Engineering project control speech recognition system and method based on artificial intelligence
By integrating the microphone cleaning and cooling functions controlled by artificial intelligence on the terminal equipment at the construction site, the problem of poor voice recognition effect of traditional walkie-talkies in noisy environments is solved, and efficient and accurate project communication and management is achieved to adapt to harsh environments. Reduces cost and user operation complexity.
Patent Information
- Application Number
- CN202411229324.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-17
AI Technical Summary
In the noisy environment of the construction site, traditional walkie-talkies have poor voice recognition effects due to dust and high temperatures, and are complex in operation, making it difficult to communicate efficiently between construction teams of multiple levels.
Design an artificial intelligence-based engineering project management and voice recognition system. The terminal equipment is equipped with a microphone, camera and temperature sensor. Through artificial intelligence, the motor can clean saliva and foreign objects, adjust the rotation of the diaphragm and mesh to achieve cleaning and heat dissipation, and ensure sound. Effects and integrate speech recognition and communication management.
It improves the voice recognition effect at the construction site, reduces communication delays and human errors, reduces equipment costs, simplifies user operations, adapts to harsh environments, extends the service life of the equipment, and improves the efficiency and convenience of project management.
Smart Images
Figure CN119152853A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of project management, and in particular to an engineering project management and control speech recognition system and method based on artificial intelligence. Background Art
[0002] Civil Engineering is a general term for the science and technology of building various land engineering facilities. It refers to the materials and equipment used, as well as the technical activities such as survey, design, construction, maintenance, and repair, as well as the objects of engineering construction. That is, various engineering facilities built on the ground, underground, or on land, directly or indirectly serving human life, production, military, and scientific research.
[0003] Existing projects are divided into multiple construction projects, each of which is divided into multiple construction units, and each construction unit has multiple construction teams or construction personnel. Since there are many construction levels in the entire construction project, information release and statistics are required for project management during the construction process. Most of them are done by the person in charge of each level notifying the next construction level or uploading the statistics to the previous construction level, and repeating the operation to achieve the initial purpose. In order to overcome the above problems, the existing technology uses intercoms to achieve rapid transmission of messages, but there are the following problems: 1. Since the construction environment is noisy, in order to transmit information in a noisy environment, you can only speak loudly, which also causes the saliva brought out with the airflow to easily stick to the surface of the microphone; 2. And the construction site is dusty. Dust can easily combine with saliva, making the mesh of the microphone mesh easily clogged, changing the physical structure, resulting in unclear reception, poor communication efficiency, and reduced voice recognition effect; 3. The vast majority of construction projects do not have temperature control devices such as air conditioners, resulting in high working environment temperatures, which in turn causes the diaphragm of the walkie-talkie to deform easily and the voice deformation, which in turn makes the subsequent voice recognition effect poor; 4. Walkie-talkies also have certain learning and usage thresholds. In actual work, many workers are still unable to fluently use walkie-talkies and the corresponding complex functions due to insufficient education, resulting in lower project management efficiency. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide an engineering project management and control speech recognition system and method based on artificial intelligence that can ensure clear sound reception and thus ensure speech recognition effect.
[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: An engineering project management and control speech recognition system based on artificial intelligence, comprising: A plurality of terminals, wherein the terminals include a voice collection device worn on a wearer, wherein the voice collection device has a first communication module, a battery and a microphone, wherein the battery is electrically connected to the first communication module and the microphone respectively; the microphone includes an outer shell, a base, a motor, a camera, a diaphragm, a mesh cover and a temperature sensor; the outer shell is provided with a sound receiving port, a mounting port and a storage space, wherein the storage space is respectively connected to the sound receiving port and the mounting port, wherein the base is detachably connected to the mounting port, wherein the motor is fixed to a surface of the base facing the storage space, wherein the mesh cover is located in the storage space and is arranged corresponding to the sound receiving port, wherein the motor is connected to the mesh cover, wherein the diaphragm and the temperature sensor are fixed in the mesh cover, wherein the diaphragm includes a sound receiving surface corresponding to the sound receiving port; wherein the imaging range of the camera includes the face of the wearer and part of the mesh cover; A control end, wherein the control end has a second communication module, wherein the second communication module communicates with the first communication modules of the plurality of terminals for control or voice transfer, wherein the control end has artificial intelligence, wherein the artificial intelligence performs voice recognition actions and heat dissipation actions, wherein the voice recognition actions include: The artificial intelligence obtains the video information of the camera through the communication connection, and at the same time controls the motor to rotate slowly so that the artificial intelligence can obtain the complete surface image of the mesh cover, and judge whether there is saliva and / or foreign matter on the surface image. If there is saliva and / or foreign matter, the artificial intelligence controls the motor to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; if not or after the throwing out is completed, the artificial intelligence controls to obtain the wearer's facial information through the camera and retrieve the wearer's mouth position. After confirming the mouth position, the motor is controlled to rotate to turn the sound receiving surface of the diaphragm toward the wearer's mouth to improve the sound receiving effect and convert the vibration information collected by the diaphragm into sound for voice recognition; The heat dissipation action includes: artificial intelligence determines whether the microphone is performing a voice recognition action, if so, no action is taken; otherwise, the artificial intelligence obtains the temperature information of the temperature sensor through a communication connection, and determines whether the temperature is higher than a preset value, if not, no action is taken; if so, the motor is controlled to rotate to drive the mesh cover and the diaphragm to rotate a predetermined number of times to achieve a heat dissipation effect.
