Bioinformatics response methods, response devices, imaging devices and media

Through the camera device, the face information is collected and recognized, and the preset model is used to determine the speaker and zoom in. This solves the problem of inaccurate recognition of speakers in multi-person meetings, realizes low-cost accurate identification and display response, and reduces data processing cost.

CN112396013BActive Publication Date: 2024-11-12ANHUI HONGCHENG OPTO-ELECTRONICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011341387.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-11-25
Publication Date
2024-11-12
Estimated Expiration
2040-11-25

AI Technical Summary

Technical Problem

In a meeting with multiple people participating, when identifying speakers through sound source positioning, the identification is inaccurate due to gathering of people, and the setting up of special data processing equipment increases costs and insufficient resource utilization.

Method used

Using biological information response method, the camera device collects face information in real time, calls the preset face recognition model to identify speech status, determine and amplify the face image of the speaker, avoid inaccuracy of sound source recognition, and reduce data Handle device dependencies.

Benefits of technology

It realizes accurate identification and display response to speakers at low cost, improves identification accuracy, reduces data processing costs, and enriches the functions of the camera device.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112396013B_ABST
    Figure CN112396013B_ABST
Patent Text Reader

Abstract

The present invention provides a biological information response method, a response device, a camera device and a medium, the method comprising: real-time acquisition of facial information of each person within the camera range of the camera device; calling a preset facial recognition model to identify the facial information, obtaining facial information matching the speech status information pre-stored in the facial recognition model, and determining the person corresponding to the matching facial information as the speaker; obtaining the facial image of the speaker, and enlarging and displaying the facial image of the speaker on a display device connected to the camera device. The present invention identifies the speaker through the preset facial recognition model in the camera device and displays the response, while enriching the functions of the camera device, and realizing accurate identification and display of the speaker at a low cost.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a biological information response method, a response device, a camera device and a medium. Background Art

[0002] The development of network technology has driven the growth of various industries and technologies. Conference systems are a product of this development. In addition to being widely used for internal corporate meetings, conference systems are also widely used in education and training. Conference systems typically include cameras and data processing equipment (such as computers). The cameras capture images of people in the conference environment for presentation, while the data processing equipment processes conference data, such as identifying attendees and speakers.

[0003] Currently, speaker identification is typically performed through acoustic localization, first determining the sound source and then identifying the speaker's face at the source. In large meetings, multiple attendees may be gathered at the source of the sound, making it difficult to distinguish the true speaker, leading to inaccurate speaker identification and display responses. Furthermore, the use of dedicated data processing equipment to process conference data hinders resource utilization and increases data processing costs.

[0004] Therefore, how to accurately identify the speaker from a large number of participants at a low cost and display a response is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] Based on the above situation, the main purpose of the present invention is to provide a biometric information response method, response device, camera device and medium, which can accurately identify the face of the speaker from a large number of participants at a low cost and display a response.

[0006] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for responding to biometric information, wherein the biometric information includes facial information, and the method for responding to the biometric information comprises:

[0008] Real-time collection of facial information of each person within the camera range of the camera;

[0009] Calling a preset face recognition model to recognize the face information, obtaining face information that matches the speech status information pre-stored in the face recognition model, and determining the person corresponding to the matching face information as the speaker;

[0010] A facial image of the speaker is acquired, and the facial image of the speaker is magnified and displayed on a display device that is communicatively connected to the camera device.

[0011] Optionally, the step of calling a preset face recognition model to recognize the face information, obtaining face information that matches the speaking status information pre-stored in the face recognition model, and determining the person corresponding to the matching face information as the speaker includes:

[0012] Calling a preset face recognition model to identify multiple pieces of facial information of each person in a continuous period of time, and obtaining the number of matching items in the multiple pieces of facial information of each person that match the pre-stored speech status information;

[0013] The number of matching items of each person is compared with a preset threshold, and the person whose number of matching items is greater than the preset threshold is determined as the speaker.

[0014] Optionally, the step of obtaining the facial image of the speaker and displaying the facial image of the speaker in an enlarged manner on a display device that is communicatively connected to the camera device includes:

[0015] If there are multiple speakers, facial images of the multiple speakers are acquired, and the facial images of the multiple speakers are amplified and transmitted to the display device for display respectively.

[0016] Optionally, after the step of displaying the facial image of the speaker in an enlarged manner on a display device that is communicatively connected to the camera device, the method further comprises:

[0017] If the speaker displayed on the display device is no longer determined to be the speaker, the facial image of the speaker is restored to a preset state.

[0018] Optionally, before the step of collecting facial information of each person within the camera range of the camera device in real time, the step includes:

[0019] Acquire facial sample data, wherein the facial sample data includes sample data in a speaking state and sample data in a non-speaking state;

[0020] The initial model is trained according to the face sample data to obtain a face recognition model.

[0021] Optionally, the biometric information further includes voiceprint information, and the method for responding to the biometric information further includes:

[0022] When a voice command is received, determining whether the voice command is valid based on the voiceprint information corresponding to the voice command;

[0023] If the voice command is valid, obtaining a command type corresponding to the voice command and determining an operating state of the display device;

[0024] If the instruction type is a power-on type and the display device is in a standby operating state, controlling the display device to power on;

[0025] If the instruction type is a standby type and the display device is in a powered-on running state, the display device is controlled to be in standby mode.

