the abnormal network information feedback unit 504 for feedback.
The abnormal network information feedback unit 504 sends the received visual data to the cloud platform through the wireless module or the communication protocol to be forwarded to a third party, or displays the visual data to the user through the connected optical projection module 2. All data to be transmitted out for a user or a third party to view are transmitted to the abnormal network information feedback unit 504 for feedback.
In an embodiment of the present invention, as shown in fig. 7, there is also provided a health data generating method based on the projector with a voice analysis function, where the method includes:
s101: the projector is started up through voice or is started up through a switch;
s102: the voice analysis module starts to input the voice information of the user;
s103: converting the recorded user voice information into a digital voice signal and extracting a voiceprint;
s104: matching the voiceprints;
specifically, whether the extracted voiceprint is matched with a prestored voiceprint or not is judged, if yes, step S105 is executed, and if not, the process is ended;
s105: sending the digital voice signal and the voiceprint to an edge computing voice processing module;
s106: carrying out semantic recognition to classify the received digital voice signals;
specifically, the edge computing voice processing module performs semantic recognition on the received digital voice signals and divides the received digital voice signals into diet information, medication information and life speech information according to a semantic recognition result.
S107: and analyzing and processing the classified digital voice signals and the voiceprint information to generate personal health data.
Specifically, the edge calculation voice processing module analyzes and processes the diet information, the medication information, the life speech information and the voiceprint information respectively to generate personal health data. The health data generation method provided by the invention is used for generating the personal health data, the operation is simple, the practicability is strong, and the generated personal health data can provide powerful data support for the body health analysis of the user.
The projector with the voice analysis function provided by the invention has the functions of projecting, playing videos, pictures, music and the like which are all possessed by common projectors, can acquire and extract body physiological information of a user such as voiceprint information and record daily life information of the user such as daily diet, medicine and life speech information by adding the voice analysis module and the edge calculation voice processing module on the projector, provides data support for the user during health diagnosis, the physiological information of the user comprises the voiceprint information of the user, and the emotion and psychological conditions of the user can be obtained by extracting and calculating the characteristics of the voiceprint information The diet rule of the user is obtained by recording and calculating the diet of the user, and when a doctor carries out health diagnosis on the user, the recent diet of the user and the condition of daily taken medicines can be provided, so that the doctor can make correct health diagnosis on the user according to the detailed personal data information, and the misdiagnosis rate is reduced.
The present invention has been further described with reference to specific embodiments, but it should be understood that the specific description herein should not be construed as limiting the spirit and scope of the invention, and that various modifications to the above-described embodiments, which would occur to persons skilled in the art upon reading this description, are within the scope of the invention.
Claims (7)
1. A projector with a voice analysis function, the projector comprising: the circuit comprises a central control module, an optical projection module, an audio output module, a power supply module, a storage module, a wireless module, an edge calculation voice processing module and a voice analysis module; the central control module is respectively and electrically connected with the optical projection module, the audio output module, the power supply module, the wireless module, the edge calculation voice processing module and the voice analysis module; the storage module is respectively and electrically connected with the central control module and the edge calculation voice processing module;
the voice analysis module comprises a recording unit, an A/D conversion unit, a denoising unit and a voiceprint detection and extraction unit which are electrically connected in sequence; the voice recording unit is used for recording voice information of a user and sending the voice information to the A/D conversion unit to be converted into a digital voice signal, and the denoising unit is used for denoising the digital voice signal and then transmitting the digital voice signal to the voiceprint detection and extraction unit;
the voiceprint detection and extraction unit receives the digital voice signal, extracts a voiceprint, compares the voiceprint with a pre-stored user voiceprint, detects a user to which the voiceprint belongs if the voiceprint is successfully compared, and sends the voiceprint, user identity information of the user to which the voiceprint belongs and the digital voice signal to the edge calculation voice processing module;
the edge calculation voice processing module comprises a high-efficiency cache unit, a neural network acceleration unit, a data visualization unit and an abnormal network information feedback unit, wherein the neural network acceleration unit is used for analyzing and processing the voice information transmitted by the voice analysis module to generate personal health data and transmitting the personal health data to the high-efficiency cache unit and the storage module for caching; the voice information received by the neural network acceleration unit at least comprises: voiceprint, diet information, medication information and life voice information;
the data visualization unit is used for performing data visualization processing on the personal health data generated by the neural network acceleration unit, transmitting the data to the abnormal network information feedback unit for feedback and transmitting the data to the storage module for storage; meanwhile, the neural network acceleration unit sends the voice information which cannot be analyzed and processed to the data visualization unit for visualization processing and transmits the voice information to the abnormal network information feedback unit for feedback, and the abnormal network information feedback unit sends the received visualization data to the cloud platform through the wireless module and transfers the visualization data to a third party.
