Self-adaptive target event deployment and control method and device
Through the adaptive target event deployment method, the feature vectors of the deployment event are obtained and compared, which solves the problem that the existing technology is difficult to adapt to dynamically change target events, and achieves efficient, general and adaptable deployment effects to complex scenarios.
Patent Information
- Application Number
- CN202411865915.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-17
- Publication Date
- 2025-04-29
AI Technical Summary
The existing target deployment technology is difficult to adapt to dynamically changing target events, and the scenario-based algorithm model has insufficient generality and complex scenario judgment capabilities.
Adaptive target event deployment method is adopted to obtain the feature vectors of the events to be deployed, image capture and target detection are performed, feature values are generated, and comparison is performed to complete target event deployment. This method supports custom event definition, uses large-scale model technology to achieve zero sample startup, and improves comparison efficiency through binary processing of feature values.
It realizes efficient monitoring and control of dynamically changing target events, improves the universality of the layout and control system and the judgment ability of complex scenarios, reduces the GPU computing burden, and improves practical results and recall rates.
Smart Images
Figure CN119904615A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical fields of large models, target events and control, and in particular to an adaptive target event control method and device. Background Art
[0002] Target control is a measure to monitor and control specific targets. It involves the use of various technical means and equipment, such as cameras, sensors, software systems, etc., to conduct all-round monitoring of specific targets or areas. In many fields, such as public safety, enterprise management, network security, etc., control is an important task.
[0003] The target control schemes of the prior art include: Target recognition scheme based on image library: This method involves pre-entering images of specific targets (such as faces) into the system, and generating feature values of these targets when entering, and storing them in the database. When a specific target is captured in the video stream, the system extracts its feature values and matches them with the feature values in the database. If the similarity exceeds the preset threshold, it is determined to be a successful match and triggers an alarm. However, this method relies on pre-collected target images and is difficult to adapt to dynamically changing target events (such as riding a bicycle without a helmet). Algorithm model scheme based on scenarios: This method solves the problem by training independent algorithm models for specific scenarios (such as illegal parking of vehicles). Although this method works well for specific scenarios, it requires training models separately for each scenario, resulting in poor versatility of the model. In addition, due to the lack of in-depth understanding of scene semantics, the judgment ability for complex scenarios (such as non-motor vehicle overload) is limited, and additional business rules and software developers are usually required. The intervention is not only inefficient, but also easy to introduce functional defects. Summary of the invention
[0004] The present application shows an adaptive target event control method and device.
[0005] In a first aspect, the present application provides an adaptive target event control method, the method comprising:
[0006] Acquire the events to be controlled, extract a preset number of feature vectors of the events to be controlled, and send the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module;
[0007] Capture pictures of preset scenes based on preset modes, and send the captured pictures to the storage module and the business deployment control module respectively;
[0008] Performing target detection on the image, generating a target to be compared, calculating a feature value of the target to be compared, and sending the feature value to a feature value comparison module;
[0009] The characteristic value of the target to be compared is compared with a preset number of characteristic vectors of the event to be controlled, and the control of the target event is completed based on the comparison result.
[0010] In an exemplary embodiment of the present disclosure, the method further includes:
[0011] Obtaining an event definition of an event to be controlled, a text of the event to be controlled, and a picture of the event to be controlled;
[0012] Based on a preset semantic understanding model, a preset number of feature vectors of the event to be controlled are extracted from the text of the event to be controlled and the picture of the event to be controlled.
[0013] In an exemplary embodiment of the present disclosure, the method further includes:
[0014] Performing binary processing on each dimension of data in a preset number of feature vectors of the events to be controlled;
[0015] A preset number of feature vectors of the events to be controlled that are binary processed, index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled are sent to the storage module and the feature value comparison module.
[0016] In an exemplary embodiment of the present disclosure, the method further includes:
[0017] Capture pictures of preset scenes based on timed frame capture;
[0018] Alternatively, a picture of a preset scene is captured based on event capture.
