CN113963415A

CN113963415A - Personnel dangerous behavior analysis method, system, device and medium

Info

Publication number: CN113963415A
Application number: CN202111265936.3A
Authority: CN
Inventors: 王�华; 李峰
Original assignee: Chongqing Zhongke Yuncong Technology Co ltd
Current assignee: Chongqing Zhongke Yuncong Technology Co ltd
Priority date: 2021-10-28
Filing date: 2021-10-28
Publication date: 2022-01-21

Abstract

The invention relates to the technical field of security protection, and particularly provides a method, a system, a device and a medium for analyzing dangerous behaviors of people, aiming at solving the problem that the conventional management and control mode cannot timely and effectively early warn the dangerous behaviors and the dangerous information without specific dangerous actions. For this purpose, the method for analyzing dangerous behaviors of people can acquire images containing faces and environments where people are located, respectively perform face recognition and character recognition on the images, analyze whether dangerous behaviors exist in the people according to the face recognition result and the character recognition result, recognize specific positions, special identifications, dangerous information and the like of the people corresponding to the face recognition result according to the character recognition result, further analyze whether dangerous behaviors exist in the people corresponding to the face recognition result, form complete and accurate clues, and facilitate effective early warning of dangerous behaviors and dangerous information without dangerous actions by a management and control mechanism.

Description

Personnel dangerous behavior analysis method, system, device and medium

Technical Field

The invention relates to the technical field of security and protection, and particularly provides a method, a system, a device and a medium for analyzing dangerous behaviors of people.

Background

With the continuous development of security and protection technology and artificial intelligence technology, the construction of safe cities becomes a current hot topic. The effective utilization of the massive video resources acquired by the security equipment is an important trend in the development of the security industry. At present, a management and control mechanism mainly manages and controls dangerous behaviors and dangerous information by applying video resources acquired by security and protection equipment in a mode of studying and judging after the fact. Although there is a management and control method for performing pre-warning management on some action behaviors by using video resources acquired by security equipment, the management and control method only considers the action behaviors recorded in the video, and can perform pre-warning after analyzing that the action behaviors are dangerous actions such as gun holding actions, but cannot perform pre-warning in time and accurately when there is no specific dangerous action but still a danger. For example, after the management and control personnel appear in the management and control site, although specific dangerous actions are not shown, dangerous behaviors are likely to be generated, and at the moment, early warning is also needed, but the early warning cannot be timely and accurately performed by adopting the management and control mode.

Accordingly, there is a need in the art for a new analysis scheme for dangerous behavior of persons to solve the above problems.

Disclosure of Invention

In order to overcome the defects, the invention is provided to solve or partially solve the problem that the conventional management and control mode cannot timely and effectively pre-alarm dangerous behaviors and dangerous information without specific dangerous actions.

In a first aspect, the present invention provides a method for analyzing dangerous behavior of a person, the method comprising:

acquiring an image which simultaneously contains the human face of a person and the environment where the person is located;

respectively carrying out face recognition and character recognition on the image to obtain a face recognition result and a character recognition result;

and analyzing whether dangerous behaviors exist in the personnel or not according to the face recognition result and the character recognition result.

In one technical solution of the above method for analyzing dangerous behaviors of people, the step of analyzing whether dangerous behaviors exist in the people according to the face recognition result and the character recognition result specifically includes:

judging whether the personnel is a preset management and control personnel or not according to the face recognition result;

when the personnel is the management and control personnel, judging whether dangerous information related to dangerous behaviors exists in the environment where the personnel is located according to the character recognition result;

and when the dangerous information exists, judging whether the management and control personnel have dangerous behaviors according to the dangerous information.

In one technical solution of the above method for analyzing dangerous behaviors of people, the dangerous information includes a location name of a preset control location and/or preset control information, and the step of determining whether the control personnel has a dangerous behavior according to the dangerous information specifically includes:

acquiring position information of image acquisition equipment for acquiring the image and time information for acquiring the image;

and judging whether dangerous behaviors exist in the control personnel according to the position information, the time information and the dangerous information.

