Bright kitchen range management system based on big dataTechnical Field
The invention relates to catering sanitary safety, in particular to a bright kitchen range management system based on big data.
Background
With the continuous improvement of living standard of people, the quality and safety of food are more and more concerned, and the concept of people is changed from how to eat full to how to eat good and safe. At present, the food safety situation in China is still severe, the food safety problem is frequent, and how to quickly and effectively solve the food safety problem is a current major subject in China.
At present, many catering enterprises still have many non-normative phenomena on daily production operation, and the dishonest phenomenon in operation is very serious, so that great risk potential is brought to the health and safety of consumers. In the face of the frequent illegal behaviors and dishonest phenomena, the traditional supervision mode relying on the home inspection of law enforcement supervisors cannot achieve good effects, the number of catering enterprises is large, the number of the law enforcement supervisors is relatively insufficient, effective supervision is difficult to achieve by relying on the existing supervision mode mainly based on the home spot inspection, and the supervision efficiency needs to be improved urgently.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects in the prior art, the invention provides a bright kitchen range management system based on big data, which can effectively overcome the defect that the daily production operation of catering enterprises cannot be comprehensively and efficiently supervised in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a bright kitchen management system based on big data comprises a plurality of front-end video shooting devices arranged in a kitchen and used for shooting the whole cooking process, a spot-check video shooting device arranged in a spot-check box for spot-check of food materials in the kitchen and used for shooting food materials, an image acquisition module and a server, wherein people images are extracted from the front-end video shooting devices, the front-end video shooting devices are connected with a first video encoder used for video coding, the spot-check video shooting devices are connected with a second video encoder used for video coding, videos coded by the first video encoder and the second video encoder are sent to the server through network transmission equipment, the server is connected with a video decoder used for decoding the coded videos, the video decoder is connected with display equipment arranged in a hall, and the server sends the videos decoded by the video decoder to a mobile terminal of a customer through a wireless communication module A terminal;
the server is connected with a storage unit used for storing the video decoded by the video decoder, the storage unit is internally divided into a first storage space used for storing the video coded by the first video coder and a second storage space used for storing the video coded by the second video coder, the server is connected with a video retrieval module used for inputting retrieval conditions and retrieving corresponding decoded video from the storage unit, and the server is connected with a video editing module used for editing the decoded video retrieved by the video retrieval module;
the server is connected with an illegal behavior recognition unit used for judging whether illegal behaviors exist in the figure image extracted by the image acquisition module, the server is connected with an illegal behavior recording module used for recording the illegal behaviors recognized by the illegal behavior recognition unit and generating an event report, the server is connected with an intelligent scoring module used for intelligently scoring according to the recognition result of the illegal behavior recording module, the server is connected with an alarm module used for giving an alarm according to the recognition result of the illegal behavior recognition unit, and the server sends the event report generated by the illegal behavior recording module to a supervision platform through a wireless communication module.
Preferably, each of said front-end video cameras is connected to one of said first video encoders.
Preferably, the first storage space stores decoded video in a time sequence of the video encoded by the first video encoder, the second storage space stores decoded video in a time sequence of the video encoded by the second video encoder, and the retrieval condition includes a type of the retrieved video and a time of the retrieved video.
Preferably, if the type of the retrieval video in the retrieval condition is the whole cooking process, the first storage space calls a corresponding decoding video according to the retrieval video time in the retrieval condition; and if the type of the retrieval video in the retrieval condition is food material, the second storage space calls the corresponding decoding video according to the time of the retrieval video in the retrieval condition.
Preferably, the illegal behavior recognition unit includes an illegal image classification library for performing self-deep learning, an image processing module for clipping the peripheries of illegal image characters stored in the illegal image classification library, a feature extraction module for extracting feature information of an image clipped by the image processing module, a feature information library for storing the feature information extracted by the feature extraction module, and a feature comparison module for comparing the feature information in the image of the character extracted by the image acquisition module with the feature information stored in the feature information library.
Preferably, the violation images stored in the violation image classification library comprise a person loading irregular violation image, a person calling violation image, a person playing mobile phone violation image and a person smoking violation image.
Preferably, the image processing module uses a person in the violation image as a center, and extends a certain area outwards for clipping, and the image acquisition module and the image processing module perform the same clipping.
