Intelligent television detects surrounding camera method, apparatus, device and storage medium

Abstract

The application discloses a smart television detection surrounding camera method and device, equipment and storage medium, relates to the technical field of intelligent detection, and includes: receiving a detection instruction, and calling a signal scanning component in the smart television according to the detection instruction; signal data of the surrounding environment of the smart television is collected through the signal scanning component, and the detection data of the surrounding environment is obtained; the detection data is analyzed and evaluated, and the camera detection result of the surrounding environment is determined. The application integrates the signal scanning component in the smart television, so that the data of the surrounding environment of the smart television is collected and analyzed and evaluated, the camera detection result of the surrounding environment is obtained, and the effect that the hidden camera is accurately detected through the smart television configured in the room is realized.

Description

Technical Field

[0001] This application relates to the field of intelligent detection technology, and in particular to a method, apparatus, device and storage medium for detecting peripheral cameras on a smart TV. Background Technology

[0002] Miniature cameras, a product of modern technology, are renowned for their compact size and powerful functionality. Designed to be concealed, these cameras are widely used in aviation, commerce, media, businesses, and homes. However, the widespread adoption of this technology has also brought some negative impacts, such as the risk of leaking corporate secrets and personal privacy. Pinhole cameras, a special type of miniature camera, are named for their use of fisheye lenses, flat lenses, or conical lenses; their concealment is even greater, making them easier to use for illegal surveillance. Some pinhole cameras can be concealed in everyday items such as routers, electronic clocks, and smoke detectors. Criminals modify these devices to cleverly hide the cameras, making them difficult for non-professionals to detect. Hotels and guesthouses have become hotspots for these hidden cameras, causing extreme unease among guests and seriously threatening their personal privacy.

[0003] Currently, most methods for detecting hidden cameras involve scanning rooms using handheld mobile devices. However, the accuracy of the detection results is directly related to the professionalism of the mobile device. Users are unlikely to purchase and carry expensive professional detection equipment just to detect rooms, making it difficult to simultaneously meet users' privacy protection needs and operational cost requirements.

[0004] Therefore, how to achieve accurate detection of hidden cameras at low cost is a problem that urgently needs to be solved. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for detecting surrounding cameras on a smart TV, aiming to solve the technical problem of how to achieve accurate detection of hidden cameras at low cost.

[0006] To achieve the above objectives, this application proposes a method for detecting surrounding cameras on a smart TV, the method comprising:

[0007] Receive detection instructions and invoke the signal scanning component in the smart TV according to the detection instructions;

[0008] The signal scanning component collects signal data from the surrounding environment of the smart TV to obtain the detection data of the surrounding environment.

[0009] The detection data is analyzed and evaluated to determine the camera detection results in the surrounding environment.

[0010] In addition, to achieve the above object, the present application also provides a smart television peripheral camera detection device, which comprises:

[0011] An initiating module, configured to receive a detection instruction and call a signal scanning component in the smart television according to the detection instruction;

[0012] A collecting module, configured to collect signal data of a peripheral environment of the smart television by the signal scanning component to obtain to-be-detected data of the peripheral environment;

[0013] A detecting module, configured to analyze and evaluate the to-be-detected data to determine a camera detection result of the peripheral environment.

[0014] In addition, to achieve the above object, the present application also provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the smart television peripheral camera detection method.

[0015] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the smart television peripheral camera detection method. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0018] Figure 1 A flowchart for the smart television peripheral camera detection method embodiment one of the present application is provided;

[0019] Figure 2 A flowchart for the smart television peripheral camera detection method embodiment two of the present application is provided;

[0020] Figure 3 A flowchart for the smart television peripheral camera detection method embodiment three of the present application is provided;

[0021] Figure 4A brief flowchart of the method for detecting a peripheral camera of an intelligent television is provided in Embodiment Three of the present application.

[0022] Figure 5 A module structure diagram of the method for detecting a peripheral camera of an intelligent television is provided in Embodiment Three of the present application.

[0023] Figure 6 A device structure diagram of the hardware running environment involved in the method for detecting a peripheral camera of an intelligent television is provided in Embodiment Three of the present application.

[0024] The object, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0026] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0027] The main solution of the embodiments of the present application is: receiving a detection instruction, and calling a signal scanning component in the intelligent television according to the detection instruction; collecting signal data of the peripheral environment of the intelligent television through the signal scanning component to obtain to-be-detected data of the peripheral environment; analyzing and evaluating the to-be-detected data to determine the camera detection result of the peripheral environment.

[0028] At present, most of the detection methods for hidden cameras are to use a handheld mobile terminal device to scan and detect a room, and the accuracy of the detection result is directly related to the professionalism of the mobile terminal device. Users often do not purchase and carry professional detection devices with high cost because of the detection needs of the room, so that the user's privacy protection needs and the use cost needs are difficult to be met at the same time. Therefore, how to accurately detect hidden cameras at low cost is a problem that needs to be solved at present.

[0029] The present application provides a solution by integrating a signal scanning component in an intelligent television to collect and analyze data of the peripheral environment of the intelligent television to obtain the camera detection result of the peripheral environment, thereby realizing accurate detection of hidden cameras through the intelligent television configured in the room.

[0030] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, an intelligent television, etc. capable of realizing the above functions. The present embodiment and the following embodiments will be described taking an intelligent television as an example.

[0031] Based on this, embodiments of this application provide a method for a smart TV to detect surrounding cameras, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the method for detecting peripheral cameras in a smart TV according to this application.

[0032] In this embodiment, the method for detecting surrounding cameras by a smart TV includes steps S10 to S30:

[0033] Step S10: Receive a detection command and invoke the signal scanning component in the smart TV according to the detection command;

[0034] It should be noted that the detection command is a command triggered by the user or the system to start camera detection, such as a command sent through a smart TV remote control, voice assistant, or mobile application; the signal scanning component can be one or more of the following signal scanning components: infrared camera, wireless signal scanning component, etc.

[0035] Understandably, since current methods for detecting hidden cameras often rely on professional detection equipment, it is difficult to simultaneously meet the needs of user privacy protection and the cost of use. Therefore, step S10 is performed by integrating a signal scanning component into a smart TV, which avoids the need for users to use additional professional equipment to detect hidden cameras, and achieves the effect of detecting hidden cameras through the smart TV already configured in the room.

[0036] Furthermore, it is understandable that if the user does not have a need to detect surrounding cameras, activating the signal scanning component integrated in the smart TV would not only cause meaningless consumption of resources but also infringe on user privacy to some extent. Therefore, performing step S10 can prevent the signal scanning component integrated in the smart TV from being called at an inappropriate time, thereby allowing the existing hardware of the smart TV to directly respond to the detection request at the appropriate time. This reduces the threshold for user detection operations while achieving a low-cost and convenient detection method.

