Remote interrogation screen control analysis method and system based on blockchain
Through the blockchain-based remote interrogation screen control analysis method, the problem of video abnormality detection in remote interrogation screen control is solved, the video quality and control effect are improved, and efficient data transmission and security are achieved.
Patent Information
- Application Number
- CN202310846873.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-11
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2043-07-11
AI Technical Summary
The existing remote interrogation screen control method is difficult to detect interrogation abnormalities in the video in a timely manner, resulting in poor remote interrogation screen control effect.
Using the blockchain-based remote interrogation screen control analysis method, abnormal behavior is identified and screen is detected by performing noise reduction processing, synchronous proofreading, digital signature encryption, blockchain network transmission, video object grading and user feature recognition. Control processing.
It improves the quality and control effect of remote interrogation video images, improves the transmission efficiency and security of videos, and provides abnormal behavior analysis for easy video control.
Smart Images

Figure CN117041641B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of remote control, and in particular to a remote interrogation screen control and analysis method and system based on blockchain. Background Art
[0002] Remote interrogation screen control refers to the process of managing and controlling the video images in remote interrogations through technical means. Remote interrogation screen control can provide opportunities for remote participation, reduce time and costs, increase flexibility, protect security and privacy, improve efficiency and effectiveness, and provide review and playback capabilities.
[0003] At present, the remote interrogation screen control method is mainly to transmit the real-time interrogation video to the control terminal through video transmission technology, and then use smart contract technology to enable the control terminal to manage the image and sound of the interrogation screen. This method may require watching and processing multiple interrogation videos at the same time, and cannot detect interrogation anomalies in the video in time, resulting in poor remote interrogation screen control effect. Summary of the invention
[0004] In order to solve the above problems, the present invention provides a remote interrogation screen control analysis method and system based on blockchain, which can improve the effect of remote interrogation video screen control.
[0005] In a first aspect, the present invention provides a remote interrogation screen control and analysis method based on blockchain, the method comprising:
[0006] Acquire a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video;
[0007] Performing background encoding on the proofreading interrogation video to obtain a video digital signal, and performing digital signature encryption on the video digital signal to obtain a signature encrypted signal;
[0008] Constructing a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; uploading the signature encrypted signal to the access center using the transmission link of the blockchain network, decrypting the signature encrypted signal in the access center to obtain a decrypted digital signal, and performing video transcoding on the decrypted digital signal to obtain a target interrogation video;
[0009] Identifying the video object of the target interrogation video, the video object includes: an interrogation object and an interrogated object, and grading the target interrogation video according to the interrogation object and the interrogated object to obtain a graded interrogation video;
[0010] According to the graded interrogation video, user features of the interrogating subject and the interrogated subject are captured respectively to obtain a first user feature and a second user feature, and the first user feature and the second user feature are respectively input into a user abnormality recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogating subject and the interrogated subject to obtain a first user abnormal behavior and a second user abnormal behavior;
[0011] Based on the first user's abnormal behavior and the second user's abnormal behavior, a picture control process is performed in the target interrogation video to obtain a picture control process result.
[0012] In a possible implementation of the first aspect, performing noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video includes:
[0013] capturing frames of the remote interrogation video;
[0014] Marking a local neighborhood of the frame;
[0015] Calculating neighborhood pixel values of the local neighborhood;
[0016] Arrange the neighborhood pixel values in order of magnitude to obtain sequential neighborhood pixel values;
[0017] Taking the central pixel value of the sequential neighborhood pixel values as the filter coefficient;
[0018] According to the filtering coefficient, filtering is performed on the local neighborhood to obtain a local filtered image;
[0019] Fusing the local filtered images to obtain a noise reduction frame;
[0020] A noise-reduced interrogation video of the remote interrogation video is generated according to the noise-reduced frame image.
[0021] In a possible implementation manner of the first aspect, filtering the local neighborhood according to the filtering coefficient to obtain a local filtered image includes:
[0022] According to the filtering coefficient, the neighborhood filtering pixel value of the local neighborhood is calculated using the following formula:
[0023] A(a,b)=median{1 / N*f(a+c,b+d)&|c=-e,b=-d}
[0024] Where A(a,b) represents the neighborhood filter pixel value, median represents the filter function, N represents the size of the local neighborhood, c represents the radius of the local neighborhood on the x-axis, d represents the radius of the local neighborhood on the y-axis, & represents the filter coefficient, f(a+c,b+d) represents the pixel value of the local neighborhood corresponding to the pixel point after the x-axis translation is c pixels and the y-axis translation is d pixels, a represents the horizontal coordinate of the local neighborhood corresponding to the pixel point, and b represents the vertical coordinate of the local neighborhood corresponding to the pixel point;
[0025] A local filtered image of the local neighborhood is constructed according to the neighborhood filtered pixel values.