2. The projector with the voice analysis function according to claim 1, wherein the voice analysis module further comprises a voice command control unit, the voice command control unit is configured to generate a command control signal according to a voice command of a user and send the command control signal to the central control module, and the central control module controls the on/off of the projector and the operation of internal systems of the projector according to the command control signal;
the voice instruction control unit is electrically connected with the denoising unit and the voiceprint detection and extraction unit.
3. The projector with voice analysis function according to claim 1, wherein the circuit further comprises a remote fingerprint switch module, the remote fingerprint switch module is electrically connected to the central control module or wirelessly connected to the central control module, a user controls the projector to turn on through the remote fingerprint switch module, and the optical projection module displays a white screen.
4. The projector with voice analysis function according to claim 1, wherein the circuit further comprises a heat dissipation module electrically connected to the central control module for dissipating heat from the operating projector.
5. The projector with the voice analysis function according to claim 1, wherein the power module comprises a power control circuit, a lithium battery and an external power adapter interface, and the lithium battery and the external power adapter interface perform power switching and input through the power control circuit.
6. The projector with voice analysis function according to claim 1, wherein the audio output module includes a built-in speaker and an audio output interface.
7. A personal health data generation method based on the projector with voice analysis function of any one of claims 1 to 6, characterized by comprising:
s101: the projector is started up through voice or is started up through a switch;
s102: the voice analysis module starts to input voice information of a user;
s103: converting the user voice information recorded in the step S102 into a digital voice signal and extracting a voiceprint;
s104: judging whether the extracted voiceprint is matched with a prestored voiceprint, if so, executing the step S105, otherwise, ending;
s105: sending the digital voice signal and the voiceprint to an edge computing voice processing module;
s106: the edge computing voice processing module carries out semantic recognition on the received digital voice signals and divides the received digital voice signals into diet information, medicine information and life speech information according to a semantic recognition result;
s107: the edge calculation voice processing module analyzes and processes the diet information, the medication information, the life speech information and the voiceprint information respectively to generate personal health data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910979936.6A CN112672120B (en) | 2019-10-15 | 2019-10-15 | Projector with voice analysis function and personal health data generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910979936.6A CN112672120B (en) | 2019-10-15 | 2019-10-15 | Projector with voice analysis function and personal health data generation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112672120A CN112672120A (en) | 2021-04-16 |
| CN112672120B true CN112672120B (en) | 2022-09-09 |
Family
ID=75400350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910979936.6A Active CN112672120B (en) | 2019-10-15 | 2019-10-15 | Projector with voice analysis function and personal health data generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112672120B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113486306B (en) * | 2021-06-28 | 2024-03-12 | 深圳市拔超科技股份有限公司 | High-definition audio/video matrix control system and method |
| CN113407922B (en) * | 2021-07-14 | 2022-06-03 | 上海万向区块链股份公司 | Intelligent intention recognition and analysis system and method based on block chain technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204945603U (en) * | 2015-09-18 | 2016-01-06 | 深圳市祈锦通信技术有限公司 | A kind of fingerprint recognition projector |
| CN105596016A (en) * | 2015-12-23 | 2016-05-25 | 王嘉宇 | Human body psychological and physical health monitoring and managing device and method |
| CN107635147A (en) * | 2017-09-30 | 2018-01-26 | 上海交通大学 | Health information management TV based on multi-modal man-machine interaction |