[0006] In order to solve the above technical problems, another technical solution adopted by the present invention is: An engineering project management and control speech recognition method based on artificial intelligence, comprising: Communicate with the voice collection device on the wearer and perform voice recognition and heat dissipation actions; The voice collection device is provided with a first communication module, a battery and a microphone, and the battery is electrically connected to the first communication module and the microphone respectively; the microphone comprises an outer shell, a base, a motor, a camera, a diaphragm, a mesh cover and a temperature sensor; the outer shell is provided with a sound receiving port, a mounting port and a storage space, and the storage space is communicated with the sound receiving port and the mounting port respectively, the base is detachably connected to the mounting port, the motor is fixed on a side of the base facing the storage space, the mesh cover is located in the storage space and is arranged corresponding to the sound receiving port, the motor is connected to the mesh cover, the diaphragm and the temperature sensor are fixed in the mesh cover, and the diaphragm comprises a sound receiving surface corresponding to the sound receiving port; the imaging range of the camera includes the face of the wearer and part of the mesh cover; The speech recognition action includes: the artificial intelligence obtains the video information of the camera through the communication connection, and at the same time controls the motor to rotate slowly so that the artificial intelligence can obtain the complete surface image of the mesh cover, and judges whether there is saliva and / or foreign matter on the surface image, and if there is saliva and / or foreign matter, controls the motor to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; if not or after the throwing out is completed, the artificial intelligence controls to obtain the facial information of the wearer through the camera and retrieve the mouth position of the wearer, and after confirming the mouth position, controls the motor to rotate so that the sound receiving surface of the diaphragm is facing the mouth of the wearer to improve the sound receiving effect and converts the vibration information collected by the diaphragm into sound for speech recognition; The heat dissipation action includes: artificial intelligence determines whether the microphone is performing a voice recognition action, if so, no action is taken; otherwise, the artificial intelligence obtains the temperature information of the temperature sensor through a communication connection, and determines whether the temperature is higher than a preset value, if not, no action is taken; if so, the motor is controlled to rotate to drive the mesh cover and the diaphragm to rotate a predetermined number of times to achieve a heat dissipation effect.
[0007] The beneficial effects of the present invention are as follows: the mesh cover is located in the accommodating space and is arranged corresponding to the sound receiving port, the motor is connected to the mesh cover, and the diaphragm and the temperature sensor are fixed in the mesh cover, so that the motor can drive the mesh cover and the diaphragm to rotate together when rotating, and then when the motor is at different speeds, the saliva and / or foreign matter on the surface or inside of the mesh cover can be thrown out to ensure the cleaning effect, and the diaphragm rotation cooling can be achieved to ensure the heat dissipation effect. It can also be combined with the camera and the control end to align the sound receiving surface with the wearer's mouth, thereby ensuring the best sound receiving effect, achieving multiple goals at one stroke, better adapting to the harsh environment corresponding to civil engineering, ensuring project management while extending the service life of the voice collection device; and the artificial intelligence integrated in the control end is not only responsible for the voice It is not only responsible for recognition, but also for overall communication management and heat dissipation control, realizing efficient and accurate processing of voice commands in engineering projects; through a centralized control terminal and a number of terminals, it can improve the efficiency and response speed of project management and communication, reduce human errors and low communication efficiency caused by traditional walkie-talkies, and the centralized control terminal can reduce the cost of the terminal, so that there is no need to install voice recognition chips and control chips on each terminal, thereby reducing costs; at the same time, the centralized control terminal can reduce the user's operating burden and usage threshold, improve the user experience and further enhance the convenience of project management; through higher priority voice recognition actions, it can ensure the priority of project management and avoid voice recognition failures due to heat dissipation. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] Figure 1 A judgment flow chart of an engineering project management and control speech recognition system based on artificial intelligence according to a specific implementation mode of the present invention; Figure 2 A schematic diagram of the microphone structure of an engineering project management and control speech recognition system based on artificial intelligence according to a specific implementation mode of the present invention; Figure 3 It is a first perspective of an exploded diagram of a microphone of an engineering project management and control speech recognition system based on artificial intelligence according to a specific embodiment of the present invention; Figure 4 A second perspective of an exploded diagram of a microphone of an engineering project management and control speech recognition system based on artificial intelligence according to a specific embodiment of the present invention; Explanation of reference numerals: 1. microphone; 11. outer shell; 111. sound receiving port; 112. mounting port; 113. accommodation space; 12. base; 13. motor; 14. camera; 15. diaphragm; 16. mesh cover. DETAILED DESCRIPTION
[0009] In order to explain the technical content, achieved objectives and effects of the present invention in detail, the following is an explanation in combination with the implementation modes and the accompanying drawings.
