Video behavior analysis management system based on artificial intelligence

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly relates to a video behavior analysis management system based on artificial intelligence, which comprises a video acquisition module used for shooting the environment of a production line; the personnel analysis module is used for analyzing the actions of the personnel according to the images in the content shot by the video acquisition module so as to analyze whether the actions of the personnel and wearing violate rules or not; and the sound analysis module is used for analyzing the personnel sound and the equipment sound according to the sound in the content shot by the video acquisition module so as to analyze the problems existing in the equipment in the production line. According to the invention, while personnel behaviors in the production line are analyzed, equipment problems and solutions thereof can be analyzed, so that the application range is widened, and personnel can perform timely targeted maintenance on the equipment when the equipment has problems.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a video behavior analysis and management system based on artificial intelligence. Background Art

[0002] The production line refers to the route that the product production process takes, that is, the route that starts from the raw materials entering the production site and goes through a series of production activities such as processing, transportation, assembly, and inspection.

[0003] At present, monitoring systems are usually used in production lines to analyze the behavior of personnel to determine whether they have violated regulations. However, the existing monitoring systems have relatively single functions and can usually only analyze the actions of personnel. When equipment has problems, it is unable to judge and analyze the problems that arise, which has limitations. Therefore, an artificial intelligence-based video behavior analysis management system is invented. Summary of the invention

[0004] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0005] A video behavior analysis and management system based on artificial intelligence, comprising:

[0006] Video acquisition module, used to shoot the environment of the production line;

[0007] A personnel analysis module is used to analyze the actions of personnel based on the images captured by the video acquisition module to analyze whether the actions and clothing of personnel are in violation of regulations;

[0008] The sound analysis module is used to analyze the sounds of people and equipment based on the sounds in the content captured by the video acquisition module, so as to analyze the problems existing in the equipment in the production line;

[0009] The sound analysis module comprises:

[0010] The sound preprocessing module is used to collect, amplify and classify the sound in the content captured by the video acquisition module;

[0011] A problem acquisition module is used to analyze the problems existing in the device according to the sound processed by the sound preprocessing module to obtain the problems existing in the device;

[0012] A solution acquisition module is used to acquire a corresponding solution when the problem acquisition module acquires a device problem;

[0013] The playing module is used to play the solution when the solution acquisition module acquires the solution to solve the device problem.

[0014] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the personnel analysis module includes:

[0015] An image acquisition module is used to acquire images from the content captured by the video acquisition module;

[0016] The feature extraction module is used to extract the features of a person based on the image acquired by the image acquisition module.

[0017] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the personnel analysis module also includes:

[0018] The clothing storage module is used to store images of various illegal clothing;

[0019] A clothing comparison module, used to compare the features extracted by the feature extraction module with the images stored in the clothing storage module;

[0020] The clothing judgment module is used to judge whether the features extracted by the feature extraction module are similar to those in the clothing storage module. If so, it means that the person has violated the rules.

[0021] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the personnel analysis module also includes:

[0022] Action storage module, used to store images of various illegal actions;

[0023] An action comparison module, used to compare the features extracted by the feature extraction module with the images stored in the action storage module;

[0024] The action judgment module is used to judge whether the features extracted by the feature extraction module are similar to those in the action storage module. If so, it means that the personnel have violated the rules.

[0025] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the sound preprocessing module includes:

[0026] A sound acquisition module is used to acquire the sound in the content captured by the video acquisition module;

[0027] The sound amplification module is used to amplify the sound collected by the sound collection module to avoid the phenomenon of missing analysis due to the sound being too small;

[0028] The sound classification module is used to classify the sounds collected by the sound collection module after the sound amplification module amplifies the sounds, including human sounds and equipment sounds.

[0029] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the question acquisition module includes:

[0030] A text conversion module, used to convert the human voice into text when the sound classification module classifies the human voice;

[0031] The text analysis module is used to analyze the text converted by the text conversion module to parse out the text of the relevant device.

[0032] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the question acquisition module also includes:

[0033] The text storage module is used to store various texts related to equipment problems;

[0034] The text comparison module is used to compare the text analyzed by the text analysis module with the text stored in the text storage module.

[0035] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the question acquisition module also includes:

[0036] The text judgment module is used to judge whether the text analyzed by the text analysis module is similar to the text storage module. If so, the problem of the device will be obtained;

[0037] The sound storage module is used to store various sounds produced by the device during operation when a problem occurs.

[0038] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the question acquisition module also includes:

[0039] A sound comparison module, used for comparing the classified sound with the sound stored in the sound storage module when the sound classification module classifies the device sound;

[0040] The sound judgment module is used to judge whether the classified device sound exists in the sound storage module. If so, the problem of the device will be obtained.

[0041] As a preferred solution of the video behavior analysis management system based on artificial intelligence described in the present invention, the solution acquisition module includes:

[0042] Problem storage module, used to store various problems of the equipment and their solutions;

[0043] A problem comparison module, used to compare the device problems determined by the text determination module and the sound determination module with the problems stored in the problem storage module;

[0044] The problem judgment module is used to judge whether the equipment problems judged by the text judgment module and the sound judgment module are similar to those in the problem storage module. If so, a solution to the equipment problem will be obtained.