[0026] In a possible implementation of the first aspect, synchronously proofreading the video sound and the video picture in the noise reduction interrogation video to obtain the proofread interrogation video includes:
[0027] Capturing the voice of the person in the video sound and the lip shape of the person in the video picture;
[0028] Calculating the audio synchronization between the character's voice and the character's lip shape;
[0029] When the audio synchronization is lower than the preset audio synchronization limit;
[0030] Recording abnormal descriptions of the character's voice and the character's lip shape;
[0031] Analyzing the audio synchronization mode of the video sound and the video picture according to the abnormal description;
[0032] According to the audio synchronization method, the video sound and the video picture in the noise reduction interrogation video are synchronously proofread to obtain the proofread interrogation video.
[0033] In a possible implementation of the first aspect, the step of performing digital signature encryption on the video digital signal to obtain a signature encrypted signal includes:
[0034] Configuring a signature condition for encrypting the video digital signal;
[0035] Generate a signature key for the video digital signal according to the signature condition;
[0036] Signing the video digital signal according to the signature key and the signature condition to obtain a signature value of the video digital signal;
[0037] When the signature value is successfully verified, the digital encryption signal is generated.
[0038] In a possible implementation manner of the first aspect, signing the video digital signal according to the signature key and the signature condition to obtain the signature value of the video digital signal includes:
[0039] According to the signature key and the signature condition, the video digital signal is signed using the following formula to obtain the signature value of the video digital signal:
[0040] (f,g)=(((h^(modj))mod k),(((i^-1*(H(M)+xf))mod k)))
[0041] Among them, (f,g) represents the signature value, f represents the temporary key of the video digital signal, g represents the signature result generated after the video digital signal is signed, h represents the corresponding random number in the signature condition, mod represents the modulus operation, j and k represent the corresponding prime numbers in the signature condition, i and x represent the corresponding random integers in the signature condition, H(M) represents the hash value of the video digital signal, and M represents the video digital signal.
[0042] In a possible implementation manner of the first aspect, identifying the video object of the target interrogation video includes:
[0043] identifying a video subject of the target interrogation video;
[0044] Marking a subject outline of the video subject;
[0045] Calculating a subject anthropomorphism value of the subject outline;
[0046] When the subject anthropomorphism value is greater than a preset standard anthropomorphism value;
[0047] The video subject corresponding to the subject anthropomorphism value is used as the video pair of the target interrogation video.
[0048] In a possible implementation manner of the first aspect, calculating the subject anthropomorphism value of the subject outline includes:
[0049] analyzing contour features of the subject contour;
[0050] According to the outline features, the subject anthropomorphism value of the subject outline is calculated using the following formula:
[0051]
[0052] Among them, J nr represents the subject anthropomorphic value, J m represents the mth subject contour, F m represents the mth contour feature, q represents the contour area of the subject contour, ρ represents the human body shape map, and UTT represents the similarity function.
[0053] In a possible implementation of the first aspect, performing picture control processing in the target interrogation video based on the first user abnormal behavior and the second user abnormal behavior to obtain a picture control processing result includes:
[0054] Calculate a first behavior abnormality value and a second behavior abnormality value of the first user abnormal behavior and the second user abnormal behavior respectively;
[0055] When the first behavior abnormal value is greater than a preset first abnormal threshold, analyzing a first abnormal feature of the first user's abnormal behavior;
[0056] When the second behavior abnormality value is greater than a preset second abnormality threshold, analyzing a second abnormal feature of the second user's abnormal behavior;
[0057] constructing a video control rule for the target interrogation video according to the first abnormal feature and the second abnormal feature;
[0058] According to the video control rule, the picture control processing in the target interrogation video is executed to obtain the picture control processing result.
[0059] In a second aspect, the present invention provides a remote interrogation screen control and analysis system based on blockchain, the system comprising:
[0060] An interrogation video proofreading module is used to obtain a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video;
[0061] A video signal signature module is used to perform background encoding on the proofreading interrogation video to obtain a video digital signal, and perform digital signature encryption on the video digital signal to obtain a signature encrypted signal;
[0062] A video signal decryption module is used to construct a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; the signature encrypted signal is uploaded to the access center by using the transmission link of the blockchain network, and the signature encrypted signal is decrypted in the access center to obtain a decrypted digital signal, and the decrypted digital signal is transcoded to obtain a target interrogation video;
[0063] An interrogation video grading module is used to identify the video object of the target interrogation video, wherein the video object includes: an interrogation object and an interrogated object, and to grade the target interrogation video according to the interrogation object and the interrogated object to obtain a graded interrogation video;
[0064] A user anomaly analysis module is used to capture user features of the interrogation subject and the interrogated subject respectively according to the graded interrogation video, obtain a first user feature and a second user feature, and input the first user feature and the second user feature into a user anomaly recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogation subject and the interrogated subject, and obtain a first user abnormal behavior and a second user abnormal behavior;
[0065] The remote image control module is used to perform image control processing in the target interrogation video based on the abnormal behavior of the first user and the abnormal behavior of the second user to obtain an image control processing result.