[0010] Please refer to Figures 1 to 4, an engineering project management and control speech recognition system based on artificial intelligence, comprising: A plurality of terminals, wherein the terminals include a voice collection device worn on a wearer, wherein the voice collection device has a first communication module, a battery and a microphone 1, wherein the battery is electrically connected to the first communication module and the microphone 1 respectively; the microphone 1 includes an outer shell 11, a base 12, a motor 13, a camera 14, a diaphragm 15, a mesh cover 16, and a temperature sensor; the outer shell 11 is provided with a sound receiving port 111, a mounting port 112 and a receiving space 113, wherein the receiving space 113 is electrically connected to the sound receiving port 111 and a mounting port 112. 11 is connected to the mounting opening 112, the base 12 is detachably connected to the mounting opening 112, the motor 13 is fixed to a surface of the base 12 facing the accommodating space 113, the mesh cover 16 is located in the accommodating space 113 and is arranged corresponding to the sound receiving opening 111, the motor 13 is connected to the mesh cover 16, the diaphragm 15 and the temperature sensor are fixed in the mesh cover 16, the diaphragm 15 includes a sound receiving surface corresponding to the sound receiving opening 111; the imaging range of the camera 14 includes the face of the wearer and part of the mesh cover 16; A control end, wherein the control end has a second communication module, wherein the second communication module communicates with the first communication modules of the plurality of terminals for control or voice transfer, wherein the control end has artificial intelligence, wherein the artificial intelligence performs voice recognition actions and heat dissipation actions, wherein the voice recognition actions include: The artificial intelligence obtains the video information of the camera 14 through the communication connection, and at the same time controls the motor 13 to rotate slowly so that the artificial intelligence can obtain the complete surface image of the mesh cover 16, and judge whether there is saliva and / or foreign matter on the surface image. If there is saliva and / or foreign matter, the motor 13 is controlled to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; if not or after the throwing out is completed, the artificial intelligence controls to obtain the wearer's facial information through the camera 14 and retrieve the wearer's mouth position. After confirming the mouth position, the motor 13 is controlled to rotate so that the sound receiving surface of the diaphragm 15 is facing the wearer's mouth to improve the sound receiving effect and convert the vibration information collected by the diaphragm 15 into sound for voice recognition; The heat dissipation action includes: artificial intelligence determines whether the microphone 1 is performing a voice recognition action, if so, no action is taken; otherwise, the artificial intelligence obtains the temperature information of the temperature sensor through a communication connection, and determines whether the temperature is higher than a preset value, if not, no action is taken; if so, the motor 13 is controlled to rotate to drive the mesh cover 16 and the diaphragm 15 to rotate a predetermined number of times to achieve a heat dissipation effect.
