Intelligent meal taking system and method based on face recognition

Abstract

The invention discloses an intelligent meal taking system and method based on face recognition, and relates to the field of intelligent meal taking, and the system comprises a plurality of meal taking windows, a weighing sensor, a face collection device, a radar detection device and a data processing device. A weighing sensor, a face acquisition device and a radar detection device are arranged at each meal taking window; the weighing sensor detects the weight of food at the food taking window in real time; the radar detection equipment detects whether a human body exists in front of the meal taking window or not in real time and the distance between the human body and the meal taking window is smaller than a preset threshold value; if yes, the face collection equipment starts to collect an image in front of the meal taking window; if not, the face acquisition equipment is dormant; and the data processing equipment performs face recognition on the image in front of each meal taking window, calculates the meal taking total price of the target user at each meal taking window according to the weight of each meal taking window and the meal product unit price, and then deducts the fees. According to the invention, the meal taking and settlement efficiency is improved, and the meal taking process is more convenient and more sanitary.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent meal taking, in particular to an intelligent meal taking system and method based on face recognition. BACKGROUND

[0002] At present, the common meal taking system in the market mostly needs the user to bind with a specific tray before taking meal, and records the meal taking information and charges through the induction device or other markers on the tray. This way has many inconveniences, on the one hand, the process of binding the tray increases the operation steps of the user, reduces the meal taking efficiency; on the other hand, the tray used belongs to public tableware, which is repeatedly used by many people, and has certain health hazards. In addition, the traditional meal taking system has certain requirements for the tray specifications, and has poor flexibility, which is difficult to meet the needs of users using different specifications of tableware to take meal.

[0003] Therefore, an intelligent meal taking system and method without tray binding, more convenient and sanitary are urgently needed. SUMMARY

[0004] The purpose of the present application is to provide an intelligent meal taking system and method based on face recognition, which can improve the meal taking and settlement efficiency, and the user can use any specification of tableware to take meal, and the meal taking process is more convenient and sanitary.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides an intelligent meal taking system based on face recognition, comprising: a plurality of meal taking windows, a weighing sensor, a face collection device, a radar detection device and a data processing device; a weighing sensor, a face collection device and a radar detection device are arranged at each meal taking window;

[0007] The weighing sensor is used to detect the weight of the meal at the meal taking window in real time;

[0008] The radar detection device is used to detect whether there is a human body in front of the meal taking window and the distance between the human body and the meal taking window is less than a preset threshold value in real time: if yes, the face collection device is controlled to start collecting the image in front of the meal taking window; if no, the face collection device is controlled to sleep;

[0009] The data processing device is used to perform face recognition on the image in front of each meal taking window, determine the target user, and calculate the total meal taking price of the target user at each meal taking window according to the weight collected by the weighing sensor at each meal taking window and the unit price of the meal at each meal taking window, and deduct the fee from the payment account previously associated with the target user according to the total meal taking price.

[0010] In an embodiment, the data processing device is a server.

[0011] In an embodiment, the data processing device is further configured to store a pre-recorded face image library; the process of identifying the target user by the data processing device through face recognition on the image in front of each pickup window comprises: face recognition on the image in front of each pickup window to obtain a target face image, and matching the target face image with the face images in the face image library to determine the target user.

[0012] In an embodiment, the data processing device is in communication connection with a canteen system to obtain the face images recorded by the canteen system and update the face image library.

[0013] In an embodiment, the face collection device collects images in front of the pickup window at a set time interval under the control of the radar detection device; the data processing device performs face recognition and matching at a set time interval according to the images collected by the face collection device to continuously identify the identity of the user.

[0014] In an embodiment, a display screen is further provided at each pickup window; the display screen is used to display the pickup weight and total price of the target user at the pickup window.

[0015] In an embodiment, the face collection device is a camera.

[0016] In an embodiment, the system further comprises an alarm device; the data processing device is further configured to control the alarm device to alarm when face recognition fails continuously for multiple times or when the fee deduction fails.

[0017] In a second aspect, the present application provides an intelligent pickup method based on face recognition, comprising:

[0018] For any pickup window, the radar detection device at the pickup window is used to detect whether there is a human body in front of the pickup window and the distance between the human body and the pickup window is less than a preset threshold value: if yes, the face collection device at the pickup window is controlled to start collecting images in front of the pickup window; if no, the face collection device at the pickup window is controlled to sleep;

[0019] The weight of the food at the pickup window is detected in real time by the weighing sensor at the pickup window.

[0020] The image in front of the pickup window is recognized by the data processing device to determine the target user, and the total price of the target user at the pickup window is calculated according to the weight collected by the weighing sensor at the pickup window and the unit price of the food at the pickup window.

