A weighing algorithm for automatically removing the weight of a spoon from an electronic scale

Abstract

The application discloses a kind of electronic scale automatic removal spoon weight's weight calculation algorithm, including when the weight sensor is measured to decrement, decrement change analysis module extracts decrement change characteristic, and judge whether the decrement change characteristic is consistent with food decrement change characteristic;If it is judged to be consistent, the decrement value is actual decrement value, and calculation processing module calculates the price of food actual decrement and displays real-time total amount and food decrement price;If it is judged to be inconsistent, calculation processing module subtracts the spoon weight value obtained by the spoon weight model from the decrement value, to obtain actual decrement value, and calculation processing module calculates the price of food actual decrement and displays real-time total amount and food decrement price;Self-learning module analyzes the decrement data analyzed by decrement change analysis module and the actual decrement data obtained by calculation processing module, optimizes the spoon weight value in spoon weight model, solves the additional cost problem of consumer caused by spoon misjudgment in traditional self-service weighing system.

Description

[TECHNICAL FIELD]

[0001] The present application relates to a kind of electronic scale automatic removal spoon weight's weight calculation algorithm. [BACKGROUND]

[0002] With the rise of smart restaurant, self-service weighing system is widely used in catering industry. The system calculates the consumption amount of customers by automatically weighing the weight of food, greatly improving the service efficiency of restaurant. However, in practical application, the weighing system often encounters some unavoidable errors. For example, when customers use spoons to pick up food, but the spoons are not put back in place in time, or the network environment is unstable, resulting in settlement calculation error, the system may incorrectly calculate the weight of the spoon as part of the food, resulting in overestimation of the consumption amount of the user. [SUMMARY]

[0003] The present application overcomes the shortcomings of the prior art and provides an electronic scale automatic removal spoon weight's weight calculation algorithm.

[0004] To achieve the above purpose, the present application adopts the following technical solutions:

[0005] An electronic scale automatic removal spoon weight's weight calculation algorithm, characterized by: comprising a weighing sensor arranged in the scale body capable of measuring the weight of the weighing disc and food, a data processing unit arranged in the scale body capable of converting the weight of the food measured by the weighing sensor into a weight value and automatically identifying and removing the weight of the spoon, a display screen connected to the scale body, and a background server presetting food categories and unit prices, the data processing unit includes a weight reduction change analysis module for determining whether the weight reduction of the weighing disc is food reduction or spoon reduction, a self-learning module for establishing a spoon weight model and optimizing the spoon weight precision in the model by analyzing data through the weight reduction change analysis module, and a calculation processing module for calculating the weight and price of food reduction, the weight calculation algorithm includes the following steps:

[0006] S1, the weighing sensor measures the weight of the empty disc state of the weighing disc;

[0007] S2, the weighing sensor measures the first total weight when the weighing disc carries food and places the spoon, the calculation processing module subtracts the weight of the weighing disc from the first total weight to obtain the second total weight of the sum of the weight of the food and the spoon, and displays it through the display screen;

[0008] S3, when the weighing sensor measures the second total weight reduction, the weight reduction change analysis module extracts the weight reduction change feature, and determines whether the weight reduction change feature conforms to the food weight reduction change feature;

[0009] S4, if the judgment is correct, the reduced value is the actual reduced value, the calculation processing module is connected with the background server to obtain the corresponding food unit price, and the price of the actual reduced food is calculated according to the preset unit price, and the real-time second total weight and the price of the food reduction are displayed on the display screen;

[0010] If the judgment is not correct, the calculation processing module subtracts the spoon weight value obtained from the spoon weight model in the self-learning module from the reduced value to obtain the actual reduced value, the calculation processing module is connected with the background server to obtain the corresponding food unit price, and the price of the actual reduced food is calculated according to the preset unit price, and the real-time second total weight and the price of the food reduction are displayed on the display screen;

[0011] S5, the self-learning module analyzes the reduced data analyzed by the reduced change analysis module and the actual reduced data obtained by the calculation processing module, and optimizes the spoon weight value in the spoon weight model.

[0012] The weight calculation algorithm for automatically removing the spoon weight of the electronic scale as claimed in 1, wherein the extracted reduced change features include a reduced change rate feature and a reduced change amplitude feature.

[0013] The weight calculation algorithm for automatically removing the spoon weight of the electronic scale as claimed in the above, wherein the reduced change analysis module is provided with a spoon reduced change rate preset range value and a spoon reduced change amplitude preset range value.

[0014] In S3, the reduced change analysis module judges whether the reduced change rate feature value and the reduced change amplitude feature value fall within the spoon reduced change rate preset range value and the spoon reduced change amplitude preset range value respectively.

[0015] In S4, when any feature value does not fall within the corresponding preset range value, it is judged that the reduced change feature conforms to the food reduced change feature; when the two feature values fall within the corresponding preset range values respectively, it is judged that the reduced change feature does not conform to the food reduced change feature.

