Control method and device and nonvolatile storage medium

Abstract

The application discloses a kind of arrangement and control method, device and nonvolatile storage medium.Therein, the method includes: based on the identity information of target object, determine the associated object with predetermined relationship with target object;Based on the associated feature value of associated object, determine the first arrangement and control task carried out to target object, wherein the associated feature value is the first biological characteristic value and / or first vehicle characteristic value of associated object;Video stream is identified and processed, and identification feature value is obtained;In the case where identification feature value and first arrangement and control task match, corresponding alarm information is pushed to the receiving end of arrangement and control target object.The present application solves the technical problems of related art due to single arrangement and control approach, low arrangement and control efficiency.

Description

Technical Field

[0001] This invention relates to the field of security technology, and more specifically, to a deployment method, device, and non-volatile storage medium. Background Technology

[0002] Currently, the deployment methods in related technologies are relatively simple, and most can only deploy and warn of single facial targets or vehicle targets. Furthermore, the ways to obtain deployment information about the targets are quite limited, resulting in unsatisfactory deployment efficiency.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a deployment method, apparatus, and non-volatile storage medium to at least solve the technical problems of low deployment efficiency due to the single deployment approach in related technologies.

[0005] According to one aspect of the present invention, a deployment method is provided, comprising: determining an associated object that has a predetermined relationship with the target object based on the identity information of the target object; determining a first deployment task for the target object based on the associated feature value of the associated object, wherein the associated feature value is a first biometric value and / or a first vehicle feature value of the associated object; performing identification processing on a video stream to obtain an identification feature value; and, if the identification feature value matches the first deployment task, pushing corresponding alarm information to a receiving end that deploys the target object.

[0006] According to another aspect of the present invention, a deployment device is provided, comprising: a first determining module, configured to determine an associated object having a predetermined relationship with the target object based on the identity information of the target object; a second determining module, configured to determine a first deployment task to be performed on the target object based on the associated feature value of the associated object, wherein the associated feature value is a first biometric feature value and / or a first vehicle feature value of the associated object; an identification module, configured to perform identification processing on a video stream to obtain an identification feature value; and an alarm module, configured to push corresponding alarm information to a receiving end of the deployed target object when the identification feature value matches the first deployment task.

[0007] According to another aspect of the present invention, a non-volatile storage medium is provided, the non-volatile storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor and executed by any one of the deployment methods described herein.

[0008] In this embodiment of the invention, an associated deployment method is adopted. Based on the identity information of the target object, associated objects with a predetermined relationship with the target object are identified. Based on the associated feature values ​​of the associated objects, a first deployment task for the target object is determined, wherein the associated feature values ​​are the first biometric value and / or the first vehicle feature value of the associated object. The video stream is processed to obtain identification feature values. If the identification feature values ​​match the first deployment task, corresponding alarm information is pushed to the receiving end of the deployed target object. This achieves the goal of enriching deployment methods, improving the efficiency of deploying target objects, and thus solving the technical problem of low deployment efficiency due to a single deployment method in related technologies. Attached Figure Description

[0009] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0010] Figure 1 This is a flowchart of a deployment method based on relevant technologies;

[0011] Figure 2 This is a flowchart of an optional deployment method provided according to an embodiment of the present invention;

[0012] Figure 3 This is a schematic diagram of an optional deployment method provided according to an embodiment of the present invention;

[0013] Figure 4 This is a schematic diagram of an optional deployment device provided according to an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Figure 1 This is a flowchart of a deployment method based on relevant technologies, such as... Figure 1 As shown, one deployment method in related technologies involves using visual recognition algorithms to analyze images to extract targets and their feature values. From multiple targets, a target to be monitored is selected, and filtering conditions such as the deployment location and time range are chosen based on the actual situation. Structured real-time data (data parsed from checkpoint images or video streams using visual recognition algorithms) is acquired, and data matching the capture location and time are filtered out. Data meeting a similarity threshold is calculated and compared using feature vectors and used as alarm information. The backend program pushes the alarm information to the frontend page (deployment alarm console).