[0021] According to the total meal price of the target user at each meal pickup window, the payment account pre-associated with the target user is charged.

[0022] In an embodiment, the method further comprises: when the face recognition fails continuously for multiple times or the charging fails, an alarm device is used to alarm.

[0023] According to the specific embodiments provided in the present application, the present application has the following technical effects:

[0024] The present application provides an intelligent meal pickup system and method based on face recognition. By setting a weighing sensor, a face collection device, and a radar detection device at each meal pickup window, the radar detection device and the face collection device are used to realize automatic identification of the user identity at the meal pickup window, the weighing sensor is used to automatically detect the weight of the meal, and the data processing device is used to calculate the total meal price of the user at each meal pickup window according to the meal weight of the user at each meal pickup window and the unit price of the meal at each meal pickup window, and then automatically charge the payment account pre-associated with the user. The entire process does not require manual intervention, improves the meal pickup and settlement efficiency, and the user does not need to use a unified public tray to pick up meals, nor does the user need to be bound to the tray. That is, the user can use any size of utensils to pick up meals, and the meal pickup process is more convenient and hygienic, which optimizes the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 A block diagram of an intelligent meal pickup system based on face recognition according to an embodiment of the present application is provided.

[0027] Figure 2 A flowchart of an intelligent meal pickup method based on face recognition according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0029] In order to make the above objects, features and advantages of the present application more apparent, further specific embodiments of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] In one exemplary embodiment, an intelligent meal taking system based on face recognition is provided, which is suitable for the automatic meal taking and payment scene in canteens, restaurants and other catering places, supports non-contact meal taking, and the meal materials include ceramic, glass or metal. As shown in the figure, the intelligent meal taking system based on face recognition has the following core devices, and each device works cooperatively through hardware connection and communication protocol. Figure 1

[0031] (I) Multiple meal taking windows 11. The meal taking window 11 is a physical interface for users to take meals, and a weighing sensor 12, a face collection device 13 and a radar detection device 14 are arranged at each meal taking window 11.

[0032] (II) Weighing sensor 12. The weighing sensor 12 is arranged at each meal taking window 11 to detect the weight of the meal at the meal taking window 11 in real time. Specifically, the weighing sensor 12 adopts high-precision pressure sensing technology, which can be accurate to grams, and provides data basis for meal charging.

[0033] (III) Radar detection device 14. The radar detection device 14 is used to detect whether there is a human body in front of the meal taking window 11 and the distance between the human body and the meal taking window 11 is less than a preset threshold (such as 0.5 meters): if yes, the face collection device 13 is controlled to start collecting images in front of the meal taking window 11; if not, the face collection device 13 is controlled to sleep to reduce energy consumption. The radar detection device 14 operates in a low-power mode, and only wakes up the face collection device 13 when a human body is detected, avoiding power waste caused by continuous operation of the camera, and reducing the amount of invalid data processing.

[0034] In one specific application example, the radar detection device 14 adopts a millimeter wave radar, and the detection range covers the area from 0.3 meters to 1.5 meters in front of the meal taking window 11.

[0035] (IV) Face collection device 13. The face collection device 13 can be a high-definition camera, which works under the control of the radar detection device 14. When receiving a start signal, it collects images in front of the meal taking window 11 at a set time interval (such as once every 3 seconds) to capture the facial features of the user.

[0036] ​(V) Data processing device 16. The data processing device 16 is used to perform face recognition on the image in front of each take-out window 11, determine the target user, and calculate the total price of the target user at each take-out window 11 according to the weight collected by the weighing sensor 12 at each take-out window 11 and the unit price of the meal at each take-out window 11, and deduct the payment from the payment account (such as WeChat, Alipay or canteen card account) associated with the target user in advance according to the total price of the meal.

[0037] Specifically, the data processing device 16 stores the unit price of each meal, calculates the total price of the meal at this take-out window 11 according to the weight of the meal and the unit price of the meal, and saves it. After a certain period of time (such as 15 minutes), an order is generated according to the total price of the meal at all take-out windows 11 within this period of time, and the payment is deducted from the pre-associated payment account. Further, an order confirmation request is sent to the user's mobile terminal before the payment is deducted, and the payment is executed if the user does not refuse within a certain period of time.

[0038] The data processing device 16 is usually a server with powerful computing and data processing capabilities.

[0039] The data processing device 16 is also used to store a pre-recorded face image library. The process of determining the target user by the data processing device 16 through face recognition on the image in front of each take-out window 11 includes: performing face recognition on the image in front of each take-out window 11 to obtain a target face image, matching the target face image with the face image in the face image library to determine the target user. Specifically, the feature points of the target face image are extracted and matched with the face image in the face image library to determine the identity of the target user.