[0066] Compared with the prior art, the technical principle and beneficial effects of this solution are:
[0067] The embodiment of the present invention performs noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, which can improve the video quality and clarity and enhance the viewing experience; further, the embodiment of the present invention performs synchronous proofreading of the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video, which can improve the sensitive detail scenes in the noise-reduced interrogation video and improve the video quality of the noise-reduced interrogation video; further, the embodiment of the present invention performs background encoding on the proofreading interrogation video to obtain a video digital signal, which can convert the proofreading interrogation video into a digital signal that can be transmitted, thereby improving the transmission efficiency of the video; the embodiment of the present invention constructs a blockchain network corresponding to the interrogation room and the preset access center of the remote interrogation video, which can perform data transmission and data processing through the blockchain network, thereby improving the data processing efficiency; again , further, the embodiment of the present invention can obtain the decrypted digital signal by decrypting the signature encrypted signal in the access center, which can prevent the digital signal from being leaked before being cracked, thereby improving the security of the video digital signal; finally, the embodiment of the present invention can obtain the first user feature and the second user feature by capturing the user features of the interrogation object and the interrogated object respectively according to the graded interrogation video, and can analyze the abnormalities of the interrogation object and the interrogated object through the user features, thereby providing a data basis for the later video control; the embodiment of the present invention can perform the picture control processing in the target interrogation video based on the abnormal behavior of the first user and the abnormal behavior of the second user, and obtain the picture control processing result. The control rules of the target interrogation video can be formulated through abnormal behavior analysis, thereby improving the control effect of the remote interrogation video picture. Therefore, a remote interrogation picture control analysis method and system based on blockchain proposed in the embodiment of the present invention can improve the effect of remote interrogation video picture control. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0069] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0070] Figure 1 A flowchart of a remote interrogation screen control and analysis method and system based on blockchain provided by one embodiment of the present invention;
[0071] Figure 2 A schematic diagram of a module of a blockchain-based remote interrogation screen control and analysis system provided by one embodiment of the present invention;
[0072] Figure 3 A schematic diagram of the internal structure of an electronic device that implements a blockchain-based remote interrogation screen control and analysis method and system provided in one embodiment of the present invention. DETAILED DESCRIPTION
[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0074] The embodiment of the present invention provides a remote interrogation screen control analysis method and system based on blockchain, and the execution subject of the remote interrogation screen control analysis method and system based on blockchain includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the remote interrogation screen control analysis method and system based on blockchain can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.
[0075] See also Figure 1 The figure is a flowchart of a remote interrogation screen control and analysis method and system based on blockchain provided by an embodiment of the present invention. Figure 1The blockchain-based remote interrogation screen control analysis method described in the paper includes:
[0076] S1. Obtain a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video.
[0077] In the embodiment of the present invention, the remote interrogation video refers to the interrogation room video collected by devices such as a camera and a recorder.
[0078] In the embodiment of the present invention, by performing noise reduction processing on the remote interrogation video, the noise-reduced interrogation video can be obtained, which can improve the video quality and clarity and enhance the viewing experience. The noise-reduced interrogation video refers to the video obtained after the noise reduction processing on the remote interrogation video.
[0079] As an embodiment of the present invention, the denoising process of the remote interrogation video to obtain the denoised interrogation video includes: capturing a frame of the remote interrogation video; marking a local neighbourhood of the frame; calculating neighbourhood pixel values of the local neighbourhood; arranging the neighbourhood pixel values in order of size to obtain sequential neighbourhood pixel values; taking the central pixel value of the sequential neighbourhood pixel values as a filter coefficient; filtering the local neighbourhood according to the filter coefficient to obtain a local filtered image; fusing the local filtered images to obtain a denoised frame; and generating a denoised interrogation video of the remote interrogation video according to the denoised frame.
[0080] Among them, the frame picture refers to each frame picture of the remote interrogation video; the local neighborhood refers to a set of pixels within a certain range around a certain pixel point of the frame picture as the center, the neighborhood pixel value refers to the pixel value of each pixel point in the local neighborhood, the sequential neighborhood pixel value refers to the pixel set after the neighborhood pixel values are arranged in order of size, the center pixel value refers to the center point of the sequential neighborhood pixel values, the local filtered image refers to the neighborhood set that filters the local neighborhood, and the denoised frame picture refers to a complete frame picture denoised image obtained by integrating local filtered images.
[0081] Further, in an optional implementation of the present invention, filtering the local neighborhood according to the filter coefficient to obtain a local filtered image includes: calculating the neighborhood filtered pixel value of the local neighborhood according to the filter coefficient using the following formula:
[0082] A(a,b)=median{1 / N*f(a+c,b+d)&|c=-e,b=-d}
[0083] Where A(a,b) represents the neighborhood filter pixel value, median represents the filter function, N represents the size of the local neighborhood, c represents the radius of the local neighborhood on the x-axis, d represents the radius of the local neighborhood on the y-axis, & represents the filter coefficient, f(a+c,b+d) represents the pixel value of the local neighborhood corresponding to the pixel point after the x-axis translation is c pixels and the y-axis translation is d pixels, a represents the horizontal coordinate of the local neighborhood corresponding to the pixel point, and b represents the vertical coordinate of the local neighborhood corresponding to the pixel point;
[0084] A local filtered image of the local neighborhood is constructed according to the neighborhood filtered pixel values.
