CN213814723U

CN213814723U - Automatic meal dish charging system based on AI intelligent image recognition

Info

Publication number: CN213814723U
Application number: CN202120165062.3U
Authority: CN
Inventors: 许婉淑
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-01-21
Filing date: 2021-01-21
Publication date: 2021-07-27
Anticipated expiration: 2031-01-21

Abstract

The utility model discloses a dish automatic charging system based on AI intelligent image discernment, it includes dining table, dinner plate delivery track, display screen, server host computer and collecting vat, the embedding of both sides at dining table middle part is provided with dinner plate delivery track, the embedding is installed the display screen on the dining table of dinner plate delivery track one end one side, installs the server host computer on the crossbeam of dining table bottom one side, and one side of server host computer is installed the customer end submachine, and the dinner plate is thrown in the dinner plate delivery track, and the both sides at dinner plate delivery track middle part are installed the response module, the utility model discloses novel structure, the design is ingenious, when the customer initiatively delivers the dinner plate, utilizes AI image recognition technology to realize dish charging, can realize quick charging and recovery, improves efficiency, can off-line use, avoids the error that network problem brought, and is more integrated, only needs a small amount of data to train out high accuracy model simultaneously, the identification rate is high, and the dishes do not need to be specially processed, so that the method can be suitable for most storefronts.

Description

Automatic meal dish charging system based on AI intelligent image recognition

Technical Field

The utility model relates to a meal dish charging specifically is meal dish automatic billing system based on AI intelligent image recognition.

Background

At present, the service plate is generally charged in three ways, one is manual settlement, the efficiency is low, and the labor cost is high. One is that the scheme is a dinner plate identification technology based on RFID, and the bottom of tableware is provided with an RFID radio frequency chip, and the radio frequency chip is read and written, and food information and price are bound on the chip, thereby realizing pricing, but the dish needs to be customized, the price is high, and the damage of the chip can lead to the dish being unusable.

One is a settlement system based on machine vision, for example, the settlement system of the intelligent restaurant based on machine vision of patent 2017102765124, needs to acquire the video stream of the camera in real time, and the background is processed by various algorithms to obtain the result. Therefore, the sub-recognition time is long, the recognition rate is not high, and the efficiency improvement is not obvious.

With the development of scientific and technological intelligence, more and more restaurants adopt a customer self-service ordering mode, so that the labor cost is expected to be saved, but dishes after the customer has finished eating still need special personnel to be recovered and charged, and the time and labor cost are greatly increased. Meanwhile, the existing charging equipment cannot meet the requirement of fast charging the dishes in a short time, so that the waiting time of a client is too long, and business is influenced. Therefore, the fast and automatic billing of the customer's dishes is a problem to be solved by those skilled in the art.

SUMMERY OF THE UTILITY MODEL

To the above-mentioned condition, for overcoming prior art's defect, the utility model provides a meal dish automatic billing system based on AI intelligent image identification, the effectual problem of mentioning in having solved the above-mentioned technical background.

In order to achieve the above object, the utility model provides a following technical scheme: the utility model discloses a track, display screen, server host computer, customer terminal machine, dinner plate, response module, light, camera module and collecting vat are delivered to dining table, dinner plate, the both sides embedding at dining table middle part is provided with the dinner plate and delivers the track, and the display screen is installed in the embedding on the dining table of dinner plate delivery track one end one side, installs the server host computer on the crossbeam of dining table bottom one side, and customer end submachine is installed to one side of server host computer, and the dinner plate is thrown in the dinner plate delivery track, and the response module is installed to the both sides at delivery track middle part, and the light is installed to the one end of dining table bottom crossbeam, and camera module is installed to one side of light.

Preferably, one end of the dinner plate delivery track is flush with the dinner table surface.

Preferably, the shooting angle of the camera module faces the sensing area of the sensing module.

Preferably, a collecting groove is formed in the bottom of one side of the dining table.

Preferably, a buffer pad is arranged at the bottom of the collecting tank.

Preferably, the sensing module is electrically connected to an input end of the client terminal machine, an output end of the client terminal machine is electrically connected to the camera module, the server host and an input end of the display screen, respectively, and an output end of the server host is electrically connected to an input end of the client terminal machine.

Has the advantages that: the utility model discloses during the use, prepare the flow in advance and show as figure 2: collecting a picture data set of the dinner plate in an actual use environment, counting and labeling the picture data set, starting to train a picture information processing model after the labeling is finished, analyzing an image through intelligent AI deep learning, providing accuracy after multiple times of training, finally finishing the picture information processing model, and finally deploying the picture information processing model on a server host for offline use in a storefront; the use flow is shown in fig. 3: when the dinner plate enters the dinner plate delivery track, the dinner plate is sensed when passing through the sensing module, the sensing module sends a sensing signal to the client-side submachine, the output end of the client-side submachine sends an instruction to transfer the camera module to start collecting picture information after receiving the signal, the client-side submachine sends the picture information to the server host machine for image recognition, the server host machine returns the dish recognition information to the client-side submachine after recognizing the image information, the client-side submachine displays the dish recognition information on a display screen, and the dinner plate finally falls into the collecting tank to be collected. The identification rate is high, and the dishes do not need to be specially processed, so that the method can be suitable for most storefronts.