[0037] Exemplarily, the user triggers the "camera detection" function through the remote control of the smart TV or the matching mobile phone App or the voice assistant, generates a detection instruction and sends it to the smart TV system. After the system receives the instruction, it calls the pre-integrated infrared camera (such as a CMOS sensor supporting near-infrared wave bands) and wireless signal scanning components (such as a chip set supporting Wi-Fi, Bluetooth spectrum analysis) through the internal API interface, and starts the drivers of the two. The infrared camera enters the infrared light shooting mode, and the wireless signal scanning component starts full-band scanning (including 2.4GHz / 5GHz Wi-Fi, Bluetooth and RF signals, etc.), ensuring that the hardware devices are initialized and enter the state of waiting for collection. This step uses the existing hardware resources of the smart TV through the linkage of software instructions and hardware drivers, without the need for external devices, reducing the complexity of user operation.

[0038] In step S20, the signal scanning component collects signal data of the surrounding environment of the smart TV to obtain the to-be-detected data of the surrounding environment.

[0039] It should be noted that the to-be-detected data refers to the light wave band data collected by the infrared camera and the signal source data collected by the wireless signal scanning component, which are used to analyze and evaluate whether there is a hidden camera in the surrounding environment.

[0040] Exemplarily, since the micro camera lens usually has significant reflection characteristics for infrared light, the infrared camera captures the possible camera lens reflections in the environment by scanning the room at multiple angles (such as horizontal 0°-180° rotation shooting) through the built-in gimbal or wide-angle lens, and generates multiple frames of infrared light wave band image data (including brightness, reflection point coordinates, etc.). At the same time, the wireless signal scanning component can also scan the surrounding wireless signals in real time, record the MAC addresses, signal strengths (RSSI), protocol types (such as Wi-Fi Direct, Bluetooth Low Energy) and data packet characteristics (such as periodic broadcast data packets) of all active devices, and integrate these information into a signal source data table. The data collection process lasts for a preset collection time, ensuring that all potential hidden areas and wireless signal bands in the room are covered, and finally generating a to-be-detected data set containing light wave band images and wireless signal logs.

[0041] In step S30, the to-be-detected data is analyzed and evaluated to determine the camera detection result of the surrounding environment.

[0042] It should be noted that the camera detection result is a conclusion obtained after comprehensive analysis, which can include whether there is a camera, the position information of the existing camera, the device type, the signal strength and the confidence score, etc.

[0043] It can be understood that, since the traditional detection method relies on manual judgment or a single detection index, it is easy to cause misjudgment due to subjectivity or data one-sidedness, so step S30 is performed to realize data-driven automatic analysis by classifying and evaluating multi-source data, improve the objectivity and confidence of the detection result, so as to help users quickly locate threats and take protective measures.

[0044] Exemplarily, the detection software built-in in the smart TV processes and analyzes the received to-be-detected data. First, the software filters out known safe light sources and wireless signals, such as the infrared remote control signal of the TV itself and the authorized Wi-Fi device, using a preset algorithm. Then, the software deeply analyzes the remaining unknown light sources and wireless signals to evaluate whether they match the signal characteristics emitted by the known reference camera. If data consistent with the camera characteristics are detected, the software marks these data and generates a report, and finally determines whether there is a camera in the environment around the smart TV, and finally generates a structured detection report containing confidence, location and device type.

[0045] In a feasible implementation, the signal scanning component includes an infrared camera and a wireless signal scanning component, and the to-be-detected data includes light wave band data collected by the infrared camera and signal source data collected by the wireless signal scanning component;

[0046] Step S30 can include steps S31-S33:

[0047] Step S31, the light wave band data is transmitted to an infrared light recognition model, and the light wave band data is analyzed and evaluated by the infrared light recognition model to obtain a first evaluation result;

[0048] It should be noted that the light wave band data is an environmental infrared light image or video data collected by the infrared camera, which usually contains infrared reflection information of a specific wavelength (such as near-infrared: about 750nm to 1400nm (400THz to 214THz), mid-infrared: about 1400nm to 3000nm (214THz to 100THz), far-infrared: about 3000nm to 1mm (100THz to 300GHz)), which is used to capture the reflection characteristics of the miniature camera lens; the infrared light recognition model is a preset algorithm model based on machine learning or rule engine, which can select traditional machine learning models such as support vector machine and random forest, or use neural network, for analyzing infrared light wave band data and identifying camera lens reflection characteristics; the first evaluation result is the analysis output of the infrared light recognition model on the light wave band data, which usually includes whether there is a camera reflection characteristic, position coordinates and camera suspected degree (i.e. confidence score).

[0049] It can be understood that, in order to accurately identify the infrared light source, step S31 is performed, and the infrared identification is performed by introducing a large model, so that the normal infrared light source in the environment and the infrared light emitted by the camera cannot be distinguished, and the effect of accurately identifying the potential camera infrared signal is realized.

[0050] In a feasible implementation, the step of analyzing and evaluating the light wave band data by the infrared light identification model in step S31 to obtain a first evaluation result can include steps S311-S314.

[0051] In step S311, the light wave band data is feature extracted by the infrared light identification model to obtain the to-be-identified light wave band features.

[0052] It should be noted that the to-be-identified light wave band features refer to representative feature information extracted from the light wave band data. These features can reflect specific properties of the infrared light source, such as intensity, frequency, waveform, etc. These properties are key indicators for distinguishing different types of light sources.

[0053] It can be understood that, since it is necessary to extract information representing the camera features from complex light wave band data, step S311 is performed to avoid misjudgment caused by noise, interference or complex background when directly analyzing the original infrared image. By extracting key optical features, the accuracy and robustness of detection are improved.

[0054] Exemplarily, the infrared light identification model first receives the light wave band data collected from the infrared camera, and then the model processes the data through a series of algorithms such as principal component analysis or convolutional neural network, extracts key feature parameters such as peak wavelength, spectral intensity, and spectral shape. These feature parameters are labeled as to-be-identified light wave band features and stored in memory for subsequent classification analysis.

[0055] In step S312, the to-be-identified light wave band features are classified to obtain the light wave band categories corresponding to the to-be-identified light wave band features.

[0056] It should be noted that the light wave band category is the result of classification based on the to-be-identified light wave band features, and usually includes categories such as “camera lens reflection”, “non-camera lens reflection” (such as glass, metal), and “unknown reflection”. The classification process is completed by a pre-trained infrared light identification model, and outputs the category label and confidence score corresponding to each feature, as well as the camera suspicion degree.

[0057] It can be understood that, since the extracted features need to be compared with known light source categories to determine whether the light wave band emitted by the camera, step S312 is performed, which can avoid the problem of ambiguous or unclear detection results caused by the lack of classification logic after feature extraction, thereby generating clear classification results and providing clear suspicious area information for the user, facilitating further investigation and decision-making.