In one technical solution of the above method for analyzing dangerous behaviors of people, the step of "determining whether the manager has a dangerous behavior according to the position information, the time information, and the danger information" includes:

setting an early warning rule of the dangerous behavior;

analyzing the position information, the time information and danger information existing in the environment where the control personnel are located according to the early warning rule;

judging whether dangerous behaviors exist in the management and control personnel according to the analysis result;

wherein the early warning rules include:

if the control personnel appear in a preset control place, dangerous behaviors exist; and/or if the frequency of the management and control personnel appearing in the management and control place exceeds a preset frequency threshold, dangerous behaviors exist; and/or if the danger information contains preset management and control information, dangerous behaviors exist;

and/or the image acquisition equipment comprises fixedly arranged image acquisition equipment and image acquisition equipment arranged on the movable object.

In one technical solution of the above method for analyzing dangerous behaviors of people, before the step of "analyzing whether dangerous behaviors exist in the people according to the face recognition result and the character recognition result", the method further includes:

judging whether dangerous information related to dangerous behavior exists in the environment where the personnel are located according to the character recognition result;

when the dangerous information exists in the environment, directly judging that the personnel has dangerous behaviors;

and/or the step of respectively carrying out face recognition and character recognition on the image to obtain a face recognition result and a character recognition result comprises the following steps:

extracting the face feature information of the image, and obtaining the face recognition result according to the face feature information;

performing character recognition on the image, and extracting character information in the image;

and performing semantic recognition on the character information by applying a semantic recognition technology, and obtaining the character recognition result according to the result of the semantic recognition, or performing word segmentation on the character information by applying a word segmentation tool, and obtaining the character recognition result according to the result of the word segmentation.

In a second aspect, the present invention provides a personnel hazardous behaviour analysis system, the system comprising:

the image acquisition module is configured to acquire an image which simultaneously contains the human face of the person and the environment where the person is located;

the face and character recognition module is configured to perform face recognition and character recognition on the image respectively to obtain a face recognition result and a character recognition result;

and the dangerous behavior analysis module is configured to analyze whether dangerous behaviors exist in the personnel according to the face recognition result and the character recognition result.

In one embodiment of the above personnel dangerous behavior analysis system, the dangerous behavior analysis module includes:

a control personnel judgment sub-module configured to judge whether the personnel is a preset control personnel according to the face recognition result;

the danger information judgment sub-module is configured to judge whether danger information related to dangerous behaviors exists in the environment where the personnel are located according to the character recognition result when the personnel are the management and control personnel;

and the dangerous behavior judgment submodule is configured to judge whether dangerous behaviors exist in the management and control personnel according to the dangerous information when the dangerous information exists.

In one technical solution of the above personnel dangerous behavior analysis system, the dangerous information includes a location name of a preset control location and/or preset control information, and the dangerous behavior determining submodule includes:

a position and time information acquisition unit configured to acquire position information of an image acquisition apparatus that acquires the image and time information of acquisition of the image;

and a dangerous behavior judging unit configured to judge whether dangerous behaviors exist in the management and control personnel according to the position information, the time information and the dangerous information.

In one embodiment of the above personnel dangerous behavior analysis system, the dangerous behavior determination unit includes:

an early warning rule setting subunit configured to set an early warning rule of the dangerous behavior;

a danger information analysis subunit configured to analyze the position information, the time information, and danger information existing in an environment where the management and control person is located according to the early warning rule;

a dangerous behavior judgment subunit configured to judge whether the management and control personnel has dangerous behaviors according to the analysis result;

wherein the early warning rules include:

In one technical solution of the above personnel dangerous behavior analysis system, the system further includes a dangerous behavior related information determining module, and the dangerous behavior related information determining module is configured to execute the following steps:

and/or, the face and character recognition module comprises:

a face recognition result obtaining sub-module configured to extract face feature information of the image and obtain the face recognition result according to the face feature information;

the character information extraction sub-module is configured to perform character recognition on the image and extract character information in the image;

and the character recognition result acquisition sub-module is configured to apply a semantic recognition technology to carry out semantic recognition on the character information, obtain the character recognition result according to the result of the semantic recognition, or apply a word segmentation tool to carry out word segmentation on the character information, and obtain the character recognition result according to the result of the word segmentation.

