Privacy protection method, system, device and storage medium for online conferences

Abstract

The present invention discloses a privacy protection method, system, device and storage medium for online conferences. The method includes: when the camera of a terminal device is in a closed state and the microphone is in an enabled state, determining whether there is a human body in a target area based on audio data collected by the microphone; when no human body is present in the target area, executing a corresponding privacy protection strategy, and protecting the user privacy of the online conference through the technical solution of the present application.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a privacy protection method, system, device and storage medium for online conferences. Background Art

[0002] With economic development, more and more people are focusing on improving meeting efficiency and reducing costs. Consequently, online conferencing has emerged. Also known as web conferencing or remote collaborative office work, online conferencing allows users to share data across multiple locations using the internet, effectively improving the efficiency of online collaboration. Currently, market demand for online conferencing is increasing, and users often need to use cameras and microphones to communicate during online meetings. However, if users leave a meeting for a short while or the meeting ends, leaving cameras and microphones on can pose a risk of privacy breaches. Summary of the Invention

[0003] The embodiments of the present application aim to solve the problem of the risk of user privacy leakage in online meetings by providing a privacy protection method, system, device and storage medium for online meetings.

[0004] The embodiment of the present application provides a privacy protection method for an online conference, the privacy protection method for an online conference comprising:

[0005] When the camera of the terminal device is turned off and the microphone is enabled, determine whether there is a human body in the target area based on the audio data collected by the microphone;

[0006] When there is no human body in the target area, a corresponding privacy protection strategy is executed.

[0007] In one embodiment, the step of determining whether a human body exists in the target area based on the audio data collected by the microphone includes:

[0008] Determining speech features based on the audio data collected by the microphone, and determining weighted values ​​of the speech features;

[0009] When the weighted value is less than a first preset value, determining that there is no human body in the target area;

[0010] When the weighted value is greater than or equal to a first preset value, it is determined that a human body exists in the target area.

[0011] In one embodiment, the step of determining whether a human body exists in the target area includes:

[0012] Determining the actual influence ratio of the voice feature, the penalty factor, and the preset weight of the voice feature;

[0013] Obtaining a new weight of the voice feature according to the actual influence ratio, the penalty factor, and the preset weight;

[0014] The speech features are modified using the new weights of the speech features.

[0015] In one embodiment, the online conference privacy protection method further includes:

[0016] Detecting the status of the camera of the terminal device;

[0017] When the camera of the terminal device is in an on state, determining whether there is a human body in the target area based on image data captured by the camera;

[0018] When there is no human body in the target area, the camera is turned off.

[0019] In one embodiment, the step of determining whether a human body exists in the target area based on the image data captured by the camera includes:

[0020] determining a ratio between first size information corresponding to a face region in the image data and second size information corresponding to a display screen of the image data;

[0021] When the ratio is less than a second preset value, it is determined that there is no human body in the target area;

[0022] When the ratio is greater than or equal to the second preset value, it is determined that a human body exists in the target area.

[0023] In one embodiment, when no human body exists in the target area, the step of executing the corresponding privacy protection policy includes:

[0024] When there is no human body in the target area, the privacy protection strategy implemented includes at least one of the following:

[0025] determining whether the terminal device detects a user operation within a preset time period, and when no user operation is detected within the preset time period, turning off the camera and the microphone;

[0026] detecting whether a user process or a system process of the terminal device receives a user operation within a preset time period, and turning off the camera and the microphone when no user operation is detected;

[0027] An online status inquiry interface is displayed, and when no online confirmation operation triggered by the online status inquiry interface is detected within a preset time period, the camera and the microphone are turned off.