| CN108111538A (en) * | 2018-01-25 | 2018-06-01 | 芜湖应天光电科技有限责任公司 | Smart projector speech control system and its method based on sound groove recognition technology in e |
| CN109584896A (en) * | 2018-11-01 | 2019-04-05 | 苏州奇梦者网络科技有限公司 | A kind of speech chip and electronic equipment |
| CN109830271A (en) * | 2019-01-15 | 2019-05-31 | 安徽理工大学 | A kind of health data management system and analysis method based on edge calculations and cloud computing |
| CN109859843A (en) * | 2018-10-23 | 2019-06-07 | 苏州鱼跃医疗科技有限公司 | Intelligent health all-in-one machine |
| CN109920544A (en) * | 2019-01-28 | 2019-06-21 | 浙江工业大学 | Real-time adaptive intelligent Building System based on body-sensing information |
-
2019
- 2019-10-15 CN CN201910979936.6A patent/CN112672120B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204945603U (en) * | 2015-09-18 | 2016-01-06 | 深圳市祈锦通信技术有限公司 | A kind of fingerprint recognition projector |
| CN105596016A (en) * | 2015-12-23 | 2016-05-25 | 王嘉宇 | Human body psychological and physical health monitoring and managing device and method |
| CN107635147A (en) * | 2017-09-30 | 2018-01-26 | 上海交通大学 | Health information management TV based on multi-modal man-machine interaction |
| CN108111538A (en) * | 2018-01-25 | 2018-06-01 | 芜湖应天光电科技有限责任公司 | Smart projector speech control system and its method based on sound groove recognition technology in e |
| CN109859843A (en) * | 2018-10-23 | 2019-06-07 | 苏州鱼跃医疗科技有限公司 | Intelligent health all-in-one machine |
| CN109584896A (en) * | 2018-11-01 | 2019-04-05 | 苏州奇梦者网络科技有限公司 | A kind of speech chip and electronic equipment |
| CN109830271A (en) * | 2019-01-15 | 2019-05-31 | 安徽理工大学 | A kind of health data management system and analysis method based on edge calculations and cloud computing |
| CN109920544A (en) * | 2019-01-28 | 2019-06-21 | 浙江工业大学 | Real-time adaptive intelligent Building System based on body-sensing information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112672120A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10878818B2 (en) | Methods and apparatus for silent speech interface | |
| JP6101684B2 (en) | Method and system for assisting patients | |
| CN106024016B (en) | Child nursing type robot and method for identifying crying of child | |
| KR102276415B1 (en) | Apparatus and method for predicting/recognizing occurrence of personal concerned context | |
| CN112016367A (en) | Emotion recognition system and method and electronic equipment | |
| CN112672120B (en) | Projector with voice analysis function and personal health data generation method | |
| Kabani et al. | Emotion based music player | |
| EP3890342A1 (en) | Method and apparatus for awakening wearable device | |
| US10290200B2 (en) | Speech therapeutic devices and methods | |
| JP2016062077A (en) | Interactive device, interactive system, interactive program, server, control method for server, and server control program | |
| Song et al. | Facelistener: Recognizing human facial expressions via acoustic sensing on commodity headphones | |
| CN113764099A (en) | Psychological state analysis method, device, equipment and medium based on artificial intelligence | |
| US11163822B2 (en) | Emotional experience metadata on recorded images | |
| CN112185422B (en) | Prompt message generation method and voice robot thereof | |
| WO2021134250A1 (en) | Emotion management method and device, and computer-readable storage medium | |
| Drakopoulos et al. | Emotion Recognition from Speech: A Survey. | |
| KR102029760B1 (en) | System for detecting event using user emotion analysis and method thereof | |
| CN112669963B (en) | Intelligent health machine, health data generation method and health data management system | |
| Myakala et al. | An intelligent system for infant cry detection and information in real time | |
| CN116825105A (en) | Speech recognition method based on artificial intelligence | |
| Mallol-Ragolta et al. | Performance analysis of unimodal and multimodal models in valence-based empathy recognition | |
| US20190267002A1 (en) | Intelligent system for creating and editing work instructions | |
| CN114283804A (en) | Control method and device for household appliance to output audio-visual information, storage medium and processor | |
| CN112666851A (en) | Projector with environment monitoring function and personal health data generation method | |
| JP2019128531A (en) | Voice analysis apparatus and voice analysis method |
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 |