[0016] The weight calculation algorithm for automatically removing the spoon weight of the electronic scale as claimed in the above, wherein the self-learning module is based on a machine learning algorithm, and a spoon weight model is established by the change pattern of the food weight data and the spoon weight data of the weighing sensor.

[0017] The weight calculation algorithm for automatically removing the spoon weight of the electronic scale as claimed in the above, wherein the spoon weight model analyzes the weighing data of the weighing sensor to learn the regular weight range, placement time and reduced fluctuation feature information of the spoon.

[0018] The weight calculation algorithm for automatically removing the spoon weight of the electronic scale as claimed in the above, wherein the machine learning algorithm includes a K-means clustering algorithm and a support vector machine algorithm.

[0019] The weight calculation algorithm for automatically removing the weight of a spoon from an electronic scale as described above, characterized in that the data processing unit further comprises an error correction module for correcting network fluctuations or hardware fault errors.

[0020] In S4, the error correction module monitors the network state and the decrement value, and when the monitored network fluctuation exceeds a preset value or the decrement value differs from the historical record decrement value by more than a set value, the error correction module will smooth the actual decrement value in real time according to the historical record actual decrement value.

[0021] The weight calculation algorithm for automatically removing the weight of a spoon from an electronic scale as described above, characterized in that the data processing unit further comprises a database for storing the weighing data, the weight reduction data, the actual weight reduction data, the food weight increase / decrease pattern data, the spoon weight characteristic data, and the weight change data of the food adhered to the spoon of the weighing sensor each time.

[0022] The beneficial effects of the present application are:

[0023] The present application can solve the problem of additional consumer expenses caused by misjudgment of spoons in traditional self-service weighing systems. At the same time, the present application does not require additional hardware and does not rely on external hardware identification devices. It only removes the weight of the spoon through the weighing sensor and the algorithm, reducing the system cost. The present application is efficient and accurate. Through self-learning and dynamic optimization algorithm, the system can accurately identify and remove the weight of the spoon, improving the calculation accuracy. The present application provides real-time feedback and improves user experience. Users can view the accurate food weight and consumption amount in real time, avoid excessive charges caused by misjudgment, and improve user satisfaction. The present application is intelligent and has strong adaptability. The system can adjust itself according to different scenes and user behavior habits, has strong adaptability, and the algorithm recognition ability improves continuously after long-term use. [BRIEF DESCRIPTION OF DRAWINGS]

[0024] Figure 1 The present application is a system schematic diagram. [DETAILED DESCRIPTION]

[0025] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings.

[0026] It should be noted that all directional indications, such as upper, lower, left, right, front, back, etc., are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications will also change accordingly. In addition, the description of "preferred", "suboptimal" and the like in the present application is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of indicated technical features. Therefore, the features defined as "preferred", "suboptimal" can be explicitly or implicitly included at least one of the features.

[0027] As shown in Figure 1 An electronic scale automatic spoon weight removal weighing algorithm, comprising a weighing sensor 1 arranged in the scale body capable of measuring the weight of the weighing disc and the food, a data processing unit 2 arranged in the scale body capable of converting the food weight measured by the weighing sensor 1 into a weight value and automatically identifying and removing the spoon weight, a display screen 3 connected to the scale body, and a background server 4 presetting food categories and unit prices, the data processing unit 2 comprising a weight reduction change analysis module 21 for judging whether the weight reduction of the weighing disc is a food reduction or a spoon reduction, a self-learning module 22 for establishing a spoon weight model and optimizing the spoon weight precision in the model by analyzing data through the weight reduction change analysis module 21, and a calculation processing module 23 for calculating the weight and price of the food reduction, the weighing algorithm comprising the following steps:

[0028] S1, the weighing sensor 1 measures the weight of the empty disc state of the weighing disc;

[0029] S2, the weighing sensor 1 measures the first total weight when the weighing disc carries food and places the spoon, the calculation processing module 23 subtracts the total weight from the weight of the weighing disc to obtain the second total weight of the food weight and the spoon weight, and displays it through the display screen 3;

[0030] S3, when the weighing sensor 1 measures the second total weight reduction, the weight reduction change analysis module 21 extracts the weight reduction change characteristics and judges whether the weight reduction change characteristics meet the food weight reduction change characteristics;

[0031] S4, if it is judged to be consistent, the weight reduction value is the actual weight reduction value, the calculation processing module 23 is connected with the background server 4 to obtain the corresponding food unit price, and calculates the price of the actual weight reduction of the food according to the preset unit price, and displays the real-time second total weight and the price of the food weight reduction through the display screen 3;

[0032] If the judgment is not met, the calculation processing module 23 subtracts the spoon weight value obtained from the self-learning module 22 from the reduction value to obtain the actual reduction value, the calculation processing module 23 is connected with the background server 4 to obtain the corresponding food unit price, and the actual reduction of the food is calculated according to the preset unit price, and the real-time second total weight and the price of the food reduction are displayed through the display screen 3;

[0033] S5, the self-learning module 22 analyzes the reduction data analyzed by the reduction change analysis module 21 and the actual reduction data obtained by the calculation processing module 23, and optimizes the spoon weight value in the spoon weight model.