Drawings

The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention, and together with the description serve to explain the invention and not to limit the invention. In the drawings:

fig. 1 is a schematic diagram of the overall three-dimensional structure of the present invention;

FIG. 2 is a diagram of the system of the present invention prepared in advance;

FIG. 3 is a flow chart of the system of the present invention;

reference numbers in the figures: 1. a dining table; 2. a service plate delivery track; 3. a display screen; 4. a server host; 5. a client terminal machine; 6. a dinner plate; 7. a sensing module; 8. an illuminating lamp; 9. a camera module; 10. and (4) collecting the tank.

Detailed Description

The following describes the present invention in further detail with reference to the accompanying fig. 1-3.

The embodiment is given by figures 1-3, the utility model provides an automatic accounting system for dishes based on AI intelligent image recognition, which comprises a dining table 1, a dish delivery track 2, a display screen 3, a server host machine 4 and a client sub-machine 5, dinner plate 6, response module 7, light 8, camera module 9 and collecting vat 10, the both sides embedding at 1 middle part of dining table is provided with dinner plate delivery track 2, display screen 3 is installed in the embedding on dining table 1 of 2 one end one side of dinner plate delivery track, install server host computer 4 on the crossbeam of 1 bottom one side of dining table, customer end submachine 5 is installed to one side of server host computer 4, the dinner plate has been thrown in the dinner plate delivery track 2, response module 7 is installed to the both sides at 2 middle parts of dinner plate delivery track, light 8 is installed to the one end of 1 bottom crossbeam of dining table, camera module 9 is installed to one side of light 8.

One end of the dinner plate delivery track 2 is flush with the surface of the dining table 1, thereby being convenient for comfort and integral aesthetic property when in use.

The shooting angle of the camera module 9 faces the sensing area of the sensing module 7, so that the camera module is convenient to use in a matching way.

A collection trough 10 is provided at the bottom of one side of the table 1 to facilitate collection of the trays 6.

A buffer pad is provided at the bottom of the collection trough 10 to buffer the dish 6 to some extent.

The sensing module 7 is electrically connected with the input end of the client terminal machine 5, the output end of the client terminal machine 5 is electrically connected with the input ends of the camera module 9, the server host machine 4 and the display screen 3 respectively, and the output end of the server host machine 4 is electrically connected with the input end of the client terminal machine 5, so that signal transmission and control are facilitated.

The working principle is as follows: the utility model discloses during the use, prepare the flow in advance and show as figure 2: collecting a picture data set of the dinner plate 6 in an actual use environment, counting and labeling the picture data set, starting to train a picture information processing model after the labeling is finished, analyzing an image through intelligent AI deep learning, providing accuracy after a plurality of times of training, finally finishing the picture information processing model, and finally deploying the picture information processing model on the server host 4 for off-line use in a storefront; the use flow is shown in fig. 3: after dinner plate 6 got into dinner plate delivery track 2, dinner plate 6 is sensed when response module 7, response module 7 sends the sensing signal to customer end submachine 5, customer end submachine 5 receives signal back output and sends out the instruction and mobilize camera module 9 and begin to gather picture information, customer end submachine 5 has obtained picture information back and sends to server host computer 4 and carries out image recognition, return meal dish identification information to customer end submachine 5 behind the 4 discernment image information of server host computer, customer end submachine 5 shows meal dish identification information at display screen 3, dinner plate 6 falls into collecting vat 10 at last and is collected.

Has the advantages that: the utility model discloses novel structure, think about ingeniously, when the dinner plate 6 is delivered to the customer initiative, utilize AI image recognition technology to realize the 6 charges of meal dish, can realize quick charge and retrieve, raise the efficiency, but the off-line uses, avoids the error that the network problem brought, also integrates more, only needs a small amount of data just can train out the high accuracy model simultaneously, and the recognition rate is high, also need not to the special treatment of meal dish, can adapt to most storefronts.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing embodiments, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. Automatic meal dish charging system based on AI intelligent image identification, including dining table (1), dinner plate delivery track (2), display screen (3), server host computer (4), customer end parasite aircraft (5), dinner plate (6), response module (7), light (8), camera module (9) and collecting vat (10), its characterized in that: the utility model discloses a dining table, including dining table (1), server, client terminal machine (5), dinner plate delivery track (2), server host computer (4), client terminal machine (5) are installed to the embedding on dining table (1) of dining table (1) middle part both sides embedding is provided with dinner plate delivery track (2), display screen (3) are installed in the embedding on dining table (1) of dinner plate delivery track (2) one end one side, dinner plate (6) have been thrown in dinner plate delivery track (2), response module (7) are installed to the both sides at dinner plate delivery track (2) middle part, light (8) are installed to the one end of dining table (1) bottom crossbeam, camera module (9) are installed to one side of.

2. The AI intelligent image recognition based dish automatic billing system according to claim 1, characterized in that one end of the dish delivery track (2) is flush with the surface of the dining table (1).

3. The AI intelligent image recognition based dish automatic billing system according to claim 1, characterized in that the shooting angle of the camera module (9) is oriented to the sensing area of the sensing module (7).

4. The AI intelligent image recognition based dish automatic billing system according to claim 1, characterized in that the bottom of one side of the dining table (1) is provided with a collecting groove (10).

5. AI intelligent image recognition based dish automatic billing system according to claim 4 characterized in that the collecting tank (10) is provided with a cushion at the bottom.

6. The automatic meal dish charging system based on AI intelligent image recognition as claimed in claim 1, wherein the sensing module (7) is electrically connected to the input terminal of the client terminal machine (5), the output terminal of the client terminal machine (5) is electrically connected to the input terminals of the camera module (9), the server host (4) and the display screen (3), respectively, and the output terminal of the server host (4) is electrically connected to the input terminal of the client terminal machine (5).