[0011] From the above description, it can be known that the mesh cover 16 is located in the accommodating space 113 and is arranged corresponding to the sound receiving port 111, the motor 13 is connected to the mesh cover 16, and the diaphragm 15 and the temperature sensor are fixed in the mesh cover 16, so that the motor 13 can drive the mesh cover 16 and the diaphragm 15 to rotate together when rotating, and then when the motor 13 is at different speeds, the saliva and / or foreign matter on the surface or inside of the mesh cover 16 can be thrown out to ensure the cleaning effect, and the diaphragm 15 can be rotated and cooled to ensure the heat dissipation effect, and it can also be combined with the camera 14 and the control end to align the sound receiving surface with the wearer's mouth, so as to ensure the best sound receiving effect, thereby achieving multiple goals at one stroke, better adapting to the harsh environment corresponding to civil engineering, ensuring project management while extending the service life of the voice collection device; and the control end The integrated artificial intelligence is not only responsible for voice recognition, but also for overall communication management and heat dissipation control, realizing efficient and accurate processing of voice commands in engineering projects; through a centralized control terminal and a number of terminals, it can improve the efficiency and response speed of project management and communication, reduce human errors and low communication efficiency caused by traditional walkie-talkies, and the centralized control terminal can reduce the cost of the terminal, so that there is no need to install voice recognition chips and control chips on each terminal, thereby reducing costs; at the same time, the centralized control terminal can reduce the user's operating burden and usage threshold, improve the user experience and further enhance the convenience of project management; through higher priority voice recognition actions, the priority of project management can be guaranteed to avoid voice recognition failures due to heat dissipation.
[0012] Furthermore, if there is saliva and / or foreign matter, controlling the motor 13 to rotate at a high speed to throw away the saliva and / or foreign matter on the surface further includes: If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor 13 rotates at high speed for a predetermined time, the artificial intelligence controls the motor 13 to rotate slowly again so that the artificial intelligence can obtain a complete surface image of the mesh cover 16, and judge whether there is saliva and / or foreign matter in the surface image. If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed again. If no saliva and / or foreign matter is present, it is deemed that the throwing is completed. If saliva and / or foreign matter is still present after three high-speed rotations, the control end will alarm.
[0013] From the above description, it can be seen that through multiple high-speed rotations, saliva and / or foreign objects can be thrown out, ensuring the subsequent sound reception effect and then improving the effect of voice recognition.
[0014] When the control motor 13 rotates at a high speed to throw away the saliva and / or foreign matter on the surface, the artificial intelligence identifies the position of the saliva and / or foreign matter, and the rotation speed when the saliva and / or foreign matter is toward the wearer is lower than the rotation speed when it is away from the wearer.
[0015] It can be seen from the above description that the rotation speed difference can ensure that saliva and / or foreign matter is reduced or prevented from being thrown onto the wearer's body or face.
[0016] A truncated cone tube is arranged on the outer edge of the sound receiving surface of the diaphragm 15, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
[0017] From the above description, it can be seen that through the setting of the truncated cone tube, an outward-expanding trumpet shape can be formed, which can perform directional sound amplification to ensure the subsequent voice recognition effect.
[0018] The mesh cover 16 is provided with a mark corresponding to the sound receiving surface; If the motor 13 is damaged, the wearer can move the mesh cover 16 through the sound receiving opening 111 to align the mark with the mouth.
[0019] From the above description, it can be seen that by setting the mark, manual angle adjustment can still be performed in the event that the motor 13 is damaged to ensure the sound reception effect.
[0020] An engineering project management and control speech recognition method based on artificial intelligence, comprising: Communicate with the voice collection device on the wearer and perform voice recognition and heat dissipation actions; The voice collection device has a first communication module, a battery and a microphone 1, and the battery is electrically connected to the first communication module and the microphone 1 respectively; the microphone 1 includes an outer shell 11, a base 12, a motor 13, a camera 14, a diaphragm 15, a mesh cover 16, and a temperature sensor; the outer shell 11 is provided with a sound receiving port 111, a mounting port 112 and a receiving space 113, and the receiving space 113 is communicated with the sound receiving port 111 and the mounting port 112 respectively, the base 12 is detachably connected to the mounting port 112, the motor 13 is fixed on a surface of the base 12 facing the receiving space 113, the mesh cover 16 is located in the receiving space 113 and is arranged corresponding to the sound receiving port 111, the motor 13 is connected to the mesh cover 16, the diaphragm 15 and the temperature sensor are fixed in the mesh cover 16, and the diaphragm 15 includes a sound receiving surface corresponding to the sound receiving port 111; the imaging range of the camera 14 includes the face of the wearer and part of the mesh cover 16; The speech recognition action includes: obtaining video information of the camera 14 through a communication connection, and controlling the motor 13 to rotate slowly to obtain a complete surface image of the mesh cover 16, judging the complete surface image, if not, not taking any action, and if saliva and / or foreign matter are present, controlling the motor 13 to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; after the throwing out is completed, obtaining the wearer's facial information through the camera 14 and retrieving the wearer's mouth position, and after confirming the mouth position, controlling the motor 13 to rotate so that the sound receiving surface of the diaphragm 15 is directed toward the wearer's mouth to improve the sound receiving effect and converting the vibration information collected by the diaphragm 15 into sound for speech recognition; The heat dissipation action includes: determining whether the microphone 1 is performing a voice recognition action, if so, not taking any action; otherwise, obtaining temperature information of the temperature sensor through a communication connection, and determining whether the temperature is higher than a preset value; otherwise, not taking any action; if so, controlling the motor 13 to rotate and drive the mesh cover 16 and the diaphragm 15 to rotate a predetermined number of times to achieve a heat dissipation effect.