Preferably, the feature comparison module determines that the feature information in the person image extracted by the image acquisition module is the same as the feature information stored in the feature information base, and the violation recording module records the corresponding violation.
Preferably, the intelligent scoring module performs intelligent scoring according to the number of times of violation behaviors recorded by the violation behavior recording module in unit time.
(III) advantageous effects
Compared with the prior art, the bright kitchen range management system based on the big data has the following beneficial effects:
1. the front-end video shooting device is arranged in a kitchen and used for shooting the whole cooking process, the spot check video shooting device is arranged in a spot check box for spot check of food materials in the kitchen and used for shooting the food materials, the first video encoder encodes videos shot by the front-end video shooting device, the second video encoder encodes videos shot by the spot check video shooting device, the video decoder decodes the encoded videos, and the display device is arranged in a hall and used for playing the decoded videos, so that kitchen operations of catering enterprises are transparent, and customers can better supervise;
2. the image acquisition module extracts character images from the front-end video shooting device, the violation behavior recognition unit judges whether violation behaviors exist in the character images extracted by the image acquisition module, the violation behavior recording module records the violation behaviors recognized by the violation behavior recognition unit and generates an event report, and the server sends the event report generated by the violation behavior recording module to the monitoring platform through the wireless communication module, so that the monitoring platform can monitor which violation behaviors exist in a kitchen in real time and which potential safety hazards exist;
3. the storage unit is internally divided into a first storage space used for storing and decoding a first video encoder coded video and a second storage space used for storing and decoding a second video encoder coded video, the video retrieval module is used for inputting retrieval conditions to retrieve corresponding decoded videos from the storage unit, and the video editing module edits the decoded videos retrieved by the video retrieval module, so that corresponding monitoring videos can be quickly found through the retrieval conditions, a supervision platform can conveniently obtain evidence timely, and catering enterprises can be pertinently rectified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram of the system of the present invention;
fig. 2 is a schematic diagram of an illegal behavior recognition unit according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all 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.
A bright kitchen light management system based on big data is disclosed, as shown in FIG. 1 and FIG. 2, comprising a plurality of front-end video cameras arranged in the kitchen for shooting the whole cooking process, a spot-check video camera arranged in a spot-check box for spot-checking food materials in the kitchen for shooting food materials, an image acquisition module for extracting images of people from the front-end video cameras, the front-end video shooting device is connected with a first video encoder used for video encoding, the sampling video shooting device is connected with a second video encoder used for video encoding, videos encoded by the first video encoder and the second video encoder are sent to the server through network transmission equipment, the server is connected with a video decoder used for decoding the encoded videos, the video decoder is connected with display equipment arranged in a hall, and the server sends the videos decoded by the video decoder to a mobile terminal of a customer through a wireless communication module;
the server is connected with a storage unit used for storing the video decoded by the video decoder, the storage unit is internally divided into a first storage space used for storing the video coded by the first video coder and a second storage space used for storing the video coded by the second video coder, the server is connected with a video retrieval module used for inputting retrieval conditions to retrieve the corresponding decoded video from the storage unit, and the server is connected with a video editing module used for editing the decoded video retrieved by the video retrieval module;
the server is connected with an illegal behavior recognition unit used for judging whether illegal behaviors exist in the figure image extracted from the image acquisition module, the server is connected with an illegal behavior recording module used for recording the illegal behaviors recognized by the illegal behavior recognition unit and generating an event report, the server is connected with an intelligent scoring module used for intelligently scoring according to the recognition result of the illegal behavior recording module, the server is connected with an alarm module used for alarming according to the recognition result of the illegal behavior recognition unit, and the server sends the event report generated by the illegal behavior recording module to the supervision platform through the wireless communication module.
Each front-end video camera is connected to a first video encoder.
The first storage space stores the decoded videos according to the time sequence of the videos coded by the first video coder, the second storage space stores the decoded videos according to the time sequence of the videos coded by the second video coder, and the retrieval conditions comprise the type of the retrieved videos and the time of the retrieved videos.
If the type of the retrieval video in the retrieval condition is the whole cooking process, the first storage space calls a corresponding decoding video according to the retrieval video time in the retrieval condition; and if the type of the retrieval video in the retrieval condition is food material, the second storage space calls the corresponding decoding video according to the retrieval video time in the retrieval condition.