[0019] In an exemplary embodiment of the present disclosure, the method further includes:
[0020] Performing target detection on the image to generate a target to be detected;
[0021] Based on the preset size threshold, the size of the target to be detected is judged;
[0022] Based on the confidence threshold, the confidence level of the target to be detected is judged;
[0023] Sorting the targets to be detected for size judgment and confidence judgment respectively in positive order, and selecting a preset number of targets to be detected in the positive order as targets to be compared;
[0024] A preset number of feature vectors of the target to be compared are extracted, and binary processing is performed on the preset number of feature vectors of the target to be compared to generate feature values of the target to be compared, and the feature values are sent to the feature value comparison module.
[0025] In an exemplary embodiment of the present disclosure, the method further includes:
[0026] A binary similarity comparison is performed on the feature value of the target to be compared and a preset number of feature vectors of the event to be controlled, and the target corresponding to the event to be controlled is confirmed based on a preset ratio threshold.
[0027] In an exemplary embodiment of the present disclosure, the method further includes:
[0028] The control library of the event to be controlled is updated based on a preset control library threshold.
[0029] In a second aspect, the present application shows an adaptive target event control device, the device comprising:
[0030] A control library construction module is used to obtain the events to be controlled, extract a preset number of feature vectors of the events to be controlled, and send the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module;
[0031] A picture capture module, used to capture pictures of preset scenes based on a preset mode, and send the captured pictures to the storage module and the business deployment control module respectively;
[0032] A control business module is used to perform target detection on the image, generate a target to be compared, calculate a feature value of the target to be compared, and send the feature value to a feature value comparison module;
[0033] The feature value comparison module is used to compare the feature value of the target to be compared with a preset number of feature vectors of the event to be controlled, and complete the control of the target event based on the comparison result.
[0034] In a third aspect, the present application shows an electronic device, which includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the method described in any of the above aspects.
[0035] In a fourth aspect, the present application illustrates a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a method as described in any of the above aspects.
[0036] In the fifth aspect, the present application shows a computer program product, when the instructions in the computer program product are executed by the processor of the electronic device, the electronic device can execute the method as described in any of the above aspects. In the adaptive target event control method disclosed in the present invention, the event to be controlled is obtained, the feature vectors of the preset number of events to be controlled are extracted, and the feature vectors of the preset number of events to be controlled, the index numbers corresponding to the feature vectors of the preset number of events to be controlled, and the events to be controlled corresponding to the feature vectors of the preset number of events to be controlled are sent to the storage module and the feature value comparison module; the controlled events can be customized, and support definition through a combination of text and pictures, and the user can accurately define the event according to the actual scene; support input of multiple control events at the same time. Based on the preset mode, the preset scene is captured, and the captured pictures are sent to the storage module and the business control module respectively; the picture is detected, the target to be compared is generated, the feature value of the target to be compared is calculated, and the feature value is sent to the feature value comparison module; the feature value binary processing strategy greatly reduces the efficiency of subsequent feature value comparison and improves the cost performance. The feature value of the target to be compared is compared with the preset number of feature vectors of the event to be controlled, and the target event is controlled based on the comparison results. The targets in the controlled images are confirmed and extracted one by one, and low-quality targets are filtered to reduce the computational workload of the GPU to extract features, greatly enhancing the actual combat capability. The real-time feedback module of the control library can update the high-quality pictures of the scene to the control library in real time, greatly improving the recall rate of this event in the current scene and achieving the effect of scene adaptation; using large model technology, some niche but user-concerned events do not require offline training and deployment, and can be started with zero samples; for some events that cannot be described in words, pictures can be used for control, which is more applicable to the scene. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 It is a flowchart of the steps of an adaptive target event control method of the present application.
[0038] Figure 2 This is a flow chart of building a control library for an adaptive target event control method of the present application.
[0039] Figure 3 This is a control business flow chart of an adaptive target event control method of the present application.
