Western-style food table setting calculation and scoring method
Through the combination of industrial cameras and cloud computing servers, high-precision calculation and scoring of Western food tables is achieved, and the problems of measurement deviation and insufficient functions in the existing technology are solved. Automatic calibration and accurate tableware placement scoring methods are provided, which improves the Accuracy and efficiency of ratings.
Patent Information
- Application Number
- CN202411027084.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-08
Smart Images

Figure CN118918167A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of dining table settings, and in particular refers to a method for calculating and scoring a western-style dining table setting. Background Art
[0002] Western table setting is to place all kinds of tableware on the table as required. It is an important part of restaurant catering work. It is also a skill that hotel students need to master. The quality of setting directly affects the service quality and the appearance of the restaurant. In the assessment of Western table setting for hotel students, the tableware and wine glasses are scored by judging whether they are selected accurately and whether they are placed accurately. Usually, the referee uses the naked eye and calipers to measure and the data obtained is scored. This method inevitably leads to deviation in measurement data and the scoring is not satisfactory.
[0003] In the prior art, an industrial camera is installed above the dining table to photograph the dining table from a bird's-eye view, so as to identify the dining table, tableware, and wine utensils. The model recognition training and deployment capabilities are used to achieve precision measurement and computing power, and the tableware spacing, table edge distance, and other values are measured. The deviation value and score are calculated through the AI intelligent Chinese and Western dining table positioning training system, and the score is automatically issued through the score determination setting. However, it is not possible to effectively manage the items on display or trigger corresponding functions based on the items on display. Therefore, there is an urgent need for a new method for measuring and scoring Western dining tables to solve the above problems. Summary of the invention
[0004] In order to solve the above-mentioned existing problems, the present invention provides a method for measuring and scoring a western dining table, which uses an industrial camera to take pictures, a cloud computing server to perform AI recognition and spacing measurement of tableware, and transmits the data to an AI intelligent Chinese and Western dining table positioning training system to finally complete the score determination.
[0005] The technical solution adopted by the present invention is as follows: The method for calculating and scoring a western-style dining table of the present invention comprises the following steps:
[0006] S1, captures high-definition images, industrial cameras capture tableware and wine utensils on the table;
[0007] S2, AI intelligent positioning and recognition area. The table positioning uses a variety of ISP algorithms to quickly and efficiently identify Chinese round tables and Western square tabletops, and transmit the image to the AI intelligent Chinese and Western table positioning training system through the Gigabit network port, and form a visual image. The positioning status is checked manually based on the image, and the system controls the CCM and LSC to automatically calibrate. When the table moves and deviates from the previously recognized position, the recalibration function in the AI intelligent Chinese and Western table positioning training system is operated to automatically calibrate and reposition.
[0008] S3, millisecond-level tableware recognition, uses the cloud computing server's closed-loop processing of image data to accurately identify the location, name, and quantity of tableware and wine utensils in the dining table area;
[0009] S4, intelligent distance measurement, uploads the picture to the cloud measurement server, and through the server algorithm recognition and measurement empowerment, combined with tableware recognition, desktop calibration, and optical measurement principle technology, the position of tableware and wine utensils in the image taken by the industrial camera is calculated to obtain data such as the distance between tableware and the distance between tableware and the edge of the table;
[0010] S5, compare the difference with the standard value. According to the assessment requirements, compare the measured data with the assessment standard data and output the positive and negative difference to replace the manual comparison results;
[0011] S6, the formula automatically calculates the total score, and transmits the cloud measurement server identification and measurement data to the AI intelligent Chinese and Western food table positioning training system through the data interface. The system supports the setting of numerical offset difference and deduction standards. After the setting, the data is compared and calculated by the system to obtain the score result of this table setting.
[0012] Furthermore, the parameters are set before the western-style dining table setting is measured and scored. The table type is identified through configuration, and the camera is controlled to identify and locate tables of different specifications. The tableware and wine glass identification range is controlled by configuring the cloud measurement server, so as to facilitate accurate positioning, distance measurement and score calculation.
[0013] Furthermore, the millisecond-level tableware recognition includes the following steps: data collection, data analysis, data processing, visual learning, model training, result feedback, model verification, and model deployment.
[0014] Furthermore, the formula for automatically calculating the total score includes the following steps: API data transmission, scoring standard, AI algorithm, and outputting the final score.