[0026] Optionally, after the step of controlling the display device to start up, the method further comprises:

[0027] When a download request is received, obtaining a request face image corresponding to the download request, and determining whether the download request is valid based on the request face image;

[0028] If the download request is valid, downloading the information corresponding to the download request;

[0029] If the download request is invalid, a download rejection prompt message is output based on the download request.

[0030] Optionally, after the step of controlling the display device to start up, the method further comprises:

[0031] activating a thermal imaging module in the camera device, and detecting the ambient temperature within the camera range of the camera device and the body temperature of each of the persons based on the thermal imaging module;

[0032] generating a temperature adjustment instruction corresponding to the ambient temperature, and sending the temperature adjustment instruction to a temperature control device to adjust the ambient temperature based on the temperature control device;

[0033] The body temperature of each of the persons is compared with a preset temperature threshold, and when a target body temperature greater than the preset temperature threshold is present among the body temperatures, a warning message is output.

[0034] The present invention further provides a biometric information response device, wherein the biometric information includes facial information, and the biometric information response device comprises:

[0035] The acquisition module is used to collect the facial information of each person within the camera range of the camera device in real time;

[0036] A calling module is used to call a preset face recognition model to identify the face information, obtain face information that matches the speech status information pre-stored in the face recognition model, and determine the person corresponding to the matching face information as the speaker;

[0037] The display module is used to obtain the facial image of the speaker and to magnify the facial image of the speaker and display it on a display device that is communicatively connected to the camera device.

[0038] Optionally, the calling module further includes:

[0039] a calling unit, configured to call a preset face recognition model to identify multiple pieces of face information of each person within a continuous period of time, and obtain a number of matching items in the multiple pieces of face information of each person that match the pre-stored speech status information;

[0040] The determination unit is used to compare the number of matching items of each person with a preset threshold value, and determine the person whose number of matching items is greater than the preset threshold value as the speaker.

[0041] Optionally, the display module is further used to:

[0042] If there are multiple speakers, facial images of the multiple speakers are acquired, and the facial images of the multiple speakers are amplified and transmitted to the display device for display respectively.

[0043] Optionally, the biological information response device further includes:

[0044] The restoration module is used to restore the facial image of the person to a preset state if the speaker displayed on the display device is no longer determined to be the speaker.

[0045] Optionally, the biological information response device further includes:

[0046] An acquisition module, configured to acquire facial sample data, wherein the facial sample data includes sample data in a speaking state and sample data in a non-speaking state;

[0047] The training module is used to train the initial model according to the face sample data to obtain a face recognition model.

[0048] Optionally, the biometric information further includes voiceprint information, and the biometric information response device further includes:

[0049] A first judgment module is configured to, when receiving a voice command, judge whether the voice command is valid based on the voiceprint information corresponding to the voice command;

[0050] a determination module, configured to, if the voice instruction is valid, obtain an instruction type corresponding to the voice instruction and determine an operating state of the display device;

[0051] a control module, configured to control the display device to start up if the instruction type is a power-on type and the display device is in a standby operating state;

[0052] The control module is further configured to: if the instruction type is a standby type and the display device is in a powered-on operating state, control the display device to be in standby mode.

[0053] Optionally, the biological information response device further includes:

[0054] a second judgment module, configured to, upon receiving a download request, obtain a requesting facial image corresponding to the download request, and determine whether the download request is valid based on the requesting facial image;

[0055] A download module, configured to download information corresponding to the download request if the download request is valid;

[0056] The output module is configured to output a download rejection prompt message based on the download request if the download request is invalid.

[0057] Optionally, the biological information response device further includes:

[0058] a start-up module, configured to start the thermal imaging module in the camera device and detect the ambient temperature within the camera range of the camera device and the body temperature of each person based on the thermal imaging module;

[0059] a generating module, configured to generate a temperature adjustment instruction corresponding to the ambient temperature, and send the temperature adjustment instruction to a temperature control device, so as to adjust the ambient temperature based on the temperature control device;

[0060] The comparison module is used to compare the body temperature of each person with a preset temperature threshold, and output a warning message when there is a target body temperature greater than the preset temperature threshold among the body temperatures.

[0061] The present invention also provides an imaging device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, the steps of the above-mentioned biological information response method are implemented.

[0062] The present invention also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for responding to biological information are implemented.