[0034] Specifically, the reduction change analysis module in S3 is provided with a spoon reduction change rate preset range value and a spoon reduction change amplitude preset range value; at the same time, the reduction change analysis module in S3 judges whether the reduction change rate characteristic value and the reduction change amplitude characteristic value fall within the spoon reduction change rate preset range value and the spoon reduction change amplitude preset range value respectively; therefore, when any characteristic value does not fall within the corresponding preset range value in S4, it is judged that the reduction change characteristic meets the food reduction change characteristic; when the two characteristic values respectively fall within the corresponding preset range value, it is judged that the reduction change characteristic does not meet the food reduction change characteristic.

[0035] In the case, the data processing unit further comprises an error correction module 24 for correcting network fluctuations or hardware fault errors;

[0036] The error correction module in S4 monitors the network state and the reduction value, and when the network fluctuation exceeds the preset value or the reduction value and the historical record reduction value differ by more than a set value, the error correction module will smooth the actual reduction value according to the historical record actual reduction value.

[0037] The food weight change pattern analysis in the case includes the change characteristics of food weight and the change characteristics of spoon weight. Among them,

[0038] The change characteristics of food weight: the weight of food usually presents a relatively stable and continuous increase, and the change amplitude is large in a short time.

[0039] The change characteristics of spoon weight: the weight of spoon is usually fixed, and may appear a short-term fluctuation during placement, but will not present a similar increasing pattern with the change of food weight. The change rates and amplitudes of spoon and food weight are different, and the system distinguishes them by analyzing the difference between them.

[0040] Therefore, the algorithm steps for removing the spoon weight include weight increment comparison and increment characteristic analysis.

[0041] Among them,

[0042] Weight increase ratio: The system monitors the weight increase of the weighing tray in real-time. If the system detects a sudden increase in weight over a short period, but the increase is relatively small and stable, the system judges that this part of the weight is the spoon weight.

[0043] Incremental feature analysis: By comparing the typical pattern of food weight gain, such as the gradual and sustained increase in food weight, the system judges that weight fluctuations that do not meet the characteristics of food weight gain in the short term are caused by spoons, and then deducts this part from the second total weight.

[0044] The self-learning mechanism of the present case includes dynamic adjustment of removal strategy and model training and optimization. Among them,

[0045] Dynamic adjustment of removal strategy: The system, through the self-learning module, gradually optimizes the spoon weight model according to historical data. The data after each weighing is stored, and the spoon weight model is adjusted according to the weighing result. The system analyzes the change rule of the spoon weight in each weighing data, learns the regular weight range, placement time, fluctuation characteristics and other information of the spoon.

[0046] Model training and optimization: Through machine learning algorithms such as K-means clustering and support vector machines, the system can continuously adjust and optimize the recognition accuracy of spoon and food weight changes, gradually improving the accuracy of spoon weight recognition and removal.

[0047] Error correction in the present case mainly includes network fluctuation and data stability detection: The system will monitor the network status, and if it detects weight instability caused by network fluctuations during data transmission, the system will perform smoothing correction based on historical data to prevent false calculations caused by network fluctuations.

[0048] Final removal of spoon weight: When the system confirms that the spoon weight has been correctly identified, it will deduct the spoon weight from the total weight and only keep the net weight of the food. Finally, the user's food weight to be paid is calculated, and the accurate consumption amount is generated.

[0049] The self-learning optimization mechanism in the present case is provided to ensure that the system can effectively adapt to different restaurant environments and different user usage scenarios. The self-learning mechanism of the system continuously optimizes the accuracy of removing the spoon weight, including:

[0050] Historical data accumulation: The system will accumulate a large amount of historical weighing data, including food weight increase and decrease patterns, spoon weight characteristics, and food and spoon weight changes when combined. By analyzing these data, the system can build a food and spoon weight change database.

[0051] Model self-adaptive adjustment: the system will match the current data with the historical data after each weighing, automatically adjust the algorithm parameters to remove the weight of the spoon. With the increase of the number of uses, the system will gradually optimize the removal strategy, so that the weight removal accuracy of the spoon is continuously improved.

[0052] Error correction: in some abnormal situations such as misoperation, network failure, etc., the system detects abnormalities through error detection mechanisms such as comparing the set error range, fluctuation amplitude, etc., and automatically corrects the weight data to ensure the accuracy of the removal process.