[0028] In one embodiment, the online conference privacy protection method further includes:

[0029] When the camera and microphone of the terminal device are both turned on, determining whether there is a human body in the target area based on the image data captured by the camera;

[0030] Determine whether there is a human body in the target area based on the audio data collected by the microphone;

[0031] When the image data captured by the camera determines that a human body exists in the target area, and the audio data collected by the microphone determines that no human body exists in the target area, determining whether the terminal device detects a user operation within a preset time period;

[0032] When the user operation is detected during the preset time period, it is determined that a human body exists in the target area.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also provides a privacy protection system for online conferences, comprising:

[0034] A human body detection module is used to determine whether there is a human body in the target area based on the audio data collected by the microphone when the camera of the terminal device is turned off and the microphone is enabled;

[0035] The execution module is used to execute the corresponding privacy protection strategy when there is no human body in the target area.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal device, which includes: a memory, a processor, and a privacy protection program for online meetings stored on the memory and runnable on the processor. When the privacy protection program for online meetings is executed by the processor, the steps of the above-mentioned privacy protection method for online meetings are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium on which a privacy protection program for an online meeting is stored. When the privacy protection program for an online meeting is executed by a processor, the steps of the above-mentioned privacy protection method for an online meeting are implemented.

[0038] The embodiments of the present application provide a technical solution for a privacy protection method, system, device, and storage medium for online conferences. This solution utilizes a method for determining whether a human body exists within a target area based on audio data collected by the microphone when the terminal device's camera is off and the microphone is enabled; if no human body exists within the target area, a corresponding privacy protection policy is implemented. By combining the microphone and camera to dually detect whether a human body exists within the target area, user privacy is protected using a privacy protection policy when no human body is detected within the target area, thereby achieving user privacy protection for online conferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the hardware operating environment involved in an embodiment of the present invention;

[0040] Figure 2 This is a flow chart of a first embodiment of a privacy protection method for an online conference according to the present invention;

[0041] Figure 3 This is a functional module diagram of the privacy protection system for online conferences of the present invention.

[0042] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings are only an embodiment diagram, not the entire invention. DETAILED DESCRIPTION

[0043] To address the issue of user privacy leakage in online conferences, this application employs a technical solution that, when a terminal device's camera is off and its microphone is enabled, determines whether a person is within a target area based on audio data collected by the microphone; if no person is present within the target area, a corresponding privacy protection policy is implemented. By combining the microphone and camera to dually detect the presence of a person within the target area, user privacy is protected through a privacy protection policy when no person is detected within the target area, thereby achieving user privacy protection in online conferences.

[0044] To better understand the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0045] like Figure 1 As shown, Figure 1 This is a schematic diagram of the structure of the hardware operating environment involved in the embodiment of the present invention.

[0046] It should be noted that Figure 1 This is a structural diagram of the hardware operating environment of the terminal device.

[0047] like Figure 1As shown, the terminal device may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The terminal device structure shown in the figure does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0049] like Figure 1 As shown, the memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and a privacy protection program for online meetings. The operating system is a program that manages and controls the hardware and software resources of the terminal device, and the privacy protection program for online meetings and other software or programs are also included.

[0050] exist Figure 1 In the terminal device shown, the user interface 1003 is mainly used to connect to the terminal and communicate data with the terminal; the network interface 1004 is mainly used for the background server and communicates data with the background server; the processor 1001 can be used to call the privacy protection program for the online meeting stored in the memory 1005.

[0051] In this embodiment, the terminal device includes: a memory 1005, a processor 1001, and a privacy protection program for an online meeting stored in the memory and executable on the processor, wherein:

[0052] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, the following operations are performed:

[0053] When the camera of the terminal device is turned off and the microphone is enabled, determine whether there is a human body in the target area based on the audio data collected by the microphone;

[0054] When there is no human body in the target area, a corresponding privacy protection strategy is executed.

[0055] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0056] Determining speech features based on the audio data collected by the microphone, and determining weighted values ​​of the speech features;

[0057] When the weighted value is less than a first preset value, determining that there is no human body in the target area;

[0058] When the weighted value is greater than or equal to a first preset value, it is determined that a human body exists in the target area.