[0021] Furthermore, if there is saliva and / or foreign matter, controlling the motor 13 to rotate at a high speed to throw away the saliva and / or foreign matter on the surface further includes: If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor 13 rotates at high speed for a predetermined time, the motor 13 is controlled to rotate slowly again to obtain a complete surface image of the mesh cover 16. The complete surface image is judged. If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed again. If no saliva and / or foreign matter is present, it is deemed that the throwing is completed. If saliva and / or foreign matter is still present after three high-speed rotations, an alarm is issued.
[0022] Furthermore, when the motor 13 is controlled to rotate at a high speed to throw away the saliva and / or foreign matter on the surface, the position of the saliva and / or foreign matter is identified, and the rotation speed of the saliva and / or foreign matter when it is directed toward the wearer is lower than the rotation speed when it is away from the wearer.
[0023] Furthermore, a truncated cone tube is provided on the outer edge of the sound receiving surface of the diaphragm 15, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
[0024] Furthermore, the mesh cover 16 is provided with a mark corresponding to the sound receiving surface; If the motor 13 is damaged, the wearer can move the mesh cover 16 through the sound receiving opening 111 to align the mark with the mouth. Embodiment 1
[0025] An engineering project management and control speech recognition system based on artificial intelligence, comprising: A plurality of terminals, wherein the terminals include a voice collection device worn on a wearer, wherein the voice collection device has a first communication module, a battery and a microphone 1, wherein the battery is electrically connected to the first communication module and the microphone 1 respectively; the microphone 1 includes an outer shell 11, a base 12, a motor 13, a camera 14 (fisheye camera), a diaphragm 15, a mesh cover 16, and a temperature sensor; the outer shell 11 is provided with a sound receiving port 111, a mounting port 112 and a storage space 113, wherein the storage space 113 is electrically connected to the first communication module and the microphone 1 respectively; the microphone 1 includes an outer shell 11, a base 12, a motor 13, a camera 14 (fisheye camera), a diaphragm 15, a mesh cover 16, and a temperature sensor; the outer shell 11 is provided with a sound receiving port 111, a mounting port 112 and a storage space 113, wherein the storage space 113 is electrically connected to the first communication module and the microphone 1 respectively; the storage battery ... storage battery is electrically connected to the first communication module and the microphone 1 respectively; the storage battery is electrically connected to the first communication module and the microphone 1 respectively; the storage battery is electrically connected to the first communication module and the microphone 1 respectively; the storage battery is electrically connected to the first communication module and the microphone 1 respectively; the storage battery is electrically connected to the The sound port 111 is connected to the mounting port 112, the base 12 is detachably connected to the mounting port 112, the motor 13 is fixed to a surface of the base 12 facing the accommodating space 113, the mesh cover 16 is located in the accommodating space 113 and is arranged corresponding to the sound port 111, the motor 13 is connected to the mesh cover 16, the diaphragm 15 and the temperature sensor are fixed in the mesh cover 16, and the diaphragm 15 includes a sound receiving surface corresponding to the sound port 111; the imaging range of the camera 14 includes the face of the wearer and part of the mesh cover 16; A control end, wherein the control end has a second communication module, wherein the second communication module communicates with the first communication modules of the plurality of terminals for control or voice transfer, wherein the control end has artificial intelligence, wherein the artificial intelligence performs voice recognition actions and heat dissipation actions, wherein the voice recognition actions include: The artificial intelligence obtains the video information of the camera 14 through the communication connection, and at the same time controls the motor 13 to rotate slowly (for example, 1 r / s (revolutions / second), which is convenient for the camera 14 to perform imaging. The specific rotation speed is not used to limit the protection scope of the present application, and is used as a functional limitation herein) so that the artificial intelligence can obtain a complete surface image of the mesh cover 16, and judge whether there is saliva and / or foreign matter in the surface image. If there is saliva and / or foreign matter, the motor 13 is controlled to rotate at a high speed (for example, 5-10 r / s (revolutions / second). The specific rotation speed is determined according to the size of the mesh cover 16. For example, if the diameter of the mesh cover 16 is large, the rotation speed can be low. A little, the diameter is small, then the rotation speed can be higher, as long as the effect of throwing out can be achieved, the specific rotation speed is not used to limit the protection scope of this application, it is used as a functional limitation here, and the following places where the rotation speed appears are the same) to throw out the saliva and / or foreign matter on the surface; if not or after the throwing out is completed, the artificial intelligence control obtains the wearer's facial information through the camera 14 and retrieves the wearer's mouth position, and after confirming the mouth position, controls the motor 13 to rotate so that the sound receiving surface of the diaphragm 15 faces the wearer's mouth, and then the motor 13 stops working and maintains the position to improve the sound receiving effect and convert the vibration information collected by the diaphragm 15 into sound for voice recognition; The heat dissipation action includes: artificial intelligence determines whether the microphone 1 is performing a voice recognition action, if so, no action is taken; otherwise, the artificial intelligence obtains the temperature information of the temperature sensor through a communication connection, and determines whether the temperature is higher than a preset value (for example, 50°C), if not, no action is taken; if so, the motor 13 is controlled to rotate to drive the mesh cover 16 and the diaphragm 15 to rotate a predetermined number of circles (for example, 20 circles) to achieve a heat dissipation effect.
