阅读说明：本技术 基于激光雷达的主动安全靠机控制方法及系统 (Active safety backup control method and system based on laser radar ) 是由 李懋 霍进刚 于 2021-08-18 设计创作，主要内容包括：本发明实施例提供了一种基于激光雷达的主动安全靠机控制方法及系统,对可学习目标基础检测障碍特征通过预设主动安全靠机程序的关键靠机启用节点对应的目标基础检测障碍特征进行特征学习应用,记录靠机模拟行为的行为流程信息以及靠机模拟行为的行为持续特征向量,而后通过靠机模拟行为的行为持续特征向量以及多个靠机启用节点的基础检测障碍特征信息进行计算,并计算靠机模拟行为的模拟程序指令的模拟调用指令集,从而通过靠机模拟行为的行为流程信息、行为持续特征向量以及模拟调用指令集在多个靠机启用节点信息中加载靠机模拟行为的关键数据提取。如此,考虑到靠机模拟行为与目标基础检测障碍特征之间的关系,能够提高靠机逻辑优化效率。(The embodiment of the invention provides an active safety on-machine control method and system based on a laser radar, which are used for carrying out feature learning application on learnable target basic detection obstacle features through target basic detection obstacle features corresponding to key on-machine starting nodes of a preset active safety on-machine program, recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors, then calculating through the behavior continuous feature vectors of the simulated behaviors and the basic detection obstacle feature information of a plurality of on-machine starting nodes, and calculating a simulation calling instruction set of simulation program instructions of the simulated behaviors, so that key data of the simulated behaviors are loaded in the information of the plurality of on-machine starting nodes through the behavior flow information of the simulated behaviors, the behavior continuous feature vectors and the simulation calling instruction set for extraction. Therefore, the optimization efficiency of the machine-dependent logic can be improved by considering the relation between the simulated behavior and the target basis obstacle detection characteristics.)

1. An active safety leaning machine control method based on laser radar is applied to an active safety leaning machine control system, and the method comprises the following steps:

the method comprises the steps of obtaining a plurality of safe machine-dependent process data of active safe machine-dependent activities based on a laser radar, and obtaining a plurality of machine-dependent starting node information and basic detection obstacle characteristic information of a plurality of machine-dependent starting nodes from the plurality of safe machine-dependent process data;

determining target basic detection obstacle features corresponding to key machine-dependent enabling nodes from the plurality of pieces of machine-dependent enabling node information, and acquiring learnable target basic detection obstacle features according to the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes;

performing feature learning application on the target basic detection obstacle features corresponding to the key computer-aided starting node of the learnable active computer-aided program, and recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors;

calculating through the behavior persistence feature vector of the simulated behavior and the basic detection obstacle feature information of the plurality of computer-aided enabled nodes, respectively activating the simulated behavior of the target, and calculating a simulation calling instruction set of simulation program instructions of the simulated behavior;

and loading key data extraction of the simulated behavior in the plurality of pieces of computer-dependent enabled node information through the behavior flow information of the computer-dependent behavior, the behavior persistence feature vector of the computer-dependent behavior and the simulation calling instruction set of the simulation program instruction of the computer-dependent behavior so as to perform computer-dependent logic optimization on the active safety computer-dependent activities.

2. The method of claim 1, wherein obtaining learnable target base detection obstacle features from target base detection obstacle features corresponding to the key airplane activation nodes comprises:

and inputting the target basic detection obstacle features corresponding to the key start-up nodes into a set AI model, and acquiring the non-learnable target basic detection obstacle features and the learnable target basic detection obstacle features.

3. The method according to claim 2, wherein the setting AI model is obtained by deep learning mining of a first example sample cluster and a second example sample cluster which are obtained in advance and generated in real time, and specifically comprises:

and performing feature mining on the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes of the simulated behaviors and the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes of the non-simulated behaviors based on the first example sample cluster and the second example sample cluster, determining the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes of the simulated behaviors and the non-simulated behaviors, and training based on the target basic detection obstacle features to obtain the set AI model.