[0063] Beneficial effects

[0064] This biometric information response method first uses a camera to collect facial information of each person within the camera's range in real time. A facial recognition model pre-set in the camera is then used to identify the collected facial information of each person, obtaining facial information that matches the speech status information pre-stored in the facial recognition model. The person corresponding to the matched facial information is then identified as the speaker. Furthermore, a facial image of the speaker is obtained and magnified and displayed on a display device connected to the camera. The speech status information pre-stored in the facial recognition model is information pre-set to indicate a person is in a speech state. When the facial recognition model identifies a person whose facial information matches the speech status information, the person is identified as the speaker, and their facial image is magnified and displayed. The magnified facial image distinguishes the speaker from other people, achieving accurate face recognition and magnified display of the speaker based on the facial information of multiple people. This method avoids inaccurate recognition caused by the gathering of people during speaker recognition based on sound sources, thereby improving the accuracy of speaker recognition and display. Furthermore, the present invention enables the speaker to be identified and displayed using only a camera, eliminating the need for both a camera and data processing equipment, thus reducing data processing costs. While enriching the camera's functionality, the presenter can be accurately identified and displayed at a low cost.

[0065] Other beneficial effects of the present invention will be explained through the introduction of specific technical features and technical solutions in the specific implementation methods. Those skilled in the art should be able to understand the beneficial technical effects brought about by these technical features and technical solutions through the introduction of these technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings.

[0067] Figure 1 This is a flow chart of an embodiment of the method for responding to biological information of the present invention;

[0068] Figure 2 This is a flow chart of another embodiment of the biological information response method of the present invention. DETAILED DESCRIPTION

[0069] It should be noted that the use of step numbers (letters or numbers) to refer to certain specific method steps in the present invention is solely for the purpose of convenience and brevity, and is in no way intended to limit the order of these method steps. Those skilled in the art will appreciate that the order of the relevant method steps is determined by the technology itself and should not be unduly limited by the use of step numbers.

[0070] Figure 1 This is a flow chart of an embodiment of a biological information response method of the present invention, which includes the following steps.

[0071] Step S100: collecting facial information of each person within the camera range of the camera device in real time.

[0072] The biometric information response method of this embodiment is applied to a camera device. Biometric information includes facial information. The camera device recognizes the facial information of each person in a meeting or training session, identifies the speaker, and displays a response. Furthermore, the camera device can be used in conjunction with a separate display device, such as an LCD screen, to display the participants and the identified speaker. Furthermore, the camera device can be used in conjunction with a mobile terminal, such as a smartphone or tablet computer, to display the participants and the identified speaker. However, whether using a separate display device or a mobile terminal, the camera device must establish a communication connection with the camera device. Through this communication connection, the facial images of each person captured and the identified speaker are transmitted to the display device or mobile terminal for display, thereby displaying the participants in the meeting or training session and the current speaker.

[0073] Specifically, the camera device includes a camera for external photography, which collects facial information of each person within the camera's range. The camera can be a company's conference room, where the people therein are participants, or a training classroom at an educational institution, where the people therein are students. The specific use can be set to different purposes as needed and is not limited to this. Furthermore, the collected facial information can be complete facial information including eyes, nose, and lips, or information only including the lips, and the specific setting can be based on the camera's processing capabilities and processing efficiency.

[0074] In step S200, a preset face recognition model is called to recognize the face information, and face information matching the speech status information pre-stored in the face recognition model is obtained, and the person corresponding to the matching face information is determined as the speaker.

[0075] Furthermore, a facial recognition model is pre-deployed within the camera device. This facial recognition model is used to identify whether the person whose facial information is collected is speaking. The model is trained using a large amount of facial sample data before the camera device collects facial information for identifying the speaker. Specifically, the steps of real-time collection of facial information of each person within the camera range of the camera device include:

[0076] Step a1, obtaining face sample data, wherein the face sample data includes sample data in a speaking state and sample data in a non-speaking state;

[0077] Step a2: training the initial model based on the face sample data to obtain a face recognition model.

[0078] Furthermore, in order to use the facial recognition model to identify whether a person is speaking, a large amount of sample data, including both speaking and non-speaking samples, is collected. These two types of sample data together form the facial sample data. For the speaking sample data, we first obtain videos of different people speaking, then extract multiple images containing lip position information from the speaking videos as the speaking sample data. For the non-speaking sample data, we directly obtain static images of the people.

[0079] Furthermore, the facial sample data is transferred to the initial model for training. Through multiple iterations of training the initial model with the facial sample data, the initial model converges to a binary classification model for face recognition, thus obtaining the face recognition model. The face recognition model outputs different recognition results for different facial images; for example, for a face image of a person speaking, the output recognition result is 1, while for a face image of a person not speaking, the output recognition result is 0. These different output results reflect whether a person is speaking or not.

[0080] Furthermore, after the facial information of each person is collected by the camera, the preset facial recognition model is called to recognize the collected facial information of each person, determine the facial information of each person that matches the speaking status information pre-stored in the facial recognition model, and determine the person corresponding to the matching facial information as the speaker. The pre-stored speaking status information is information indicating that the speaker corresponding to the facial information is in the speaking state. If the facial information matches the speaking status information, it indicates that the person from whom the facial information originated is likely in the speaking state, and the facial information is identified as the target facial information. If the facial information does not match the speaking status information, it indicates that the person from whom the facial information originated is likely in the non-speaking state, and the facial information is not identified and processed.