[0085] Furthermore, the embodiment of the present invention can improve the sensitive detail scenes in the noise-reduced interrogation video and improve the video quality of the noise-reduced interrogation video by synchronously proofreading the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video. The proofread interrogation video refers to the video after the sound and picture in the noise-reduced interrogation video are proofread.
[0086] As an embodiment of the present invention, the synchronous proofreading of the video sound and the video picture in the noise reduction interrogation video to obtain the proofread interrogation video includes: capturing the voice of the character in the video sound and the lip shape of the character in the video picture; calculating the audio synchronization of the character sound and the lip shape of the character; when the audio synchronization is lower than a preset audio synchronization limit; recording the abnormal description of the character sound and the lip shape of the character; according to the abnormal description, analyzing the audio synchronization method of the video sound and the video picture; according to the audio synchronization method, synchronous proofreading the video sound and the video picture in the noise reduction interrogation video to obtain the proofread interrogation video.
[0087] Among them, the character's voice and the character's lip shape refer to the audio sound and lip shape of the character in the noise reduction interrogation video, the audio synchronization refers to the consistency between the character's voice and the character's lip shape, the abnormal description refers to the characteristics of the inconsistency between the character's voice and the character's lip shape, such as stuttering, delay and other characteristics, and the audio synchronization method refers to the method of achieving consistency between the character's voice and the character's lip shape.
[0088] Furthermore, in an optional implementation of the present invention, the video sound and video picture in the noise reduction interrogation video are synchronously proofread to obtain the proofread interrogation video by fine-tuning the timeline of the video, cropping the picture, adding or deleting frames, etc.
[0089] S2. Background encoding is performed on the proofreading interrogation video to obtain a video digital signal, and the video digital signal is digitally signed and encrypted to obtain a signature encrypted signal.
[0090] The embodiment of the present invention can convert the proofreading interrogation video into a digital signal that can be transmitted by background encoding the proofreading interrogation video, thereby improving the transmission efficiency of the video. The video digital signal refers to the video digital signal obtained by encoding the proofreading interrogation video.
[0091] As an embodiment of the present invention, the proofreading and interrogation video is background-encoded to obtain a video digital signal which can be encoded by a video encoder by setting corresponding encoder parameters according to the parameters of the proofreading and interrogation video.
[0092] Furthermore, the embodiment of the present invention can improve the security of the video digital signal during transmission by digitally signing and encrypting the video digital signal to obtain a signature encrypted signal, wherein the signature encrypted signal refers to the video digital signal after the video digital signal is signed, encrypted, or other technical means are used.
[0093] As an embodiment of the present invention, the video digital signal is digitally signed and encrypted to obtain a signature encrypted signal, including: configuring a signature condition for encrypting the video digital signal; generating a signature key for the video digital signal according to the signature condition, signing the video digital signal according to the signature key and the signature condition to obtain a signature value of the video digital signal; when the signature value is successfully verified, generating the digital encrypted signal.
[0094] Among them, the signature condition refers to the prerequisite for realizing the signature of the video digital signal, the signature key refers to the video digital signal signature key generated by Euler function calculation, wherein the signature key includes: a signature private key and a signature public key, and the signature value refers to the signature value obtained after signing the video digital signal.
[0095] Furthermore, in an optional implementation of the present invention, signing the video digital signal according to the signature key and the signature condition to obtain the signature value of the video digital signal includes:
[0096] (f,g)=(((h^(modj))mod k),(((i^-1*(H(M)+xf))mod k)))
[0097] Among them, (f,g) represents the signature value, f represents the temporary key of the video digital signal, g represents the signature result generated after the video digital signal is signed, h represents the corresponding random number in the signature condition, mod represents the modulus operation, j and k represent the corresponding prime numbers in the signature condition, i and x represent the corresponding random integers in the signature condition, H(M) represents the hash value of the video digital signal, and M represents the video digital signal.
[0098] S3. Construct a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; upload the signature encrypted signal to the access center using the transmission link of the blockchain network, decrypt the signature encrypted signal in the access center to obtain a decrypted digital signal, perform video transcoding on the decrypted digital signal, and obtain the target interrogation video.
[0099] The embodiment of the present invention can improve the data processing efficiency by constructing a blockchain network corresponding to the interrogation room and the preset access center of the remote interrogation video. The blockchain network refers to the Blockchain-based Service Network (BSN), which aims to provide a public infrastructure network that can develop, deploy, operate, interoperate and supervise alliance chain applications at low cost.