4. The method of claim 3, wherein determining a target basis detection obstacle feature corresponding to a key enabled-by-machine node from the plurality of enabled-by-machine node information comprises:

and performing target basic detection obstacle feature matching on the enabled node vector set of each enabled node by the machine in the plurality of pieces of enabled node information to obtain target basic detection obstacle features corresponding to key enabled nodes of the enabled node vector set of each enabled node by the machine.

5. The method according to claim 4, wherein the applying of feature learning to the target basis detection obstacle feature corresponding to the key vehicle-dependent activation node of the preset active vehicle-dependent security program to record the behavior flow information of the simulated behavior and the behavior persistence feature vector of the simulated behavior comprises:

analyzing the target basic detection obstacle features corresponding to the determined key on-machine enabled nodes of the on-machine behavior, performing feature learning application on the target basic detection obstacle features corresponding to the key on-machine enabled nodes among enabled node vector sets of different on-machine enabled nodes, determining enabled node vector sets of the on-machine behavior at each on-machine enabled node, and recording behavior flow information of the on-machine behavior and behavior continuation feature vectors of the on-machine behavior.

6. An active safety leaning machine control system based on laser radar is characterized in that the active safety leaning machine control system is applied to the active safety leaning machine control system, and the system comprises:

the system comprises an acquisition module, a detection module and a processing module, wherein the acquisition module is used for acquiring a plurality of safe machine-dependent process data of active safe machine-dependent activities based on a laser radar, and acquiring a plurality of machine-dependent starting node information and basic detection obstacle characteristic information of a plurality of machine-dependent starting nodes from the plurality of safe machine-dependent process data;

the determining module is used for determining target basic detection obstacle features corresponding to key machine-dependent enabling nodes from the plurality of pieces of machine-dependent enabling node information and acquiring learnable target basic detection obstacle features according to the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes;

the recording module is used for carrying out feature learning application on the target basic detection obstacle features corresponding to the key computer-dependent starting node of the learnable target basic detection obstacle features through a preset active computer-dependent program, and recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors;

the calculation module is used for calculating through the behavior persistence feature vector of the on-simulation behavior and the basic detection obstacle feature information of the plurality of on-computer enabled nodes, respectively activating the target on-simulation behavior, and calculating a simulation calling instruction set of simulation program instructions of the on-simulation behavior;

and the loading module is used for loading the key data extraction of the simulated behavior in the plurality of pieces of computer-dependent enabled node information through the behavior flow information of the computer-dependent behavior, the behavior persistence characteristic vector of the computer-dependent behavior and the simulation calling instruction set of the simulation program instruction of the computer-dependent behavior so as to carry out computer-dependent logic optimization on the active safety computer-dependent activity.

7. The system of claim 6, wherein the determination module is specifically configured to:

and inputting the target basic detection obstacle features corresponding to the key start-up nodes into a set AI model, and acquiring the non-learnable target basic detection obstacle features and the learnable target basic detection obstacle features.

8. The system according to claim 7, wherein the set AI model is obtained by deep learning mining of a first example sample cluster and a second example sample cluster obtained in advance and generated in real time, and specifically includes:

and performing feature mining on the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the key on-machine starting nodes of the non-simulated behaviors, determining the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the non-simulated behaviors, and training based on the target basic detection obstacle features to obtain the set AI model.

9. The system of claim 8, wherein the determination module is specifically configured to:

and performing target basic detection obstacle feature matching on the enabled node vector set of each enabled node by the machine in the plurality of pieces of enabled node information to obtain target basic detection obstacle features corresponding to key enabled nodes of the enabled node vector set of each enabled node by the machine.

10. The system of claim 9, wherein the recording module is specifically configured to:

analyzing the target basic detection obstacle features corresponding to the determined key on-machine enabled nodes of the on-machine behavior, performing feature learning application on the target basic detection obstacle features corresponding to the key on-machine enabled nodes among enabled node vector sets of different on-machine enabled nodes, determining enabled node vector sets of the on-machine behavior at each on-machine enabled node, and recording behavior flow information of the on-machine behavior and behavior continuation feature vectors of the on-machine behavior.