[0058] Exemplarily, the extracted light wave band features to be identified are input into a pre-trained classifier (i.e., an infrared light recognition model), and the model calculates the probabilities of the features belonging to different categories (such as "camera lens reflection", "non-camera reflection", and "unknown reflection") according to the feature vectors of the features. For example, the model detects that the reflection intensity distribution of a certain feature vector highly matches the camera lens and the shape is a regular circle, and then outputs the "camera lens reflection" category with a confidence of 95%.

[0059] In step S313, the light wave band categories are mapped to corresponding target light sources, and the first camera suspiciousness of the target light sources is obtained based on the infrared light recognition model.

[0060] It should be noted that the target light source refers to a light source that may represent a camera or other device identified by analyzing the light wave band data; and the first camera suspiciousness is a quantitative index indicating the determination degree or credibility of the recognition model for the identified target light source being a camera.

[0061] In step S314, the target light sources and the first camera suspiciousness are associated and combined, and the combination result is taken as the first evaluation result.

[0062] In this embodiment, by using the infrared light recognition model to extract and classify the light wave band data, the problems of noise interference and unclear features that may occur when directly analyzing the original light wave band data are avoided, and the effect of accurately identifying and classifying the camera features from complex light source information is achieved. This method can improve the sensitivity and specificity of the detection system, ensure the accuracy and reliability of the camera detection, and effectively protect the privacy and security of the user.

[0063] In step S32, the source data is transmitted to a wireless source recognition model, the source data is analyzed and evaluated by the wireless source recognition model, and a second evaluation result is obtained.

[0064] It should be noted that the source data refers to the wireless signal information collected by the wireless signal scanning component, including the signal source type (such as Wi-Fi, Bluetooth, etc.), signal strength (in dBm, indicating the strength of the signal), signal operating frequency (such as 2.4GHz, 5GHz), etc.; the wireless source identification model is a specially designed algorithm or model, which can select traditional machine learning models such as support vector machine, random forest, or use neural network, for analyzing wireless signal data to identify whether there is a wireless communication feature related to the camera; the second evaluation result refers to the analysis result output by the wireless source identification model, including whether there is a camera-related wireless signal, device type, and camera suspicion degree, etc.

[0065] In a feasible implementation, the step of analyzing and evaluating the source data by the wireless source identification model in step S32 to obtain the second evaluation result can include steps S321-S324:

[0066] In step S321, the wireless source identification model is used to extract features from the source data to obtain the to-be-identified source features.

[0067] It should be noted that the to-be-identified source features refer to the distinctive feature information extracted from the wireless signal data. These features can reflect the technical attributes of the wireless signal source, such as signal strength variation pattern, data packet size and frequency, transmission interval, signal strength, frequency, modulation mode, transmission protocol, etc. These features are key factors for identifying different types of wireless devices.

[0068] It can be understood that since it is necessary to extract information representing the characteristics of wireless cameras from complex wireless signal data, step S321 is performed to avoid the problem of being unable to effectively identify specific devices due to signal complexity and diversity, and to filter out feature information related to cameras from a large amount of signal data, thereby providing an effective and reliable data basis for subsequent classification analysis.

[0069] Exemplarily, the wireless source identification model processes the data through a series of algorithms (such as fast Fourier transform, wavelet transform, or deep learning network) to extract feature vectors representing the characteristics of the signal source, such as signal strength variation pattern, data packet size and frequency, transmission interval, etc. These feature vectors are the to-be-identified source features.

[0070] In step S322, the to-be-identified source features are classified to obtain the source categories corresponding to the to-be-identified source features.

[0071] It should be noted that the source category refers to different categories of signal sources divided according to the characteristics of wireless signals, such as Wi-Fi devices, Bluetooth devices, mobile phone signals, camera signals, etc., each category has its specific signal characteristics and communication behavior.

[0072] It can be understood that, since the extracted features need to be compared with known wireless signal source categories to determine whether it is a signal emitted by a wireless camera, step S322 is performed to avoid the problem of being unable to distinguish between wireless cameras and other wireless devices, and to achieve accurate identification of wireless cameras.

[0073] Exemplarily, each feature vector is assigned to a corresponding source category by the wireless source identification model according to the matching degree between the extracted to-be-identified source features and the pre-defined source categories (such as ordinary Wi-Fi devices, Bluetooth devices, wireless cameras, etc.).

[0074] In step S323, the source category is mapped to the corresponding target sources, and the second camera suspicion degree of each target source is obtained based on the wireless source identification model.

[0075] It should be noted that the target source refers to a wireless communication device that may be used to transmit image or video data identified by analyzing wireless signals, which may be part of a camera for sending captured image information; the second camera suspicion degree refers to a quantitative indicator given according to the matching degree between the signal characteristics of each target source identified and the known camera signal characteristics, as well as other attributes of the signal (such as signal stability, transmission rate, transmission mode, etc.), which reflects the degree of trust of the intelligent television detection system for the identified target source whether it is really part of a camera, and whether the camera is transmitting data. The higher the second camera suspicion degree, the more the system believes that the target source is a working camera.

[0076] In step S324, the target sources and the second camera suspicion degrees are associated and combined, and the combination result is taken as the second evaluation result.

[0077] In this embodiment, by using the wireless source identification model to extract features and classify source data, the problem of being unable to effectively identify specific devices (such as wireless cameras) due to the complexity and diversity of wireless signals in wireless signal analysis is avoided, and potential camera signals are accurately identified and classified from numerous wireless signals. This method can improve the detection ability of wireless cameras, reduce false positives and false negatives, thereby effectively protecting the privacy and security of users and enhancing the security of the wireless environment.

[0078] At step S33, the camera detection result of the surrounding environment is determined according to the first evaluation result and the second evaluation result.

[0079] It can be understood that, in order to fuse the dual detection results of optical and wireless signals and solve the limitations of a single method, step S33 is performed, which can avoid missing detection caused by relying on a single detection dimension, such as a camera without a wireless function or a wireless device disguised as a lens, significantly improves the detection accuracy and coverage range through multi-source data fusion, and further obtains more comprehensive detection results.

[0080] Exemplarily, the detection software of the smart television comprehensively analyzes the first evaluation result and the second evaluation result. Target objects in the first evaluation result and the second evaluation result are extracted, and the camera suspiciousness of each target object is extracted, wherein the target objects include target light sources in the first evaluation result and target signal sources in the second evaluation result. Then, the orientation features of the target light sources and the target signal sources are identified, and the camera suspiciousness of the target light sources and the target signal sources is fused based on the orientation features to obtain the comprehensive camera suspiciousness of each target object. Finally, the camera detection result of the surrounding environment is generated according to each target object and each comprehensive camera suspiciousness. For example: first, the software compares the signal sources marked as suspicious in the two evaluation results. If both of them indicate that there is a suspicious signal at the same position, the position is highly suspected to be the position of the camera. Then, the software weights the two results according to a preset weight distribution rule. For example, if the result of the infrared light recognition model is more reliable, the weight will be higher. Finally, the software combines the evaluation results after weighting and determines the final camera detection result through a decision algorithm. If the total score obtained by the decision algorithm exceeds a preset threshold, the system determines that there is a camera in the environment, and displays the detection result through a user interface, including the possible position of the camera, the signal strength, and the camera suspiciousness. In this way, the user can take appropriate protective measures to protect personal privacy and safety according to the information.