[0059] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0060] Determining the actual influence ratio of the voice feature, the penalty factor, and the preset weight of the voice feature;

[0061] Obtaining a new weight of the voice feature according to the actual influence ratio, the penalty factor, and the preset weight;

[0062] The speech features are modified using the new weights of the speech features.

[0063] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0064] Detecting the status of the camera of the terminal device;

[0065] When the camera of the terminal device is in an on state, determining whether there is a human body in the target area based on image data captured by the camera;

[0066] When there is no human body in the target area, the camera is turned off.

[0067] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0068] determining a ratio between first size information corresponding to a face region in the image data and second size information corresponding to a display screen of the image data;

[0069] When the ratio is less than a second preset value, it is determined that there is no human body in the target area;

[0070] When the ratio is greater than or equal to the second preset value, it is determined that a human body exists in the target area.

[0071] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0072] When there is no human body in the target area, the privacy protection strategy implemented includes at least one of the following:

[0073] determining whether the terminal device detects a user operation within a preset time period, and when no user operation is detected within the preset time period, turning off the camera and the microphone;

[0074] detecting whether a user process or a system process of the terminal device receives a user operation within a preset time period, and turning off the camera and the microphone when no user operation is detected;

[0075] An online status inquiry interface is displayed, and when no online confirmation operation triggered by the online status inquiry interface is detected within a preset time period, the camera and the microphone are turned off.

[0076] When the processor 1001 calls the privacy protection program for the online conference stored in the memory 1005, it also performs the following operations:

[0077] When the camera and microphone of the terminal device are both turned on, determining whether there is a human body in the target area based on the image data captured by the camera;

[0078] Determine whether there is a human body in the target area based on the audio data collected by the microphone;

[0079] When the image data captured by the camera determines that a human body exists in the target area, and the audio data collected by the microphone determines that no human body exists in the target area, determining whether the terminal device detects a user operation within a preset time period;

[0080] When the user operation is detected during the preset time period, it is determined that a human body exists in the target area. The technical solution of the present application will be described below in the form of embodiments.

[0081] like Figure 2 As shown, in the first embodiment of the present application, the privacy protection method of the online conference of the present application includes the following steps:

[0082] Step S110: When the camera of the terminal device is in an off state and the microphone is in an on state, it is determined whether there is a human body in the target area based on the audio data collected by the microphone.

[0083] Step S120: When there is no human body in the target area, executing a corresponding privacy protection policy.

[0084] In this embodiment, the terminal device may be a PC, or a mobile terminal device with a display function, such as a smartphone, tablet computer, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, or portable computer. The terminal device may include a camera, a microphone, a sound pickup, and the like.

[0085] Install software that can be used for online meetings on the terminal device. Users can pre-set the working status of the camera and microphone on the software to be enabled, so that the camera and microphone will be automatically turned on the next time a meeting is started. Alternatively, when the software is enabled, the working status of the camera and microphone can be set to be off by default, and the user can enable the camera or microphone as needed. When the user enables the software, if it detects that the user has turned on the camera, the default background image can be displayed to actively protect the user's privacy. When it detects that the user has turned on the microphone, the collected audio data can be filtered to filter out other ambient sounds to retain the user's voice, thereby protecting the user's privacy.

[0086] In this embodiment, the privacy protection method for online conferences of this application can be applied to scenarios such as online conferences and online lectures. For example, during an online conference, if a user leaves the terminal device midway, there is a risk of privacy leakage if the camera and microphone are left on. Alternatively, if a user believes the meeting is over but forgets to close the client, there is a risk of privacy leakage if the camera and microphone are left on. Therefore, during an online conference, it is necessary to detect the presence of human bodies in the target area in real time.

[0087] Specifically, the camera status and the microphone status are first detected. When the camera of the terminal device is in the off state and the microphone is in the enabled state, it is determined whether there is a human body in the target area based on the audio data collected by the microphone; when there is no human body in the target area, the corresponding privacy protection strategy is executed.