[0081] Furthermore, the matching degree between the facial information and the speech status information can be represented by the degree of similarity between the two. A preset value is set to indicate a high degree of similarity. If the similarity between the two exceeds the preset value, indicating a high degree of similarity, the two are considered a match. Conversely, if the similarity between the two does not exceed the preset value, indicating a low degree of similarity, the two are considered a mismatch.

[0082] Step S300: Acquire a facial image of the speaker, and magnify and display the facial image of the speaker on a display device that is communicatively connected to the camera device.

[0083] Furthermore, after the speaker is identified from among the various persons, a facial image of the speaker is acquired. This facial image can be acquired in real time through a camera to show the speaker's speaking status; or the facial images of each person can be pre-recorded into a camera device and acquired by identifying the facial image that matches the speaker among the recorded facial images of each person. Thereafter, the acquired facial image is amplified and transmitted to a display device that is communicatively connected to the camera device. If the camera device is used in conjunction with a separate display device, the amplified facial image is transmitted to the display device for display; if the camera device is used in conjunction with a mobile terminal, the amplified facial image is transmitted to the display device of the mobile terminal for display.

[0084] It should be noted that facial images of all other participants, excluding the speaker, are also captured and transmitted to a display device connected to the camera. By enlarging and displaying only the speaker's facial image, the person corresponding to that facial image is identified as the speaker. While displaying all participants, the speaker is distinguished from the other participants.

[0085] Understandably, multiple people may be speaking simultaneously. In this case, each person's facial information may contain multiple facial information that matches the pre-stored speaking status information. Each person corresponding to the matching facial information is a speaker and has a corresponding facial image, so it is necessary to magnify and display the multiple facial images. Therefore, the steps of obtaining the facial images of the speakers and magnifying and displaying the facial images of the speakers on a display device that is communicatively connected to the camera device include:

[0086] Step S310 : If there are multiple speakers, facial images of the multiple speakers are acquired, and the facial images of the multiple speakers are amplified and transmitted to the display device for display respectively.

[0087] Furthermore, it is determined whether there are multiple pieces of facial information that match the pre-stored speaking status information. If there are multiple pieces, then multiple speakers are determined, indicating that multiple people are speaking at the same time. At this time, facial images of multiple speakers are acquired, and after the multiple facial images are enlarged, they are transmitted to the display device and displayed side by side. The enlargement operation of the facial image can be based on a pre-set size ratio. For example, if the facial images of non-speaking persons are displayed at a size ratio of a, the facial images of speakers can be displayed at a size ratio of 2a. If it is determined that only a single piece of facial information matches the pre-stored speaking status information, it means that only a certain person is currently speaking. At this time, the facial image of the single speaker is acquired, and after the facial image is enlarged and processed, it is transmitted to the display device for display, thereby realizing the distinction between speakers and non-speakers.

[0088] Understandably, speakers in meetings or training sessions vary, with different speakers appearing at different times. Therefore, after identifying and magnifying the facial image of the current speaker, facial information of each speaker is continuously acquired and identified, so that when the speaker changes, the facial image of the new speaker can be magnified and displayed. Specifically, after the step of magnifying and displaying the facial image of the speaker on a display device communicatively connected to the camera device, the following steps are included:

[0089] Step b: If the speaker displayed on the display device is no longer determined to be the speaker, the facial image of the speaker is restored to a preset state.

[0090] Furthermore, the camera device continuously collects facial information of each person within its camera range, and the newly collected facial information is identified by the facial recognition model to determine the facial information that matches the pre-stored speaking status information. If the matched facial information changes, it means that the speaker has changed, and the facial image of the changed speaker is obtained and enlarged and displayed on the display device. If the matched facial information does not change, the display device continues to display the original facial image. In addition, in the case where the matched facial information changes, the original facial information no longer matches the pre-stored speaking status information, indicating that the speaker displayed on the display device is no longer in the speaking state and is no longer determined to be the speaker, so the facial image of the person is restored to the preset state, and the facial image originally enlarged and displayed is restored to the preset state. The preset state is a pre-set size ratio for displaying facial images of non-speaking persons, which can be specifically set according to the screen size of the display device.

[0091] In the biometric information response method of this embodiment, a camera device first collects facial information of each person within the camera's camera range in real time. A pre-set facial recognition model in the camera device is then used to identify the collected facial information of each person, obtaining facial information that matches the speech status information stored in the facial recognition model. The person corresponding to the matching facial information is then identified as the speaker. A facial image of the speaker is then obtained and magnified and displayed on a display device connected to the camera device. The speech status information stored in the facial recognition model is pre-set information indicating a person is in a speech state. When the facial recognition model identifies a person whose facial information matches the speech status information, the person is identified as the speaker, and their facial image is obtained and magnified for display. The magnified facial image distinguishes the speaker from other people, achieving accurate recognition and magnified display of the speaker's face based on the facial information of multiple people. This avoids the problem of inaccurate recognition caused by the gathering of people during speaker recognition based on sound sources, thereby improving the accuracy of speaker recognition and display. Furthermore, the present invention enables the speaker to be identified and displayed using only a camera, eliminating the need for both a camera and data processing equipment, thus reducing data processing costs. While enriching the camera's functionality, the presenter can be accurately identified and displayed at a low cost.