[0026] If there is saliva and / or foreign matter, controlling the motor 13 to rotate at a high speed to throw the saliva and / or foreign matter on the surface further includes: If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor 13 rotates at high speed for a predetermined time (for example, 5 seconds), the artificial intelligence controls the motor 13 to rotate slowly again so that the artificial intelligence can obtain a complete surface image of the mesh cover 16, and judge whether there is saliva and / or foreign matter in the surface image. If there is saliva and / or foreign matter, the motor 13 is controlled to rotate at high speed again. If there is no saliva and / or foreign matter, it is deemed that the throwing is completed. If saliva and / or foreign matter still exists after three high-speed rotations, the control end will alarm.
[0027] When the control motor 13 rotates at a high speed to throw away the saliva and / or foreign matter on the surface, the artificial intelligence identifies the position of the saliva and / or foreign matter, and the rotation speed when the saliva and / or foreign matter is toward the wearer is lower than the rotation speed when it is away from the wearer.
[0028] A truncated cone tube is arranged on the outer edge of the sound receiving surface of the diaphragm 15, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
[0029] The mesh cover 16 is provided with a mark corresponding to the sound receiving surface; If the motor 13 is damaged, the wearer can move the mesh cover 16 through the sound receiving opening 111 to align the mark with the mouth. Embodiment 2
[0030] An engineering project management and control speech recognition method based on artificial intelligence, comprising: Communicate with the voice collection device on the wearer and perform voice recognition and heat dissipation actions; The voice collection device has a first communication module, a battery and a microphone 1, and the battery is electrically connected to the first communication module and the microphone 1 respectively; the microphone 1 includes an outer shell 11, a base 12, a motor 13, a camera 14, a diaphragm 15, a mesh cover 16, and a temperature sensor; the outer shell 11 is provided with a sound receiving port 111, a mounting port 112 and a receiving space 113, and the receiving space 113 is communicated with the sound receiving port 111 and the mounting port 112 respectively, the base 12 is detachably connected to the mounting port 112, the motor 13 is fixed on a surface of the base 12 facing the receiving space 113, the mesh cover 16 is located in the receiving space 113 and is arranged corresponding to the sound receiving port 111, the motor 13 is connected to the mesh cover 16, the diaphragm 15 and the temperature sensor are fixed in the mesh cover 16, and the diaphragm 15 includes a sound receiving surface corresponding to the sound receiving port 111; the imaging range of the camera 14 includes the face of the wearer and part of the mesh cover 16; The speech recognition action includes: obtaining video information of the camera 14 through a communication connection, and controlling the motor 13 to rotate slowly to obtain a complete surface image of the mesh cover 16, judging the complete surface image, and if there is saliva and / or foreign matter, controlling the motor 13 to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; after the throwing out is completed, the facial information of the wearer is obtained through the camera 14 and the mouth position of the wearer is retrieved, and after the mouth position is confirmed, the motor 13 is controlled to rotate so that the sound receiving surface of the diaphragm 15 is directed toward the wearer's mouth to improve the sound receiving effect and convert the vibration information collected by the diaphragm 15 into sound for speech recognition; The heat dissipation action includes: determining whether the microphone 1 is performing a voice recognition action, if so, not taking any action; otherwise, obtaining temperature information of the temperature sensor through a communication connection, and determining whether the temperature is higher than a preset value; otherwise, not taking any action; if so, controlling the motor 13 to rotate and drive the mesh cover 16 and the diaphragm 15 to rotate a predetermined number of times to achieve a heat dissipation effect.