[0088] According to the above technical solution, this embodiment adopts a method of determining a first detection result based on the image data captured by the camera and a second detection result based on the audio data collected by the microphone when it is detected that both the camera and the microphone of the terminal device are in an enabled state. When the first detection result is inconsistent with the second detection result, it is determined whether the terminal device has detected a user operation within a preset time period. When a user operation is detected, it is determined whether a human body exists in the target area. Since the microphone and the camera are combined to dually detect whether a human body exists in the target area, and when the detection results of the two are inconsistent, it is determined which of the above results is to be used by detecting whether a user operation is received, thereby avoiding misjudgment due to the difference in the above detection results, which may lead to leakage of user privacy, and realizing the protection of the privacy of online conference users.

[0089] In one embodiment, when there is no human body in the target area, executing the corresponding privacy protection policy specifically includes the following steps:

[0090] When the terminal device's camera is disabled but the microphone is enabled, and the microphone detects the absence of a human within the target area based on audio data collected by the microphone, an online status inquiry interface is displayed on the terminal device's screen. If the online status inquiry interface receives an online confirmation action within a preset time period, it indicates that a human is within the target area. In this case, the meeting is not terminated, and the user's status is marked as "away." If no online confirmation action is detected, the microphone is muted, automatically protecting user privacy when the user leaves the meeting or the meeting ends.

[0091] When the camera of the terminal device is not enabled but the microphone is enabled, when it is determined based on the audio data collected by the microphone that there is no human body in the target area, the user process or system process of the terminal device is detected to see if it receives a user operation. If so, it indicates that there is a human body in the target area. In this case, the meeting is not ended and the status is marked as left. When no user process or system process is detected, the microphone is turned off. For example, it can be detected whether there is a folder, picture or video being dragged in the background, or whether other applications are started or closed. If so, it indicates that there is a human body in the target area. If not, the microphone is turned off. This allows for automatic protection of user privacy when the user leaves the meeting or the meeting ends.

[0092] In one embodiment, the step of determining whether a human body is in the target area based on audio data collected by a microphone includes:

[0093] Step S111 : determining speech features based on the audio data collected by the microphone, and determining weighted values ​​of the speech features.

[0094] Step S112: when the weighted value is less than a first preset value, determining that there is no human body in the target area;

[0095] Step S113: When the weighted value is greater than or equal to a first preset value, it is determined that a human body exists in the target area.

[0096] In this embodiment, audio data collected by a microphone is processed. The continuous analog audio signal from the microphone is converted to digital form at a certain sampling frequency to obtain audio data. There are two important indicators for audio data processing: sampling frequency and sampling size. The sampling frequency refers to the number of samples taken per unit time. The higher the sampling frequency, the smaller the intervals between sampling points, resulting in a more realistic sound. The sampling size refers to the number of bits used to record the size of each sample value. It determines the dynamic range of the sample. The more bits, the more subtle the recorded sound changes, and the larger the amount of data obtained.

[0097] In this embodiment, when it is detected that the camera is turned off and the microphone is enabled, audio data of a preset length can be recorded through the microphone, and voice features in the audio data can be extracted. There can be one voice feature, or two can exist at the same time. When there are multiple voice features, the accuracy of the human body detection result can be improved. At the same time, when there are multiple voice features, the feature values ​​of each voice feature can be added to obtain a weighted value of the voice feature. The weighted value is compared with the first preset value to determine the human body detection result. Specifically, when the weighted value is less than the first preset value, it is determined that there is no human body inside the target area. When the weighted value is greater than or equal to the first preset value, it is determined that there is a human body in the target area. When there are multiple voice features, whether there is a human body in the target area is determined based on the relationship between the voice feature and the preset threshold.

[0098] Specifically, audio data of a preset length collected by a microphone can be obtained; short-time energy features, resonance peak features and Mel-frequency cepstral coefficient features can be determined based on the audio data; and weighted values ​​of the short-time energy features, the resonance peak features and the Mel-frequency cepstral coefficient features can be determined.