Technical Field

The invention relates to the technical field of active safety, in particular to a method and a system for controlling an active safety backup machine based on a laser radar.

Background

At present, in the process of carrying out the mechanical-dependent logic optimization on the active safety mechanical activity, the relation between some simulated behaviors and the target basic detection obstacle characteristics is not considered, so that the mechanical-dependent logic optimization efficiency of the active safety mechanical activity is not high.

Disclosure of Invention

In view of this, an object of the embodiments of the present invention is to provide a method and a system for controlling an active security backup based on a laser radar, which can effectively improve the backup logic optimization efficiency of active security backup activities.

In a first aspect, an embodiment of the present invention provides an active security backup control method based on a laser radar, which is applied to an active security backup control system, and the method includes:

the method comprises the steps of obtaining a plurality of safe machine-dependent process data of active safe machine-dependent activities based on a laser radar, and obtaining a plurality of machine-dependent starting node information and basic detection obstacle characteristic information of a plurality of machine-dependent starting nodes from the plurality of safe machine-dependent process data;

determining target basic detection obstacle features corresponding to key machine-dependent enabling nodes from the plurality of pieces of machine-dependent enabling node information, and acquiring learnable target basic detection obstacle features according to the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes;

performing feature learning application on the target basic detection obstacle features corresponding to the key computer-aided starting node of the learnable active computer-aided program, and recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors;

calculating through the behavior persistence feature vector of the simulated behavior and the basic detection obstacle feature information of the plurality of computer-aided enabled nodes, respectively activating the simulated behavior of the target, and calculating a simulation calling instruction set of simulation program instructions of the simulated behavior;

and loading the key data extraction of the simulated behavior in the plurality of the on-board enabled node information through the behavior flow information of the on-board simulated behavior, the behavior persistence feature vector of the on-board simulated behavior and the simulation calling instruction set of the simulation program instruction of the on-board simulated behavior.

Wherein, the obtaining of learnable target basis detection obstacle features according to the target basis detection obstacle features corresponding to the key machine-dependent activation node comprises:

and inputting the target basic detection obstacle features corresponding to the key start-up nodes into a set AI model, and acquiring the non-learnable target basic detection obstacle features and the learnable target basic detection obstacle features.

The setting AI model is obtained by deep learning and mining through a first example sample cluster and a second example sample cluster which are obtained in advance and generated in real time, and specifically comprises the following steps:

and performing feature mining on the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the key on-machine starting nodes of the non-simulated behaviors, determining the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the non-simulated behaviors, and training to obtain the set AI model.

Wherein the determining the target basis detection obstacle feature corresponding to the key machine-dependent enabled node from the plurality of machine-dependent enabled node information comprises:

and performing target basic detection obstacle feature matching on the enabled node vector set of each enabled node by the machine in the plurality of pieces of enabled node information to obtain target basic detection obstacle features corresponding to key enabled nodes of the enabled node vector set of each enabled node by the machine.

The method for performing feature learning application on the target basis detection obstacle features corresponding to the key computer-aided starting node of the learnable target basis detection obstacle features through the preset active computer-aided program, and recording behavior flow information of simulated behaviors and behavior persistence feature vectors of the simulated behaviors includes:

analyzing the target basic detection obstacle features corresponding to the determined key on-machine enabled nodes of the on-machine behavior, performing feature learning application on the target basic detection obstacle features corresponding to the key on-machine enabled nodes among enabled node vector sets of different on-machine enabled nodes, determining enabled node vector sets of the on-machine behavior at each on-machine enabled node, and recording behavior flow information of the on-machine behavior and behavior continuation feature vectors of the on-machine behavior.