[0081] In this embodiment, by transmitting the optical band data to the infrared light recognition model and the signal source data to the wireless signal source recognition model, the problems of misjudgment and missed detection caused by a single detection method are avoided, and the camera detection accuracy and reliability are improved by comprehensively analyzing and evaluating two kinds of data sources. This method can simultaneously utilize the characteristics of infrared light and wireless signals, ensuring comprehensive detection of potential cameras in the environment, thereby effectively protecting user privacy and reducing the risk of illegal monitoring.

[0082] In a feasible implementation, step S33 can include steps S331-S334:

[0083] At step S331, the media access control (MAC) address in the signal source data is obtained, and the MAC address is transmitted to the MAC recognition model.

[0084] It should be noted that the MAC identification model refers to a preset database or algorithm system, which contains the MAC address prefix information of known device manufacturers, and can identify the device manufacturer of the device through the prefix of the MAC address.

[0085] It can be understood that since the MAC address is a unique identifier of the wireless device, the manufacturer of the device can be tracked by identifying the MAC address, so step S331 can avoid the problem of being unable to determine the identity of the wireless device, thereby achieving the effect of assisting in judging the device type through the device manufacturer information.

[0086] Step S332, identifying the corresponding device manufacturer according to the MAC address through the MAC identification model;

[0087] It can be understood that since devices produced by different device manufacturers have different purposes and characteristics, step S332 can avoid the problem of being unable to use device manufacturer information to improve detection accuracy, thereby achieving the effect of improving camera detection accuracy in combination with manufacturer information.

[0088] Exemplarily, after receiving the MAC address, the MAC identification model queries its built-in database, which contains the MAC address prefix of each device manufacturer and its corresponding information. The model determines the device manufacturer corresponding to each MAC address by comparing the organization unique identifier in the MAC address prefix.

[0089] Step S333, associating and combining the device manufacturer and the third camera suspiciousness of the device manufacturer, and taking the combination result as the third evaluation result;

[0090] It should be noted that the third camera suspiciousness refers to a quantitative index given according to the matching degree of the device manufacturer identified according to the MAC address and the known camera device manufacturer database. The score reflects the trust degree of the intelligent television detection system for the device manufacturer identified according to the MAC address whether it is possible to produce camera devices. The higher the third camera suspiciousness, the more the system believes that the device manufacturer is associated with the production of camera devices, thereby increasing the possibility that the device is a camera. The third evaluation result refers to an evaluation result based on the device manufacturer information identified according to the MAC address whether the wireless device detected in the environment is likely to be a camera. The result may indicate that a device is produced by a camera manufacturer, thereby increasing the possibility that it is a camera.

[0091] Exemplarily, whether the manufacturer has the relevant business of producing the camera is evaluated according to the camera suspicion degree of the corresponding camera, and the evaluation process can be performed by querying a preset manufacturer-suspicion degree table or calling a preset large model to perform intelligent evaluation, so that the associated device manufacturer and the camera suspicion degree constitute a structured third evaluation result, which can be represented as a device manufacturer + probability value.

[0092] In step S334, the camera detection result of the surrounding environment is determined according to the first evaluation result, the second evaluation result and the third evaluation result.

[0093] It can be understood that since the judgment is only based on the infrared detection result and the source feature detection result, there may still be uncertainty, so step S334 is performed to further enrich the multi-source data, thereby further improving the comprehensiveness and reliability of the camera detection.

[0094] Exemplarily, the first evaluation result (result based on infrared light data analysis), the second evaluation result (result based on wireless signal feature classification) and the third evaluation result (device manufacturer information based on MAC address identification) are comprehensively analyzed, and an algorithm is used to weigh the three results. For example, if at least two results indicate the possibility of the presence of a camera, the system will determine that there is a camera in the environment, and display the detection result through the user interface, including the possible position of the camera, the signal strength, the camera suspicion degree, etc.

[0095] In this embodiment, the camera detection result is determined by further considering the corresponding device manufacturer according to the MAC address in the wireless source data and comprehensively analyzing the three evaluation results, which avoids the misjudgment and missed detection problems caused by insufficient coverage of the detection method, and achieves the effect of improving the accuracy, comprehensiveness and reliability of the camera detection.

[0096] In a feasible implementation, step S334 can include steps S100-S600:

[0097] In step S100, each target object in the first evaluation result, the second evaluation result and the third evaluation result, and the camera suspicion degree of each target object are obtained, wherein the target object includes a target light source in the first evaluation result, a target source in the second evaluation result, and a device manufacturer in the third evaluation result.

[0098] In step S200, the relative angle and relative distance of each target light source are measured, and the first orientation feature of each target light source is calculated based on the relative angle and the relative distance.

[0099] It should be noted that the first orientation feature refers to the position information of the target light source in space, including but not limited to angle, distance and other coordinate data. These features help determine the specific position of each target object in the physical space, thereby providing a basis for subsequent camera suspiciousness fusion.

[0100] Exemplarily, for each target light source, the system measures its angle and distance relative to the detection device using triangulation method, and obtains the first orientation feature of each target light source based on these calculation results

[0101] Step S300, the signal strength and phase difference in the target source data of each target source are obtained, and the second orientation feature of each target source is calculated based on the signal strength and phase difference;

[0102] It should be noted that the second orientation feature refers to the position information of the target source in space, including but not limited to angle, distance and other coordinate data. These features help determine the specific position of each target object in the physical space, thereby providing a basis for subsequent camera suspiciousness fusion.

[0103] Exemplarily, for each target source, the system analyzes the signal strength and phase difference in the source data, then estimates the distance of each target source using the signal strength attenuation model, and estimates the direction of each target source through the phase difference. Based on these estimation results, the second orientation feature of each target source is calculated.

[0104] Step S400, query the device deployment location corresponding to each device manufacturer, and map the device deployment location to the third orientation feature of each device manufacturer;

[0105] It should be noted that the third orientation feature refers to the position information of the device manufacturer in space, including but not limited to angle, distance and other coordinate data. These features help determine the specific position of each target object in the physical space, thereby providing a basis for subsequent camera suspiciousness fusion.

[0106] Exemplarily, for each device manufacturer, the system may need to estimate its orientation depending on the device deployment location. A device database can be established to record the device deployment location of each device manufacturer and map these deployment locations to the corresponding third orientation feature, thereby determining the orientation information of each device manufacturer.

[0107] Step S500, the camera suspiciousness of the fusible target light source, the fusible target source and the fusible device manufacturer is weighted and fused to obtain the comprehensive camera suspiciousness of each target object, wherein the first orientation feature, the second orientation feature and the third orientation feature of the fusible target light source, the fusible target source and the fusible device manufacturer are in the same regional range.