[0045] Compared with existing technologies:

[0046] By setting up a personnel analysis module for analyzing personnel actions based on images in the content captured by the video acquisition module, and by setting up a sound analysis module for analyzing personnel sounds and equipment sounds based on sounds in the content captured by the video acquisition module, it is possible to analyze equipment problems and their solutions while analyzing personnel behaviors in the production line, which not only increases the scope of use but also enables personnel to perform timely and targeted repairs on the equipment when problems occur with the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0049] The present invention provides a video behavior analysis management system based on artificial intelligence, please refer to Figure 1 ;

[0050] It includes: a video acquisition module, which is used to shoot the environment at the production line; a personnel analysis module, which is used to analyze the movements of personnel based on the images in the content captured by the video acquisition module, so as to analyze whether the movements and clothing of personnel are in violation of regulations; and a sound analysis module, which is used to analyze the sounds of personnel and equipment based on the sounds in the content captured by the video acquisition module, so as to analyze the problems existing in the equipment in the production line.

[0051] The personnel analysis module includes: an image acquisition module, which is used to acquire images from the content captured by the video acquisition module; a feature extraction module, which is used to extract the features of the personnel based on the images acquired by the image acquisition module; a clothing storage module, which is used to store images of various illegal clothing; a clothing comparison module, which is used to compare the features extracted by the feature extraction module with the images stored in the clothing storage module; a clothing judgment module, which is used to judge whether the features extracted by the feature extraction module are similar in the clothing storage module, and if so, it means that the personnel have violated the rules; an action storage module, which is used to store images of various illegal actions; an action comparison module, which is used to compare the features extracted by the feature extraction module with the images stored in the action storage module; and an action judgment module, which is used to judge whether the features extracted by the feature extraction module are similar in the action storage module, and if so, it means that the personnel have violated the rules.

[0052] The sound analysis module includes: a sound preprocessing module, which is used to collect, amplify and classify the sound in the content captured by the video acquisition module; a problem acquisition module, which is used to analyze the problem existing in the device according to the sound processed by the sound preprocessing module to obtain the problem existing in the device; a solution acquisition module, which is used to obtain the corresponding solution when the problem acquisition module obtains the device problem; a playback module, which is used to play the solution to solve the device problem when the solution acquisition module obtains the solution to solve the device problem;

[0053] The sound preprocessing module includes: a sound collection module, which is used to obtain the sound in the content shot by the video collection module; a sound amplification module, which is used to amplify the sound collected by the sound collection module to avoid missing analysis due to the sound being too small; and a sound classification module, which is used to classify the sound collected by the sound collection module after the sound amplification module amplifies it, including human sound and equipment sound.

[0054] The problem acquisition module includes: a text conversion module, which is used to convert the human voice into text when the sound classification module classifies the human voice; a text analysis module, which is used to analyze the text converted by the text conversion module to analyze the text related to the equipment; a text storage module, which is used to store various texts related to the equipment problems; a text comparison module, which is used to compare the text analyzed by the text analysis module with the text stored in the text storage module; a text judgment module, which is used to judge whether the text analyzed by the text analysis module is similar in the text storage module, and if so, the problem of the equipment will be obtained; a sound storage module, which is used to store various sounds of the equipment when the equipment has problems; a sound comparison module, which is used to compare the classified sound with the sound stored in the sound storage module when the sound classification module classifies the equipment sound; and a sound judgment module, which is used to judge whether the classified equipment sound is similar in the sound storage module, and if so, the problem of the equipment will be obtained.

[0055] The solution acquisition module includes: a problem storage module, which is used to store various equipment problems and their solutions; a problem comparison module, which is used to compare the equipment problems judged by the text judgment module and the sound judgment module with the problems stored in the problem storage module; and a problem judgment module, which is used to judge whether the equipment problems judged by the text judgment module and the sound judgment module are similar to those in the problem storage module. If so, a solution to the equipment problem will be obtained.

[0056] When used, the specific steps are as follows:

[0057] Step 1: Use the video acquisition module to shoot the environment of the production line;

[0058] Step 2: The image captured by the video acquisition module is acquired through the image acquisition module. After acquisition, the features of the person are extracted by the feature extraction module according to the image acquired by the image acquisition module. After extraction, the features extracted by the feature extraction module are compared with the images stored in the clothing storage module through the clothing comparison module. After comparison, the clothing judgment module is used to determine whether the features extracted by the feature extraction module are similar to those in the clothing storage module. If so, it indicates that the person has violated the rules. In addition, after the features of the person are extracted by the feature extraction module according to the images acquired by the image acquisition module, the features extracted by the feature extraction module are compared with the images stored in the action storage module through the action comparison module. After comparison, the action judgment module is used to determine whether the features extracted by the feature extraction module are similar to those in the action storage module. If so, it indicates that the person has violated the rules.