[0099] Twenty seconds of audio is recorded, and the short-time energy features, formant features, and Mel-frequency cepstral coefficient features (MFCC features) of the speech are extracted.

[0100] The short-term energy characteristic can be expressed as the volume of a person's speech. When the user is away from the conference equipment, the volume is lower. The formula for the short-term energy characteristic is as follows:

[0101]

[0102] Among them, E(i) represents the energy function within the collected i frame, It represents the square of the mth sample value of the i-th frame speech signal, and N represents the frame length.

[0103] Formant characteristics are a type of sound quality feature that measures speech clarity and intelligibility. When a user leaves the conference room, other voice information may be present in the environment, but the quality of this information will be significantly lower than that of a normal conference call. This application uses linear predictive coding (LPC) to extract the first three formant frequencies and bandwidths as sound quality features.

[0104] MFCC features, also known as Mel-frequency cepstral coefficients, are spectral features that conform to the human hearing mechanism, namely, the nonlinear relationship between the pitch and frequency of sounds heard by humans. Spectral features reflect the relationship between changes in vocal tract shape and vocalization movements. The distribution of spectral energy across frequency ranges is significantly different between a normal conference call and ambient speech leaving the device. The formula for calculating the Mel-frequency is as follows:

[0105]

[0106] Where f is the frequency of the speech signal. The preprocessed signal is subjected to fast Fourier transform, Mel filtering, energy spectrum logarithm operation, and discrete cosine transform to extract MFCC features.

[0107] By extracting the characteristic values ​​of these three voice features as input variables and applying a weighted score, if the score falls below a threshold, it is determined that the user has left the device.

[0108] According to the above technical solution, this embodiment determines the weighted value of the voice feature and then determines whether there is a human body in the target area based on the weighted value.

[0109] In one embodiment, after step S113, the following steps are specifically included:

[0110] Step S210, determining the actual influence ratio of the voice feature, the penalty factor, and the preset weight of the voice feature;

[0111] Step S220: obtaining a new weight of the voice feature according to the actual influence ratio, the penalty factor, and the preset weight;

[0112] Step S230: Modify the speech feature using the new weight of the speech feature.

[0113] In this embodiment, if it is determined that the user has left the conference device, it is determined whether the terminal device detects user operation within a preset period of time. For example, a message is displayed on the terminal device asking whether the user is online for 20 seconds. At the same time, the user's response result is to click "No" or not to respond. The recorded audio data is input into the speech analysis module as a factor affecting the weight of each variable. Let the preset weight of each feature value be k i If the current user's answer is no, the algorithm makes an error, and the penalty factor C is increased to weaken the weight of the feature value that affects the current judgment, so as to achieve the purpose of correction. The new weight is: k i '=Cg(i)k i Among them, k i ' is the new weight, C is the penalty factor, and g(i) is the actual influence ratio of the current speech feature, thereby realizing the correction of the speech feature.

[0114] According to the above technical solution, this embodiment adds a penalty factor to correct the voice feature, thereby avoiding misjudgment caused by the user triggering the online confirmation operation multiple times.

[0115] In one embodiment, at any position of each step of the first embodiment, the following steps are further included:

[0116] Step S310, detecting the status of the camera of the terminal device;

[0117] Step S320, when the camera of the terminal device is in an on state, determining whether there is a human body in the target area based on the image data captured by the camera;

[0118] Step S330: When there is no human body in the target area, turn off the camera.

[0119] In this embodiment, at the end of a meeting or during a meeting, the terminal device's camera status is detected. When the camera is activated, the presence of a human body within the target area is determined based on the image data captured by the camera. If no human body is present within the target area, the camera is directly turned off. Alternatively, if no human body is present within the target area, the terminal device is determined to have detected a user operation within a preset period of time. If not, the camera is turned off.