[0108] It should be noted that the comprehensive camera suspicion degree refers to a new camera suspicion degree obtained by weighting average or other weighting fusion algorithm processing of camera suspicion degrees from different evaluation results (target light source, target signal source, device manufacturer). The score integrates information in multiple dimensions to more accurately evaluate the possibility that the target object is a camera.

[0109] It can be understood that, since the evaluation results of multiple different dimensions are often difficult to be successfully fused into an evaluation effect for a specific object, step S500 is performed to avoid the problem that different dimension evaluation results of the same object cannot be effectively fused, thereby enhancing the accuracy of camera recognition.

[0110] Exemplarily, the system uses a multi-factor score fusion algorithm to combine the orientation features of each target object with its camera suspicion degree, for example, by weighting average or other machine learning models to calculate a comprehensive camera suspicion degree, which score more comprehensively reflects the possibility that the target object is a camera.

[0111] Step S600, the target objects and the comprehensive camera suspicion degrees are associated and combined, and the combination result is taken as the camera detection result of the surrounding environment.

[0112] In this embodiment, by performing data fusion and analysis based on the orientation features of the objects, the problem that different dimension evaluation results of the same object cannot be effectively fused is avoided, and accurate detection and positioning of potential cameras in the surrounding environment are realized. Specifically, by recognizing the orientation features of each target object and fusing its camera suspicion degree, the accuracy and reliability of the detection are effectively improved. Finally, the camera detection result is generated according to the comprehensive camera suspicion degree, which not only reduces the false positive rate, but also ensures the comprehensiveness and practicality of the detection result.

[0113] The embodiment provides a method for detecting a camera in a surrounding environment of a smart television. The method integrates a signal scanning component in the smart television, and thus performs data acquisition and analysis and evaluation on the surrounding environment of the smart television to obtain a camera detection result of the surrounding environment, thereby achieving the effect of accurately detecting a hidden camera through a smart television configured in a room.

[0114] In a feasible implementation, the method for detecting a camera in a surrounding environment of a smart television further includes steps A01-A02:

[0115] Step A01, obtaining a light wave band data annotation set, wherein the light wave band data annotation set includes an infrared light data subset;

[0116] It should be noted that the light wave band data annotation set refers to a data set containing multiple light wave band data and its corresponding annotations (such as light source type, characteristics, etc.), and the infrared light data subset refers to a data set specifically for infrared wave band.

[0117] Step A02, training a preset first machine learning model according to the light wave band data annotation set to obtain an infrared recognition model.

[0118] It should be noted that the first machine learning model refers to a general machine learning model framework for processing light wave band data. After training with a specific data set, the model can be converted into an infrared recognition model with specific functions.

[0119] It can be understood that, due to the performance deficiency or misrecognition problem that may occur when using a general model to process a specific task, step A02 is performed to train a special recognition model for the characteristics of infrared light, which can avoid the performance deficiency of the general model in data processing, thereby realizing efficient recognition and classification of infrared light.

[0120] For example, first, the light wave band data annotation set is preprocessed, including filtering, denoising, etc., to extract useful frequency characteristics, and then frequency, amplitude, phase, etc. Features will be used to train AI models. In addition, the data set is divided into a training set and a validation set for model training and performance evaluation, wherein the validation set is used to evaluate the accuracy, recall rate, precision rate, etc. of the model.

[0121] In this embodiment, a general machine learning model is trained based on light wave data of different frequencies to train a special recognition model for the characteristics of infrared light, thereby improving the accuracy of infrared light recognition.

[0122] In a feasible implementation, the method of detecting a surrounding camera by the smart television further includes steps B01-B02:

[0123] Step B01, obtaining a source data annotation set, wherein the source data annotation set includes a wireless camera data annotation subset;

[0124] It should be noted that the source data annotation set refers to a data set containing various wireless signal sources, including signal data of normal devices (such as mobile phones, computers, routers, etc.) and various types of cameras. These data sets have been annotated by humans or automatically, marking the source and characteristics of the signal; the wireless camera data annotation subset refers to the part of the source data annotation set specifically for wireless camera signals. This part contains unique information and annotations of wireless camera signals.

[0125] Step B02, training the preset second machine learning model according to the source data annotation set to obtain a wireless source recognition model.

[0126] It should be noted that the second machine learning model refers to a general machine learning model framework that has not been optimized and trained for the wireless signal recognition task before the task is performed.

[0127] It can be understood that, due to the performance deficiency or misrecognition problem that may occur when a general model is used to process a wireless signal recognition task, step B02 is performed to train a special recognition model for the signal characteristics of the wireless camera, which can avoid the performance deficiency of data processing by the general model, thereby realizing efficient recognition and classification of the wireless camera signal.

[0128] Exemplarily, useful features are extracted from the source data annotation set, such as signal strength change pattern, data packet size and frequency, transmission interval, etc., and signal processing techniques are used to analyze the time domain and frequency domain characteristics of the signal, so that the model learns to recognize the signal characteristics of different devices.

[0129] In this embodiment, a special recognition model is trained for the characteristics of the wireless camera by training the general machine learning model based on different types of wireless signal data, thereby improving the accuracy of recognizing the wireless camera.

[0130] In a feasible embodiment, the method further comprises steps C01-C02:

[0131] Step C01, obtaining a MAC address data annotation set, wherein the MAC address data annotation set comprises MAC addresses, device manufacturers, and the correspondence between the MAC addresses and the device manufacturers;

[0132] Step C02, training the preset third machine learning model according to the MAC address data annotation set to obtain a MAC address recognition model.

[0133] It should be noted that the third machine learning model refers to a general machine learning model framework that has not been optimized and trained for the task of associating MAC addresses with device manufacturers before the task is performed.

[0134] It can be understood that, due to the performance deficiency or misrecognition problem that may occur when a general model is used to process a wireless signal recognition task, step C02 is performed to train a model for identifying the correspondence between MAC addresses and device manufacturers, which can avoid the performance deficiency of data processing by the general model, thereby realizing the effect of quickly and accurately identifying the manufacturers of wireless devices.

[0135] Exemplarily, the general machine learning model is trained based on the MAC address data set to identify the manufacturer information through the organization unique identifier of the MAC address, and then some tools and websites are connected to obtain the device manufacturer data, so as to indirectly identify whether it is a camera through the MAC address.

[0136] In this embodiment, the general machine learning model is trained based on the MAC address data to train a special recognition model for the MAC characteristics of the camera manufacturer, thereby improving the accuracy of identifying the camera manufacturer.