[0017] The methods described above in related technologies reveal that the deployment methods are relatively limited, mostly only capable of monitoring and issuing warnings for single facial or vehicle targets. Therefore, these technologies suffer from unsatisfactory target coverage and low deployment efficiency.

[0018] According to an embodiment of the present invention, a method embodiment for deployment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0019] Figure 2 This is a flowchart of a deployment method according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0020] Step S202: Based on the identity information of the target object, determine the associated objects that have a predetermined relationship with the target object.

[0021] It is understandable that, in order to expand the information channels needed for deployment, associated objects with a predetermined relationship with the target object are identified based on the target object's identity information.

[0022] Optionally, the aforementioned pre-arranged relationship can be of various types, such as kinship or registration under the same document type.

[0023] In an optional embodiment, the method further includes: querying a preset driver management database based on the identity information of the associated object to determine the vehicle information of vehicles under the name of the associated object; querying a preset population database based on the identity information of the associated object to obtain the registration information already entered by the associated object; and determining the associated feature value based on the vehicle information of vehicles under the name of the associated object and the registration information already entered by the associated object.

[0024] It is understandable that after identifying the associated objects, their identity information can be obtained. This identity information is then used to help derive the associated feature value. Based on the associated object's identity information, a query is performed in a pre-defined vehicle registration database to obtain vehicle information registered under the associated object's name. Based on the associated object's identity information, a query is performed in a pre-defined population database to obtain the associated object's already entered registration information. Based on the vehicle information registered under the associated object's name and the already entered registration information, the associated feature value is determined. Through this process, utilizing the associated object's identity information to obtain vehicle information registered under the associated object's name and the associated object's already entered registration information facilitates the acquisition of highly informative associated feature values.

[0025] Optionally, the vehicle information of the vehicles under the aforementioned associated object shall include at least: the license plate number, vehicle appearance, and vehicle model of the vehicles under the aforementioned associated object.

[0026] Optionally, the registration information already entered for the aforementioned associated objects shall include at least: the name, photo, and preset characteristic values ​​of the aforementioned associated objects.

[0027] Optionally, the aforementioned preset feature values ​​can be of various types, such as already recorded physical characteristics, such as being one-eyed, etc.

[0028] Optionally, the aforementioned population database can be of various types, such as population registration information stored in ARANGODB (a native multi-model database). Similarly, the aforementioned driver management database can be of various types, such as vehicle registration information stored in MongoDB (a distributed document storage database).

[0029] In an optional embodiment, before determining the associated object with a predetermined relationship to the target object based on the target object's identity information, the method further includes: determining whether the target object's identity information has been obtained; if the target object's identity information has not been obtained, determining whether the target object's license plate number has been obtained; if the target object's license plate number has been obtained, determining the associated object based on the target object's license plate number.

[0030] It's understandable that the target object's identification information might not be available. If this isn't the case, the system checks if the target object's license plate number is available. The license plate number is more readily obtainable than the identification information. If the target object's license plate number is obtained, the associated object is determined based on it. Through this process, it's possible to determine the target object's associated objects even when its identification information is unavailable.

[0031] In one optional embodiment, determining the associated object based on the license plate number of the target object includes: querying a preset driver management database based on the license plate number of the target object to determine the identity information of the target object; and determining the associated object based on the identity information of the target object.

[0032] Understandably, since vehicle registration information generally includes the owner's identification information, it is easy to obtain the target's identification information by querying a pre-defined vehicle registration database using the target's license plate number. Based on the target's identification information, associated objects are then identified.

[0033] In one optional embodiment, if the license plate number of the target object is not obtained, at least one image of the target object is acquired; the at least one image is processed for recognition to obtain the target object's feature value and the second deployment task corresponding to the feature value, wherein the feature value is at least the target object's first biometric value and / or first vehicle feature value; if the feature value matches the second deployment task, corresponding alarm information is pushed to the receiving end.