[0120] According to the above technical solution, when the terminal device starts the camera but does not enable the microphone, this embodiment can determine whether there is a human body in the target area based on the image data captured by the camera and turn off the camera.

[0121] In one embodiment, determining whether a human body exists in the target area according to the image data captured by the camera in step S320 specifically includes the following steps:

[0122] Step S111, determining a ratio between first size information corresponding to a face region in the image data and second size information corresponding to a display screen of the image data;

[0123] Step S112: when the ratio is less than a second preset value, determining that there is no human body in the target area;

[0124] Step S113: When the ratio is greater than or equal to the second preset value, it is determined that there is a human body in the target area.

[0125] In this embodiment, when it is detected that the camera of the terminal device is in an enabled state, the face detection module library is used to detect the human figure in the picture to obtain the face area, which is marked by the face detection frame. The first size information and the second size information can be any one of the length, width or area of ​​the face area. When the first size information is the length of the face area, the second size information is also the length of the face area. For example, the width d of the face area is calculated. The ratio k of the width of the face area to the current display screen is calculated, k=d / width. Width is the width of the current display screen. If the ratio k is less than the second preset value or the face area does not exist, it is determined that there is no human body in the target area, that is, the user has left the terminal device. On the contrary, when the ratio is greater than or equal to the second preset value, it is determined that there is a human body in the target area, that is, the user has not left the device.

[0126] According to the above technical solution, this embodiment determines the ratio of the width of the face area to the width of the current display screen through the image data captured by the camera, and then determines whether there is a human body in the target area based on the ratio.

[0127] In one embodiment, at any position of each step of the first embodiment, the following steps are further included:

[0128] Step S410: When the camera and microphone of the terminal device are both turned on, determining whether there is a human body in the target area based on image data captured by the camera;

[0129] Step S420, determining whether there is a human body in the target area based on the audio data collected by the microphone;

[0130] Step S430: When the image data captured by the camera determines that a human body exists in the target area, and the audio data collected by the microphone determines that no human body exists in the target area, determining whether the terminal device detects a user operation within a preset time period;

[0131] Step S440: When the user operation is detected in the preset time period, it is determined that there is a human body in the target area.

[0132] In this embodiment, when it is detected that the camera and microphone of the terminal device are in the enabled state, it is determined whether there is a human body in the target area based on the image data captured by the camera, and at the same time, it is determined whether there is a human body in the target area based on the audio data collected by the microphone.

[0133] Specifically, this embodiment uses the example of a meeting in which both the camera and microphone are enabled. When a user enters a meeting using the meeting address and number, a human body detection program is initiated. When the user turns on the camera and microphone, the terminal device's camera captures images in real time. The captured image data is processed to determine whether a human body is present in the current camera image. Simultaneously, the presence of a human body is determined based on the audio data collected by the microphone. Specifically, the audio features of the audio data can be analyzed to determine whether a human body is present.

[0134] In this embodiment, if the presence of a human body in the target area is determined based on image data captured by the camera, while the absence of a human body in the target area is determined based on audio data collected by the microphone, then the two detection results are inconsistent. In this case, the user operation can be detected by detecting whether a user operation is detected within a preset time period. This can be done by displaying a control in the display window of the terminal device and detecting whether a trigger operation of the display control is received within a preset time period to further determine whether a user operation is detected. Alternatively, the user operation can be detected by detecting whether a reply message sent by a user ID appears in the chat window of the terminal device within a preset time period to further determine whether a user operation is detected. Alternatively, after the robot inquires, the user's response signal is received within a preset time period to further determine whether a user operation is detected. The above-mentioned preset time periods can be set according to actual circumstances. When a user operation is detected within the preset time period, it indicates that a human body is present in the target area.