[0040] Figure 4 This is a feature value comparison flow chart of an adaptive target event control method of the present application.
[0041] Figure 5 This is a structural block diagram of an adaptive target event control device of the present application.
[0042] Figure 6This is an overall architecture diagram of an adaptive target event control device of the present application.
[0043] Figure 7 It is a block diagram of an electronic device of the present application.
[0044] Figure 8 It is a block diagram of a computer-readable storage medium of the present application. DETAILED DESCRIPTION
[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0046] Reference Figure 1 , shows a flowchart of the steps of an adaptive target event control method of the present application, which can be applied to electronic devices, wherein the method specifically may include the following steps:
[0047] Step S110, obtaining the events to be controlled, extracting a preset number of feature vectors of the events to be controlled, and sending the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module;
[0048] Step S120, capturing pictures of the preset scene based on the preset mode, and sending the captured pictures to the storage module and the business deployment control module respectively;
[0049] Step S130, performing target detection on the image, generating a target to be compared, calculating a feature value of the target to be compared, and sending the feature value to a feature value comparison module;
[0050] Step S140, comparing the feature value of the target to be compared with a preset number of feature vectors of the event to be controlled, and completing the control of the target event based on the comparison result.
[0051] In the adaptive target event control method disclosed in the present invention, the events to be controlled are obtained, the feature vectors of the preset number of events to be controlled are extracted, and the feature vectors of the preset number of events to be controlled, the index numbers corresponding to the feature vectors of the preset number of events to be controlled, and the events to be controlled corresponding to the feature vectors of the preset number of events to be controlled are sent to the storage module and the feature value comparison module; the controlled events can be customized, and support definition through a combination of text and pictures, and users can accurately define events according to actual scenes; support input of multiple control events at the same time. Based on the preset mode, the preset scene is captured, and the captured pictures are sent to the storage module and the business control module respectively; target detection is performed on the picture, the target to be compared is generated, the feature value of the target to be compared is calculated, and the feature value is sent to the feature value comparison module; the feature value binary processing strategy greatly reduces the efficiency of subsequent feature value comparison and improves the cost performance. The feature value of the target to be compared is compared with the feature vectors of the preset number of events to be controlled, and the target event control is completed based on the comparison result. The targets in the control images are confirmed and extracted one by one, and low-quality targets are filtered to reduce the computational workload of the GPU to extract features, greatly enhancing the actual combat capability. The control library real-time feedback module can update the high-quality images of the scene to the control library in real time, greatly improving the recall rate of this event in the current scene and achieving the effect of scene adaptation; using large model technology, some niche but user-concerned events do not require offline training and deployment, and can be started with zero samples; for some events that cannot be described in words, pictures can be used for control, which is more applicable to the scene.
[0052] Embodiment 1:
[0053] In step S110, the events to be controlled are obtained, a preset number of feature vectors of the events to be controlled are extracted, and the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled are sent to the storage module and the feature value comparison module.
[0054] Specifically, the step of obtaining and extracting a preset number of feature vectors of the event to be controlled includes:
[0055] Obtaining an event definition of an event to be controlled, a text of the event to be controlled, and a picture of the event to be controlled;
[0056] Based on a preset semantic understanding model, a preset number of feature vectors of the event to be controlled are extracted from the text of the event to be controlled and the picture of the event to be controlled.
[0057] In the embodiment of this example, the method further includes:
[0058] Performing binary processing on each dimension of data in a preset number of feature vectors of the events to be controlled;
[0059] A preset number of feature vectors of the events to be controlled that are binary processed, index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled are sent to the storage module and the feature value comparison module.
[0060] In step S120, pictures of the preset scene are captured based on the preset mode, and the captured pictures are sent to the storage module and the business deployment control module respectively.
[0061] There are two ways to capture pictures:
[0062] Capture pictures of preset scenes based on timed frame capture;
[0063] Alternatively, a picture of a preset scene is captured based on event capture.