[0034] It is understandable that, in the absence of identification information and license plate number of the target object, at least one image containing the target object is acquired and processed using an image-based control method. This involves identifying and processing the at least one image to obtain the target object's feature values. Based on these feature values, a second control task corresponding to the feature values ​​is determined. It should be noted that the feature values ​​can be the target object's first biometric value and / or first vehicle feature value; that is, identifying and processing the biometric and vehicle features included in the at least one acquired image. Through the above processing, an image-based control method can be used to control the target object.

[0035] Optionally, the above recognition process can be varied. For example, several images can be uploaded consecutively, and each image can be analyzed by a recognition algorithm to identify several targets (faces and vehicles). Up to 20 targets can be selected, and three thresholds can be set for driver / passenger capture, pedestrian capture, and dynamic face capture. Uploaded images can be requested to be stored in the WeedFS file system (a simple, scalable distributed file system used for fast storage of large numbers of files) or stored in a local directory on the server.

[0036] Step S204: Based on the association feature values ​​of the aforementioned associated objects, determine the first deployment task for the aforementioned target objects, wherein the aforementioned association feature values ​​are the first biometric value and / or the first vehicle feature value of the aforementioned associated objects.

[0037] It is understandable that utilizing the associated feature values ​​of related objects expands the coverage of the target object's surveillance, determining the first surveillance task for the target object. The associated feature values ​​are the first biometric value and / or the first vehicle feature value of the related object. Through the above processing, related objects are found by identifying the target object, and then the first surveillance task is determined based on the associated feature values ​​of the related objects. This helps to enrich the surveillance methods and achieve better surveillance results.

[0038] Optionally, the aforementioned first biometric value can be of various types, such as: facial feature value, voiceprint feature value, body feature value, iris feature value, etc.

[0039] In an optional embodiment, determining the first deployment task for the target object based on the association feature value of the associated object includes: querying a preset driver management database based on the identity information of the target object to determine the vehicle information of vehicles registered under the name of the target object; querying a preset population database based on the identity information of the target object to obtain the registration information already entered by the target object; determining the target feature value of the target object based on the vehicle information of vehicles registered under the name of the target object and the registration information already entered by the target object, wherein the target feature value is the first biometric feature value and / or the first vehicle feature value of the target object; and obtaining the first deployment task based on the association feature value and the target feature value.

[0040] It can be understood that the deployment and acquisition of information is based on a combination of the target object and its associated objects, i.e., based on the associated feature value and the target feature value, to obtain the first deployment task. To obtain the target feature value, a query is performed in a pre-set driver management database based on the target object's identity information to determine the vehicle information of vehicles registered under the target object's name. A query is also performed in a pre-set population database based on the target object's identity information to obtain the target object's registered information. Based on the vehicle information of vehicles registered under the target object's name and the target object's registered information, the target feature value of the target object is determined. Through the above processing, the relevant information of the target object and its associated objects is combined, and based on the associated feature value and the target feature value, the first deployment task for deploying control over the target object is determined.

[0041] Optionally, the vehicle information of the vehicles under the name of the aforementioned target object shall include at least: the license plate number, vehicle appearance, and vehicle model of the vehicles under the name of the aforementioned target object.

[0042] Optionally, the registration information already entered for the target object includes at least: the target object's name, photo, and preset characteristic values.

[0043] In an optional embodiment, after processing the video stream to obtain identification feature values, the method further includes: if the identification feature values ​​are a second biometric value and a second vehicle feature value, establishing a biometric topic queue for storing the second biometric value and a vehicle topic queue for storing the second vehicle feature value in a preset message system; comparing the second vehicle feature value obtained by subscribing to the vehicle topic queues with the first deployment task using a preset vehicle deployment program to obtain a vehicle deployment result; comparing the second biometric value obtained by subscribing to the biometric topic queues with the first deployment task using a preset biometric deployment program to obtain a biometric deployment result; and determining whether the identification feature value matches the first deployment task based on the vehicle deployment result and the biometric deployment result.