[0135] In one embodiment, when the presence of a human body in the target area is determined based on image data captured by the camera, and when the absence of a human body in the target area is determined based on audio data collected by the microphone, the presence of a human body in the target area is determined. Alternatively, when the absence of a human body in the target area is determined based on image data captured by the camera, and the presence of a human body in the target area is determined based on audio data collected by the microphone, it is determined whether the terminal device detects a user operation within a preset time period, and when a user operation is detected, the presence of a human body in the target area is determined.

[0136] According to the above technical solution, this embodiment performs corresponding processing when the detection results of the camera and the microphone are inconsistent to avoid misjudgment that may lead to leakage of user privacy.

[0137] The embodiments of the present invention provide embodiments of a privacy protection method for an online conference. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that shown here.

[0138] like Figure 3 As shown, the present application provides a privacy protection system for online conferences, which includes:

[0139] The human body detection module 10 is used to determine whether there is a human body in the target area based on the audio data collected by the microphone when the camera of the terminal device is in the off state and the microphone is in the on state. In one embodiment, the human body detection module 10 is used to determine the voice feature based on the audio data collected by the microphone, and determine the weight value of the voice feature; when the weight value is less than a first preset value, it is determined that there is no human body in the target area; when the weight value is greater than or equal to the first preset value, it is determined that there is a human body in the target area. In one embodiment, a correction module is further connected after the human body detection module 10, and the correction module is used to determine the actual influence ratio of the voice feature, the penalty factor and the preset weight of the voice feature; obtain the new weight of the voice feature according to the actual influence ratio, the penalty factor and the preset weight; and correct the voice feature using the new weight of the voice feature.

[0140] The execution module 20 is configured to execute a corresponding privacy protection policy when no human body exists in the target area. In one embodiment, the execution module 20 is configured to execute a privacy protection policy when no human body exists in the target area, including at least one of the following: determining whether the terminal device detects a user operation within a preset period of time, and turning off the camera and the microphone when no user operation is detected within the preset period of time; detecting whether the user process or system process of the terminal device receives a user operation within a preset period of time, and turning off the camera and the microphone when no user operation is detected; displaying an online status inquiry interface, and turning off the camera and the microphone when no online confirmation operation triggered by the online status inquiry interface is detected within a preset period of time.

[0141] In one embodiment, the online conference privacy protection system further includes a first processing module configured to detect the status of the terminal device's camera; when the terminal device's camera is on, determine whether a human body is within a target area based on image data captured by the camera; and deactivate the camera if no human body is within the target area. In one embodiment, the first processing module is configured to determine a ratio between first size information corresponding to a facial region in the image data and second size information corresponding to a display screen of the image data; if the ratio is less than a second preset value, determine that no human body is within the target area; and if the ratio is greater than or equal to the second preset value, determine that a human body is within the target area.

[0142] In one embodiment, the privacy protection system for online meetings also includes a second processing module, which is used to determine whether there is a human body in the target area based on image data captured by the camera when the camera and microphone of the terminal device are both in an on state; determine whether there is a human body in the target area based on audio data collected by the microphone; when the image data captured by the camera determines that there is a human body in the target area, and the audio data collected by the microphone determines that there is no human body in the target area, determine whether the terminal device detects a user operation within a preset time period; when the user operation is detected within the preset time period, determine that there is a human body in the target area.

[0143] The specific implementation of the privacy protection system for online conferences of the present invention is basically the same as the above-mentioned embodiments of the privacy protection method for online conferences, and will not be repeated here.

[0144] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, which stores a privacy protection program for an online meeting. When the privacy protection program for an online meeting is executed by a processor, the privacy protection program for an online meeting implements the various steps of the privacy protection method for an online meeting as described above, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0145] Since the storage medium provided in the embodiments of this application is the storage medium used to implement the method of the embodiments of this application, those skilled in the art will be able to understand the specific structure and variations of the storage medium based on the method described in the embodiments of this application, and therefore will not be described in detail here. All storage media used in the method of the embodiments of this application fall within the scope of protection to be provided by this application.