[0064] In step S130, target detection is performed on the image to generate a target to be compared, feature values of the target to be compared are calculated, and the feature values are sent to a feature value comparison module.
[0065] The control business module receives the image and calls the large model feature extraction module to first detect the target in the image and identify the target in the image. It supports the setting of the maximum number of targets, confidence threshold, and target size. The detailed processing steps are as follows:
[0066] Performing target detection on the image to generate a target to be detected;
[0067] Based on the preset size threshold, the size of the target to be detected is judged;
[0068] Based on the confidence threshold, the confidence level of the target to be detected is judged;
[0069] Sorting the targets to be detected for size judgment and confidence judgment respectively in positive order, and selecting a preset number of targets to be detected in the positive order as targets to be compared;
[0070] A preset number of feature vectors of the target to be compared are extracted, and binary processing is performed on the preset number of feature vectors of the target to be compared to generate feature values of the target to be compared, and the feature values are sent to the feature value comparison module.
[0071] In step S140, the characteristic value of the target to be compared is compared with a preset number of characteristic vectors of the event to be controlled, and the control of the target event is completed based on the comparison result.
[0072] The feature value comparison module compares the target feature value analyzed in real time with the feature vector in the memory, and then performs feedback update logic of the corresponding event control library. Specifically, it includes the following steps:
[0073] A binary similarity comparison is performed on the feature value of the target to be compared and a preset number of feature vectors of the event to be controlled, and the target corresponding to the event to be controlled is confirmed based on a preset ratio threshold.
[0074] In the embodiment of this example, the method further includes:
[0075] The control library of the event to be controlled is updated based on a preset control library threshold.
[0076] In the embodiment of this example, the disclosure is based on a multimodal large model, combined with semantic understanding, video, and picture intelligent analysis technology, to identify targets in natural language and key frames in the video, and then convert them into feature vectors and align them in a high-dimensional space to achieve the purpose of controlling all elements in the video, while also supporting the recognition of differentiated features such as quantity, position, and action. Control is performed based on custom text or pictures or a combination of pictures and text, achieving zero-sample startup, which greatly improves the applicability of control scenarios.
[0077] Embodiment 2:
[0078] In the embodiment of this example, the adaptive target event control method disclosed in the present invention can achieve: users can customize control events, and accurately set events in actual application scenarios through a combination of text and pictures; the system supports users to input multiple control events; by binary processing feature values, the time for feature value comparison is effectively reduced, and efficiency and cost-effectiveness are improved; the system can review and screen target images one by one, exclude low-quality targets, and reduce the computational burden of GPU processing features, thereby enhancing the actual combat effect; the control library has a real-time feedback function, which can synchronize high-quality pictures of the scene to the control library in real time, significantly improving the recognition rate of specific events in the current scene, and realizing scene adaptation; using large model technology, even niche events that users are concerned about can achieve zero-sample startup without offline training and deployment; for events that are difficult to describe in words, control can be carried out through pictures, which enhances the applicability of the scene.
[0079] In this exemplary embodiment, if Figure 2As shown in the figure, users can input the definitions of multiple groups of control events at one time, including associated text, pictures, and picture-text combinations, and this information will be sent to the library management module. This module uses powerful large-model semantic analysis technology to extract feature vectors for each independent text or picture content, and ensures that these vectors are compared in the same metric space, thereby generating N feature vectors for each event. In order to improve the efficiency of subsequent feature comparison, these feature vectors will be binarized: specifically, the dimensional data of each feature vector is converted into binary form, that is, data containing only 0 and 1. The processed N binary feature values, together with their index numbers and associated target events, will be stored in the feature value storage module, and these data will also be copied to the memory of the feature value comparison module for fast comparison.