[0100] As an embodiment of the present invention, the blockchain network for constructing the remote interrogation video corresponding to the interrogation room and the preset access center constructs a p2p blockchain network through a consensus algorithm.
[0101] Furthermore, the embodiment of the present invention utilizes the transmission link of the blockchain network to upload the signature encryption signal to the access center, and can realize encrypted transmission of the signature encryption signal through the transmission link, thereby improving data security.
[0102] As an embodiment of the present invention, uploading the signed encrypted signal to the access center using the transmission link of the blockchain network can be achieved through a point-to-point protocol in the blockchain network.
[0103] Furthermore, in the embodiment of the present invention, the decrypted digital signal can be obtained by decrypting the signature encrypted signal in the access center to obtain a decrypted digital signal, thereby preventing the digital signal from being leaked before being cracked, thereby improving the security of the video digital signal. The decrypted digital signal refers to the digital signal after the signature encrypted signal is decrypted.
[0104] As an embodiment of the present invention, the signature encrypted signal is decrypted in the access center to obtain a decrypted digital signal, which can be decrypted by a public key of a signature key corresponding to the signature encrypted signal.
[0105] Furthermore, the embodiment of the present invention can restore the decrypted digital signal to a video by performing video transcoding on the decrypted digital signal to obtain a target interrogation video, wherein the target interrogation video refers to an interrogation video obtained by performing a transcoding operation on the decrypted digital signal of the remote interrogation video.
[0106] As an embodiment of the present invention, the decrypted digital signal is subjected to video transcoding to obtain the target interrogation video, which can be decoded by setting corresponding decoder parameters according to the parameters of the decrypted digital signal through a signal decoder.
[0107] S4. Identify the video object of the target interrogation video, wherein the video object includes an interrogation object and an interrogated object. According to the interrogation object and the interrogated object, the target interrogation video is graded to obtain a graded interrogation video.
[0108] The embodiment of the present invention identifies the video object of the target interrogation video, and the video object can extract the video body of the target interrogation video, thereby quickly extracting the main content of the video and improving the efficiency of obtaining video information. The interrogation object refers to the object being interrogated in the target interrogation video, and the interrogated object refers to the object being interrogated by the person being interrogated in the target interrogation video.
[0109] As an embodiment of the present invention, the identifying of the video object of the target interrogation video includes: identifying the video subject of the target interrogation video; marking the subject outline of the video subject; calculating the subject anthropomorphism value of the subject outline; when the subject anthropomorphism value is greater than a preset standard anthropomorphism value; taking the video subject corresponding to the subject anthropomorphism value as the video object of the target interrogation video.
[0110] Among them, the video subject refers to the entity content of the target interrogation video, such as entities such as people, computers, chairs, etc., the subject outline refers to the appearance shape of the video subject, and the subject anthropomorphism value refers to the degree of similarity of the subject outline to a human figure.
[0111] Further, in an optional implementation of the present invention, the calculating the subject anthropomorphic value of the subject outline includes: analyzing the outline features of the subject outline; and calculating the subject anthropomorphic value of the subject outline using the following formula according to the outline features:
[0112]
[0113] Among them, J nr represents the subject anthropomorphic value, J m represents the mth subject contour, F m represents the mth contour feature, q represents the contour area of the subject contour, ρ represents the human body shape map, and UTT represents the similarity function.
[0114] Furthermore, the embodiment of the present invention can multi-level the video by grading the target interrogation video according to the interrogation object and the interrogated object, so that each subject is presented in more detail, thereby improving the control effect of the remote interrogation video. The graded interrogation video refers to a plurality of videos obtained by dividing the target interrogation video according to the video object.
[0115] As an embodiment of the present invention, the target interrogation video is graded according to the interrogation object and the interrogated object, and the graded interrogation video can be obtained by dividing the target interrogation video into multiple levels with the interrogation object and the interrogated object as the video center respectively.
[0116] S5. According to the graded interrogation video, the user features of the interrogating object and the interrogated object are captured respectively to obtain a first user feature and a second user feature, and the first user feature and the second user feature are respectively input into a user abnormality recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogating object and the interrogated object to obtain a first user abnormal behavior and a second user abnormal behavior.
[0117] The embodiment of the present invention captures the user features of the interrogating object and the interrogated object respectively according to the graded interrogation video, and obtains the first user feature and the second user feature. The user features can be used to analyze the abnormalities of the interrogating object and the interrogated object, and provide a data basis for later video control. The first user feature and the second user feature refer to the features of the interrogating object and the interrogated object in the interrogation video, such as sound features, action features, etc.
[0118] As an embodiment of the present invention, the user features of the interrogating subject and the interrogated subject are captured respectively based on the graded interrogation video, and the first user feature and the second user feature can be captured by a feature function.