[0092] Furthermore, another embodiment of the method for responding to biological information of the present invention is proposed.

[0093] Another embodiment of the method for responding to biometric information differs from the embodiment of the method for responding to biometric information described above in that the steps of calling a preset face recognition model to recognize the face information, obtaining face information that matches the speech status information pre-stored in the face recognition model, and determining the person corresponding to the face information that matches the face information as the speaker include:

[0094] Step S210: calling a pre-stored face recognition model to identify multiple pieces of face information of each person in a continuous time period, and obtaining the number of matching items in the multiple pieces of face information of each person that match the pre-stored speech status information;

[0095] In step S220 , the number of matching items of each person is compared with a preset threshold value, and the person whose number of matching items is greater than the preset threshold value is determined as the speaker.

[0096] In this embodiment, the speakers are determined based on the number of matching items between the facial information of each person and the pre-stored speech status information within a continuous time period. The continuous time period is a time range set in advance according to the needs, such as 2 seconds, 5 seconds, etc. At the same time, a preset threshold value representing the number of matching items is set in advance. The number of matching items that reach the preset threshold within the continuous time period is used to reflect the continuity of the speech and avoid the inaccuracy of a single match. Specifically, the preset face recognition model in the camera device is called to identify the multiple facial information of each person within the continuous time period, and the number of matching items in the multiple facial information of each person within the continuous time period that match the pre-stored speech status information is obtained. The multiple facial information of each person within the continuous time period is the information obtained by first shooting a video of each person through a camera, and then performing image capture of the video according to a certain time period, reflecting the changing state of each person's face within the continuous time period.

[0097] Furthermore, the facial recognition model is invoked to identify each person's facial information, determine whether each facial information item matches the pre-stored speaking status information, and count the number of items determined to be matches to obtain a matching number. After all multiple facial information items for each person are fully identified within a continuous time period, the matching number for each person is obtained. The matching number for each person is compared with a preset threshold to determine whether it exceeds the threshold. If it exceeds the threshold, it indicates that a majority of the facial information for that person within the continuous time period matches the pre-stored speaking status information, indicating that the person is likely speaking. After comparing the matching number for each person with the preset threshold, the number of matching items for each person that exceeds the preset threshold is determined. This number of matching items is then set as the target matching number. The facial information from which each target matching number originates is then searched. Persons with the found facial information are therefore identified as speakers, thereby determining the speaker from among the various persons.

[0098] This embodiment identifies speakers based on the number of matches between each person's facial information and pre-stored speech status information within a continuous time period. Only when the number of matches exceeds a preset threshold is a person with that type of facial information identified as a target. This prevents accidental movements that could cause their facial information to match pre-stored speech status information, leading to misidentification as a speaker. This ensures accurate speaker identification.

[0099] Furthermore, another embodiment of the bio-information response method of the present invention is proposed. Figure 2 This is a flow chart of another embodiment of the method for responding to biological information of the present invention.

[0100] Another embodiment of the method for responding to biometric information differs from the above embodiment of the method for responding to biometric information in that the biometric information also includes voiceprint information, and the method for responding to biometric information further includes:

[0101] Step S400, when a voice command is received, determining whether the voice command is valid based on the voiceprint information corresponding to the voice command;

[0102] Step S500: If the voice command is valid, obtaining the command type corresponding to the voice command and determining the operating state of the display device;

[0103] Step S600: If the instruction type is a power-on type and the display device is in a standby state, control the display device to power on;

[0104] Step S700: If the instruction type is a standby type and the display device is in a powered-on state, control the display device to be in standby mode.

[0105] The camera device of this embodiment is provided with a function for controlling the operation of a display device to which it is in communication via voice control. Specifically, when the camera device receives a voice command, it first extracts the voiceprint information therein and calls pre-set reference voiceprint information. The read voiceprint information is then compared with the reference voiceprint information to determine the validity of the voice command. The pre-set reference voiceprint information is the pre-recorded voiceprint information of a person who can control the operation of the display device. If the comparison determines that the read voiceprint information matches any of the reference voiceprint information, it indicates that the person from whom the read voiceprint information originated has the authority to control the operation of the display device, and the voice command is therefore determined to be valid. Conversely, if the comparison determines that the read voiceprint information does not match any of the reference voiceprint information, it indicates that the person from whom the read voiceprint information originated does not have the authority to control the operation of the display device, and the voice command is therefore determined to be invalid, and a prompt message indicating that the voice command is invalid is fed back.

[0106] Furthermore, for a valid voice command, the operating state of the display device is switched based on the type of voice command. The types of voice commands include a power-on type and a standby type, which are used to control the display device to power on and to standby, respectively. Specifically, after determining that the voice command is valid, the command type corresponding to the voice command is obtained, and the operating state of the display device is determined. The command type can be determined by identifying voice information carried in the voice command. If the identified voice information carries information such as "power on" or "open," the command type is determined to be the power-on type. If the identified voice information carries information such as "power off" or "standby," the command type is determined to be the standby type. Furthermore, the operating state of the display device can be determined by the communication connection status between the camera device and the display device. The camera device sends a test message to the display device. If the display device correctly returns a reply message, the communication connection between the camera device and the display device is normal, and the operating state of the display device is determined to be power on. If the display device does not correctly return a reply message, the communication connection between the camera device and the display device is abnormal, and the operating state of the display device is determined to be other than standby.