[0044] It is understandable that video stream recognition processing yields a large number of feature values. To avoid data loss, a biometrics queue is established in the pre-defined message system to store the second biometrics values, and a vehicle queue is established to store the second vehicle feature values. Subscribing to the second vehicle feature values ​​in the vehicle queue and the second biometrics queue improves real-time processing capabilities. Pre-defined vehicle and biometrics control procedures are compared to obtain biometrics control results and vehicle control results. Based on the vehicle and biometrics control results, it is determined whether the identified feature values ​​match the first control task.

[0045] Optionally, the aforementioned second biometric value and second vehicle characteristic value can be structured data.

[0046] Optionally, the above-mentioned recognition processing of the video stream can be a cluster of visual recognition algorithms.

[0047] Optionally, the above-mentioned preset messaging system can be of various types. For example, the Kafaka messaging system is preferred, but RabbitMQ (an open-source message broker software) and Redis (a remote dictionary software) can also be used.

[0048] It should be noted that after the video stream is parsed by the algorithm cluster, it is pushed to the corresponding topic (i.e., topic queue) in the Kafaka messaging system according to the type of feature values. The face detection and vehicle detection programs respectively process the feature value comparison of the corresponding types. First, data that matches the capture time and capture location is filtered out. Face detection and vehicle feature detection calculate similarity through feature vectors and compare data that meets the threshold. Vehicle license plate and vehicle model detection directly compares the detected license plate and vehicle model with the license plate and vehicle model in the real-time data.

[0049] In one alternative embodiment, the control can be set up based solely on vehicles. The control can be set up by inputting a precise license plate number or a vague vehicle that has a predetermined association with the target object, as well as the vehicle model.

[0050] In one optional embodiment, a full-database deployment can be selected to achieve overall deployment of all targets in an existing static deployment database. Knowing only that the target object is a subset of all targets in a preset database, the static deployment database is queried and selected. This static deployment database is stored in MySQL (a relational database). A deployment database can be created according to actual needs, importing feature values ​​such as license plate numbers or facial features for deployment submission.

[0051] Step S206: Perform recognition processing on the video stream to obtain recognition feature values.

[0052] It is understandable that after determining the first deployment task, the acquired video stream is processed to obtain identification feature values ​​for comparison and matching.

[0053] Optionally, the video stream mentioned above can be a real-time video stream.

[0054] Step S208: If the above-mentioned identification feature value matches the above-mentioned first deployment task, push the corresponding alarm information to the receiving end of the deployed target object.

[0055] It is understood that the aforementioned identification feature values, when matched with the first deployment task, are considered as clues to finding the target object, and corresponding alarm information is pushed to the receiving end of the target object.

[0056] In one optional embodiment, the above-mentioned method of pushing corresponding alarm information to the receiving end of the target object includes: establishing a result topic queue for storing alarm information in a preset message system; and pushing corresponding alarm information to the receiving end based on the alarm information obtained by subscribing to the result topic queue.

[0057] It is understandable that a result topic queue is established in the preset message system to store alarm information, and in order to improve the real-time performance of alarms and reduce server pressure, the corresponding alarm information is pushed to the receiving end in a targeted manner.

[0058] Optionally, the alarm information can also be stored in a columnar storage database. Since the alarm information data is large and will not be changed or deleted, using a columnar storage database helps the receiving end to retrieve it.

[0059] Optionally, the above-mentioned use of nested sockets to bind the identifier of the receiving end with the identifier of the nested socket can be stored in Redis, which is beneficial for accurately pushing alarm information to each receiving end according to the target object's receiving end.

[0060] Optionally, alarm data can be pushed to the corresponding receiving end using WebSocket (a protocol for full-duplex communication over a single TCP connection).

[0061] Through the above steps S202 to S208, the purpose of enriching the deployment methods can be achieved, and the technical effect of improving the deployment efficiency of the target object can be realized. This solves the technical problem of low deployment efficiency due to the single deployment method in related technologies.