[0119] Furthermore, the embodiment of the present invention respectively inputs the first user feature and the second user feature into the user abnormality identification model pre-trained in the blockchain network to respectively identify the abnormal user behaviors of the interrogation object and the interrogated object, and obtains the first user abnormal behavior and the second user abnormal behavior. The first user feature and the second user feature can be used as input values to calculate the user abnormality through the trained model, and the user abnormal behavior provides a data basis for the subsequent screen control analysis, thereby improving the necessity and accuracy of screen control. Among them, the first user abnormal behavior and the second user abnormal behavior refer to the abnormal behaviors of the interrogation object and the interrogated object that exceed the normal state in the interrogation video.
[0120] As an embodiment of the present invention, the first user feature and the second user feature are respectively input into a user anomaly recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogation object and the interrogated object, and obtain first abnormal user behaviors and second abnormal user behaviors. The user anomaly recognition model can be trained through a large amount of user feature data to improve the accuracy of the user anomaly recognition model. When the accuracy is greater than a preset standard, the user anomaly recognition model executes the identification of abnormal user behaviors of the interrogation object and the interrogated object.
[0121] S6. Based on the abnormal behavior of the first user and the abnormal behavior of the second user, perform picture control processing in the target interrogation video to obtain a picture control processing result.
[0122] In the embodiment of the present invention, based on the abnormal behavior of the first user and the abnormal behavior of the second user, the screen control processing in the target interrogation video is performed, and the screen control processing result is obtained. The control rules of the target interrogation video can be formulated through abnormal behavior analysis to improve the control effect of the remote interrogation video screen. The screen control processing result refers to the screen control result obtained after the screen control processing is performed on the target interrogation video.
[0123] As an embodiment of the present invention, based on the first user's abnormal behavior and the second user's abnormal behavior, the screen control processing in the target interrogation video is performed to obtain the screen control processing result, including: respectively calculating the first behavior abnormal value and the second behavior abnormal value of the first user's abnormal behavior and the second user's abnormal behavior; when the first behavior abnormal value is greater than a preset first abnormal threshold, analyzing the first abnormal feature of the first user's abnormal behavior; when the second behavior abnormal value is greater than a preset second abnormal threshold, analyzing the second abnormal feature of the second user's abnormal behavior; according to the first abnormal feature and the second abnormal feature, constructing the video control rule of the target interrogation video; according to the video control rule, performing the screen control processing in the target interrogation video to obtain the screen control processing result.
[0124] Among them, the first behavior abnormality value and the second behavior abnormality value refer to the abnormal degree of abnormal behavior of the interrogation object and the interrogated object, the first abnormal feature refers to the behavioral feature of the abnormal behavior of the first user, and the second abnormal feature refers to the behavioral feature of the abnormal behavior of the second user. The video control rule refers to the rule for executing control on the target interrogation video, such as rules for enlarging the interrogation object and amplifying the voice of the interrogated person.
[0125] It can be seen that the embodiment of the present invention performs noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, which can improve the video quality and clarity and enhance the viewing experience; further, the embodiment of the present invention performs synchronous proofreading of the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video, which can improve the sensitive detail scenes in the noise-reduced interrogation video and improve the video quality of the noise-reduced interrogation video; further, the embodiment of the present invention performs background encoding on the proofreading interrogation video to obtain a video digital signal, which can convert the proofreading interrogation video into a digital signal that can be transmitted, thereby improving the transmission efficiency of the video; the embodiment of the present invention constructs a blockchain network corresponding to the interrogation room and the preset access center of the remote interrogation video, which can perform data transmission and data processing through the blockchain network, thereby improving the data processing efficiency ; Again, further, the embodiment of the present invention can obtain the decrypted digital signal by decrypting the signature encrypted signal in the access center, which can prevent the digital signal from being leaked before being cracked, thereby improving the security of the video digital signal; Finally, the embodiment of the present invention can obtain the first user feature and the second user feature by capturing the user features of the interrogation object and the interrogated object respectively according to the graded interrogation video, and can analyze the abnormalities of the interrogation object and the interrogated object through the user features, so as to provide a data basis for the later video control; The embodiment of the present invention performs the picture control processing in the target interrogation video based on the abnormal behavior of the first user and the abnormal behavior of the second user, and obtains the picture control processing result. The control rules of the target interrogation video can be formulated through abnormal behavior analysis, thereby improving the control effect of the remote interrogation video picture. Therefore, a remote interrogation picture control analysis method based on blockchain proposed in the embodiment of the present invention can improve the effect of remote interrogation video picture control.
[0126] like Figure 2 The figure shows a functional module diagram of the remote interrogation screen control and analysis system based on blockchain of the present invention.