[0015] Furthermore, the data collection and processing first creates a model of the tableware and wine utensils that need to be identified in the image in the cloud computing server, selects the object area and names it, in order to clarify the objects that need to be identified, and then uses the cloud computing server AI recognition to realize automatic recognition of the tableware and wine utensils on the table after the system is photographed.
[0016] Furthermore, the model training adopts the method of visual learning + incremental training, multiple recognition / calculation under different thresholds, and the algorithm adopts mAP (average accuracy of all categories) to measure the algorithm effect index, and the recognition accuracy reaches 99.8%.
[0017] The beneficial effects achieved by the present invention using the above structure are as follows: automatic positioning through a high-precision industrial array camera to achieve high-definition overhead photo shooting, accurate identification and measurement of dining tables, tableware, and wine utensils through a measurement server, and the names of the tableware and wine utensils and measurement data are calculated and identified through an AI intelligent Chinese and Western dining table positioning training system to calculate and obtain assessment index data, which are compared with the assessment standard values to obtain positive and negative deviation values, and the final score is calculated through preset increase and decrease rules, and the measurement visualization image is retained for use as a basis for assessment score determination, which is convenient and efficient. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is a schematic diagram of the structure of the Western dining table setting measurement and scoring system proposed in this plan;
[0019] Figure 2 This is a flow chart of the western dining table setting measurement and scoring method proposed in this plan;
[0020] Figure 3 This is the millisecond-level tableware recognition flow chart of the Western dining table setting measurement and scoring method proposed in this solution;
[0021] Figure 4 This is a flow chart for automatically calculating the total score using the formula for the Western dining table setting measurement and scoring method proposed in this plan.
[0022] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: 1. dining table, 2. industrial camera, 3. cloud computing server, 4. AI intelligent Chinese and Western dining table positioning training system. DETAILED DESCRIPTION
[0023] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0024] like Figure 1 and Figure 2 As shown, the western-style dining table measurement and scoring method proposed in this scheme includes the following steps:
[0025] S1, captures high-definition images, industrial cameras capture tableware and wine utensils on the table;
[0026] S2, AI intelligent positioning and recognition area. The table positioning uses a variety of ISP algorithms to quickly and efficiently identify Chinese round tables and Western square tabletops, and transmit the image to the AI intelligent Chinese and Western table positioning training system through the Gigabit network port, and form a visual image. The positioning status is checked manually based on the image, and the system controls the CCM and LSC to automatically calibrate. When the table moves and deviates from the previously recognized position, the recalibration function in the AI intelligent Chinese and Western table positioning training system is operated to automatically calibrate and reposition.
[0027] S3, millisecond-level tableware recognition, uses the cloud computing server's closed-loop processing of image data to accurately identify the location, name, and quantity of tableware and wine utensils in the dining table area;
[0028] S4, intelligent distance measurement, uploads the picture to the cloud measurement server, and through the server algorithm recognition and measurement empowerment, combined with tableware recognition, desktop calibration, and optical measurement principle technology, the position of tableware and wine utensils in the image taken by the industrial camera is calculated to obtain data such as the distance between tableware and the distance between tableware and the edge of the table;
[0029] S5, compare the difference with the standard value. According to the assessment requirements, compare the measured data with the assessment standard data and output the positive and negative difference to replace the manual comparison results;
[0030] S6, the formula automatically calculates the total score, and transmits the cloud measurement server identification and measurement data to the AI intelligent Chinese and Western food table positioning training system through the data interface. The system supports the setting of numerical offset difference and deduction standards. After the setting, the data is compared and calculated by the system to obtain the score result of this table setting.
[0031] like Figure 1 to Figure 3 As shown, the millisecond-level tableware recognition includes the following steps: data collection, data analysis, data processing, visual learning, model training, result feedback, model verification, and model deployment. For the data collection and processing, the tableware and wine utensils that need to be identified in the image are first created in the cloud computing server, and the object area and name are selected to clarify the objects to be identified. Then, the cloud computing server AI is used for recognition, so that the system can automatically recognize the tableware and wine utensils on the desktop after shooting. The model training uses the method of visual learning + incremental training, and multiple recognition / calculations are performed under different thresholds. The algorithm uses mAP (average accuracy of all categories) to measure the algorithm effect index, and the recognition accuracy reaches 99.8%.