In another aspect, an embodiment of the present invention further provides an active safety backup control system based on a laser radar, which is applied to the active safety backup control system, and the system includes:

the system comprises an acquisition module, a detection module and a processing module, wherein the acquisition module is used for acquiring a plurality of safe machine-dependent process data of active safe machine-dependent activities based on a laser radar, and acquiring a plurality of machine-dependent starting node information and basic detection obstacle characteristic information of a plurality of machine-dependent starting nodes from the plurality of safe machine-dependent process data;

the determining module is used for determining target basic detection obstacle features corresponding to key machine-dependent enabling nodes from the plurality of pieces of machine-dependent enabling node information and acquiring learnable target basic detection obstacle features according to the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes;

the recording module is used for carrying out feature learning application on the target basic detection obstacle features corresponding to the key computer-dependent starting node of the learnable target basic detection obstacle features through a preset active computer-dependent program, and recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors;

the calculation module is used for calculating through the behavior persistence feature vector of the on-simulation behavior and the basic detection obstacle feature information of the plurality of on-computer enabled nodes, respectively activating the target on-simulation behavior, and calculating a simulation calling instruction set of simulation program instructions of the on-simulation behavior;

and the loading module is used for loading the key data extraction of the simulated behavior in the plurality of the computer-aided enabled node information through the behavior flow information of the simulated behavior, the behavior persistence characteristic vector of the simulated behavior and the simulation calling instruction set of the simulation program instruction of the simulated behavior.

The active safety on-machine control method and system based on the laser radar, provided by the embodiment of the invention, determine the target basic detection obstacle characteristics corresponding to the key on-machine starting node from the information of the plurality of on-machine starting nodes, acquire the learnable target basic detection obstacle characteristics according to the target basic detection obstacle characteristics corresponding to the key on-machine starting node, then perform characteristic learning application on the learnable target basic detection obstacle characteristics through the target basic detection obstacle characteristics corresponding to the key on-machine starting node of a preset active safety on-machine program, record the behavior flow information of the on-machine simulation behavior and the behavior continuation characteristic vector of the on-machine simulation behavior, then respectively activate the on-machine simulation behavior by calculating the behavior continuation characteristic vector of the on-machine simulation behavior and the basic detection obstacle characteristic information of the plurality of on-machine starting nodes, and a simulation calling instruction set of a simulation program instruction of the simulated behavior is calculated, so that the critical data extraction of the simulated behavior is loaded in the information of the plurality of computer-dependent enabled nodes through the behavior flow information, the behavior persistence characteristic vector and the simulation calling instruction set of the simulated behavior, and the computer-dependent logic optimization is carried out on the active safety computer-dependent activities. Therefore, the dependence logic optimization efficiency of active safety dependence on the aircraft activity can be effectively improved by considering the relation between the dependence on the simulated behavior and the target basic detection obstacle characteristics.

In order to make the aforementioned objects, features and advantages of the embodiments of the present invention comprehensible, embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a schematic flow chart illustrating a method for controlling an active safety device based on a lidar according to an embodiment of the present invention;

fig. 2 shows a functional block diagram of an active safety device control system based on lidar according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood by the scholars in the technical field, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The terms "first," "second," "third," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic flowchart illustrating a method for controlling an active safety device based on a lidar according to an embodiment of the present invention, where the method may be performed by an active safety device control system.

The active safety relying machine control system may comprise one or more processors, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The active safety device control system may also include any storage medium for storing any kind of information such as code, settings, data, etc. For example, and without limitation, the storage medium may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent fixed or removable components of an active safety device control system. In one case, when the processor executes the associated instructions stored in any storage medium or combination of storage media, the active reclining control system can perform any of the operations of the associated instructions. The active safety device control system further comprises one or more drive units for interacting with any storage medium, such as a hard disk drive unit, an optical disk drive unit, etc.

The active safety recliner control system also includes an input/output (I/O) for receiving various inputs (via the input unit) and for providing various outputs (via the output unit). One particular output mechanism may include a presentation device and an associated Graphical User Interface (GUI). The active safety reclining control system may also include one or more network interfaces for exchanging data with other devices via one or more communication units. One or more communication buses couple the above-described components together.

The communication unit may be implemented in any manner, e.g., over a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication unit may comprise any combination of hardwired links, wireless links, routers, gateway functions, named active security relying control systems, etc., governed by any protocol or combination of protocols.