[0127] The blockchain-based remote interrogation screen control and analysis system 200 of the present invention can be installed in an electronic device. According to the functions implemented, the blockchain-based remote interrogation screen control and analysis system can include an interrogation video proofreading module 201, a video signal signature module 202, a video signal decryption module 203, an interrogation video grading module 204, a user abnormality analysis module 205 and a remote screen control module 206. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0128] In the embodiment of the present invention, the functions of each module / unit are as follows:
[0129] The interrogation video proofreading module 201 is used to obtain a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video;
[0130] The video signal signature module 202 is used to perform background encoding on the proofreading interrogation video to obtain a video digital signal, and perform digital signature encryption on the video digital signal to obtain a signature encrypted signal;
[0131] The video signal decryption module 203 is used to construct a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; the signature encrypted signal is uploaded to the access center by using the transmission link of the blockchain network, and the signature encrypted signal is decrypted in the access center to obtain a decrypted digital signal, and the decrypted digital signal is transcoded to obtain the target interrogation video;
[0132] The interrogation video grading module 204 is used to identify the video object of the target interrogation video, wherein the video object includes: the interrogation object and the interrogated object, and to grade the target interrogation video according to the interrogation object and the interrogated object to obtain a graded interrogation video;
[0133] The user anomaly analysis module 205 is used to capture the user features of the interrogation subject and the interrogated subject respectively according to the graded interrogation video, obtain a first user feature and a second user feature, and input the first user feature and the second user feature into a user anomaly recognition model pre-trained in the blockchain network, so as to respectively identify the user abnormal behaviors of the interrogation subject and the interrogated subject, and obtain a first user abnormal behavior and a second user abnormal behavior;
[0134] The remote image control module 206 is used to perform image control processing in the target interrogation video based on the abnormal behavior of the first user and the abnormal behavior of the second user to obtain an image control processing result.
[0135] In detail, each module in the blockchain-based remote interrogation screen control and analysis system 200 in the embodiment of the present invention is used in the same manner as described above. Figure 1 The blockchain-based remote interrogation screen control and analysis method has the same technical means and can produce the same technical effects, so it will not be repeated here.
[0136] like Figure 3 The figure is a schematic diagram of the structure of an electronic device for realizing a remote interrogation screen control and analysis method based on blockchain according to the present invention.
[0137] The electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a blockchain-based remote interrogation screen control and analysis system and program.
[0138] In some embodiments, the processor 30 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 30 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, and executes or executes the programs or modules stored in the memory 31 (for example, executing the remote interrogation screen control and analysis system and program based on blockchain, etc.), and calls the data stored in the memory 31 to execute various functions of the electronic device and process data.
[0139] The memory 31 includes at least one type of readable storage medium, which includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc.
[0140] The communication bus 32 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus.
[0141] The communication interface 33 is used for communication between the electronic device 3 and other devices, and includes a network interface and a user interface.
[0142] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0143] For example, although not shown, the electronic device may also include a power source (such as a battery) for powering various components, various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be described in detail here.
[0144] It should be understood that the embodiment is for illustrative purposes only and the scope of the patent invention is not limited to this structure.
[0145] The database configuration connection program stored in the memory 31 in the electronic device is a combination of multiple computer programs. When running in the processor 30, the above-mentioned blockchain-based remote interrogation screen control and analysis method can be implemented.
[0146] Specifically, the specific implementation method of the processor 30 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.
[0147] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium.
[0148] The present invention also provides a storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement the above-mentioned blockchain-based remote interrogation screen control and analysis method.
[0149] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0150] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A remote interrogation screen control and analysis method based on blockchain, characterized in that: The method comprises: Acquire a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain a noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video; Performing background encoding on the proofreading interrogation video to obtain a video digital signal, and performing digital signature encryption on the video digital signal to obtain a signature encrypted signal; Constructing a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; uploading the signature encrypted signal to the access center using the transmission link of the blockchain network, decrypting the signature encrypted signal in the access center to obtain a decrypted digital signal, and performing video transcoding on the decrypted digital signal to obtain a target interrogation video; Identifying the video object of the target interrogation video, the video object includes: an interrogation object and an interrogated object, and grading the target interrogation video according to the interrogation object and the interrogated object to obtain a graded interrogation video; According to the graded interrogation video, user features of the interrogating subject and the interrogated subject are captured respectively to obtain a first user feature and a second user feature, and the first user feature and the second user feature are respectively input into a user abnormality recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogating subject and the interrogated subject to obtain a first user abnormal behavior and a second user abnormal behavior; Based on the abnormal behavior of the first user and the abnormal behavior of the second user, performing image control processing in the target interrogation video to obtain an image control processing result; The step of identifying the video object of the target interrogation video comprises: identifying a video subject of the target interrogation video; Marking a subject outline of the video subject; Calculating a subject anthropomorphism value of the subject outline; When the subject anthropomorphism value is greater than a preset standard anthropomorphism value; Using the video subject corresponding to the subject anthropomorphism value as the video pair of the target interrogation video; The performing of the picture control processing in the target interrogation video based on the first user abnormal behavior and the second user abnormal behavior to obtain the picture control processing result includes: Calculate a first behavior abnormality value and a second behavior abnormality value of the first user abnormal behavior and the second user abnormal behavior respectively; When the first behavior abnormal value is greater than a preset first abnormal threshold, analyzing a first abnormal feature of the first user's abnormal behavior; When the second behavior abnormality value is greater than a preset second abnormality threshold, analyzing a second abnormal feature of the second user's abnormal behavior; constructing a video control rule for the target interrogation video according to the first abnormal feature and the second abnormal feature; According to the video control rule, the picture control processing in the target interrogation video is executed to obtain the picture control processing result.