[0053] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made under the inventive concept of the present application, using the contents of the present application specification and drawings, or directly or indirectly applied to other related technical fields is included in the patent protection scope of the present application.

Claims

1. A weighing algorithm for electronic scales that automatically removes the weight of a spoon, characterized in that: The system includes a weighing sensor (1) installed inside the scale body to measure the weight of the weighing pan and food, a data processing unit (2) installed inside the scale body to convert the weight of the food measured by the weighing sensor (1) into a weight value and automatically identify and remove the weight of the spoon, a display screen (3) connected to the scale body, and a back-end server (4) with preset food types and unit prices. The data processing unit (2) includes a weight reduction change analysis module (21) for determining whether the weight reduction of the weighing pan is a reduction in food or a reduction in the weight of the spoon, a self-learning module (22) for establishing a spoon weight model and optimizing the spoon weight accuracy in the model by analyzing the data through the weight reduction change analysis module (21), and a calculation processing module (23) for calculating the weight reduction of food and the price. The weighing algorithm includes the following steps: S1, Weighing sensor (1) measures the weight of the weighing pan in an empty state; S2, The weighing sensor (1) measures the first total weight when the weighing pan is loaded with food and the spoon is placed on it. The calculation and processing module (23) subtracts the weight of the weighing pan from the first total weight to obtain the second total weight, which is the sum of the weight of the food and the weight of the spoon, and displays it on the display screen (3). S3. When the weighing sensor (1) measures the second total weight reduction, the weight reduction change analysis module (21) extracts the weight reduction change characteristics and determines whether the weight reduction change characteristics conform to the food weight reduction change characteristics. S4. If the judgment is correct, the reduction value is the actual reduction value. The calculation and processing module (23) connects with the back-end server (4) to obtain the corresponding food unit price, calculates the price of the actual reduction of food according to the preset unit price, and displays the real-time second total weight and the price of food reduction through the display screen (3). If the judgment does not meet the requirements, the calculation and processing module (23) subtracts the spoon weight value obtained from the spoon weight model in the self-learning module (22) from the reduction value to obtain the actual reduction value. The calculation and processing module (23) connects with the back-end server (4) to obtain the corresponding food unit price, calculates the price of the actual reduction of food according to the preset unit price, and displays the real-time second total weight and the price of food reduction through the display screen (3). S5. The self-learning module (22) analyzes the reduction data analyzed by the reduction change analysis module (21) and the actual reduction data obtained by the calculation and processing module (23), and optimizes the spoon weight value in the spoon weight model. The extracted characteristics of the decrease include the rate of decrease and the magnitude of the decrease. The reduction change analysis module (21) has preset range values ​​for the rate of change of spoon reduction and preset range values ​​for the magnitude of spoon reduction; The reduction change analysis module (21) in S3 determines whether the characteristic value of the reduction change rate and the characteristic value of the reduction change amplitude fall within the preset range values ​​of the spoon reduction change rate and the preset range values ​​of the spoon reduction change amplitude, respectively. In S4, if any feature value does not fall within the corresponding preset range value, it is determined that the reduction change feature conforms to the food reduction change feature. When the two feature values ​​fall within their respective preset range values, it is determined that the reduction change feature does not conform to the food reduction change feature.

2. The weighing algorithm for automatically removing the weight of a spoon from an electronic scale according to claim 1, characterized in that: The self-learning module (22) is based on machine learning algorithms and uses a weighing sensor (1) to establish a spoon weight model based on the changing patterns of food weight data and spoon weight data.

3. The weighing algorithm for automatically removing the weight of a spoon from an electronic scale according to claim 2, characterized in that: The spoon weight model analysis uses the weighing data of the weighing sensor (1) to learn the spoon's normal weight range, placement time, and weight loss fluctuation characteristics.

4. The weighing algorithm for automatically removing the weight of a spoon from an electronic scale according to claim 2, characterized in that: Machine learning algorithms include K-means clustering and support vector machine algorithms.

5. The weighing algorithm for automatically removing the weight of a spoon from an electronic scale according to claim 1, characterized in that: The data processing unit (2) also includes an error correction module (24) for correcting network fluctuations or hardware failure errors. In S4, the error correction module (24) monitors the network status and reduction value. When the monitored network fluctuation exceeds the preset value or the reduction value differs from the historical reduction value by more than the set value, the error correction module (24) will smooth the real-time actual reduction value according to the historical actual reduction value.

6. The weighing algorithm for automatically removing the weight of a spoon from an electronic scale according to claim 1, characterized in that: The data processing unit (2) also includes a database (25) for storing weighing data, weight loss data, actual weight loss data, food weight increase / decrease pattern data, spoon weight characteristic data and weight change data of food adhering to the spoon for each weighing by the weighing sensor (1).

Images