The detailed steps of the active safety backup control method based on the laser radar are described below

Step 100, obtaining a plurality of safe machine-dependent process data of active safe machine-dependent activities based on the laser radar, and obtaining a plurality of machine-dependent starting node information and basic detection obstacle feature information of a plurality of machine-dependent starting nodes from the plurality of safe machine-dependent process data.

Step 200, determining target basic detection obstacle features corresponding to key machine-dependent enabling nodes from the plurality of pieces of machine-dependent enabling node information, and acquiring learnable target basic detection obstacle features according to the target basic detection obstacle features corresponding to the key machine-dependent enabling nodes.

And 300, performing feature learning application on the target basic detection obstacle features corresponding to the key computer-aided starting nodes of the learnable active computer-aided program, and recording behavior flow information of simulated behaviors and behavior continuous feature vectors of the simulated behaviors.

Step 400, calculating through the behavior persistence feature vector of the on-device simulation behavior and the basic detection obstacle feature information of the plurality of on-device activation nodes, respectively activating the target on-device simulation behavior, and calculating a simulation calling instruction set of simulation program instructions of the on-device simulation behavior.

Step 500, loading the key data of the simulated behavior in the plurality of pieces of machine-dependent enabled node information through the behavior flow information of the simulated behavior, the behavior persistence feature vector of the simulated behavior, and the simulation calling instruction set of the simulation program instruction of the simulated behavior, and extracting.

To sum up, in the present embodiment, a target basic detection obstacle feature corresponding to a key computer-aided enabled node is determined from a plurality of computer-aided enabled node information, a learnable target basic detection obstacle feature is obtained according to the target basic detection obstacle feature corresponding to the key computer-aided enabled node, then a feature learning application is performed on the learnable target basic detection obstacle feature through the target basic detection obstacle feature corresponding to the key computer-aided enabled node of a preset active computer-aided program, behavior flow information of a computer-aided behavior and a behavior continuation feature vector of the computer-aided behavior are recorded, then the behavior continuation feature vector simulated by the computer-aided behavior and the basic detection obstacle feature information of the plurality of computer-aided enabled nodes are calculated, the target computer-aided behavior is activated respectively, and a simulation call instruction set of a simulation program instruction of the computer-aided behavior is calculated, and loading the key data extraction of the simulated behavior in the plurality of pieces of machine-dependent enabled node information through the behavior flow information, the behavior persistence feature vector and the simulation calling instruction set of the simulated behavior. Therefore, the optimization efficiency of the machine-dependent logic can be improved by considering the relation between the simulated behavior and the target basis obstacle detection characteristics.

Specifically, in step 200, the target basic detection obstacle feature corresponding to the key machine-dependent activation node may be input into a set AI model to obtain the non-learnable target basic detection obstacle feature and the learnable target basic detection obstacle feature.

The set AI model is obtained by performing deep learning excavation on a first example sample cluster and a second example sample cluster which are obtained in advance and generated in real time, for example, feature excavation may be performed on target basis detection obstacle features corresponding to key machine-dependent activation nodes of each simulated behavior and target basis detection obstacle features corresponding to key machine-dependent activation nodes of non-simulated behavior, and target basis detection obstacle features corresponding to key machine-dependent activation nodes of the simulated behavior and the non-simulated behavior are determined to obtain the set AI model through training.

In step 200, the present embodiment may specifically perform target basis detection obstacle feature matching on the enabled node vector set of each enabled node in the plurality of pieces of enabled-node-by-machine information, so as to obtain a target basis detection obstacle feature corresponding to the key enabled-by-machine node in the enabled node vector set of each enabled-by-machine node.

In step 300, the embodiment may specifically analyze the target basic detection obstacle features corresponding to the determined key on-machine enabled nodes of the on-machine behavior, perform feature learning application on the target basic detection obstacle features corresponding to the key on-machine enabled nodes among the enabled node vector sets of different on-machine enabled nodes, determine the enabled node vector sets of the on-machine behavior at each on-machine enabled node, and record behavior flow information of the on-machine behavior and the behavior continuation feature vectors of the on-machine behavior.