In a third aspect, a control device is provided, which comprises a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, and the program codes are suitable for being loaded and executed by the processor to execute the personnel dangerous behavior analysis method according to any one of the above-mentioned technical solutions of the personnel dangerous behavior analysis method.

In a fourth aspect, a computer readable storage medium is provided, having stored therein a plurality of program codes adapted to be loaded and run by a processor to perform the method of human risk behavior analysis according to any one of the above-mentioned aspects.

One or more technical schemes of the invention have at least one or more of the following beneficial effects:

in the technical scheme of the invention, the image which simultaneously contains the face of the person and the environment of the person can be obtained, the face recognition and the character recognition are respectively carried out on the image, and whether the person has dangerous behaviors or not is further analyzed according to the face recognition result and the character recognition result. Through the configuration mode, the character recognition result of the environment where the person is located can be obtained through character recognition, whether the person corresponding to the face recognition result appears in a control place or not can be recognized according to the character recognition result, whether control information exists in the environment where the person is located or not, whether dangerous information related to dangerous behaviors exists in the environment where the person is located or not and the like can be recognized, whether dangerous behaviors exist in the person corresponding to the face recognition result or not can be analyzed according to the content, and therefore complete and accurate clue information is formed, and effective early warning processing can be timely achieved when various dangerous behaviors and dangerous information without specific dangerous actions by a control mechanism.

Drawings

The disclosure of the present invention will become more readily understood with reference to the accompanying drawings. As will be readily understood by those skilled in the art: these drawings are for illustrative purposes only and are not intended to constitute a limitation on the scope of the present invention. Wherein:

FIG. 1 is a schematic flow chart of the main steps of a method for analyzing dangerous behavior of people according to one embodiment of the present invention;

FIG. 2 is a main block diagram of a personnel hazardous behavior analysis system according to one embodiment of the invention;

fig. 3 is a flow chart illustrating main steps of a method for analyzing dangerous behaviors of people according to an embodiment of the present invention.

Detailed Description

Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.

In the description of the present invention, a "module" or "processor" may include hardware, software, or a combination of both. A module may comprise hardware circuitry, various suitable sensors, communication ports, memory, may comprise software components such as program code, or may be a combination of software and hardware. The processor may be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and/or signal processing functionality. The processor may be implemented in software, hardware, or a combination thereof. Non-transitory computer readable storage media include any suitable medium that can store program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random-access memory, and the like. The term "a and/or B" denotes all possible combinations of a and B, such as a alone, B alone or a and B. The term "at least one A or B" or "at least one of A and B" means similar to "A and/or B" and may include only A, only B, or both A and B. The singular forms "a", "an" and "the" may include the plural forms as well.

Referring to fig. 1, fig. 1 is a schematic flow chart of main steps of a personnel dangerous behavior analysis method according to an embodiment of the invention. As shown in fig. 1, the method for analyzing human risk behavior in the embodiment of the present invention mainly includes the following steps S101 to S103.

Step S101: and acquiring an image simultaneously containing the human face of the person and the environment where the person is located.

In this embodiment, an image including both the face of the person and the environment in which the person is located can be obtained.

In one embodiment, the image including the face of the person and the environment where the person is located may be an image acquired by an image acquisition device, and the image may include face snapshot data of the person and image data of the environment where the person is located.

In one embodiment, the image capturing device may include a fixedly disposed image capturing device and an image capturing device disposed on the movable object. If the image acquisition equipment can be security monitoring cameras arranged at all places in a city, fixedly arranged human face bayonet monitoring equipment, bayonet snapshot equipment arranged on a vehicle, snapshot equipment arranged on a taxi and the like.

In one embodiment, the image may be an image acquired by an image acquisition device, an image acquired by an offline video file, or an image acquired by a network picture.

Step S102: and respectively carrying out face recognition and character recognition on the image to obtain a face recognition result and a character recognition result.