[0062] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 3 This is a schematic diagram of an optional deployment method provided by an embodiment of the present invention, such as... Figure 3As shown, based on multi-target fusion control and early warning, depending on the specific relevant information of the target object obtained, one or more of four control methods can be selected for control. These control methods include at least: map-based control, vehicle-based control, full-dimensional control, and whole-database control. The following discusses... Figure 3 Please provide a detailed explanation:

[0063] Image-based deployment allows for the continuous uploading of multiple images containing the target object. Each image is analyzed by a recognition algorithm to identify several targets (faces and vehicles). Up to 10 targets can be selected, with thresholds set for three types of capture: vehicular and pedestrian capture, and dynamic face capture. Uploaded images can be requested to be stored in the WeedFS file system or stored in a local directory on the server.

[0064] Select vehicle control; this is a control method only for automobiles. You can enter the precise license plate number or a vague license plate number and vehicle model to conduct control.

[0065] Choosing full-dimensional surveillance is a method of finding and controlling related people and vehicles based on the target, including the following two options:

[0066] Inputting identity information will retrieve the target's (i.e., the target object) and related persons' (i.e., associated persons, such as parents, siblings) names, identity information, photos, and preset feature values ​​from the population database (population registration information stored in arangodb). Based on the target and related persons' identity information, the system will then retrieve the vehicle registration database (vehicle registration information stored in mongodb) to obtain relevant information about vehicles registered under the target's name.

[0067] Entering the license plate number will retrieve the vehicle registrant from the driver management database. Then, based on the registrant's identification information, the database will be searched to obtain the target and related persons (such as parents, siblings), including their names, identification information, photos, and preset characteristic values. Finally, the preset characteristic values ​​(such as biometric features) of the target and related persons, along with the registered vehicle's license plate number, will be selected for monitoring.

[0068] Choosing full-database deployment allows for comprehensive deployment of all targets in an existing static deployment database. When only a portion of the targets in the preset database is known, the static deployment database is queried and selected. This database is stored in MySQL (a relational database). Custom deployment databases can be created based on actual needs, importing features such as license plate numbers or facial characteristics for deployment submission.

[0069] When a control task is obtained by using one or more of the above four control methods to control the target object, the control task is obtained.

[0070] The retrieved video stream is parsed by an algorithm cluster, processed for identification, and then pushed to the corresponding topic queue in the Kafka messaging system based on the target type. The face detection and vehicle detection programs process the corresponding types of detection orders in the detection tasks, first filtering out data that matches the capture time and location. Face detection and vehicle feature detection calculate similarity using feature vectors and compare data that meets the threshold. Vehicle license plate and model detection directly compares the detected license plate and model with those in the real-time data.

[0071] In addition to being pushed to the Kafka alert console (frontend program), alert results are also stored in the ClickHouse database. The ClickHouse database is a columnar storage database. Since the alert information data is large and not modified or deleted, using a columnar storage database facilitates retrieval by the receiving end. Clicking on the alert information of the control task in the alert console allows searching the ClickHouse database to view the historical alert information of the control task for the target object. It should be noted that using nested sockets to bind the receiver's identifier with the nested socket identifier, which can be stored in Redis, allows for precise push of alert information to each receiver based on the required target object. WebSockets (a protocol for full-duplex communication over a single TCP connection) are used to push alert data to the corresponding receiver.

[0072] The above-mentioned optional implementation methods achieve at least the following effects: Multiple deployment methods facilitate deployment. Target feature-based deployment can be achieved by uploading images, or target deployment can be performed by entering ID numbers or license plate numbers for associated queries. Furthermore, all previously saved targets can be deployed. Real-time alerts are effective; accessed checkpoint data is identified and published to the Kafka message system, subsequently consumed and processed by the alert program. Alert data is proactively pushed to specific receiving ends, improving alert real-time performance and reducing server load.

[0073] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0074] This embodiment also provides a deployment device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0075] According to embodiments of the present invention, an apparatus embodiment for implementing the deployment method is also provided. Figure 4 This is a schematic diagram of a deployment device according to an embodiment of the present invention, such as... Figure 4 As shown, the above-mentioned control device includes a first determination module 402, a second determination module 404, an identification module 406, and an alarm module 408. The device will be described below.