Fig. 2 is a functional block diagram of an active safety reclining control system based on a laser radar according to an embodiment of the present invention, where the functions implemented by the active safety reclining control system based on a laser radar may correspond to the steps executed by the foregoing method. The active safety leaning machine control system based on the laser radar can be understood as the active safety leaning machine control system or a processor of the active safety leaning machine control system, and can also be understood as a component which is independent from the active safety leaning machine control system or the processor and realizes the functions of the active safety leaning machine control system under the control of the active safety leaning machine control system, and the functions of all functional modules of the active safety leaning machine control system based on the laser radar are explained in detail below.

The obtaining module 201 is configured to obtain multiple pieces of safe machine-dependent process data of active safe machine-dependent activities based on the laser radar, and obtain multiple pieces of machine-dependent enabled node information and basic detection obstacle feature information of multiple machine-dependent enabled nodes from the multiple pieces of safe machine-dependent process data.

A determining module 202, configured to determine, from the plurality of pieces of machine-dependent enabled node information, a target basis detection obstacle feature corresponding to a key machine-dependent enabled node, and obtain a learnable target basis detection obstacle feature according to the target basis detection obstacle feature corresponding to the key machine-dependent enabled node.

The recording module 203 is configured to perform feature learning application on the target basis detection obstacle feature corresponding to the key computer-aided activation node of the preset active computer-aided program on the learnable target basis detection obstacle feature, and record behavior flow information of the simulated behavior and a behavior persistence feature vector of the simulated behavior.

The calculation module 204 is configured to calculate, through the behavior persistence feature vector of the on-device simulation behavior and the basic detection obstacle feature information of the multiple on-device activation nodes, respectively activate the target on-device simulation behavior, and calculate a simulation call instruction set of a simulation program instruction of the on-device simulation behavior.

A loading module 205, configured to load the critical data extraction of the simulated behavior in the plurality of machine-dependent enabled node information through the behavior flow information of the simulated behavior, the behavior persistence feature vector of the simulated behavior, and the simulation call instruction set of the simulation program instruction of the simulated behavior.

Wherein the determining module 202 obtains the learnable target basis detection obstacle feature by:

and inputting the target basic detection obstacle features corresponding to the key start-up nodes into a set AI model, and acquiring the non-learnable target basic detection obstacle features and the learnable target basic detection obstacle features.

The set AI model is obtained by deep learning and mining of a first example sample cluster and a second example sample cluster which are obtained in advance and generated in real time, and the specific mode comprises the following steps:

and performing feature mining on the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the key on-machine starting nodes of the non-simulated behaviors, determining the target basic detection obstacle features corresponding to the key on-machine starting nodes of the simulated behaviors and the non-simulated behaviors, and training to obtain the set AI model.

Wherein, the method for determining the target basic detection obstacle feature corresponding to the key machine-dependent enabling node from the plurality of machine-dependent enabling node information comprises the following steps:

and performing target basic detection obstacle feature matching on the enabled node vector set of each enabled node by the machine in the plurality of pieces of enabled node information to obtain target basic detection obstacle features corresponding to key enabled nodes of the enabled node vector set of each enabled node by the machine.

The recording module 203 may perform feature learning application on the target basis detection obstacle feature corresponding to the key computer-aided activation node of the preset active computer-aided safety program on the learnable target basis detection obstacle feature in the following manner, and record behavior flow information of simulated behaviors and behavior persistence feature vectors of the simulated behaviors:

analyzing the target basic detection obstacle features corresponding to the determined key on-machine enabled nodes of the on-machine behavior, performing feature learning application on the target basic detection obstacle features corresponding to the key on-machine enabled nodes among enabled node vector sets of different on-machine enabled nodes, determining enabled node vector sets of the on-machine behavior at each on-machine enabled node, and recording behavior flow information of the on-machine behavior and behavior continuation feature vectors of the on-machine behavior.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

Alternatively, all or part of the implementation may be in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, active security console system, or data center to another website site, computer, active security console system, or data center via wire (e.g., coaxial cable, fiber optics, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device including one or more integrated active safety systems, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any drawing credit or debit acknowledgement in the claims should not be construed as limiting the claim concerned.