[0031] If there is saliva and / or foreign matter, controlling the motor 13 to rotate at a high speed to throw the saliva and / or foreign matter on the surface further includes: If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor 13 rotates at high speed for a predetermined time, the motor 13 is controlled to rotate slowly again to obtain a complete surface image of the mesh cover 16. The complete surface image is judged. If saliva and / or foreign matter is present, the motor 13 is controlled to rotate at high speed again. If no saliva and / or foreign matter is present, it is deemed that the throwing is completed. If saliva and / or foreign matter is still present after three high-speed rotations, an alarm is issued.
[0032] When the motor 13 is controlled to rotate at a high speed to throw away the saliva and / or foreign matter on the surface, the position of the saliva and / or foreign matter is identified, and the rotation speed of the saliva and / or foreign matter when it is facing the wearer is lower than the rotation speed when it is away from the wearer.
[0033] A truncated cone tube is arranged on the outer edge of the sound receiving surface of the diaphragm 15, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
[0034] The mesh cover 16 is provided with a mark corresponding to the sound receiving surface; If the motor 13 is damaged, the wearer can move the mesh cover 16 through the sound receiving opening 111 to align the mark with the mouth.
[0035] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's specification and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. An engineering project management and control speech recognition system based on artificial intelligence, characterized in that: include: A plurality of terminals, wherein the terminals include a voice collection device worn on a wearer, wherein the voice collection device has a first communication module, a battery and a microphone, wherein the battery is electrically connected to the first communication module and the microphone respectively; the microphone includes an outer shell, a base, a motor, a camera, a diaphragm, a mesh cover and a temperature sensor; the outer shell is provided with a sound receiving port, a mounting port and a storage space, wherein the storage space is respectively connected to the sound receiving port and the mounting port, wherein the base is detachably connected to the mounting port, wherein the motor is fixed to a surface of the base facing the storage space, wherein the mesh cover is located in the storage space and is arranged corresponding to the sound receiving port, wherein the motor is connected to the mesh cover, wherein the diaphragm and the temperature sensor are fixed in the mesh cover, wherein the diaphragm includes a sound receiving surface corresponding to the sound receiving port; wherein the imaging range of the camera includes the face of the wearer and part of the mesh cover; A control end, wherein the control end has a second communication module, wherein the second communication module communicates with the first communication modules of the plurality of terminals for control or voice transfer, wherein the control end has artificial intelligence, wherein the artificial intelligence performs voice recognition actions and heat dissipation actions, wherein the voice recognition actions include: The artificial intelligence obtains the video information of the camera through the communication connection, and at the same time controls the motor to rotate slowly so that the artificial intelligence can obtain the complete surface image of the mesh cover, and judge whether there is saliva and / or foreign matter on the surface image. If there is saliva and / or foreign matter, the artificial intelligence controls the motor to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; if not or after the throwing out is completed, the artificial intelligence controls to obtain the wearer's facial information through the camera and retrieve the wearer's mouth position. After confirming the mouth position, the motor is controlled to rotate to turn the sound receiving surface of the diaphragm toward the wearer's mouth to improve the sound receiving effect and convert the vibration information collected by the diaphragm into sound for voice recognition; The heat dissipation action includes: artificial intelligence determines whether the microphone is performing a voice recognition action, if so, no action is taken; otherwise, the artificial intelligence obtains the temperature information of the temperature sensor through a communication connection, and determines whether the temperature is higher than a preset value, if not, no action is taken; if so, the motor is controlled to rotate to drive the mesh cover and the diaphragm to rotate a predetermined number of times to achieve a heat dissipation effect.
2. The artificial intelligence-based engineering project management and control speech recognition system according to claim 1 is characterized in that: If there is saliva and / or foreign matter, the motor is controlled to rotate at a high speed to throw the saliva and / or foreign matter on the surface away, further comprising: If saliva and / or foreign matter is present, the motor is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor rotates at high speed for a predetermined time, the artificial intelligence controls the motor to rotate slowly again so that the artificial intelligence can obtain a complete surface image of the mesh cover and judge whether there is saliva and / or foreign matter in the surface image. If saliva and / or foreign matter is present, the motor is controlled to rotate at high speed again. If no saliva and / or foreign matter is present, it is deemed that the throwing is completed. If saliva and / or foreign matter is still present after three high-speed rotations, the control end will alarm.