2. The method according to claim 1, characterized in that The performing noise reduction processing on the remote interrogation video to obtain the noise-reduced interrogation video includes: capturing frames of the remote interrogation video; Marking a local neighborhood of the frame; Calculating neighborhood pixel values of the local neighborhood; Arrange the neighborhood pixel values in order of magnitude to obtain sequential neighborhood pixel values; Taking the central pixel value of the sequential neighborhood pixel values as the filter coefficient; According to the filtering coefficient, filtering is performed on the local neighborhood to obtain a local filtered image; Fusing the local filtered images to obtain a noise reduction frame; A noise-reduced interrogation video of the remote interrogation video is generated according to the noise-reduced frame image.
3. The method according to claim 1, characterized in that The step of synchronously proofreading the video sound and the video picture in the noise reduction interrogation video to obtain the proofread interrogation video includes: Capturing the voice of the person in the video sound and the lip shape of the person in the video picture; Calculating the audio synchronization between the character's voice and the character's lip shape; When the audio synchronization is lower than the preset audio synchronization limit; Recording abnormal descriptions of the character's voice and the character's lip shape; Analyzing the audio synchronization mode of the video sound and the video picture according to the abnormal description; According to the audio synchronization method, the video sound and the video picture in the noise reduction interrogation video are synchronously proofread to obtain the proofread interrogation video.
4. The method according to claim 1, characterized in that The step of digitally signing and encrypting the video digital signal to obtain a signature encrypted signal comprises: Configuring a signature condition for encrypting the video digital signal; Generate a signature key for the video digital signal according to the signature condition; Signing the video digital signal according to the signature key and the signature condition to obtain a signature value of the video digital signal; When the signature value is successfully verified, a digital encryption signal is generated.
5. A remote interrogation screen control and analysis system based on blockchain, characterized in that: The system comprises: An interrogation video proofreading module is used to obtain a remote interrogation video, perform noise reduction processing on the remote interrogation video to obtain a noise-reduced interrogation video, and synchronously proofread the video sound and video picture in the noise-reduced interrogation video to obtain a proofread interrogation video; A video signal signature module is used to perform background encoding on the proofreading interrogation video to obtain a video digital signal, and perform digital signature encryption on the video digital signal to obtain a signature encrypted signal; A video signal decryption module is used to construct a blockchain network of the interrogation room and the preset access center corresponding to the remote interrogation video; the signature encrypted signal is uploaded to the access center by using the transmission link of the blockchain network, and the signature encrypted signal is decrypted in the access center to obtain a decrypted digital signal, and the decrypted digital signal is transcoded to obtain a target interrogation video; An interrogation video grading module is used to identify the video object of the target interrogation video, wherein the video object includes: an interrogation object and an interrogated object, and to grade the target interrogation video according to the interrogation object and the interrogated object to obtain a graded interrogation video; A user anomaly analysis module is used to capture user features of the interrogation subject and the interrogated subject respectively according to the graded interrogation video, obtain a first user feature and a second user feature, and input the first user feature and the second user feature into a user anomaly recognition model pre-trained in the blockchain network to respectively identify abnormal user behaviors of the interrogation subject and the interrogated subject, and obtain a first user abnormal behavior and a second user abnormal behavior; A remote image control module, configured to perform image control processing in the target interrogation video based on the abnormal behavior of the first user and the abnormal behavior of the second user, and obtain an image control processing result; The step of identifying the video object of the target interrogation video comprises: identifying a video subject of the target interrogation video; Marking a subject outline of the video subject; Calculating a subject anthropomorphism value of the subject outline; When the subject anthropomorphism value is greater than a preset standard anthropomorphism value; Using the video subject corresponding to the subject anthropomorphism value as the video pair of the target interrogation video; The performing of the picture control processing in the target interrogation video based on the first user abnormal behavior and the second user abnormal behavior to obtain the picture control processing result includes: Calculate a first behavior abnormality value and a second behavior abnormality value of the first user abnormal behavior and the second user abnormal behavior respectively; When the first behavior abnormal value is greater than a preset first abnormal threshold, analyzing a first abnormal feature of the first user's abnormal behavior; When the second behavior abnormality value is greater than a preset second abnormality threshold, analyzing a second abnormal feature of the second user's abnormal behavior; constructing a video control rule for the target interrogation video according to the first abnormal feature and the second abnormal feature; According to the video control rule, the picture control processing in the target interrogation video is executed to obtain the picture control processing result.