[0059] Step three: The sound in the content shot by the video acquisition module is acquired through the sound acquisition module. After acquisition, the sound collected by the sound acquisition module will be amplified by the sound amplification module. After amplification, the sound classification module can classify the sound collected by the sound acquisition module according to the amplified sound, including human voice and equipment sound. After classification, the text conversion module can convert the human voice into text when the sound classification module classifies the human voice. After conversion, the text converted by the text conversion module will be analyzed by the text analysis module to parse out the text of the relevant equipment. After analysis, the text analyzed by the text analysis module will be compared with the text stored in the text storage module through the text comparison module. After comparison, the text judgment module will be used to judge whether the text analyzed by the text analysis module exists in the text storage module. similar, if it exists, the problem of the device will be obtained; in addition, after the sound is classified by the sound classification module, the sound comparison module will be used to compare the classified sound with the sound stored in the sound storage module when the sound classification module classifies the device sound. After comparison, the sound judgment module will be used to determine whether the classified device sound is similar in the sound storage module. If so, the problem of the device will be obtained; after acquisition, the device problem determined by the text judgment module and the sound judgment module will be compared with the problem stored in the problem storage module through the problem comparison module. After comparison, the problem judgment module will be used to determine whether the device problem determined by the text judgment module and the sound judgment module is similar in the problem storage module. If so, the solution to the device problem will be obtained. After acquisition, the obtained device problem and its solution will be played through the playback module.

[0060] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A video behavior analysis and management system based on artificial intelligence, characterized in that: include: Video acquisition module, used to shoot the environment of the production line; A personnel analysis module is used to analyze the actions of personnel based on the images captured by the video acquisition module to analyze whether the actions and clothing of personnel are in violation of regulations; The sound analysis module is used to analyze the sounds of people and equipment based on the sounds in the content captured by the video acquisition module, so as to analyze the problems existing in the equipment in the production line; The sound analysis module comprises: The sound preprocessing module is used to collect, amplify and classify the sound in the content captured by the video acquisition module; A problem acquisition module is used to analyze the problems existing in the device according to the sound processed by the sound preprocessing module to obtain the problems existing in the device; A solution acquisition module is used to acquire a corresponding solution when the problem acquisition module acquires a device problem; A playback module, used to play a solution to a device problem when the solution acquisition module acquires the solution; The question acquisition module includes: A text conversion module, used to convert the human voice into text when the sound classification module classifies the human voice; A text parsing module is used to parse the text converted by the text conversion module to parse out the text of the relevant device; The question acquisition module also includes: The text storage module is used to store various texts related to equipment problems; A text comparison module is used to compare the text analyzed by the text analysis module with the text stored in the text storage module; The question acquisition module also includes: The text judgment module is used to judge whether the text analyzed by the text analysis module is similar to the text storage module. If so, the problem of the device will be obtained; The sound storage module is used to store various sounds of the device when a problem occurs during its operation; The question acquisition module also includes: A sound comparison module, used for comparing the classified sound with the sound stored in the sound storage module when the sound classification module classifies the device sound; The sound judgment module is used to judge whether the classified device sound exists in the sound storage module. If so, the problem of the device will be obtained.

2. The video behavior analysis and management system based on artificial intelligence according to claim 1 is characterized in that: The personnel analysis module includes: An image acquisition module is used to acquire images from the content captured by the video acquisition module; The feature extraction module is used to extract the features of a person based on the image acquired by the image acquisition module.

3. The video behavior analysis and management system based on artificial intelligence according to claim 2 is characterized in that: The personnel analysis module also includes: The clothing storage module is used to store images of various illegal clothing; A clothing comparison module, used to compare the features extracted by the feature extraction module with the images stored in the clothing storage module; The clothing judgment module is used to judge whether the features extracted by the feature extraction module are similar to those in the clothing storage module. If so, it means that the person has violated the rules.

4. The video behavior analysis and management system based on artificial intelligence according to claim 3 is characterized in that: The personnel analysis module also includes: Action storage module, used to store images of various illegal actions; An action comparison module, used to compare the features extracted by the feature extraction module with the images stored in the action storage module; The action judgment module is used to judge whether the features extracted by the feature extraction module are similar to those in the action storage module. If so, it means that the personnel have violated the rules.

5. The video behavior analysis and management system based on artificial intelligence according to claim 1 is characterized in that: The sound preprocessing module comprises: A sound acquisition module is used to acquire the sound in the content captured by the video acquisition module; The sound amplification module is used to amplify the sound collected by the sound collection module to avoid the phenomenon of missing analysis due to the sound being too small; The sound classification module is used to classify the sounds collected by the sound collection module after the sound amplification module amplifies the sounds, including human sounds and equipment sounds.

6. The video behavior analysis and management system based on artificial intelligence according to claim 1 is characterized in that: The solution acquisition module includes: Problem storage module, used to store various problems of the equipment and their solutions; A problem comparison module, used to compare the device problems determined by the text determination module and the sound determination module with the problems stored in the problem storage module; The problem judgment module is used to judge whether the equipment problems judged by the text judgment module and the sound judgment module are similar to those in the problem storage module. If so, a solution to the equipment problem will be obtained.

Images