[0137] Based on the first embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the subsequent will not be described in detail. On this basis, please refer to Figure 2 , after step S30, the method of detecting the surrounding camera by the smart TV further includes steps S40-S50:

[0138] Step S40, based on the camera suspicious degree of the camera detection result, the camera detection result is data filtered to obtain the target detection result in the camera detection result;

[0139] It should be noted that the camera suspicious degree refers to a quantitative index given by the analysis model when evaluating the camera detection result. The index reflects the confidence degree of the model for the correctness of the detection result. The score is usually based on the consistency degree of the detection result with the known mode or feature, and the prediction probability of the model for the result; the target detection result refers to the detection result that the system considers most likely to represent the existence of the camera after the camera suspicious degree filtering. These results are the final conclusion of the system output, which is used to report to the user or take further action.

[0140] It can be understood that due to the complexity of the real environment, some uncertain or low confidence results may be generated in the detection process, resulting in a large number of detection results with certain probability but can be ignored in the final detection result. Therefore, step S40 is performed to avoid misreporting these low-probability detection results to the user, thereby reducing the false positive probability and ensuring that the user receives high-confidence information after filtering.

[0141] Exemplarily, a confidence threshold is first set, and then the camera suspicious degree of each camera detection result is compared with the threshold. Only when the camera suspicious degree is higher than or equal to the preset threshold, the corresponding detection result will be considered as the target detection result. These high-confidence results are filtered out to form a list of target detection results for further processing or reporting.

[0142] Step S50, output the target detection result.

[0143] Exemplarily, the system pops up a notification window on the TV screen, or displays the location, type and camera suspiciousness of the target camera on a dedicated security monitoring interface. In addition, the system can also notify the user of the target detection result through sound warning, mobile application push notification or email, etc., to ensure that the user can learn about the potential security threat in time and take appropriate protective measures.

[0144] In this embodiment, by performing quantitative evaluation and screening of the detection result based on the camera suspiciousness, only the detection result with high confidence is output as the target detection result, avoiding false positives and unnecessary redundant information display caused by low confidence results, and improving the simplicity and reliability of the detection result and the user's trust in the system detection.

[0145] Based on the first and / or second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiments one and two can be referred to the above introduction, and will not be repeated hereinafter. On this basis, please refer to Figure 3 , after step 30, the smart TV detection surrounding camera method can further include steps S60-S70:

[0146] Step S60, output the camera detection result, and receive the feedback data corresponding to the camera detection result;

[0147] It should be noted that the feedback data refers to the confirmation information or correction information provided by the user or other system to the output camera detection result, which can be the user's response to confirm whether the detection result is correct, or the user's report of false positives or false negatives.

[0148] It can be understood that in order to verify the accuracy of the detection result and obtain information in actual use from the user, step S60 can avoid the problem that the detection result does not match the actual situation, thereby ensuring the continuous improvement of the system and the user satisfaction.

[0149] Exemplarily, after the detection system of the smart TV completes the camera detection, it will display the detection result through the user interface, including the location, signal strength and camera suspiciousness of the camera. At the same time, the system will provide an interactive interface to allow the user to confirm or object to the detection result. The user can provide feedback by clicking the confirmation button, selecting the false positive / missed report option or directly marking the error on the interface. The system records these user feedback data and associates them with the corresponding detection result for subsequent analysis.

[0150] Exemplarily, after determining the camera detection result of the surrounding environment, the camera detection result is data-screened based on the camera detection result camera suspiciousness, to obtain a target detection result in the camera detection result, and the target detection result is output. Then, feedback data corresponding to the target detection result is received, wherein the feedback data can be data input by a user according to a system-provided interactive interface.

[0151] In step S70, training data is generated according to the feedback data, and the preset recognition model is trained through the training data, wherein the recognition model is used to perform the step of analyzing and evaluating the to-be-detected data.

[0152] It should be noted that the training data refers to labeled information extracted from the feedback data, which is used to guide the recognition model to learn how to more accurately identify the camera. These data usually include correct detection results and error detection cases, as well as related environmental parameters; the recognition model can include an infrared light recognition model, a wireless signal source recognition model, and a MAC recognition model.

[0153] It can be understood that, since the recognition model needs to be continuously updated and learned to adapt to new environments and challenges, step S70 is performed to avoid the performance degradation or obsolescence of the model due to lack of updates, thereby improving the generalization ability of the model and ensuring the long-term effectiveness of the model.

[0154] Exemplarily, the system processes the collected user feedback data and converts it into a format that can be used for machine learning model training. This includes marking the correct detection results confirmed by the user as positive samples, marking the false positive results marked by the user as negative samples, and extracting the corresponding feature data. Then, the system inputs these labeled data sets as training data into the recognition model, and optimizes the parameters of the model through an iterative training process. After training is completed, the updated model will be able to more accurately analyze and evaluate the to-be-detected data, improving the accuracy and efficiency of camera detection.

[0155] In this embodiment, by using the user interaction feedback and machine learning model iterative training method, the problems of long-term accuracy decline and poor adaptability caused by model solidification and environmental changes are avoided, and the effects of continuously optimizing the recognition model, improving the detection accuracy, and adapting to different environmental changes are achieved. Through this process, the system not only can correct the false detection in time, but also can continuously improve its learning ability, ensuring long-term high-efficiency camera detection performance.

[0156] Exemplarily, in order to help understand the implementation process of the intelligent television detection surrounding camera method obtained after combining the above-mentioned embodiment one, please refer to Figure 4 , Figure 4A brief flowchart of a method for detecting a peripheral camera of a smart television is provided, and specifically,

[0157] After starting the smart television, a camera detection mode in the smart television is selected to start a wireless signal scanning component to collect wireless signal sources around the smart television in the mode to obtain signal source data, and then the signal source data is filtered based on the signal source strength of each signal source in the signal source data. In the case where the signal source strength of any one signal source in the signal source data is greater than a preset threshold, a scanning component such as an infrared sensor (i.e., an infrared camera) is started to perform strong light scanning of different wavelengths on the signal source area range to obtain light waveband data. The signal source data and the light waveband data obtained above are compressed, encrypted and packaged to obtain to-be-detected data, and the data is attached to the smart television ID and then sent to a cloud server cluster to reconstruct the to-be-detected data in the cluster so that the data meets the requirements of an AI structure algorithm. Then, an AI algorithm is used in the cloud cluster, i.e., a corresponding infrared recognition model, a wireless signal source recognition model and a MAC address recognition model are called to analyze the corresponding to-be-detected data to determine whether there is a suspicious device, and then the detection result is returned to the smart television to feed back the detection result to the user through the user interface of the smart television. If a suspicious device is found, an alarm is issued and a processing suggestion is provided.

[0158] It should be noted that the process of using an AI algorithm, i.e., calling a corresponding infrared recognition model, a wireless signal source recognition model and a MAC address recognition model to analyze the corresponding to-be-detected data, can occur in the cloud server cluster to reduce the hardware cost of the local smart television and improve the recognition performance, or can occur in the local model of the smart television to protect user privacy and reduce the demand for network transmission conditions.