In this embodiment, face recognition may be performed on the image acquired in step S101 to acquire a face recognition result, and character recognition may be performed on the image acquired in step S101 to acquire a character recognition result. It should be noted that, in this embodiment, a face recognition method and a character recognition method, which are conventional in the field of image processing technology, may be adopted to perform face recognition and character recognition on an image respectively, so as to obtain a face recognition result and a character recognition result.

Step S103: and analyzing whether the personnel have dangerous behaviors or not according to the face recognition result and the character recognition result.

In this embodiment, the face recognition result and the character recognition result acquired in step S102 may be analyzed to determine whether a person corresponding to the face recognition result has a dangerous behavior.

Based on the steps S101 to S103, the present invention can acquire the image including the face of the person and the environment where the person is located, and perform face recognition and character recognition on the image, respectively, and further analyze whether the person has dangerous behaviors according to the face recognition result and the character recognition result. Through the configuration mode, the character recognition result of the environment where the person is located can be obtained through character recognition, whether the person corresponding to the face recognition result appears in a control place or not can be recognized according to the character recognition result, whether control information exists in the environment where the person is located or not, whether dangerous information related to dangerous behaviors exists in the environment where the person is located or not can be recognized, whether the person corresponding to the face recognition result has the dangerous behaviors or not can be further analyzed according to the content, and therefore complete and accurate clue information is formed, and therefore timely and effective early warning processing can be conducted on various dangerous behaviors and dangerous information without specific dangerous actions by a control mechanism.

Step S102 and step S103 will be further described below.

In one implementation manner of the embodiment of the present invention, the step S102 may further include the following steps:

step S1021: and extracting the face characteristic information of the image, and obtaining a face recognition result according to the face characteristic information.

In this embodiment, the face feature information in the image acquired in step S101 may be extracted, and a face recognition result may be acquired according to the face feature information.

Step S1022: and performing character recognition on the image, and extracting character information in the image.

In the present embodiment, character recognition may be performed on the image acquired in step S101 to extract character information in the image.

In one embodiment, the text information in the image may be extracted by using an OCR (Optical Character Recognition) Recognition method.

Step S1023: and performing semantic recognition on the character information by applying a semantic recognition technology, and obtaining a character recognition result according to a semantic recognition result.

In this embodiment, a semantic recognition technology may be applied to perform named entity recognition on the text information obtained in step S1022, obtain entities in the text information, further obtain entity relationships between the entities, generate structured data corresponding to the text information according to the entities and the entity relationships, and use the structured data as a text recognition result. Among them, the semantic recognition technology is a technology for realizing effective communication between a person and a computer by using a natural language. Named entity recognition is a basic task in semantic recognition technology, i.e. recognizing entities with specific meaning or strong reference in text. And after the named entities are identified, the relationship between the entities can be further extracted to obtain the entity relationship between the entities.

In one embodiment, the entity relationship may include attribute classification of the entity, and if the entity obtained by semantic recognition according to the text information includes an entity related to a bank, it may be determined that the person is in the bank according to the entity relationship of the entity.

In an implementation manner of the embodiment of the present invention, the character recognition result may be obtained according to the following steps:

step S1024: and (4) segmenting the word information by applying a word segmentation tool, and obtaining a word recognition result according to the word segmentation result.

In this embodiment, a word segmentation tool may be applied to segment the word information obtained in step S1022, and a word recognition result may be obtained according to the word segmentation result.

In one embodiment, a tool such as a lucene word segmentation device can be used for intelligently recognizing word groups of the text information, so that data processing of the text information is realized, the text information can be searched, and the text information which can be searched is used as a text recognition result. The lucene participlaner is an open-source full-text search engine tool and can provide the functions of inquiring and indexing characters.

In one implementation manner of the embodiment of the present invention, step S103 may further include:

step S1031: and judging whether the personnel is a preset management and control personnel or not according to the face recognition result.

In this embodiment, whether the person corresponding to the face recognition result is a preset control person or not may be determined according to the face recognition result obtained in step S102. The management and control personnel refer to personnel needing management and control by a management and control organization.