[0076] The first determining module 402 is used to determine the associated object that has a predetermined relationship with the target object based on the identity information of the target object;

[0077] The second determining module 404 is connected to the first determining module 402 and is used to determine the first deployment task for the target object based on the association feature value of the aforementioned associated object, wherein the association feature value is the first biometric value and / or the first vehicle feature value of the aforementioned associated object.

[0078] The recognition module 406, connected to the second determination module 404, is used to perform recognition processing on the video stream to obtain recognition feature values;

[0079] The alarm module 408, connected to the identification module 406, is used to push corresponding alarm information to the receiving end of the target object when the identification feature value matches the first deployment task.

[0080] In a deployment device provided by this embodiment of the invention, a first determining module 402 is used to determine associated objects that have a predetermined relationship with the target object based on the identity information of the target object; a second determining module 404, connected to the first determining module 402, is used to determine a first deployment task for the target object based on the associated feature values ​​of the associated objects, wherein the associated feature values ​​are the first biometric value and / or the first vehicle feature value of the associated objects; an identification module 406, connected to the second determining module 404, is used to perform identification processing on the video stream to obtain identification feature values; and an alarm module 408, connected to the identification module 406, is used to push corresponding alarm information to the receiving end of the deployed target object when the identification feature values ​​match the first deployment task. This achieves the goal of enriching deployment methods, realizing the technical effect of improving the deployment efficiency of target objects, and thus solving the technical problem of low deployment efficiency due to a single deployment method in related technologies.

[0081] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0082] It should be noted that the first determining module 402, the second determining module 404, the identification module 406, and the alarm module 408 mentioned above correspond to steps S202 to S208 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but they are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0083] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0084] The aforementioned deployment device may also include a processor and a memory. The first determination module 402, the second determination module 404, the identification module 406, the alarm module 408, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0085] The processor contains a core that retrieves the corresponding program unit from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0086] This invention provides a non-volatile storage medium storing a program that, when executed by a processor, implements a deployment method.

[0087] This invention provides an electronic device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: based on the identity information of a target object, it determines an associated object with a predetermined relationship to the target object; based on the associated feature values ​​of the associated objects, it determines a first deployment task for the target object, wherein the associated feature values ​​are a first biometric value and / or a first vehicle feature value of the associated object; it performs recognition processing on a video stream to obtain recognition feature values; and when the recognition feature values ​​match the first deployment task, it pushes corresponding alarm information to a receiving end that controls the target object. The device in this document can be a server, PC, etc.

[0088] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: determining an associated object with a predetermined relationship to the target object based on the identity information of the target object; determining a first deployment task for the target object based on the association feature value of the associated object, wherein the association feature value is a first biometric value and / or a first vehicle feature value of the associated object; performing recognition processing on the video stream to obtain recognition feature value; and pushing corresponding alarm information to the receiving end of the target object when the recognition feature value matches the first deployment task.

[0089] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0094] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0095] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0096] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0097] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A deployment method, characterized in that, include: Based on the identity information of the target object, identify associated objects that have a predetermined relationship with the target object; Based on the association feature value of the associated object, a first deployment task is determined for the target object, wherein the association feature value is the first biometric value and / or the first vehicle feature value of the associated object, and the first deployment task is determined based on the association feature value and the target feature value, wherein the target feature value is the first biometric value and / or the first vehicle feature value of the target object; The video stream is processed for identification to obtain identification feature values; If the identified feature value matches the first deployment task, the corresponding alarm information is pushed to the receiving end of the deployed target object; Before determining the associated object with a predetermined relationship to the target object based on the target object's identity information, the method further includes: determining whether the target object's identity information has been obtained; if the target object's identity information has not been obtained, determining whether the target object's license plate number has been obtained; if the target object's license plate number has not been obtained, not determining the associated object, and obtaining at least one captured image including the target object; performing recognition processing on the at least one captured image to obtain the target object's collection feature value and the second deployment task corresponding to the collection feature value, wherein the collection feature value is at least the target object's first biometric feature value and / or first vehicle feature value; and pushing corresponding alarm information to the receiving end when the recognition feature value matches the second deployment task.