[0159] In addition, it should be noted that the to-be-transmitted data can be pre-filtered to simplify the data and improve the efficiency of subsequent data processing, or the light waveband data and the signal source data can be collected at the same time to ensure that all the collected data can be effectively analyzed and evaluated, thereby improving the accuracy and comprehensiveness of the recognition.

[0160] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the smart television peripheral camera detection method of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0161] The present application also provides a smart television peripheral camera detection device, which is described with reference to Figure 5 The smart television peripheral camera detection device comprises:

[0162] The starting module 10 is configured to receive a detection instruction and call a signal scanning component in the smart television according to the detection instruction.

[0163] The acquisition module 20 is configured to acquire signal data of the surrounding environment of the smart television through a signal scanning component to obtain to-be-detected data of the surrounding environment;

[0164] The detection module 30 is configured to analyze and evaluate the to-be-detected data to determine a camera detection result of the surrounding environment.

[0165] Optionally, the signal scanning component includes an infrared camera and a wireless signal scanning component, and the to-be-detected data includes light wave band data and signal source data, wherein the light wave band data is acquired by the infrared camera, and the signal source data is acquired by the wireless signal scanning component.

[0166] The detection module 30 is further configured to:

[0167] transmit the light wave band data to an infrared light recognition model, analyze and evaluate the light wave band data through the infrared light recognition model, and obtain a first evaluation result;

[0168] transmit the signal source data to a wireless signal source recognition model, analyze and evaluate the signal source data through the wireless signal source recognition model, and obtain a second evaluation result;

[0169] determine the camera detection result of the surrounding environment according to the first evaluation result and the second evaluation result.

[0170] Optionally, the detection module 30 is further configured to:

[0171] extract features of the light wave band data through the infrared light recognition model to obtain to-be-recognized light wave band features;

[0172] classify the to-be-recognized light wave band features to obtain a light wave band category corresponding to the to-be-recognized light wave band features;

[0173] map the light wave band category to corresponding target light sources, and obtain first camera suspicious degrees of the target light sources based on the infrared light recognition model;

[0174] associate and combine the target light sources and the first camera suspicious degrees, and take a combination result as the first evaluation result.

[0175] Optionally, the detection module 30 is further configured to:

[0176] extract features of the signal source data through the wireless signal source recognition model to obtain to-be-recognized signal source features;

[0177] classify the to-be-recognized signal source features to obtain a signal source category corresponding to the to-be-recognized signal source features;

[0178] map the source category to corresponding target sources, and obtain second camera suspiciousness of the target sources based on the wireless source identification model;

[0179] combine the target sources and the second camera suspiciousness, and take the combination result as a second evaluation result.

[0180] Optionally, the detection module 30 is further configured to:

[0181] obtain a media access control (MAC) address in the source data, and transmit the MAC address to a MAC identification model;

[0182] identify a corresponding device manufacturer according to the MAC address through the MAC identification model;

[0183] combine the device manufacturer and third camera suspiciousness of the device manufacturer, and take the combination result as a third evaluation result;

[0184] determine a camera detection result of the surrounding environment according to the first evaluation result, the second evaluation result, and the third evaluation result.

[0185] Optionally, the detection module 30 is further configured to:

[0186] obtain target objects in the first evaluation result, the second evaluation result, and the third evaluation result, and camera suspiciousness of the target objects, wherein the target objects include the target light sources in the first evaluation result, the target sources in the second evaluation result, and the device manufacturers in the third evaluation result;

[0187] measure relative angles and relative distances of the target light sources, and calculate first orientation features of the target light sources based on the relative angles and the relative distances;

[0188] obtain signal strengths and phase differences in source data of the target sources, and calculate second orientation features of the target sources based on the signal strengths and the phase differences;

[0189] query device deployment locations corresponding to the device manufacturers, and map the device deployment locations to third orientation features of the device manufacturers;

[0190] weight and fuse camera suspiciousness of the fusable target light sources, the fusable target sources, and the fusable device manufacturers to obtain comprehensive camera suspiciousness of the target objects, wherein first orientation features, second orientation features, and third orientation features of the fusable target light sources, the fusable target sources, and the fusable device manufacturers indicate orientations in the same area range;

[0191] Correlate and combine each target object and each comprehensive camera suspicious degree, and take the combination result as the camera detection result of the surrounding environment.

[0192] Optionally, the smart television detects that the output module 40 in the surrounding camera device is used to:

[0193] Based on the camera detection result, the camera detection result is data filtered according to the camera suspicious degree, and the target detection result in the camera detection result is obtained;

[0194] Output the target detection result.

[0195] Optionally, the smart television detects that the feedback module 50 in the surrounding camera device is used to:

[0196] Output the camera detection result, and receive the feedback data corresponding to the camera detection result;

[0197] Generate training data according to the feedback data, and train the preset recognition model through the training data, wherein the recognition model is used to execute the step of analyzing and evaluating the to-be-detected data.

[0198] The smart television detects the surrounding camera device provided by the application, adopts the smart television detection surrounding camera method in the above-mentioned embodiments, and can solve the technical problem of how to accurately detect the hidden camera at low cost. Compared with the prior art, the smart television detects the surrounding camera device provided by the application has the same beneficial effects as the smart television detection surrounding camera method provided by the above-mentioned embodiments, and other technical features in the smart television detects the surrounding camera device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0199] The application provides an electronic device, which comprises at least one processor and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the smart television detection surrounding camera method in the above-mentioned embodiment one.

[0200] The following refers to Figure 6The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of this application. The electronic devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0201] like Figure 6 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0202] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0203] The electronic device provided by the present application adopts the smart television detection of surrounding camera method in the above-mentioned embodiments, and can solve the technical problem of how to accurately detect hidden cameras at low cost. Compared with the prior art, the electronic device provided by the present application has the same beneficial effects as the smart television detection of surrounding camera method provided by the above-mentioned embodiments, and other technical features in the electronic device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0204] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0205] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0206] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the smart television detection of surrounding camera method in the above-mentioned embodiments.

[0207] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), and the like, or any suitable combination of the above.

[0208] The computer readable storage medium described above may be contained in an electronic device, or may exist separately without being assembled into an electronic device.

[0209] The computer readable storage medium described above carries one or more programs, which, when executed by an electronic device, cause the electronic device to: receive a detection instruction, and call a signal scanning component in the smart television according to the detection instruction; perform signal data collection on the surrounding environment of the smart television through the signal scanning component to obtain to-be-detected data of the surrounding environment; analyze and evaluate the to-be-detected data to determine a camera detection result of the surrounding environment.

[0210] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0211] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or in the reverse order, depending on the functionality involved. It is also noted that each block of the block diagrams and / or flow diagrams and combinations of blocks in the block diagrams and / or flow diagrams can be implemented by special purpose hardware-based systems which perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0212] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0213] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer programs) for executing the above-mentioned method for detecting a surrounding camera by an intelligent television, and can solve the technical problem of how to accurately detect a hidden camera at low cost. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the method for detecting a surrounding camera by an intelligent television provided by the above-mentioned embodiments, and will not be described here.