[0146] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0150] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third etc. does not indicate any order. These words may be interpreted as names.

[0151] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0152] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A privacy protection method for an online conference, characterized in that: The privacy protection method for the online conference includes: When the camera of the terminal device is in an off state and the microphone is in an enabled state, determining voice features based on audio data collected by the microphone, and determining weighted values ​​of the voice features; When the weighted value is greater than or equal to a first preset value, determining that a human body exists in the target area; determining an actual influence ratio of the voice feature, a penalty factor, and a preset weight of the voice feature; obtaining a new weight of the voice feature based on the actual influence ratio, the penalty factor, and the preset weight; and modifying the voice feature using the new weight of the voice feature; When the weighted value is greater than or equal to a first preset value, determining that a human body exists in the target area; When there is no human body in the target area, a corresponding privacy protection strategy is executed.

2. The privacy protection method for an online conference as claimed in claim 1, wherein: The privacy protection method for the online conference also includes: Detecting the status of the camera of the terminal device; When the camera of the terminal device is in an on state, determining whether there is a human body in the target area based on image data captured by the camera; When there is no human body in the target area, the camera is turned off.

3. The privacy protection method for an online conference as claimed in claim 2, wherein: The step of determining whether a human body exists in the target area based on the image data captured by the camera includes: determining a ratio between first size information corresponding to a face region in the image data and second size information corresponding to a display screen of the image data; When the ratio is less than a second preset value, it is determined that there is no human body in the target area; When the ratio is greater than or equal to the second preset value, it is determined that a human body exists in the target area.

4. The privacy protection method for an online conference as claimed in claim 1, wherein: When there is no human body in the target area, the step of executing the corresponding privacy protection policy includes: When there is no human body in the target area, the privacy protection strategy implemented includes at least one of the following: determining whether the terminal device detects a user operation within a preset time period, and when no user operation is detected within the preset time period, turning off the camera and the microphone; detecting whether a user process or a system process of the terminal device receives a user operation within a preset time period, and turning off the camera and the microphone when no user operation is detected; An online status inquiry interface is displayed, and when no online confirmation operation triggered by the online status inquiry interface is detected within a preset time period, the camera and the microphone are turned off.

5. The privacy protection method for an online conference as claimed in claim 1, wherein: The privacy protection method for the online conference also includes: When the camera and microphone of the terminal device are both turned on, determining whether there is a human body in the target area based on the image data captured by the camera; Determine whether there is a human body in the target area based on the audio data collected by the microphone; When the image data captured by the camera determines that a human body exists in the target area, and the audio data collected by the microphone determines that no human body exists in the target area, determining whether the terminal device detects a user operation within a preset time period; When the user operation is detected during the preset time period, it is determined that a human body exists in the target area.

6. A privacy protection system for online conferences, characterized in that: The privacy protection system for online conferences includes: A human body detection module is used to determine, when the camera of the terminal device is in an off state and the microphone is in an enabled state, voice features based on the audio data collected by the microphone, and determine a weighted value of the voice features; when the weighted value is greater than or equal to a first preset value, determine that a human body exists in the target area; determine an actual influence ratio of the voice features, a penalty factor, and a preset weight of the voice features; obtain a new weight of the voice features based on the actual influence ratio, the penalty factor, and the preset weight; modify the voice features using the new weight of the voice features; and when the weighted value is greater than or equal to the first preset value, determine that a human body exists in the target area; The execution module is used to execute the corresponding privacy protection strategy when there is no human body in the target area.

7. A terminal device, characterized in that: The terminal device includes: a memory, a processor, and a privacy protection program for an online meeting stored in the memory and executable on the processor. When the privacy protection program for an online meeting is executed by the processor, the steps of the privacy protection method for an online meeting according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a privacy protection program for an online conference, and when the privacy protection program for an online conference is executed by a processor, the steps of the privacy protection method for an online conference are implemented as described in any one of claims 1 to 5.

Images