In one embodiment, images acquired by different image acquisition devices can be acquired, and face clustering technology is applied to cluster and archive face recognition results. The face clustering technique refers to an algorithm for grouping faces in a set according to identities (e.g., face feature information).

In one embodiment, the face feature information archived in the cluster may be compared with face feature information in a management and control personnel library of the management and control mechanism, and whether a person corresponding to the acquired face feature information is a management and control person in the management and control personnel library of the management and control mechanism is determined.

Step S1032: when the personnel are the management and control personnel, whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located is judged according to the character recognition result.

In this embodiment, when the person corresponding to the face recognition result is a management and control person, whether dangerous information related to dangerous behaviors exists in the environment where the person is located may be determined according to the character recognition result obtained in step S102.

Step S1033: when dangerous information exists, whether dangerous behaviors exist in the management and control personnel is judged according to the dangerous information.

In this embodiment, when it is determined in step S1032 that the dangerous information related to the dangerous behavior exists, whether the management and control personnel has the dangerous behavior may be determined according to the dangerous information.

In one embodiment, the danger information may include a location name of a preset controlled location, preset controlled information, and the like, and it may be determined whether the text recognition result includes the location name and/or the controlled information of the controlled location. If the character recognition result comprises the place name and/or the management and control information of the management and control place, the dangerous information related to the dangerous behaviors in the environment where the personnel are located can be considered to exist. Those skilled in the art can set the site name of the preset control site and the preset control information according to the actual application requirements. For example, the preset place may be a bank, and the place name of the place may be a bank name. The preset management and control information may be preset violence information.

In one embodiment, step S1033 may further include:

step S10331: position information of an image pickup device which picks up an image and time information of the picked-up image are acquired.

Step S10332: and judging whether dangerous behaviors exist in the management and control personnel according to the position information, the time information and the dangerous information.

In this embodiment, the position information of the image capturing device that captures the image and the time information of the captured image may be acquired, and whether the manager has a dangerous behavior or not may be determined according to the position information, the time information, and the dangerous information determined in step S1032.

In one embodiment, step S10332 may further include:

step S103321: setting early warning rules of dangerous behaviors;

step S103322: analyzing the position information, the time information and dangerous information existing in the environment where the control personnel are located according to the early warning rule;

step S103323: and judging whether dangerous behaviors exist in the management and control personnel according to the analysis result.

Wherein, the early warning rule includes: if the control personnel appear in a preset control place, dangerous behaviors exist; if the frequency of the management and control personnel appearing in the management and control site exceeds a preset frequency threshold, dangerous behaviors exist; if the dangerous information contains preset control information, dangerous behaviors exist.

In this embodiment, the early warning rule of the dangerous behavior may be set according to the management and control requirement of the management and control organization. The early warning rule can be that when the control personnel appear in a preset control place, dangerous behaviors are judged to exist; or when the frequency of the management and control personnel appearing in the management and control place exceeds a preset frequency threshold value, judging that dangerous behaviors exist; or the dangerous information existing in the environment where the control personnel are located comprises preset control information, and then dangerous behaviors are judged to exist. Those skilled in the art can set the control location, the frequency threshold, the control information, etc. according to the needs of the practical application. The position information and the time information of the image acquisition equipment and the dangerous information existing in the environment where the control personnel are located can be analyzed according to the early warning rules, and whether dangerous behaviors exist in the control personnel is judged according to the analysis result.

Specifically, the position information of the image acquisition device and the time information of the acquired image can be referenced to analyze the danger information existing in the environment where the control personnel are located, for example, the spatial position where the control personnel are located can be judged according to the position information of the image acquisition device, and the time when the danger information exists can be judged according to the time information of the acquired image. The position information of the image acquisition equipment and the time information of the acquired image are synthesized to analyze the danger information in the environment where the management and control personnel are located, so that whether the management and control personnel appear in the management and control place managed and controlled by the management and control mechanism or not, whether the management and control personnel frequently appear in the management and control place or not (the frequency appearing in the management and control place exceeds a preset frequency threshold) and whether the management and control information for managing and controlling the management and control mechanism is contained in the environment where the management and control personnel appear can be determined. Therefore, the time and space information of the management and control personnel can be mastered comprehensively, and early warning can be timely realized when dangerous behaviors occur.