[0214] The above merely describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or the like, which is made based on the technical concept of the present application and the content of the specification and drawings, is included in the patent protection scope of the present application.

Claims

1. A method for detecting surrounding cameras on a smart TV, characterized in that, The smart television detects a surrounding camera method comprises: receiving a detection instruction, and calling an infrared camera and a wireless signal scanning component in the smart television according to the detection instruction; signal data of the surrounding environment of the smart television is collected by the infrared camera and the wireless signal scanning component, and light wave band data of the surrounding environment collected by the infrared camera and source data of the surrounding environment collected by the wireless signal scanning component are obtained; the light wave band data is transmitted to an infrared light identification model, and the light wave band data is analyzed and evaluated by the infrared light identification model to obtain a first evaluation result; the source data is transmitted to a wireless source identification model, and the source data is analyzed and evaluated by the wireless source identification model to obtain a second evaluation result; a camera detection result of the surrounding environment is determined according to the first evaluation result and the second evaluation result; the step of determining the camera detection result of the surrounding environment according to the first evaluation result and the second evaluation result comprises: each target object in the first evaluation result and the second evaluation result and a camera suspected degree of the target object are obtained, wherein the target object comprises a target light source in the first evaluation result and a target source in the second evaluation result; a relative angle and a relative distance of each target light source are measured, and a first orientation feature of each target light source is calculated based on the relative angle and the relative distance; a signal strength and a phase difference of each target source are obtained, and a second orientation feature of each target source is calculated based on the signal strength and the phase difference; a camera suspected degree of a fusible target light source and a fusible target source is weighted and fused to obtain a comprehensive camera suspected degree of each target object, wherein a first orientation feature of the fusible target light source and a second orientation feature of the fusible target source are in the same area range; the target objects and the comprehensive camera suspected degrees are associated and combined, and a combination result is taken as the camera detection result of the surrounding environment.

2. The smart television detecting peripheral camera method of claim 1, wherein, the step of analyzing and evaluating the light wave band data by the infrared light identification model to obtain the first evaluation result comprises: feature extraction of the light wave band data is performed by the infrared light identification model to obtain a to-be-identified light wave band feature; classification of the to-be-identified light wave band feature is performed to obtain a light wave band category corresponding to the to-be-identified light wave band feature; the light wave band category is mapped to corresponding target light sources, and first camera suspected degrees of the target light sources are obtained based on the infrared light identification model; the target light sources and the first camera suspected degrees are associated and combined, and a combination result is taken as the first evaluation result.

3. The smart television detecting peripheral camera method of claim 1, wherein, the step of analyzing and evaluating the source data by the wireless source identification model to obtain the second evaluation result comprises: feature extraction of the source data is performed by the wireless source identification model to obtain a to-be-identified source feature; classification of the to-be-identified source feature is performed to obtain a source category corresponding to the to-be-identified source feature; mapping the source category to corresponding target sources, and obtaining second camera suspiciousness of the target sources based on the wireless source identification model; associating and combining the target sources and the second camera suspiciousness, and taking the combination result as a second evaluation result.

4. The smart TV detecting peripheral camera method of claim 1, wherein, The camera detection result of the surrounding environment is further based on a third evaluation result, and the obtaining process of the third evaluation result includes: obtaining the media access control (MAC) address in the source data, and transmitting the MAC address to a MAC identification model; identifying the corresponding device manufacturer according to the MAC address through the MAC identification model; associating and combining the device manufacturer and the third camera suspiciousness of the device manufacturer, and taking the combination result as a third evaluation result.

5. The smart television detecting peripheral camera method of claim 4, wherein, The step of weighting and fusing the camera suspiciousness of the fusible target light source and the fusible target source to obtain the comprehensive camera suspiciousness of each target object further includes: obtaining each target object in the third evaluation result and the camera suspiciousness of each target object in the third evaluation result, wherein the target object in the third evaluation result includes the device manufacturer in the third evaluation result; querying the device deployment location corresponding to each device manufacturer, and mapping the device deployment location to the third position feature of each device manufacturer; The step of weighting and fusing the camera suspiciousness of the fusible target light source and the fusible target source to obtain the comprehensive camera suspiciousness of each target object includes: weighting and fusing the camera suspiciousness of the fusible target light source, the fusible target source and the fusible device manufacturer to obtain the comprehensive camera suspiciousness of each target object, wherein the first position feature of the fusible target light source, the second position feature of the fusible target source and the third position feature of the fusible device manufacturer are in the same area range.

6. The smart television detecting peripheral camera method of claim 1, wherein, The step of determining the camera detection result of the surrounding environment further includes: outputting the camera detection result and receiving feedback data corresponding to the camera detection result; generating training data according to the feedback data, and training the infrared light identification model and the wireless source identification model through the training data. 7.A smart TV detects a peripheral camera device, characterized in that, The smart TV detects the surrounding camera device, which includes: a starting module for receiving a detection instruction and calling an infrared camera and a wireless signal scanning component in the smart TV according to the detection instruction; a collection module for collecting signal data of the surrounding environment of the smart TV through the infrared camera and the wireless signal scanning component, obtaining light wave band data of the surrounding environment collected by the infrared camera, and source data of the surrounding environment collected by the wireless signal scanning component; The detection module is configured to transmit the light wave band data to an infrared light recognition model, analyze and evaluate the light wave band data by using the infrared light recognition model, and obtain a first evaluation result; transmit the signal source data to a wireless signal source recognition model, analyze and evaluate the signal source data by using the wireless signal source recognition model, and obtain a second evaluation result; and determine a camera detection result of the surrounding environment according to the first evaluation result and the second evaluation result. The step of determining the camera detection result of the surrounding environment according to the first evaluation result and the second evaluation result includes: obtaining each target object in the first evaluation result and the second evaluation result and a camera suspicious degree of each target object, wherein the target object includes a target light source in the first evaluation result and a target signal source in the second evaluation result; measuring a relative angle and a relative distance of each target light source, and calculating a first orientation feature of each target light source based on the relative angle and the relative distance; obtaining a signal strength and a phase difference of each target signal source, and calculating a second orientation feature of each target signal source based on the signal strength and the phase difference; weighting and fusing the camera suspicious degrees of fusable target light sources and fusable target signal sources to obtain a comprehensive camera suspicious degree of each target object, wherein the first orientation feature of the fusable target light source and the second orientation feature of the fusable target signal source indicate orientations in a same area range; and associating and combining each target object and each comprehensive camera suspicious degree, and taking a combination result as the camera detection result of the surrounding environment.

8. An electronic device, comprising: The device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the intelligent television detection surrounding camera method according to any one of claims 1 to 6.

9. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program. When the computer program is executed by a processor, the steps of the intelligent television detection surrounding camera method according to any one of claims 1 to 6 are implemented.

Images