[0032] like Figure 1 to Figure 4 As shown, the formula for automatically calculating the total score includes the following steps: API data transmission, scoring standard, AI algorithm, and outputting the final score.
[0033] Among them, the parameters are set before the western-style table setting is measured and scored. The table type is identified through configuration, and the camera is controlled to identify and locate tables of different specifications. The tableware and wine glass recognition range is controlled by configuring the cloud measurement server, which facilitates accurate positioning, distance measurement and score calculation.
[0034] When used specifically, pictures are taken with industrial cameras, and the cloud computing server performs AI recognition and spacing measurement of tableware, and transmits the data to the AI intelligent Chinese and Western dining table positioning training system to finally complete the score determination. It provides convenient and efficient Chinese and Western food assessment, measurement and scoring services, and automatically positions high-precision industrial array cameras to achieve high-definition overhead photo shooting. The table, tableware, and wine utensils are accurately identified and measured by the computing server. The AI intelligent Chinese and Western dining table positioning training system calculates the names and measurement data of the tableware and wine utensils identified, calculates the assessment index data, and compares it with the assessment standard values to obtain the positive and negative deviation values. The final score is calculated through the preset increase and decrease rules, and the measurement visualization image is retained as a basis for the assessment score determination.
[0035] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0036] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for calculating and scoring a western-style dining table, characterized in that: The following steps are involved: S1, captures high-definition images, industrial cameras capture tableware and wine utensils on the table; S2, AI intelligent positioning and recognition area. The table positioning uses a variety of ISP algorithms to quickly and efficiently identify Chinese round tables and Western square tabletops, and transmit the image to the AI intelligent Chinese and Western table positioning training system through the Gigabit network port, and form a visual image. The positioning status is checked manually based on the image, and the system controls the CCM and LSC to automatically calibrate. When the table moves and deviates from the previously recognized position, the recalibration function in the AI intelligent Chinese and Western table positioning training system is operated to automatically calibrate and reposition. S3, millisecond-level tableware recognition, uses the cloud computing server's closed-loop processing of image data to accurately identify the location, name, and quantity of tableware and wine utensils in the dining table area; S4, intelligent distance measurement, uploads the picture to the cloud measurement server, and through the server algorithm recognition and measurement empowerment, combined with tableware recognition, desktop calibration, and optical measurement principle technology, the position of tableware and wine utensils in the image taken by the industrial camera is calculated to obtain data such as the distance between tableware and the distance between tableware and the edge of the table; S5, compare the difference with the standard value. According to the assessment requirements, compare the measured data with the assessment standard data and output the positive and negative difference to replace the manual comparison results; S6, the formula automatically calculates the total score, and transmits the cloud measurement server identification and measurement data to the AI intelligent Chinese and Western food table positioning training system through the data interface. The system supports the setting of numerical offset difference and deduction standards. After the setting, the data is compared and calculated by the system to obtain the score result of this table setting.
2. A method for calculating and scoring a western-style dining table according to claim 1, characterized in that: Before the western-style dining table setting is measured and scored, parameters are first set. The table type is identified through configuration, and the camera is controlled to identify and locate tables of different specifications. The tableware and wine glass identification range is controlled by configuring the cloud measurement server, so as to facilitate accurate positioning, distance measurement and score calculation.
3. A method for calculating and scoring a western-style dining table according to claim 2, characterized in that: The millisecond-level tableware recognition includes the following steps: data collection, data analysis, data processing, visual learning, model training, result feedback, model verification, and model deployment.
4. A method for calculating and scoring a western-style dining table according to claim 3, characterized in that: The formula for automatically calculating the total score includes the following steps: API data transmission, scoring standards, AI algorithm, and outputting the final score.
5. A method for calculating and scoring a western-style dining table according to claim 4, characterized in that: The data collection and processing first creates a model of the tableware and wine utensils that need to be identified in the image in the cloud computing server, selects the object area and names it, in order to clarify the objects that need to be identified, and then uses the cloud computing server AI recognition to realize automatic recognition of the tableware and wine utensils on the desktop after the system is photographed.
6. A method for calculating and scoring a western-style dining table according to claim 5, characterized in that: The model training adopts the method of visual learning + incremental training, multiple recognition / calculation under different thresholds, and the algorithm adopts mAP (average accuracy of all categories) to measure the algorithm effect index.