3. The artificial intelligence-based engineering project management and control speech recognition system according to claim 1 is characterized in that: When the motor is controlled to rotate at high speed to throw away saliva and / or foreign objects on the surface, artificial intelligence identifies the location of the saliva and / or foreign objects, and the rotation speed of the saliva and / or foreign objects when they are facing the wearer is lower than the rotation speed when they are away from the wearer.
4. The artificial intelligence-based engineering project management and control speech recognition system according to claim 1 is characterized in that: A truncated cone tube is arranged on the outer edge of the sound receiving surface of the diaphragm, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
5. The artificial intelligence-based engineering project management and control speech recognition system according to claim 1 is characterized in that: The mesh cover is provided with a mark corresponding to the sound receiving surface; If the motor is damaged, the wearer should move the mesh cover through the sound receiving port to align the mark with the mouth.
6. A speech recognition method for engineering project management based on artificial intelligence, characterized in that: include: Communicate with the voice collection device on the wearer and perform voice recognition and heat dissipation actions; The voice collection device is provided with a first communication module, a battery and a microphone, and the battery is electrically connected to the first communication module and the microphone respectively; the microphone comprises an outer shell, a base, a motor, a camera, a diaphragm, a mesh cover and a temperature sensor; the outer shell is provided with a sound receiving port, a mounting port and a storage space, and the storage space is communicated with the sound receiving port and the mounting port respectively, the base is detachably connected to the mounting port, the motor is fixed on a side of the base facing the storage space, the mesh cover is located in the storage space and is arranged corresponding to the sound receiving port, the motor is connected to the mesh cover, the diaphragm and the temperature sensor are fixed in the mesh cover, and the diaphragm comprises a sound receiving surface corresponding to the sound receiving port; the imaging range of the camera includes the face of the wearer and part of the mesh cover; The speech recognition action includes: obtaining video information from the camera through a communication connection, and controlling the motor to rotate slowly to obtain a complete surface image of the mesh cover, judging the complete surface image, and if saliva and / or foreign matter are present, controlling the motor to rotate at a high speed to throw out the saliva and / or foreign matter on the surface; after the throwing out is completed, obtaining the wearer's facial information through the camera and retrieving the wearer's mouth position, and after confirming the mouth position, controlling the motor to rotate so that the sound receiving surface of the diaphragm is facing the wearer's mouth to improve the sound receiving effect and converting the vibration information collected by the diaphragm into sound for speech recognition; The heat dissipation action includes: determining whether the microphone is performing a voice recognition action, if so, not taking any action; if not, obtaining temperature information of a temperature sensor through a communication connection, and determining whether the temperature is higher than a preset value; if not, not taking any action; if so, controlling the motor to rotate to drive the mesh cover and the diaphragm to rotate a predetermined number of times to achieve a heat dissipation effect.
7. The method for speech recognition of engineering project management based on artificial intelligence according to claim 6 is characterized in that: If there is saliva and / or foreign matter, the motor is controlled to rotate at a high speed to throw the saliva and / or foreign matter on the surface away, further comprising: If saliva and / or foreign matter is present, the motor is controlled to rotate at high speed to throw out the saliva and / or foreign matter on the surface. After the motor rotates at high speed for a predetermined time, the motor is controlled to rotate slowly again to obtain a complete surface image of the mesh cover. The complete surface image is judged. If saliva and / or foreign matter is present, the motor is controlled to rotate at high speed again. If no saliva and / or foreign matter is present, it is deemed that the throwing is completed. If saliva and / or foreign matter is still present after three high-speed rotations, an alarm is issued.
8. The method for speech recognition of engineering project management based on artificial intelligence according to claim 6 is characterized in that: When the motor is controlled to rotate at a high speed to throw away the saliva and / or foreign matter on the surface, the position of the saliva and / or foreign matter is identified, and the rotation speed of the saliva and / or foreign matter when it is directed toward the wearer is lower than the rotation speed when it is away from the wearer.
9. The method for speech recognition of engineering project management based on artificial intelligence according to claim 6 is characterized in that: A truncated cone tube is arranged on the outer edge of the sound receiving surface of the diaphragm, and the larger end of the truncated cone tube is the end away from the sound receiving surface.
10. The method for speech recognition of engineering project management and control based on artificial intelligence according to claim 6, characterized in that: The mesh cover is provided with a mark corresponding to the sound receiving surface; If the motor is damaged, the wearer should move the mesh cover through the sound receiving port to align the mark with the mouth.