[0040] The data processing device 16 is in communication connection with the canteen system to obtain the face image recorded by the canteen system and update the face image library to ensure the accuracy and timeliness of the face image library. Specifically, the data processing device 16 and the canteen system realize data synchronization through API interface. When the canteen system adds a new user or changes the user's face information, the data processing device 16 automatically obtains the updated face image and performs incremental update on the face image library to ensure the accuracy of recognition.

[0041] In a specific application example, the face collection device 13 collects images in front of the take-out window 11 at a set time interval under the control of the radar detection device 14. The data processing device 16 performs face recognition and matching at a set time interval according to the images collected by the face collection device 13 to continuously identify the identity of the user.

[0042] (VI) Display screen 15. Each take-out window 11 is also provided with a display screen 15. The display screen 15 is used to display the target user's take-out weight, take-out total price, and other information at the take-out window 11, improving interaction transparency.

[0043] (VII) Alarm device 17. The data processing device 16 is also used to control the alarm device 17 (such as a buzzer or indicator light) to alarm when continuous face recognition fails (such as more than 3 times) or fee deduction fails, so that the staff can handle it in time.

[0044] In this application, multiple take-out windows 11 work in parallel, each take-out window 11 independently completes the detection, identification, and billing process, and the data processing device 16 uniformly manages the data of each take-out window 11, realizing efficient operation of the overall system.

[0045] The process of taking out food using the face recognition intelligent take-out system provided in this application is as follows:

[0046] (1) Enter the face information into the canteen system and store it in the data processing device 16.

[0047] (2) The user carries any size of utensils to the take-out window 11, the radar detection device 14 of the take-out window 11 detects the human body and the distance between the human body and the take-out window 11 is less than the preset threshold, the face collection device 13 starts to collect images, the data processing device 16 identifies the face in the image and matches it with the faces in the face image library to determine the target user.

[0048] (3) The user takes out food from the take-out window 11, and the data processing device 16 calculates the total price of this take-out window 11 according to the weight collected by the weighing sensor 12 and the stored single price of the food, and saves it.

[0049] (4) The user moves to the next take-out window 11 and repeats steps (2) and (3) above until the taking out is finished.

[0050] (5) When the radar detection device 14 cannot detect the human body in front of the take-out window 11, it means that the taking out is finished, and the face collection device 13 is stopped.

[0051] (6) After a certain period of time, the data processing device 16 automatically generates an order according to the total price of the user at all take-out windows 11 in this time period and deducts the fee from the pre-bound account.

[0052] Based on the same inventive concept, the embodiments of the present application also provide an intelligent take-out method using the above-mentioned face recognition-based intelligent take-out system, as shown in Figure 2 A face recognition-based intelligent take-out method is provided, which includes the following steps 21 to 25.

[0053] Step 21, for any pickup window 11, detect whether there is a human body in front of the pickup window 11 and the distance between the human body and the pickup window 11 is less than a preset threshold in real time by the radar detection device 14 at the pickup window 11: if yes, control the face collection device 13 at the pickup window 11 to start collecting images in front of the pickup window 11; if no, control the face collection device 13 at the pickup window 11 to sleep.

[0054] Step 22, detect the weight of the food at the pickup window 11 in real time by the weighing sensor 12 at the pickup window 11.

[0055] Step 23, perform face recognition on the images in front of the pickup window 11 by the data processing device 16 to determine the target user, and calculate the total price of the target user at the pickup window 11 according to the weight collected by the weighing sensor 12 at the pickup window 11 and the unit price of the food at the pickup window 11.

[0056] Step 24, deduct the total price of the target user at each pickup window 11 from the payment account previously associated with the target user.

[0057] Step 25, when consecutive face recognition fails or deduction fails, alarm by the alarm device 17.

[0058] Compared with the prior art, the present application has the following beneficial effects:

[0059] ① Improve the pickup efficiency: through the automatic face recognition and settlement process, without manual intervention, the single user pickup settlement time can be shortened to within 10 seconds, compared with the traditional manual settlement efficiency is improved by more than 50%, effectively alleviating the queuing problem during the peak dining period.

[0060] ② Improve the accuracy of settlement: based on the weighing sensor 12 and the system automatic calculation of the charging mode, avoid manual calculation error, the charging accuracy rate is 100%, and the identity authentication error rate of face recognition technology is less than 0.01%, which ensures the safety of the payment link.