The violation behavior identification unit comprises a violation image classification library for self deep learning, an image processing module for cutting the periphery of a violation image figure stored in the violation image classification library, a feature extraction module for extracting feature information of an image cut by the image processing module, a feature information library for storing the feature information extracted by the feature extraction module, and a feature comparison module for comparing the feature information in the figure image extracted by the image acquisition module with the feature information stored in the feature information library.
The illegal images stored in the illegal image classification library comprise illegal images which are loaded by people and are not standardized, illegal images which are called by people, illegal images which are played by people when people play mobile phones, and illegal images which are smoked by people.
The image processing module takes a person in the illegal image as a center, a certain area is expanded outwards for cutting, and the image acquisition module and the image processing module perform the same cutting.
And the characteristic comparison module judges that the characteristic information in the figure image extracted by the image acquisition module is the same as the characteristic information stored in the characteristic information base, and the violation behavior recording module records the corresponding violation behavior.
And the intelligent scoring module intelligently scores according to the times of the illegal behaviors recorded by the illegal behavior recording module in unit time.
The front end video shooting device is arranged in the kitchen and used for shooting the whole cooking process, the selective examination video shooting device is arranged in a selective examination box for selectively examining food materials in the kitchen and used for shooting the food materials, a first video encoder encodes videos shot by the front end video shooting device, a second video encoder encodes videos shot by the selective examination video shooting device, a video decoder decodes the encoded videos, a display device is arranged in a hall and used for playing the decoded videos, kitchen operation transparency of catering enterprises is realized, and customers can monitor better.
The image acquisition module extracts figure images from the front-end video shooting device, the violation identification unit judges whether violation exists or not from the figure images extracted by the image acquisition module, the violation recording module records the violation identified by the violation identification unit and generates an event report, and the server sends the event report generated by the violation recording module to the monitoring platform through the wireless communication module, so that the monitoring platform can monitor which violations exist in a kitchen in real time and which potential safety hazards exist. Because the front-end video shooting device is provided with a plurality of devices, the violation identification unit can comprehensively judge whether the violation behaviors exist in the figure images of various angles, and the violation behavior identification accuracy is effectively improved.
The violation behavior identification unit comprises a violation image classification library for self deep learning, an image processing module for cutting the periphery of a violation image figure stored in the violation image classification library, a feature extraction module for extracting feature information of an image cut by the image processing module, a feature information library for storing the feature information extracted by the feature extraction module, and a feature comparison module for comparing the feature information in the figure image extracted by the image acquisition module with the feature information stored in the feature information library.
The illegal images stored in the illegal image classification library comprise illegal images which are loaded by people and are not standardized, illegal images which are called by people, illegal images which are played by people when people play mobile phones, and illegal images which are smoked by people.
The image processing module takes a person in the illegal image as a center, a certain area is expanded outwards for cutting, and the image acquisition module and the image processing module perform the same cutting.
And the characteristic comparison module judges that the characteristic information in the figure image extracted by the image acquisition module is the same as the characteristic information stored in the characteristic information base, and the violation behavior recording module records the corresponding violation behavior.
The storage unit is internally divided into a first storage space used for storing and decoding a first video encoder coded video and a second storage space used for storing and decoding a second video encoder coded video, the video retrieval module is used for inputting retrieval conditions to retrieve corresponding decoded videos from the storage unit, and the video editing module edits the decoded videos retrieved by the video retrieval module, so that corresponding monitoring videos can be quickly found through the retrieval conditions, a supervision platform can conveniently obtain evidence timely, and catering enterprises can be pertinently rectified.
The first storage space stores the decoded videos according to the time sequence of the videos coded by the first video coder, the second storage space stores the decoded videos according to the time sequence of the videos coded by the second video coder, and the retrieval conditions comprise the type of the retrieved videos and the time of the retrieved videos.
If the type of the retrieval video in the retrieval condition is the whole cooking process, the first storage space calls a corresponding decoding video according to the retrieval video time in the retrieval condition; and if the type of the retrieval video in the retrieval condition is food material, the second storage space calls the corresponding decoding video according to the retrieval video time in the retrieval condition.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.