[0107] Furthermore, if it is determined that the instruction type is a power-on type, and the display device is currently in a standby operating state, then a power-on type voice instruction is used to switch the current standby operating state of the display device to a power-on operating state, that is, to control the display device to power on and operate. If it is determined that the instruction type is a standby type, and the display device is currently in a power-on operating state, then a standby type voice instruction is used to switch the current power-on operating state of the display device to a standby operating state, that is, to control the display device to standby. If the state to which the instruction type switches the display device is consistent with the operating state of the display device, such as the instruction type is a power-on type and the operating state is power-on, or the instruction type is a standby type and the operating state is standby, then the operating state of the display device is not switched, and a prompt message indicating that no switching is required is output.

[0108] It should be noted that, since the display device communicatively connected to the camera device can be a separate display device or a display device in a mobile terminal, the switching of the operating status of the display device in this embodiment varies depending on the type of display device. For a separate display device, the switching of the operating status can be switching the power-on operating state to the power-off standby state, or switching the power-off standby state to the power-on operating state. For the display device in the mobile terminal, the switching of the operating status can be switching the state of displaying the participating personnel to the state of displaying the home page of the mobile terminal, or switching the state of displaying the home page of the mobile terminal to the state of displaying the participating personnel. In this way, for different types of display devices, the switching of the operating status is performed in different ways to facilitate the participation and use of the participating personnel.

[0109] Understandably, during a meeting or training session, there may be a need to download files. To this end, the camera device in this embodiment supports the downloading requirement after the display device is powered on. Specifically, the steps of controlling the display device to power on include:

[0110] Step c1, when a download request is received, obtaining a requesting face image corresponding to the download request, and judging whether the download request is valid based on the requesting face image;

[0111] Step c2: if the download request is valid, downloading the information corresponding to the download request;

[0112] Step c3: If the download request is invalid, output a download rejection prompt message based on the download request.

[0113] Furthermore, when a download request is requested, a download request is triggered by sound or by touching the display device. Upon receiving such a download request, the camera device captures a facial image of the person initiating the download request. Specifically, upon receiving the download request, a prompt message may be output, prompting the person initiating the download request to upload their facial image. The camera device receives the facial image uploaded based on the prompt message as the request facial image. Furthermore, based on the request facial image, the camera device determines whether the download request is valid. Specifically, a reference facial image is pre-recorded for a person with download permission. Upon receiving the request facial image, the image is compared with the reference facial image to determine whether the request facial image matches any of the reference facial images. If any of the reference images match, the person from which the request facial image originated has download permission, and the download request is deemed valid. The download operation is then performed on the information requested. If the comparison determines that the request facial image does not match either of the reference images, the person from which the request facial image originated does not have download permission, and the download request is deemed invalid. A download rejection prompt message is output to deny the download request. In this way, by determining the validity of the download request, the security of the download operation is ensured, and downloaders without download permissions are prevented from downloading information unrelated to the meeting or training, or downloading attack information, which may affect the progress of the meeting or training.

[0114] Furthermore, the camera device may also be equipped with a thermal imaging module to detect the temperature in the room where the camera device is located and the body temperature of each person after the display device is turned on. Specifically, the step of controlling the display device to turn on the display device includes:

[0115] Step d1, starting the thermal imaging module in the camera device, and detecting the ambient temperature within the camera range of the camera device and the body temperature of each of the people based on the thermal imaging module;

[0116] Step d2, generating a temperature adjustment instruction corresponding to the ambient temperature, and sending the temperature adjustment instruction to a temperature control device, so as to adjust the ambient temperature based on the temperature control device;

[0117] In step d3, the body temperature of each person is compared with a preset temperature threshold, and when a target body temperature greater than the preset temperature threshold is present among the body temperatures, a warning message is output.

[0118] Furthermore, after the control display device is turned on, the thermal imaging module within the camera device is activated. This thermal imaging module preferably measures temperature using infrared light. The thermal imaging module emits infrared light to detect the ambient temperature and the body temperature of each person within the camera's imaging range. Furthermore, a human comfort temperature is pre-set, and the detected ambient temperature is compared with the human comfort temperature to determine whether the difference between the two exceeds a preset difference. If the difference is greater than the preset difference, it indicates that the difference between the ambient temperature and the human comfort temperature is significant, requiring adjustment of the ambient temperature. A temperature adjustment instruction corresponding to the ambient temperature is generated, and the temperature within the imaging range is adjusted using this temperature adjustment instruction. The temperature adjustment instruction can be output via infrared light emitted by the thermal imaging module to a temperature control device within the imaging range, such as an air conditioner, to activate the temperature control device and set its operating temperature to adjust the temperature.