[0061] ③ Reduce labor cost: the system can realize unmanned guard, reduce the dependence of the canteen on the cashier, a single canteen can save 30%-50% of the labor cost, especially suitable for large-scale catering places.

[0062] (4) Optimized user experience: real-time display of meal pickup information and automatic deduction function make the meal pickup process more convenient and transparent; radar detection and energy-saving design reduce invalid operation of the device, and improve the intelligent level of the system. Moreover, users do not need to use a unified public tray to pick up meals, and do not need to bind the tray before picking up meals. Any size of tableware can be used to pick up meals, and the meal pickup process is more convenient and hygienic.

[0063] (5) Enhanced system reliability: alarm device 17 and abnormal log recording function can timely discover and handle face recognition failure, abnormal deduction and other problems, reduce system failure risk, and ensure the continuity of catering service.

[0064] (6) Support data management: data processing device 16 can store all meal pickup records, payment data and user information, provide data support for canteen management, and facilitate sales statistics, inventory management and user behavior analysis.

[0065] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0066] In the present application, all actions of obtaining signals, information or data are carried out under the premise of complying with the corresponding data protection regulations and policies of the place, and under the premise of obtaining authorization from the owner of the corresponding device.

[0067] The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0068] Each technical feature of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of each technical feature in the above embodiments are not described, but as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present application.

[0069] The principles and implementation manners of the present application are described herein by using specific examples, and the above examples are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will have changes. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A smart meal pickup system based on facial recognition, characterized in that, The system includes: multiple food pick-up windows, weighing sensors, facial recognition devices, radar detection devices, and data processing devices; each food pick-up window is equipped with a weighing sensor, a facial recognition device, and a radar detection device. The weighing sensor is used to detect the weight of the food at the food pick-up window in real time; The radar detection device is used to detect in real time whether there is a human body in front of the food pick-up window and whether the distance between the human body and the food pick-up window is less than a preset threshold: if yes, the face acquisition device is controlled to start acquiring images in front of the food pick-up window; if no, the face acquisition device is controlled to go into sleep mode. The data processing device is used to perform facial recognition on the images in front of each food pick-up window to identify the target user, and calculate the total price of the target user's food pick-up at each food pick-up window based on the weight collected by the weighing sensor at each food pick-up window and the unit price of the food at each food pick-up window, and deduct the total price from the payment account pre-linked to the target user.

2. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, The data processing device is a server.

3. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, The data processing device is also used to store a pre-recorded facial image library; The process by which the data processing device performs facial recognition on the images in front of each food pick-up window to determine the target user includes: performing facial recognition on the images in front of each food pick-up window to obtain the target facial image, and matching the target facial image with facial images in the facial image database to determine the target user.

4. The intelligent meal pickup system based on facial recognition according to claim 3, characterized in that, The data processing device is connected to the canteen system to obtain facial images recorded by the canteen system and update the facial image database.

5. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, Under the control of the radar detection device, the face capture device captures images in front of the food pick-up window at set time intervals; the data processing device performs face recognition and matching based on the images captured by the face capture device at set time intervals to continuously identify the user's identity.

6. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, Each food pick-up window is also equipped with a display screen; the display screen is used to show the weight of the food picked up by the target user at the food pick-up window and the total price of the food picked up.

7. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, The face capture device is a camera.

8. The intelligent meal pickup system based on facial recognition according to claim 1, characterized in that, The system also includes an alarm device; the data processing device is further used to control the alarm device to issue an alarm when face recognition or payment fails multiple times in a row.

9. A smart meal-taking method based on facial recognition, employing the smart meal-taking system based on facial recognition as described in any one of claims 1-8, characterized in that, The method includes: For any food pick-up window, the radar detection device at the pick-up window can detect in real time whether there is a human body in front of the pick-up window and whether the distance between the human body and the pick-up window is less than a preset threshold. If yes, the face capture device at the pick-up window is controlled to start capturing images in front of the pick-up window; if no, the face capture device at the pick-up window is controlled to go into sleep mode. The weight of the food at the food pick-up window is detected in real time by a weighing sensor at the pick-up window. The data processing device performs facial recognition on the image in front of the food pick-up window to identify the target user, and calculates the total price of the target user's food pick-up at the food pick-up window based on the weight collected by the weighing sensor at the food pick-up window and the unit price of the food at the food pick-up window. The total cost of the food picked up by the target user at each food pick-up window will be deducted from the pre-linked payment account of the target user.

10. The intelligent meal-taking method based on facial recognition according to claim 9, characterized in that, The method further includes: If facial recognition or payment fails multiple times in a row, an alarm will be triggered via the alarm device.

Images