[0080] In this exemplary embodiment, if Figure 3 As shown, after receiving the picture, the control business module will start the feature extraction function of the large model and first detect the targets in the picture. Users can set the maximum number of targets (N), confidence threshold and target size (width, height) according to actual conditions. During the processing, first filter out the targets whose sizes meet the preset conditions, and exclude those small targets whose width or height is less than the set value, because they provide less information and may affect the accuracy of the control. Next, compare the confidence of the target with the preset threshold, and exclude those targets with lower confidence, which may affect the quality due to blur, exposure and other problems. Then, sort the remaining targets by confidence. If the number of targets exceeds N, only the top N with the highest confidence are retained; if it does not exceed, all targets are retained. Finally, feature extraction is performed on these screened targets, and the extracted features are binarized so that they can be sent one by one to the feature value comparison module for analysis. Such settings allow users to flexibly configure parameters according to actual scenarios, but it should be noted that the more control targets there are, the more GPU resources are consumed. In the embodiment of this example, Figure 4 As shown, the feature value comparison module compares the target feature value analyzed in real time with the feature vector in the memory, and then performs feedback update logic of the corresponding event control library. The detailed process is as follows:
[0081] First, the target feature is compared with the feature vector in the memory one by one for binary similarity. The calculation formula is: Among them, X i and Y i are the i-th data of eigenvector 1 and eigenvector 2 respectively, δ is the indicator function, when X i ≠Y iThe value is 0 when the target event is equal to 0, otherwise it is 1, and n is the number of binary bits of the feature vector. The calculated similarity will be compared with the internally set matching threshold. If it is greater than the threshold, it is considered to be a match. After the first match, the index number and similarity of the feature vector are recorded. When the match is repeated again, the new similarity is compared with the previously recorded one, and the index number with the higher similarity is retained and updated until all feature vectors are matched, thereby obtaining the final feature value index number. Due to the use of binary comparison, the calculation efficiency is extremely high. At this time, a single event corresponds to multiple feature vectors. As long as any similarity meets the requirements, the target event can be considered to have occurred. Then, the corresponding event definition is found according to the feature value index, triggering the control event. In addition, in order to improve the control effect, a feedback module for real-time updating of the control library is designed. The obtained similarity is compared with the control library threshold set by the user. If it exceeds the threshold and the target score meets the requirements, the feature vector is added to the control library of the event. The control library of each event can store up to 16 feature vectors. If this number is exceeded, the target score comparison will be performed, and the latest 16 feature vectors with the highest score will be retained. When a new target arrives, it will be compared with the latest control library, which contains on-site materials, thereby significantly improving the recall rate in the current scene and achieving scene adaptation.
[0082] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily required by the present application.
[0083] Reference Figure 5 , shows a structural block diagram of an adaptive target event control device of the present application, the device includes a control library construction module 210, a picture capture module 220, a control business module 230 and a feature value comparison module 240, wherein:
[0084] The control library construction module 210 is used to obtain the events to be controlled, extract a preset number of feature vectors of the events to be controlled, and send the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module;
[0085] The picture capture module 220 is used to capture pictures of preset scenes based on a preset mode, and send the captured pictures to the storage module and the business deployment control module respectively;
[0086] The control business module 230 is used to perform target detection on the image, generate a target to be compared, calculate a feature value of the target to be compared, and send the feature value to a feature value comparison module;
[0087] The feature value comparison module 240 is used to compare the feature value of the target to be compared with a preset number of feature vectors of the event to be controlled, and complete the control of the target event based on the comparison result.
[0088] In this exemplary embodiment, if Figure 6 As shown, the adaptive target event control device constructs a complete system solution based on the all-things detection and semantic understanding capabilities provided by the big model technology, including a text / picture library management module, a feature storage module, a big model feature extraction module, a feature comparison module 240, a picture capture module 220, a control business module 230, and a picture storage module.
[0089] Optionally, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.
[0090] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0091] Figure 7 800 is a block diagram of an electronic device 800 shown in the present application. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
[0092] Reference Figure 7 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .
[0093] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.
[0094] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, images, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
[0095] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.