In one implementation of the embodiment of the present invention, the present invention may further include, in addition to the steps S101 to S103, a step S104:

step S104: judging whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located according to the character recognition result; when dangerous information exists in the environment, the personnel are directly judged to have dangerous behaviors.

In the embodiment, whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located can be judged according to the character recognition result, and whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located can be directly judged. Specifically, the control mechanism may set dangerous information related to dangerous behaviors, such as key words related to dangerous behaviors, and may directly determine that a person has a dangerous behavior if there are such key words in the environment where the person is located. That is, whether the person is a preset manager or not, as long as the environment has dangerous information, it can be determined that the person has dangerous behaviors.

In one embodiment, after the face recognition result cluster is filed, whether the face recognition result is a person who has not entered identity information in the management and control organization may be determined. If the personnel who do not enter the identity information for the management and control organization, early warning rules can be set, dangerous behavior analysis is carried out on the personnel, and therefore timely early warning is carried out on the dangerous behavior.

In one embodiment, the face recognition result, the character recognition result, the position information of the image acquisition device, the image acquisition time information, and the like of the person may be combined to generate a person database, and the person behavior may be analyzed according to the person database.

Referring to fig. 3, fig. 3 is a schematic flow chart illustrating main steps of a personnel risk behavior analysis method according to an embodiment of the invention. As shown in fig. 3, in the present embodiment, an image including a face of a person and an environment where the person is located may be obtained by a face snapshot machine (image capture device), where the image including the face may be used as a small image and the image of the environment where the person is located may be used as a panoramic image. And after the face recognition is carried out on the small graph, generating a staff archive cluster through a face clustering technology. And performing OCR character recognition on the panoramic image to acquire character information in the panoramic image, and recognizing the character information by applying a semantic recognition technology to enrich the dimension of information of the personnel file cluster. Further, a specific personnel management and control model and an abnormal behavior management and control model can be applied to analyze the personnel file clustering, a management and control information early warning model is applied to analyze the semantic recognition result, and the early warning research and judgment of dangerous behaviors of personnel are carried out according to the analysis results of the specific personnel management and control model, the abnormal behavior management and control model and the management and control information early warning model. The specific functions of the specific personnel management and control model may be referred to in steps S1031 to S1033 of the foregoing method embodiment, the specific functions of the abnormal behavior management and control model may be referred to in steps S103321 to S103323 of the foregoing method embodiment, and the specific functions of the management and control information early warning model may be referred to in step S104 of the foregoing method embodiment.

It should be noted that, although the foregoing embodiments describe each step in a specific sequence, those skilled in the art will understand that, in order to achieve the effect of the present invention, different steps do not necessarily need to be executed in such a sequence, and they may be executed simultaneously (in parallel) or in other sequences, and these changes are all within the protection scope of the present invention.

Furthermore, the invention also provides a system for analyzing the dangerous behaviors of the personnel.

Referring to fig. 2, fig. 2 is a main structural block diagram of a personnel risk behavior analysis system according to an embodiment of the present invention. As shown in fig. 2, the system for analyzing dangerous behaviors of people in the embodiment of the present invention may include an image acquisition module, a face and character recognition module, and a dangerous behavior analysis module. In this embodiment, the image acquisition module may be configured to acquire an image that includes both the face of the person and the environment in which the person is located. The face and character recognition module can be configured to perform face recognition and character recognition on the image respectively to obtain a face recognition result and a character recognition result. The dangerous behavior analysis module can be configured to analyze whether dangerous behaviors exist or not according to the face recognition result and the character recognition result.

In one embodiment, the dangerous behavior analysis module may include a manager judgment submodule, a dangerous information judgment submodule, and a dangerous behavior judgment submodule. In this embodiment, the management and control person judgment sub-module may be configured to judge whether the person is a preset management and control person according to the face recognition result. The danger information judgment submodule can be configured to judge whether danger information related to dangerous behaviors exists in the environment where the personnel are located according to the character recognition result when the personnel are the management and control personnel. The dangerous behavior judgment submodule can be configured to judge whether dangerous behaviors exist in the management and control personnel according to the dangerous information when the dangerous information exists.