[0119] At the same time, a preset temperature threshold representing the normal body temperature of the human body is pre-set, and the detected body temperature of each person is compared with the preset temperature threshold to determine whether there is a body temperature greater than the preset temperature threshold among the body temperatures of each person. If there is a body temperature greater than the preset temperature threshold, it means that there are people with abnormal body temperatures among the people. After the body temperatures of each person are compared with the preset temperature threshold, all body temperatures greater than the preset temperature threshold can be determined, and all body temperatures greater than the preset temperature threshold can be set as target body temperatures. Warning information is output for each target body temperature, reminding and preventing people with target body temperatures from participating in meetings or training, or directly disbanding meetings or training. In this way, it is avoided that there are people with abnormal body temperatures and people in sick states among the gathered people, the spread of the disease is prevented, and the health and safety of each person is ensured.

[0120] This embodiment integrates voice control function, download function and temperature detection function into the camera device. While accurately displaying the face of the speaker at a low cost through the camera device, it greatly enriches the functions of the camera device, which is conducive to the promotion and use of the camera device.

[0121] The present invention further provides a biometric information response device, wherein the biometric information includes facial information, and the biometric information response device comprises:

[0122] The acquisition module is used to collect the facial information of each person within the camera range of the camera device in real time;

[0123] A calling module is used to call a preset face recognition model to identify the face information, obtain face information that matches the speech status information pre-stored in the face recognition model, and determine the person corresponding to the matching face information as the speaker;

[0124] The display module is used to obtain the facial image of the speaker and to magnify the facial image of the speaker and display it on a display device that is communicatively connected to the camera device.

[0125] Furthermore, the calling module further includes:

[0126] a calling unit, configured to call a preset face recognition model to identify multiple pieces of face information of each person within a continuous period of time, and obtain a number of matching items in the multiple pieces of face information of each person that match the pre-stored speech status information;

[0127] The determination unit is used to compare the number of matching items of each person with a preset threshold value, and determine the person whose number of matching items is greater than the preset threshold value as the speaker.

[0128] Furthermore, the display module is also used for:

[0129] If there are multiple speakers, facial images of the multiple speakers are acquired, and the facial images of the multiple speakers are amplified and transmitted to the display device for display respectively.

[0130] Furthermore, the biological information response device further includes:

[0131] The restoration module is used to restore the facial image of the person to a preset state if the speaker displayed on the display device is no longer determined to be the speaker.

[0132] Furthermore, the biological information response device further includes:

[0133] An acquisition module, configured to acquire facial sample data, wherein the facial sample data includes sample data in a speaking state and sample data in a non-speaking state;

[0134] The training module is used to train the initial model according to the face sample data to obtain a face recognition model.

[0135] Furthermore, the biometric information also includes voiceprint information, and the biometric information response device also includes:

[0136] A first judgment module is configured to, when receiving a voice command, judge whether the voice command is valid based on the voiceprint information corresponding to the voice command;

[0137] a determination module, configured to, if the voice instruction is valid, obtain an instruction type corresponding to the voice instruction and determine an operating state of the display device;

[0138] a control module, configured to control the display device to start up if the instruction type is a power-on type and the display device is in a standby operating state;

[0139] The control module is further configured to: if the instruction type is a standby type and the display device is in a powered-on operating state, control the display device to be in standby mode.

[0140] Furthermore, the biological information response device further includes:

[0141] a second judgment module, configured to, upon receiving a download request, obtain a requesting facial image corresponding to the download request, and determine whether the download request is valid based on the requesting facial image;

[0142] A download module, configured to download information corresponding to the download request if the download request is valid;

[0143] The output module is configured to output a download rejection prompt message based on the download request if the download request is invalid.

[0144] Furthermore, the biological information response device further includes:

[0145] a start-up module, configured to start the thermal imaging module in the camera device and detect the ambient temperature within the camera range of the camera device and the body temperature of each person based on the thermal imaging module;

[0146] a generating module, configured to generate a temperature adjustment instruction corresponding to the ambient temperature, and send the temperature adjustment instruction to a temperature control device, so as to adjust the ambient temperature based on the temperature control device;

[0147] The comparison module is used to compare the body temperature of each person with a preset temperature threshold, and output a warning message when there is a target body temperature greater than the preset temperature threshold among the body temperatures.

[0148] The specific implementation of the biological information response device of the present invention is basically the same as the embodiments of the biological information response method described above, and will not be repeated here.

[0149] The present invention also proposes a camera device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the computer program is executed by the processor, each step of the biometric information response method described above is implemented.

[0150] The specific implementation of the camera device of the present invention is basically the same as the above-mentioned embodiments of the method for responding to biological information, and will not be repeated here.

[0151] The present invention also provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for responding to biological information are implemented.

[0152] The readable storage medium of the present invention is preferably a computer-readable storage medium, and its specific implementation is basically the same as the above-mentioned embodiments of the bio-information response method, and will not be repeated here.

[0153] Those skilled in the art will appreciate that, provided there is no conflict, the above preferred solutions can be freely combined and superimposed.

[0154] It should be understood that the above-mentioned embodiments are merely illustrative and non-restrictive. Without departing from the basic principles of the present invention, various obvious or equivalent modifications or substitutions that can be made by those skilled in the art to the above-mentioned details will be included in the scope of the claims of the present invention.