[0096] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
[0097] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.
[0098] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.
[0099] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
[0100] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast operation information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (I rDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0101] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.
[0102] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0103] Figure 8 19 is a block diagram of a computer-readable storage medium 1900 shown in the present application. For example, the computer-readable storage medium 1900 may be provided as a server.
[0104] Reference Figure 8 , the computer-readable storage medium 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.
[0105] The computer readable storage medium 1900 may also include a power supply component 1926 configured to perform power management of the computer readable storage medium 1900, a wired or wireless network interface 1950 configured to connect the computer readable storage medium 1900 to a network, and an input / output (I / O) interface 1958. The computer readable storage medium 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.
[0106] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
[0108] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.
[0109] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0111] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0112] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0113] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0114] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.
[0115] 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 who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. An adaptive target event control method, characterized in that: The method comprises: Acquire the events to be controlled, extract a preset number of feature vectors of the events to be controlled, and send the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module; Capturing pictures of preset scenes based on preset modes, and sending the captured pictures to the storage module and the business deployment control module respectively; Performing target detection on the image, generating a target to be compared, calculating a feature value of the target to be compared, and sending the feature value to a feature value comparison module; The characteristic value of the target to be compared is compared with a preset number of characteristic vectors of the event to be controlled, and the control of the target event is completed based on the comparison result.
2. The method according to claim 1, characterized in that The method further comprises: Obtaining an event definition of an event to be controlled, a text of the event to be controlled, and a picture of the event to be controlled; Based on a preset semantic understanding model, a preset number of feature vectors of the event to be controlled are extracted from the text of the event to be controlled and the picture of the event to be controlled.
3. The method according to claim 2, characterized in that The method further comprises: Performing binary processing on each dimension of data in a preset number of feature vectors of the events to be controlled; A preset number of feature vectors of the events to be controlled that are binary processed, index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled are sent to the storage module and the feature value comparison module.
4. The method according to claim 1, characterized in that The method further comprises: Capture pictures of preset scenes based on timed frame capture; Alternatively, a picture of a preset scene is captured based on event capture.
5. The method according to claim 1, characterized in that The method further comprises: Performing target detection on the image to generate a target to be detected; Based on the preset size threshold, the size of the target to be detected is judged; Based on the confidence threshold, the confidence level of the target to be detected is judged; Sorting the targets to be detected for size judgment and confidence judgment respectively in positive order, and selecting a preset number of targets to be detected in the positive order as targets to be compared; A preset number of feature vectors of the target to be compared are extracted, and binary processing is performed on the preset number of feature vectors of the target to be compared to generate feature values of the target to be compared, and the feature values are sent to the feature value comparison module.
6. The method according to claim 1, characterized in that The method further comprises: A binary similarity comparison is performed on the feature value of the target to be compared and a preset number of feature vectors of the event to be controlled, and the target corresponding to the event to be controlled is confirmed based on a preset ratio threshold.
7. The method according to claim 1, characterized in that The method further comprises: The control library of the event to be controlled is updated based on a preset control library threshold.
8. An adaptive target event control device, characterized in that: The device comprises: A control library construction module is used to obtain the events to be controlled, extract a preset number of feature vectors of the events to be controlled, and send the preset number of feature vectors of the events to be controlled, the index numbers corresponding to the preset number of feature vectors of the events to be controlled, and the events to be controlled corresponding to the preset number of feature vectors of the events to be controlled to the storage module and the feature value comparison module; A picture capture module, used to capture pictures of preset scenes based on a preset mode, and send the captured pictures to the storage module and the business deployment control module respectively; A control business module is used to perform target detection on the image, generate a target to be compared, calculate a feature value of the target to be compared, and send the feature value to a feature value comparison module; The feature value comparison module is used to compare the feature value of the target to be compared with a preset number of feature vectors of the event to be controlled, and complete the control of the target event based on the comparison result.
9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 7 when executed by the processor.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.