In one embodiment, the dangerous information may include a location name of a preset control location and/or preset control information, and the dangerous behavior determination submodule may include a location and time information obtaining unit and a dangerous behavior determination unit. In the present embodiment, the position and time information acquisition unit may be configured to acquire position information of an image capturing apparatus that captures an image and time information of capturing an image. The dangerous behavior judging unit may be configured to judge whether a dangerous behavior exists in the management and control person according to the position information, the time information, and the dangerous information.

In one embodiment, the dangerous behavior judgment unit may include an early warning rule setting subunit, a dangerous information analysis subunit, and a dangerous behavior judgment subunit. In this embodiment, the early warning rule setting subunit may be configured to set an early warning rule of a dangerous behavior. The danger information analysis subunit can be configured to analyze the position information, the time information and the danger information existing in the environment where the control personnel are located according to the early warning rule. The dangerous behavior judgment subunit may be configured to judge whether the management and control person has dangerous behavior according to the analysis result. Wherein, the early warning rule includes: if the control personnel appear in a preset control place, dangerous behaviors exist; if the frequency of the control personnel appearing in the control place exceeds a preset frequency threshold value, dangerous behaviors exist; if the danger information contains preset control information, dangerous behaviors exist.

In one embodiment, the system for analyzing dangerous behaviors of people can further comprise a dangerous behavior related information judgment module. In this embodiment, the dangerous behavior related information judgment module may be configured to perform the following steps: judging whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located according to the character recognition result; when dangerous information exists in the environment, the existence of dangerous behaviors of the personnel is directly judged.

In one embodiment, the face and word recognition module may include a face recognition result obtaining sub-module, a word information extracting sub-module, and a word recognition result obtaining sub-module. In this embodiment, the face recognition result obtaining sub-module may be configured to extract face feature information of the image, and obtain the face recognition result according to the face feature information. The text information extraction sub-module can be configured to perform text recognition on the image and extract text information in the image. The character recognition result acquisition sub-module can be configured to apply a semantic recognition technology to carry out semantic recognition on character information and obtain a character recognition result according to the result of the semantic recognition, or apply a word segmentation tool to carry out word segmentation on the character information and obtain a character recognition result according to the result of the word segmentation.

In one embodiment, the image capture device may include a fixedly disposed image capture device and an image capture device disposed on a movable object.

The above-mentioned personnel dangerous behavior analysis system is used for executing the embodiments of the personnel dangerous behavior analysis method shown in fig. 1 and fig. 3, and the technical principles, the solved technical problems and the generated technical effects of the two are similar, and it can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process and related descriptions of the personnel dangerous behavior analysis system may refer to the contents described in the embodiments of the personnel dangerous behavior analysis method, and no further description is given here.

It will be understood by those skilled in the art that all or part of the flow of the method according to the above-described embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used to implement the steps of the above-described embodiments of the method when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying said computer program code, medium, U-disk, removable hard disk, magnetic diskette, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signal, telecommunication signal, software distribution medium or the like. It should be noted that the computer readable storage medium may contain content that is appropriately increased or decreased according to the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, according to legislation and patent practice, the computer readable storage medium does not include electrical carrier signals and telecommunications signals.

Furthermore, the invention also provides a control device. In an embodiment of the control device according to the present invention, the control device comprises a processor and a storage device, the storage device may be configured to store a program for executing the method for analyzing dangerous behavior of persons according to the above-mentioned method embodiment, and the processor may be configured to execute a program in the storage device, the program including but not limited to a program for executing the method for analyzing dangerous behavior of persons according to the above-mentioned method embodiment. For convenience of explanation, only the parts related to the embodiments of the present invention are shown, and details of the specific techniques are not disclosed. The control device may be a control device apparatus formed including various electronic apparatuses.