Claims

1. A biological information response method, characterized in that: The biological information includes face information, and the response method of the biological information includes: Real-time collection of facial information of each person within the camera range of the camera device; Calling a preset face recognition model to recognize the face information, obtaining face information matching the speech state information pre-stored in the face recognition model, and determining the person corresponding to the matching face information as the speaker; wherein the face recognition model is trained with sample data in the speech state and sample data in the non-speech state; the sample data in the speech state includes multiple images containing lip positions captured from the speech video; Acquire a facial image of the speaker, and magnify and display the facial image of the speaker on a display device that is communicatively connected to the camera device; The steps of calling a preset face recognition model to recognize the face information, obtaining face information matching the speech status information pre-stored in the face recognition model, and determining the person corresponding to the matching face information as the speaker include: Calling a preset face recognition model to identify multiple pieces of face information of each person in a continuous period of time, and obtaining the number of matching items that match the pre-stored speech status information among the multiple pieces of face information of each person; Compare the number of matching items of each person with a preset threshold value, and determine the person whose number of matching items is greater than the preset threshold value as the speaker; The multiple facial information of each person in a continuous period of time is obtained by first shooting a video of each person with a camera and then capturing images of the video according to a time period, reflecting the changing state of each person's face in the continuous period of time.

2. The biological information response method according to claim 1, characterized in that: The step of obtaining the facial image of the speaker and enlarging the facial image of the speaker and displaying it on a display device connected to the camera device in communication includes: If there are multiple speakers, facial images of the multiple speakers are acquired, and the facial images of the multiple speakers are enlarged and transmitted to the display device for display respectively.

3. The biological information response method according to claim 1, characterized in that: After the step of enlarging the facial image of the speaker and displaying it on a display device connected to the camera device, the following steps are included: If the speaker displayed on the display device is no longer determined as the speaker, the facial image of the speaker is restored to a preset state.

4. The biological information response method according to any one of claims 1 to 3, characterized in that: The step of collecting face information of each person within the camera range of the camera device in real time includes: Acquire face sample data, wherein the face sample data includes sample data in a speaking state and sample data in a non-speaking state; The initial model is trained according to the face sample data to obtain a face recognition model.

5. The biological information response method according to any one of claims 1 to 3, characterized in that: The biometric information also includes voiceprint information, and the method for responding to the biometric information also includes: When a voice command is received, judging whether the voice command is valid according to the voiceprint information corresponding to the voice command; If the voice command is valid, obtaining a command type corresponding to the voice command and determining an operating state of the display device; If the instruction type is a power-on type, and the display device is in a standby operating state, then the display device is controlled to power on and operate; If the instruction type is a standby type and the display device is in a powered-on running state, the display device is controlled to be in standby mode.

6. The biological information response method according to claim 5, characterized in that: The step of controlling the display device to start up and run comprises: When a download request is received, obtaining a request face image corresponding to the download request, and judging whether the download request is valid according to the request face image; If the download request is valid, downloading the information corresponding to the download request; If the download request is invalid, a download rejection prompt message is output based on the download request.

7. The biological information response method according to claim 5, characterized in that: The step of controlling the display device to start up and run comprises: Starting the thermal imaging camera module in the camera device, and detecting the ambient temperature within the camera range of the camera device and the body temperature of each of the persons based on the thermal imaging camera module; generating a temperature adjustment instruction corresponding to the ambient temperature, and sending the temperature adjustment instruction to a temperature control device, so as to adjust the ambient temperature based on the temperature control device; The body temperature of each of the persons is compared with a preset temperature threshold, and when a target body temperature greater than the preset temperature threshold is present among the body temperatures, a warning message is output.

8. A biological information response device, characterized in that: The biological information includes facial information, and the biological information response device includes: A collection module, used to collect face information of each person within the camera range of the camera device in real time; A calling module is used to call a preset face recognition model to recognize the face information, obtain face information matching the speech state information pre-stored in the face recognition model, and determine the person corresponding to the matching face information as the speaker; wherein the face recognition model is obtained by training sample data in the speech state and sample data in the non-speech state; the sample data in the speech state includes multiple images containing lip positions captured from the speech video; A display module, used for acquiring a facial image of the speaker, and enlarging the facial image of the speaker and displaying it on a display device that is communicatively connected to the camera device; The steps of calling a preset face recognition model to recognize the face information, obtaining face information matching the speech status information pre-stored in the face recognition model, and determining the person corresponding to the matching face information as the speaker include: Calling a preset face recognition model to identify multiple pieces of face information of each person in a continuous period of time, and obtaining the number of matching items that match the pre-stored speech status information among the multiple pieces of face information of each person; Compare the number of matching items of each person with a preset threshold value, and determine the person whose number of matching items is greater than the preset threshold value as the speaker; The multiple facial information of each person in a continuous period of time is obtained by first shooting a video of each person with a camera and then capturing images of the video according to a time period, reflecting the changing state of each person's face in the continuous period of time.

9. A camera device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.