2. The method according to claim 1, characterized in that, The method further includes: Based on the identity information of the associated object, a query is performed in a preset driver management database to determine the vehicle information of vehicles under the name of the associated object; Based on the identity information of the associated object, a query is performed in a preset population database to obtain the registration information that the associated object has been entered; Based on the vehicle information of the vehicles under the name of the associated object and the registration information already entered by the associated object, the associated feature value is determined.

3. The method according to claim 1, characterized in that, The step of determining the first control task for the target object based on the association feature value of the associated object includes: Based on the identity information of the target object, a query is performed in a preset driver management database to determine the vehicle information of the vehicles registered under the name of the target object; Based on the identity information of the target object, a query is performed in a preset population database to obtain the registration information that the target object has been entered into; Based on the vehicle information of the vehicles under the name of the target object and the registration information already entered by the target object, the target feature value of the target object is determined, wherein the target feature value is the first biometric value and / or the first vehicle feature value of the target object; Based on the associated feature value and the target feature value, the first deployment task is obtained.

4. The method according to claim 1, characterized in that, Before determining the associated objects with a predetermined relationship to the target object based on the target object's identity information, the method further includes: If the license plate number of the target object is obtained, the associated object is determined based on the license plate number of the target object.

5. The method according to claim 4, characterized in that, Determining the associated object based on the license plate number of the target object includes: Based on the license plate number of the target object, a query is performed in a preset driver management database to determine the identity information of the target object; The associated object is determined based on the identity information of the target object.

6. The method according to claim 1, characterized in that, After performing recognition processing on the video stream to obtain recognition feature values, the method further includes: When the identified feature value is the second biometric value and the second vehicle feature value, a biometric topic queue for storing the second biometric value and a vehicle topic queue for storing the second vehicle feature value are established in a preset message system. Based on the second vehicle feature value obtained from subscribing to the vehicle topic queue and the first deployment task, a preset vehicle deployment program is used to compare them to obtain the vehicle deployment result. Based on the second biological feature value obtained from subscribing to the biological topic queue and the first deployment task, a preset biological deployment program is used to compare them to obtain the biological deployment result. Based on the vehicle deployment results and the biological deployment results, determine whether the identification feature value matches the first deployment task.

7. The method according to any one of claims 1 to 6, characterized in that, The step of pushing corresponding alarm information to the receiving end of the monitored target object includes: Establish a result topic queue in the preset messaging system to store alarm information; Based on the alarm information obtained from subscribing to the result topic queue, the corresponding alarm information is pushed to the receiving end.

8. A deployment and control device, characterized in that, include: The first determining module is used to determine the associated objects that have a predetermined relationship with the target object based on the identity information of the target object; The second determining module is used to determine a first deployment task for the target object based on the association feature value of the associated object, wherein the association feature value is the first biometric value and / or the first vehicle feature value of the associated object, and the first deployment task is determined based on the association feature value and the target feature value, wherein the target feature value is the first biometric value and / or the first vehicle feature value of the target object. The recognition module is used to process the video stream for recognition and obtain recognition feature values; The alarm module is used to push corresponding alarm information to the receiving end of the target object when the identification feature value matches the first deployment task; The device is further configured to, before determining the associated object with a predetermined relationship to the target object based on the target object's identity information, determine whether the target object's identity information has been obtained; if the target object's identity information has not been obtained, determine whether the target object's license plate number has been obtained; if the target object's license plate number has not been obtained, do not determine the associated object, and obtain at least one captured image including the target object; perform recognition processing on the at least one captured image to obtain the target object's collection feature value and the second deployment task corresponding to the collection feature value, wherein the collection feature value is at least the target object's first biometric feature value and / or first vehicle feature value; and push corresponding alarm information to the receiving end when the recognition feature value matches the second deployment task.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions, which are adapted to be loaded by a processor and executed by the deployment method according to any one of claims 1 to 7.

Images