Further, the invention also provides a computer readable storage medium. In one computer-readable storage medium embodiment according to the present invention, a computer-readable storage medium may be configured to store a program for executing the human risk behavior analysis method of the above-described method embodiment, and the program may be loaded and executed by a processor to implement the above-described human risk behavior analysis method. For convenience of explanation, only the parts related to the embodiments of the present invention are shown, and details of the specific techniques are not disclosed. The computer readable storage medium may be a storage device formed of various electronic devices, and optionally, the computer readable storage medium is a non-transitory computer readable storage medium in an embodiment of the present invention.

Further, it should be understood that, since the modules are only configured to illustrate the functional units of the apparatus of the present invention, the corresponding physical devices of the modules may be the processor itself, or a part of software, a part of hardware, or a part of a combination of software and hardware in the processor. Thus, the number of individual modules in the figures is merely illustrative.

Those skilled in the art will appreciate that the various modules in the apparatus may be adaptively split or combined. Such splitting or merging of specific modules does not cause the technical solutions to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.

Claims

1. A method for analyzing dangerous behaviors of people, the method comprising:

and analyzing whether the personnel have dangerous behaviors or not according to the face recognition result and the character recognition result.

2. The method for analyzing dangerous behaviors of people according to claim 1, wherein the step of analyzing whether the people have dangerous behaviors according to the face recognition result and the character recognition result specifically comprises:

3. The method for analyzing dangerous behaviors of people according to claim 2, wherein the dangerous information includes a location name of a preset control location and/or preset control information, and the step of determining whether the control personnel has dangerous behaviors according to the dangerous information specifically includes:

and judging whether dangerous behaviors exist in the management and control personnel according to the position information, the time information and the dangerous information.

4. The personnel dangerous behavior analysis method according to claim 3, wherein the step of determining whether the management and control personnel has dangerous behavior according to the position information, the time information and the dangerous information comprises:

setting an early warning rule of the dangerous behavior;

wherein the early warning rules include:

if the control personnel appear in a preset control place, dangerous behaviors exist; and/or the presence of a gas in the gas,

if the frequency of the management and control personnel appearing in the management and control place exceeds a preset frequency threshold value, dangerous behaviors exist; and/or the presence of a gas in the gas,

if the dangerous information contains preset control information, dangerous behaviors exist;

5. The method for analyzing dangerous behaviors of people according to claim 1, wherein before the step of analyzing whether dangerous behaviors exist in the people according to the face recognition result and the character recognition result, the method further comprises:

judging whether dangerous information related to dangerous behaviors exists in the environment where the personnel are located according to the character recognition result;

when the dangerous information exists in the environment, directly judging that the personnel has dangerous behaviors; and/or the presence of a gas in the gas,

the steps of respectively carrying out face recognition and character recognition on the image to obtain a face recognition result and a character recognition result comprise:

6. A system for analyzing dangerous behavior of persons, the system comprising:

7. The personnel hazardous behavior analysis system of claim 6, wherein the hazardous behavior analysis module comprises:

8. The personnel dangerous behavior analysis system according to claim 7, wherein the dangerous information comprises a location name of a preset control location and/or preset control information, and the dangerous behavior judgment sub-module comprises:

a position and time information acquisition unit configured to acquire position information of an image acquisition device that acquires the image and time information of acquisition of the image;

9. The personnel dangerous behavior analysis system according to claim 8, wherein the dangerous behavior judgment unit comprises:

wherein the early warning rules include:

10. The system for analyzing dangerous behavior of people according to claim 6, further comprising a dangerous behavior related information determining module configured to perform the steps of:

the face and character recognition module comprises:

and the character recognition result acquisition sub-module is configured to apply a semantic recognition technology to carry out semantic recognition on the character information and obtain the character recognition result according to the result of the semantic recognition, or apply a word segmentation tool to carry out word segmentation on the character information and obtain the character recognition result according to the result of the word segmentation.

11. A control device comprising a processor and a storage device adapted to store a plurality of program codes, characterized in that said program codes are adapted to be loaded and run by said processor to perform the method of human risk behavior analysis according to any of claims 1 to 5.

12. A computer-readable storage medium, in which a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and executed by a processor to perform the method for human risk behavior analysis according to any one of claims 1 to 5.